Search

In the context of large-scale wind power access to the power system, it is urgent to explore new probabilistic supply–demand analysis methods. This paper proposes a wind power stochastic and extreme scenario generation method considering wind power–temperature correlations and carries out probabilistic supply–demand balance analysis based on it. Firstly, the influence of temperature on wind power output is analyzed via Pearson coefficient to obtain the correlation between wind power and temperature. Secondly, based on the historical wind power curve, a large number of wind power output scenarios are randomly generated while fully preserving its characteristics, and probabilistic supply–demand analysis is carried out. Thirdly, for the extreme case of continuous multi-day extreme heat without wind, extreme scenarios are selected from the generated scenarios for supply–demand balance analysis. Finally, a practical example in a province in central-eastern China is used to verify the effectiveness of the proposed method. The results indicate that the scenario generation method can effectively capture the historical wind power characteristics and can be better applied to the diversified supply and demand balance analysis to obtain more accurate analysis results. [ABSTRACT FROM AUTHOR]

The temporal variation of wind power is primarily influenced by wind speed, exhibiting high levels of randomness and fluctuation. The accuracy of short-term wind power forecasts is greatly affected by the quality of Numerical Weather Prediction (NWP) data. However, the prediction error of NWP is common, and posing challenges to the precision of wind power prediction. To address this issue, the paper proposes a NWP wind speed error correction model based on Residual Network-Gated Recurrent Unit (ResNet-GRU). The model corrects the forecasted wind speeds at different heights to provide reliable data foundation for subsequent predictions. Furthermore, in order to overcome the difficulty of selecting network parameters for the combined prediction model, we integrate the Kepler Optimization Algorithm (KOA) intelligent algorithm to achieve optimal parameter selection for the model. We propose a Convolutional Neural Network-Long and Short-Term Memory Network (CNN-LSTM) based on Attention Mechanism for short-term wind power prediction. Finally, the proposed methods are validated using data from a wind farm in northwest China, demonstrating their effectiveness in improving prediction accuracy and their practical value in engineering applications. [ABSTRACT FROM AUTHOR]

With the increasing penetration of renewable energy resources, their variable, intermittent and unpredictable characteristics bring new challenges to the power system. These challenges require micro-meteorological data and techniques to provide more support for the power systems, including planning, dispatching, operation, and so on. This paper aims to provide readers with insights into the effects of micro-meteorology on power systems, as well as the actual improvement brought by micro-meteorology in some power system scenarios. This paper provides a review including the relevant micro-meteorological techniques such as observation, assimilation and numerical techniques, as well as artificial intelligence, presenting a relatively complete overview of the most recent and relevant micro-meteorology-related literature associated with power systems. The impact of micro-meteorology on power systems is analyzed in six different forms of power generation and three typical scenarios of different stages in the power system, as well as integrated energy systems and disaster prevention and reduction. Finally, a case study in China is provided. This case takes wind power prediction as an example in a power system to compare the performance when applying micro-meteorological data or not. The experimental results demonstrated that using the micro-meteorological reanalysis dataset with high spatial--temporal resolution for wind power prediction performed better, verifying the improvement of micro-meteorology to the power system to some extent. [ABSTRACT FROM AUTHOR]

Wind power generation is a renewable energy source, and its power output is influenced by multiple factors such as wind speed, direction, meteorological conditions, and the characteristics of wind turbines. Therefore, accurately predicting wind power is crucial for the grid operation and maintenance management of wind power plants. This paper proposes a hybrid model to improve the accuracy of wind power prediction. Accurate wind power forecasting is critical for the safe operation of power systems. To improve the accuracy of wind power prediction, this paper proposes a hybrid model incorporating variational modal decomposition (VMD), a Sparrow Search Algorithm (SSA), and a temporal-convolutional-network-based bi-directional gated recurrent unit (TCN-BiGRU). The model first uses VMD to break down the raw power data into several modal components, and then it builds an SSA-TCN-BIGRU model for each component for prediction, and finally, it accumulates all the predicted components to obtain the wind power prediction results. The proposed short-term wind power prediction model was validated using measured data from a wind farm in China. The proposed VMD-SSA-TCN-BiGRU forecasting framework is compared with benchmark models to verify its practicability and reliability. Compared with the TCN-BiGRU, the symmetric mean absolute percentage error, the mean absolute error, and the root mean square error of the VMD-SSA-TCN-BiGRU model reduced by 34.36%, 49.14%, and 55.94%. [ABSTRACT FROM AUTHOR]

A convenient and effective method based on vector analysis was proposed in this paper to quantitatively describe the pattern of the wind speed distribution curve. This method can accurately describe the steepness of the single‐peak curve by using two parameters of concentration degree (CD) and concentration period (CP). Through the analysis of wind speed data in China over the past 40 years, this paper found that regional wind resources with larger CD were poorer, while regional wind resources with larger CP were richer. In addition, there were obvious cubic relationships between the CP and the average wind power density. These two parameters could reflect the richness of wind energy and realize the comparisons of wind resources across time and scales. In comparison with conventional approaches, this method is simpler and avoids fitting process, which has broad promotion prospects in the field of power grids. [ABSTRACT FROM AUTHOR]

The analysis of marine environmental parameters plays a significant role in various aspects, including sea surface target detection, the monitoring of the marine ecological environment, marine meteorology and disaster forecasting, and the monitoring of internal waves in the ocean. In particular, for sea surface target detection, the accurate and high-resolution input of marine environmental parameters is crucial for multi-scale sea surface modeling and the prediction of sea clutter characteristics. In this paper, based on the low-resolution wind speed, significant wave height, and wave period data provided by ECMWF for the surrounding seas of China (specified latitude and longitude range), a deep learning model based on a residual structure is proposed. By introducing an attention module, the model effectively addresses the poor modeling performance of traditional methods like nearest neighbor interpolation and linear interpolation at the edge positions in the image. Experimental results demonstrate that with the proposed approach, when the spatial resolution of wind speed increases from 0.5° to 0.25°, the results achieve a mean square error (MSE) of 0.713, a peak signal-to-noise ratio (PSNR) of 49.598, and a structural similarity index measure (SSIM) of 0.981. When the spatial resolution of the significant wave height increases from 1° to 0.5°, the results achieve a MSE of 1.319, a PSNR of 46.928, and an SSIM of 0.957. When the spatial resolution of the wave period increases from 1° to 0.5°, the results achieve a MSE of 2.299, a PSNR of 44.515, and an SSIM of 0.940. The proposed method can generate high-resolution marine environmental parameter data for the surrounding seas of China at any given moment, providing data support for subsequent sea surface modeling and for the prediction of sea clutter characteristics. [ABSTRACT FROM AUTHOR]

In recent years, a series of environmental problems have come one after another under the use of traditional fossil energy, such as greenhouse effect, acid rain, haze and so on. In order to solve the environmental problems and achieve sustainable development, seeking alternative resources has become the direction of joint efforts of China and the world. As an important part of new energy, wind energy needs strong wind speed prediction support in terms of providing stable electric power. As a result, it is very important to improve the accuracy of wind speed prediction. In view of this, this paper proposes a signal processing method based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) combined with singular value decomposition (SVD), and uses Elman neural network optimized by particle swarm optimization algorithm (PSO) and autoregressive integrated moving average model (ARIMA) to predict the intrinsic mode functions (IMFs). Firstly, CEEMDAN combined with SVD is used to decompose and denoise the data, and the weights and thresholds of Elman are optimized by PSO. Finally, the optimized Elman and ARIMA are used to respectively predict the processed wind speed data components, and then the final prediction results are obtained. The final prediction results show that the proposed model can improve the effect of wind speed prediction, reduce the prediction error, and provide strong support for the stable operation of wind farms and the grid connection of power plants. [ABSTRACT FROM AUTHOR]

A wind–hydrogen coupled power generation system can effectively reduce the power loss caused by wind power curtailment and further improve the ability of the energy system to accommodate renewable energy. However, the feasibility and economy of deploying such a power generation system have not been validated through large-scale practical applications, and the economic comparison between regions and recommendations on construction are still lacking. In order to solve the aforementioned problems, this paper establishes an economic analysis model for the wind–hydrogen coupled power generation system and proposes a linear optimisation-based priority analysis method focusing on the major net present value for regional energy system as well as a cost priority analysis method for hydrogen production within sample power plants. The case study proves the effectiveness of the proposed analysis methods, and the potential to develop wind–hydrogen coupled power generation systems in various provinces is compared based on the national wind power data in recent years. This provides recommendations for the future pilot construction and promotion of wind–hydrogen coupled power generation systems in China. [ABSTRACT FROM AUTHOR]

The randomness and instability of wind power bring challenges to power grid dispatching. Accurate prediction of wind power is significant to ensure the stable development of power grid. In this paper, a new ultra-short-term wind power forecasting model based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and long-short-term memory (LSTM) network optimized by improved whale optimization algorithm (IWOA) is proposed. Firstly, CEEMDAN is applied to decompose the power history data into several intrinsic mode functions (IMFs) and a residual (RS) to reduce the complexity and unsteadiness of the original data. Then the partial autocorrelation method is used to analyze and select the input variables of each IMF and the residual. Finally, the IWOA-LSTM prediction model is established, and the parameters of LSTM are optimized by using the improved whale optimization algorithm. Each IMF and the residual are predicted respectively. The prediction results are superimposed to obtain the final wind power prediction value. The hybrid model is applied to the ultra-short-term wind power prediction of a wind farm in northern China. The prediction results of comparison experiments with other 11 models prove the effectiveness of the proposed model. [ABSTRACT FROM AUTHOR]

In this paper, a method for joint sea surface rainfall intensity (RI), wind speed, and wave height retrieval based on spaceborne global navigation satellite system reflectometry (GNSS-R) data is proposed, which especially considers the effects between these two parameters. A method of rainfall detection (RD) according to different wind speed ranges is also proposed by mitigating the impact of swell and wind speed. The results, with data collected over the oceans near Southeast Asia, show that the RD method has a detection accuracy of up to 81.74%. The RI retrieval accuracy can reach about 2 mm/h by simultaneously correcting the effects of wind speed and swell. The accuracy of wind speed retrieval is improved by about 5% after removing rainfall interference through RD in advance. After considering the influence of wind speed and eliminating rainfall interference, the retrieval accuracy of significant wave height (SWH) is improved by about 18%. Finally, the deep convolutional neural network (DCNN) model is built to estimate the SWH of the swell. The results show that the retrieval accuracy of the swell height is better than 0.20 m after excluding rainfall interference. The proposed joint retrieval method provides an important reference for the future acquisition of multiple high-precision marine geophysical parameters by spaceborne GNSS-R technology. [ABSTRACT FROM AUTHOR]

Comprehensive bridge design should consider simultaneous actions of wind and temperature. The current load combination method of directly superposing extreme wind and temperature actions ignores the correlation between wind and temperature, resulting in too conservative bridge load estimates, and limiting the further development of the bridge span. Therefore, this paper proposes a method to determine the joint distribution of wind speed, wind direction, and air temperature actions on long-span bridges based on trivariate metaelliptical and Plackett copulas. First, the technique of establishing the trivariate joint distribution via trivariate metaelliptical and Plackett copulas is introduced. Next, the conditional joint distributions of wind speed and air temperature under the specific wind directions are derived from these. Using the concept of conditional bivariate Kendall return period (KRP) proposed in this paper, the conditional KRP isolines of wind speed and air temperature for specific wind directions are constructed. Then, conditional joint estimates of wind speed and air temperature actions for several specific wind directions are obtained using the following principle: the conditional bivariate design return period should be equal to the conditional univariate one. The method feasibility is verified by the case study of the Changtai Yangtze River Bridge in China, which is currently under construction and will be the largest cable-stayed bridge in the world. The results show that the joint actions of wind and temperature on the bridge greatly reduce as compared with the simple superposition of extreme wind and temperature actions specified in the design code. Moreover, a significant contribution of wind direction in the above joint distribution on the large-span bridge load is proved. [ABSTRACT FROM AUTHOR]

A series of main supporting policies implemented by the government from 2009 to 2016 is summarized in this paper. Due to the lack of studies on wind energy development in China up to the 13th Five-Year Plan, this paper aims to provide a systematic overview of the evolution and implementation of onshore and offshore wind power development, as well as analyze the localization and competitiveness of wind power enterprises. This paper introduces how the Chinese government efficiently promotes the drastic wind power development by means of fiscal and non-fiscal policies, which includes stimulating the wind power investment, addressing the wind power curtailment problem, localizing the Chinese-owned manufacturers in domestic markets and internationalizing the exposure of Chinese-owned enterprises. This paper concludes that the effectiveness of wind power policies enacted is high, and they play a vital role in the Chinese wind power market. Abbreviations: FYP: Five Year Plan; UNFCCC: United Nations Framework Convention on Climate Change; CDM: Clean Development Mechanism: REL: Renewable Energy Law; NDRC: National Development and Reform Commission; MF: Ministry of Finance; SC: State Council; FIT: Feed–in–Tariff; CWEA: Chinese Wind Energy Association; NEA: National Energy Administration; SGCC: State Grid Corporation of China; CSG: China Southern Power Grid Corporation; SOEs: State–owned enterprises; NEB: National Energy Bureau [ABSTRACT FROM AUTHOR]

With the increasing application of wind energy, reliable wind speed prediction has become imperative. However, prior studies predominantly concentrated on single-model predictions, disregarding the inherent uncertainty in wind speed. This oversight resulted in inadequate deterministic and probabilistic forecasting outcomes across varying scenarios. To make up for these shortcomings, a novel forecasting system combining a data preprocessing technique, a sub-model selection method, and a modified multi-objective integrate optimization strategy is designed in this paper. According to the data obtained from China's wind farm, the forecasting efficiency of this system is verified from multiple perspectives. The findings show that the system takes advantage of each model to boost the precision and stability of point prediction successfully. Furthermore, it achieves higher interval coverage and narrower interval width under distinct confidence levels. These results highlight the system's potential as a reliable technical support for efficient dispatching of the entire power system. [ABSTRACT FROM AUTHOR]

Wind power forecasting is a typical high-dimensional and multi-step time series prediction problem. Data-driven prediction methods using machine learning show advantages over traditional physical or statistical methods, especially for wind farms with complex meteorological conditions. Thus, effective use of different data sources and data types will help improve power forecasting accuracy. In this paper, a multi-source data fusion method is proposed, which integrates the static information of the wind turbine with observational and forecasting meteorological information together to further improve the power forecasting accuracy. Firstly, the characteristics of each time step are re-characterized by using the self-attention mechanism to integrate the global information of multi-source data, and the Res-CNN network is used to fuse multi-source data to improve the prediction ability of input variables. Secondly, static variable encoding and feature selection are carried out, and the time-varying variables are combined with static variables for collaborative feature selection, so as to effectively eliminate redundant information. A forecasting model based on the Encoder–Decoder framework is constructed with LSTM as the basic unit, and the Add&Norm mechanism is introduced to further enhance the input variable information. In addition, the self-attention mechanism is used to integrate the global time information of the decoded results, and the Time Distributed mechanism is used to carry out multi-step prediction. Our training and testing data are obtained from an operating wind farm in northwestern China. Results show that the proposed method outperforms a classic AI forecasting method such as that using the Seq2Seq+attention model in terms of prediction accuracy, thus providing an effective solution for multi-step forecasting of wind power in wind farms. [ABSTRACT FROM AUTHOR]

Short-term wind speed forecasting is fundamental to improving the stability of power grid operation and enhancing its transmission efficiency; thus, it has long been a research hotspot. Nonetheless, quantities of literature in this field only used the single prediction model and overemphasized deterministic prediction, which resulted in deficient forecasting performance. To address these issues, a novel point and interval combination prediction system was developed in this paper. Specifically, wind speed time series were reconstructed by dividing windows and fuzzification to input highly effective data; next, four single prediction models and a multi-objective weight-determining mechanism were integrated to obtain the point prediction results; and their distributions were assessed to implement interval prediction under distinct confidence levels. In the meantime, this study demonstrated that the proposed system reached the Pareto optimal by the theoretical proof, and empirical research was conducted based on 10-min real wind speed data from the wind farm in China. Judging from the experimental results, the combination prediction system was always capable of providing the most satisfactory forecasting performance by contrast with the comparative models. Consequently, it has broad application prospects in guiding the operation of wind farms and optimizing the power grid dispatching. [ABSTRACT FROM AUTHOR]

Due to the insufficient consideration of medium and long-term wind power contract power in short-term dispatch, long-term planning and real-time consumption of wind power cannot be effectively undertaken, resulting in a large amount of abandoned wind power. A way to improve the wind power absorption capacity has become an urgent problem to be studied. According to the characteristics of the market and dispatching in the process of wind-fire integration construction, this paper constructs a wind power consumption model that connects the mid- and long-term transaction power decomposition and short-term dispatch. Considering the unit output characteristics and maintenance, the monthly contract electricity is decomposed into daily electricity, and the nesting of medium and long-term transactions and short-term scheduling is realized; the second stage is a short-term multi-objective optimal scheduling model considering the decomposition of contract electricity and the output of non-bidding units to improve the real-time consumption of wind power. Finally, a province in northwest China is taken as an example to verify the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

In this paper, a short-term wind speed prediction model, called CEEMDAN-SE-Improved PIO-GRNN, is proposed to optimize the accuracy of the short-term wind speed forecast. This model is established on account of the optimized General Regression Neural Network (GRNN) method optimized by three algorithms, which are Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN), Sample Entropy (SE), and Pigeon Inspired Optimization (PIO), separately. Firstly, decomposing the original wind speed sequences into several subsequences with different complexity by CEEMDAN. Then, the complexity of each subsequence is judged by SE and the similar subsequences are combined into a new sequence to reduce the scale of calculation. Afterwards, the GRNN model optimized by improved PIO is used to predict each new sequence. Finally, the predicted results are superposed as the eventual predicted value. Implementing the prediction for the wind speed data of a wind field in north China within 30 days by applying the different prediction models, namely, GRNN, CEEMDAN-GRNN, Improved PIO-GRNN, and CEEMDAN-SE-Improved PIO-GRNN which are proposed in this paper. Comparing the prediction curves of different models with the fitting curve of the actual wind speed shows that the optimal fitting effect and minimum error value are included in CEEMDAN-SE-Improved PIO-GRNN model. Specifically, the values of mean squared error (MSE), mean absolute error (MAE) and weighted mean absolute percentage error (WMAPE) separately decrease by 0.6222, 0.3334, and 8.5766%, which compare with the single prediction model GRNN. Meanwhile, diebold-mariano (DM) test shows that the prediction ability of the two models is significantly different. The above statements indicate the proposed model does great advance in the precision of short-term wind speed prediction. [ABSTRACT FROM AUTHOR]

As a promising renewable solution for sustainable power generation worldwide, wind energy is receiving continuing attention from both industry and the academic community. However, the randomness and intermittency of wind energy will affect the stable operation and stability of the power system and further affect the economic benefits of the power grid. What makes the matter worse is the inevitable coupling between each pair of wind turbines in the large-scale wind farm. Besides, the resolution of prediction is severely limited by the spatial scale of wind farms. These problems bring great difficulties for the control and scheduling of wind farms. To this end, this paper proposes a novel wind speed prediction method for wind farms by borrowing some wisdom from machine learning methods. First, density peak clustering (DPC) is employed to separate the tremendous number of scattered wind turbines into a much significantly reduced number of groups, the wind turbines in each of which are treated as a unity. Based on the priority setting of each indicator in clustering, the data are preprocessed with different weightings. Principal component analysis is utilized to avoid DPC's poor clustering effects in case the dataset is high-dimensional. Finally, by considering simultaneous effects from historical and present data, long short-term memory based deep learning neural networks are trained and used to iteratively predict the potential of the wind energy in each unit for each time slot. The effectiveness of the proposed algorithm is verified by taking an in-service wind farm in China as an example. [ABSTRACT FROM AUTHOR]

In order to ensure the driving safety of vehicles in windy environments, a wind monitoring and warning system is widely used, in which a wind speed prediction algorithm with better stability and sufficient accuracy is one of the key factors to ensure the smooth operation of the system. In this paper, a novel short-term wind speed forecasting model, combining complementary ensemble empirical mode decomposition (CEEMD), auto-regressive integrated moving average (ARIMA), and support vector machine (SVM) technology, is proposed. Firstly, EMD and CEEMD are used to decompose the measured wind speed sequence into a finite number of intrinsic mode functions (IMFs) and a decomposed residual. Each of the IMF subseries has better linear characteristics. The ARIMA algorithm is adopted to predict each of the subseries. Then, a new subseries is reconstructed using the sum of the predicted errors of all subseries. The high nonlinear features of the reconstructed error subseries are modeled using SVM, which is suitable to process nonlinear data. Finally, the superposition of all prediction results is performed to obtain the final predicted wind speed. To verify the stability and accuracy of the model, two typhoon datasets, measured from the south coast of China, are used to test the proposed methods. The results show that the proposed hybrid model has a better predictive ability than single models and other combined models. The root mean squared errors (RMSEs) of the hybrid model for the three wind speed datasets are 0.839, 0.529, and 0.377, respectively. The combination of CEEMD with ARIMA contributes most of the prediction performance to the hybrid model. It is feasible to apply the hybrid model to wind speed prediction. [ABSTRACT FROM AUTHOR]

Summary: Wind power prediction (WPP) is one of the key techniques to eliminate the adverse impact of large proportion of wind power on power grid, while it faces the main problem of low prediction accuracy. The main contribution of this paper is a new data sample division method based on China's 24 solar terms (24STs) for wind power prediction. The 24STs is an astronomical and meteorological calendar summarized by ancient Chinese, and it more accurately reflects the law of the seasonal changes, the phenomenon of phenology, and climate characteristics compared with the calendar month. In the paper, firstly, the reasonableness of the division of 24STs is verified from the point of temperature and wind speed; secondly, four meteorological factors related to wind power output are used for similarity calculation, and the results show that the data samples in the same STs have higher similarity than those in the same semi‐month based on Gregorian; finally, the WPP models are established with the 24STs sample division method and the semi‐month sample division method, and the case proves that the 24STs method has higher prediction accuracy because it can grasp the seasonal changes law of some meteorological elements more accurately. [ABSTRACT FROM AUTHOR]

Summary: As the installed capacity of wind power continues to increase, the problem of curtailed wind power is becoming serious in China, especially in the northern region during the winter heating season. To solve the problem of wind‐heat conflict during the heating period in the Three North area, an electric boiler with thermal storage (EBTS) is installed at the end of the grid where wind power is difficult to accommodate and using curtailed wind power to supply heat promotes local accommodation. In this paper, a multi‐objective optimization model of wind power accommodation based on the wind power–EBTS system for heating is established. The goals of maximizing wind power accommodation, minimizing the number of times EBTS must be adjusted, and minimizing operating costs are presented, and a bi‐level optimization scheme is designed. An improved multi‐objective particle swarm optimization algorithm is used to solve these functions, and an optimal compromise solution from the generated Pareto solution set is filtered using the fuzzy membership method. Based on actual data from a demonstration project in China's Jilin Province, the simulation results verify that this method can effectively reduce operating costs and improve wind power accommodation. [ABSTRACT FROM AUTHOR]

In this paper, a least squares support vector machine (LSSVM) model with parameter optimization is proposed for solving the problem that the forecast accuracy of neural network model and support vector machine model is not desirable for the sake of improving short-term wind speed forecast accuracy further. The parameters of LSSVM are optimized by the improved ant colony algorithm. Firstly, the parameters of LSSVM are regarded as the position vector of ants. Another argument is that the global search is carried out by selecting some ants randomly from the ant colony to guide the whole ant colony, while searching the optimal ant neighborhood. Furthermore, the optimal parameters of the model are obtained, and the wind speed prediction model of LSSVM is established through parameter optimization. Taking a wind farm in North China as an example, the collected wind speed data were taken in predicted experience, besides the results were compared with the BP neural network model and the LSSVM model. The results show that this model has significant advantages compared with the other two models and has high practical significance. [ABSTRACT FROM AUTHOR]

Accurately predicting wind power is premise for the large‐scale integration of wind energy into the power grid and realizing reliable power grid scheduling and efficient wind farm operation. The spatial–temporal differences between the acquisition points of numerical weather prediction and wind farm sites should be considered because they significantly affect the accuracy of wind power output. Meanwhile, since there are different actual constraints on wind farm electrical networks and units, and the weather conditions may vary, there are no universal methods for identifying and correcting wind power output. To this end, this paper proposes a wind speed calibration model based on an Attention‐Bi‐LSTM network and a self‐adaptive recognition‐correction model based on SHAP‐CART classification for wind power output prediction. First, a spatial–temporal dataset is established by using real weather data from wind farm sites and data from the surrounding NWP points. Then, wind speed is accurately calibrated using the Attention‐Bi‐LSTM model. Next, considering the practical constraints on wind farm electrical networks and units, the self‐adaptive recognition‐correction model based on SHAP‐CART classification is employed to effectively recognize and predict the operating states and power output of the units, thus improving the accuracy and stability of wind power output prediction. Finally, the effectiveness and superiority of the proposed method is verified by using a wind farm in Eastern China as an example and analyzing the prediction results in various approaches. © 2023 Institute of Electrical Engineer of Japan and Wiley Periodicals LLC. [ABSTRACT FROM AUTHOR]

Due to the significant intermittent, stochastic and non-stationary nature of wind power generation, it is difficult to achieve the desired prediction accuracy. Therefore, a wind power prediction method based on improved variational modal decomposition with permutation entropy is proposed. First, based on the meteorological data of wind farms, the Spearman correlation coefficient method is used to filter the meteorological data that are strongly correlated with the wind power to establish the wind power prediction model data set; then the original wind power is decomposed using the improved variational modal decomposition technique to eliminate the noise in the data, and the decomposed wind power is reconstructed into a new subsequence by using the permutation entropy; with the meteorological data and the new subsequence as input variables, a stacking deeply integrated prediction model is developed; and finally the prediction results are obtained by optimizing the hyperparameters of the model algorithm through a genetic algorithm. The validity of the model is verified using a real data set from a wind farm in north-west China. The results show that the mean absolute error, root mean square error and mean absolute percentage error are improved by at least 33.1%, 56.1% and 54.2% compared with the autoregressive integrated moving average model, the support vector machine, long short-term memory, extreme gradient enhancement and convolutional neural networks and long short-term memory models, indicating that the method has higher prediction accuracy. [ABSTRACT FROM AUTHOR]

How to consider both the influence of weather and wind power in the modeling process of probability distribution of wind power forecast error (WPFE), and to emphasize the application value of conditional modeling, is rarely studied at present. This paper proposes a novel method of conditional probability distribution modeling for WPFE. This method uses a proposed MNSGA-II-Kmeans algorithm to perform multi-objective clustering of multi-dimensional influencing factors (MDIF), including weather and wind power. It can maximize the difference between the probability distributions of each MDIF mode's WPFE while clustering, thus ensuring the application value of the conditional modeling way. Based on the clustering results, by using the versatile distribution to simulate the probability distribution of WPFE and the support vector machine to realize the recognition of MDIF modes, the specific conditional probability distribution function of WPFE can be provided to stochastic economic dispatch by identifying the forecast MDIF data. A wind plant of north China with historical data is selected for calculation. The results verify the effectiveness of the proposed method, and by comparison with the non-conditional probability distribution of WPFE that does not consider MDIF, it can effectively increase the wind power consumption of the power system. [ABSTRACT FROM AUTHOR]

Renewable energy represented by wind energy plays an increasingly important role in China's national energy system. The accurate prediction of wind power generation is of great significance to China's energy planning and power grid dispatch. However, due to the late development of the wind power industry in China and the lag of power enterprise information, there are little historical data available at present. Therefore, the traditional large sample prediction method is difficult to be applied to the forecasting of wind power generation in China. For this kind of small sample and poor information problem, the grey prediction method can give a good solution. Thus, given the seasonal and long memory characteristics of the seasonal wind power generation, this paper constructs a seasonal discrete grey prediction model based on collaborative optimization. On the one hand, the model is based on moving average filtering algorithm to realize the recognition of seasonal and trend features. On the other hand, based on the optimization of fractional order and initial value, the collaborative optimization of trend and season is realized. To verify the practicability and accuracy of the proposed model, this paper uses the model to predict the quarterly wind power generation of China from 2012Q1 to 2020Q1, and compares the prediction results with the prediction results of the traditional GM(1,1) model, SGM(1,1) model and Holt-Winters model. The results are shown that the proposed model has a strong ability to capture the trend and seasonal fluctuation characteristics of wind power generation. And the long-term forecasts are valid if the existing wind power expansion capacity policy is maintained in the next four years. Based on the forecast of China's wind power generation from 2021Q2 to 2024Q2 in the future, it is predicted that China's wind power generation will reach 239.09 TWh in the future, which will be beneficial to the realization of China's energy-saving and emission reduction targets. [ABSTRACT FROM AUTHOR]

Accurate and stable ultra-short-term wind speed prediction is very valuable for the dispatch planning and operational security for the wind power system, however it's very difficult to obtain satisfactory forecasting results in the wind power system due to the complexity and non-linearity of the wind speed series. In this paper, a novel hybrid model combined multi-objective optimization, data preprocessing technology and Elman neural network was proposed to forecast ultra-short-term wind speed, including 30min and 10min wind speed. To obtain better forecasting results with high accuracy and strong stability, multi-objective optimization target was utilized to balance the variance and bias of the forecasted series. Complementary ensemble empirical mode decomposition was used to remove the noise in the original data and several IMFs were obtained. This paper proposed a new optimization algorithm combined adaptive wind driven optimization and modified simulated annealing to optimize initial weights and thresholds of ENN. Wind speed data from two observation sites in China was involved in this paper to verify the forecasting performance of the proposed model. The simulation results illustrate that the proposed hybrid model has the best forecasting results at all step among all related models. • A new hybrid is proposed to forecast wind speed in this paper. • Data preprocessing technology is introduced to improve the forecasting performance. • Multi-objective optimization target is utilized to obtain stability and accuracy forecasting results. • The results are validated well in China. [ABSTRACT FROM AUTHOR]

With the large-scale development of offshore wind farms, China's offshore wind power process is becoming more and more perfect. How to accurately forecast offshore wind power, especially under the influence of transitional weather, is a difficult problem to be solved. Therefore, in order to accurately forecast offshore wind power in the extreme small sample event, this paper proposes a method for predicting wind power before the turning weather based on meteorological element selection and small sample learning and expansion. The method improves the prediction accuracy of offshore wind power under typhoons and cold waves by constructing meteorological features in transitional weather such as typhoons and cold waves, expanding the small sample using time series, and modelling the relationship between the expanded meteorological factors and wind power. [ABSTRACT FROM AUTHOR]

With the increasing proportion of wind power connected to grid, power system dispatching is facing more and more challenges from uncertainty. To cope with this uncertainty, robust optimization has been applied in unit commitment (UC) problem. In this paper, a multi-band uncertainty set considering the temporal correlation (MBUSCTC) of wind/load prediction error is proposed firstly, which has two characteristics: (1) The MBUSCTC rigorously and realistically reflect the distribution characteristics of uncertainties in uncertainty intervals, thereby effectively reducing the conservatism of the traditional singe-band uncertainty set; (2) the temporal correlation constraints of wind power/load prediction errors in MBUSCTC could limit the realization of uncertainties fluctuating frequently in uncertain intervals, thereby eliminating scenarios with lower probability in uncertainty sets. Then the proposed MBUSCTC is applied to UC problem, leading a robust UC model based on MBUSCTC, which is solved by Benders decomposition method and C&CG method. Finally, case studies based on the modified IEEE-118 bus system and an actual power system of China demonstrate that the proposed method can effectively reduce the conservativeness of the robust UC model and ensure the robustness of the unit commitment solution. [ABSTRACT FROM AUTHOR]

The combined heat and power system (CHPS) is one important type of the integrated energy system in Northern China. Compared with the independently operated power system, the combined heat and power system (CHPS) has a great potential to improve the utilization of wind energy in virtue of the energy storage of the heating system and power‐to‐heat (P2H) devices. This paper studies the optimal operation of the CHPS equipped with the electric boiler (EB) and heat pump (HP). Comprehensive factors are considered, including P2H conversion, the thermal inertia of district heating network (DHN) and buildings, and adjustable heat loads. An equivalent model of the heating system is developed to express the direct mathematical relations between the heat source and heat loads. Redundant details of the DHN are simplified to reduce the complexity of the optimization problem. Furthermore, a self‐repair method incorporated with the real‐coded genetic algorithm (RCGA) is proposed to efficiently handle the nonlinear constraints. The effectiveness of the solving method is verified in case studies. The impacts of the EB and the HP on the CHPS are compared in details. The results show that the HP offers better performance than the EB on coal saving and improving wind power integration. [ABSTRACT FROM AUTHOR]

• The training time of Long Short-Term Memory is reduced by changing network structure. • A new hybrid model is proposed for wind speed forecasting. • Four experiments are designed to verify the performance and reliability of the model. Obtaining accurate wind speed forecast result plays a decisive role in ensuring the reliable operation of the power system integrated with large-scale wind power. Deep learning methods are increasingly being used to predict wind speed, which have relatively high prediction accuracy but more time-consuming training processes. The purposes of this study are further to improve the prediction accuracy of the wind speed and reduce the training time of the deep learning method. In this paper, a novel hybrid model, New Cell Update Long Short-Term Memory combined with Empirical Wavelet Transform, is proposed to increase the prediction accuracy in shorter training time. At first, the original wind speed sequence is preprocessed into a series of sub-sequence by the empirical wavelet decomposition. Then each sub-sequence is trained by New Cell Update Long Short-Term Memory which is proposed by this paper respectively and the sum of each sub-sequence is treated as the final prediction results. In order to verify the performance of the proposed model, different decomposition methods and different prediction methods are compared on the four actual wind speed prediction cases in the Inner Mongolia, China from prediction accuracy and training time. The results demonstrate that: (1) New Cell Update Long Short-Term Memory network has slightly higher prediction accuracy and shorter training time than Long Short-Term Memory network. (2) The prediction accuracy of the model is significantly improved after empirical wavelet decomposition. Therefore, New Cell Update Long Short-Term Memory network combined with empirical wavelet decomposition is a competitive wind speed prediction method compared to the existing state-of-the-art approach. [ABSTRACT FROM AUTHOR]

Traditional static neural networks often fail to describe dynamic flood processes, while recurrent neural networks can reflect this dynamic feature of flooding. In this paper, a real-time framework for probabilistic flood forecasting using an Elman neural network is presented. Based on this framework, flood forecasting models with different lead times are developed and trained by a real-time recurrent learning algorithm for forecasting the inflow of the Xianghongdian reservoir of the Huai River in East China. The performances of these models are evaluated. The forecasting model having a 3 h lead time meets the precision requirements and is chosen as the deterministic flood forecasting model. Compared with the multilayer perceptron having a 3 h lead time, the relative error of flood volume is 5.28% less, and the coefficient of efficiency is 0.105 greater. We further analyze the error characteristics of the selected model and derive the discharge probability density function based on the heterogeneity of error distributions. The forecasted discharge intervals with different confidence levels, the expected values, and the median values are obtained. The results show that the average relative errors of flood volume and peak discharge obtained by the median value forecasting are −1.66% and 5.69% respectively, and the coefficient of efficiency is 0.784. The performance of the median value forecasting was slightly better than that of the deterministic forecasting, and considerably better than that of the expected value forecasting. This study demonstrates that the proposed model has high practicability and can provide decision support for flood control. [ABSTRACT FROM AUTHOR]

Wind power prediction technology is important for building novel power systems with a high proportion of renewable energy. The quality of Numerical weather prediction (NWP) has a significant impact on the accuracy of ultra-short-term wind power prediction (USTWPP). However, existing NWP do not reflect the adaptability of different weather processes, because of it' s forecasting errors. In view of this, this paper proposes an USTWPP method based on NWP wind speed correction and division of transitional weather process. The combined prediction method was first used to correct the NWP wind speed, and then we use the double clustering method to divide the transitional weather processes to establish a model for USTWPP based on different scenarios, the overall method was finally applied to a wind farm in west inner Mongolia, China. Compared to the pre-correction, the wind speed forecasted RMSE was reduced by 1.702 and the MAE by 1.366. Based on the wind power ultra-short-term prediction method proposed in this paper, the average reduction in RMSE is 5.93% and in MAE is 4.82% compared to the various comparison methods in the four seasons. The USTWPP method combining wind speed correction and double clustering division of transitional weather scenarios can significantly improve accuracy of USTWPP. • Propose a new NWP correction mechanism to improve the NWP forecasted errors. • Propose a multiple clustering method to improve the wind power prediction accuracy. • Propose weighted evaluation indicators of sequential and non-sequential clustering. • It provides new ideas for wind power prediction under different weather scenarios. • Proposed power prediction idea reduces the RMSE and MAE on average 5.93% and 4.82%. [ABSTRACT FROM AUTHOR]

To ensure the operational reliability of power systems, it is important for wind speed signal forecasting systems of wind turbines to be efficient, accurate and stable. This paper proposes a two-phase deep learning structure with network augmentation and pruning. By introducing the cross-correlation and quasi-convex optimization, a fractional quadratic programming problem and related convex optimization models are constructed to generate the augmented data for this proposed internal network; by pruning weakly correlated convolution channels, the redundant features of its external network are reduced. Furthermore, the closed-form solution of the convex optimization model is derived, which reduces the computational complexity considerably from O(n *log(2 N)) to O(n). The proposed approach has been extensively validated using the real data of the wind farm in China. The results of the numerical experiments demonstrate that the proposed method achieves the superior performance in the training flexibility, model accuracy, stability, and interpretability. [ABSTRACT FROM AUTHOR]

Aiming at the problem that the traditional wind power forecasting is difficult to deal with a large amount of strong volatility data and limited processing capacity of time series, a wind power forecasting method based on multi-model combination under stacking framework was proposed. First, the wind turbine data are cleaned by density-based spatial clustering of applications with the noise clustering method. Considering the differences of data observation and training principles, the proposed stacking method embedded multiple machine learning algorithms to utilize their diversified strength. The stacking base-learner includes the CBLSTM model, which has the advantages of deep architecture feature extraction, and takes into account data timing and nonlinear relationship as well as XGBoost and other tree ensemble learning models that were suitable for complex data modeling. The feasibility of the algorithm was verified by using the actual wind power data of two wind farms in Northeast and Western China. Experimental results show that the stacking ensemble learning method proposed has better forecasting performance and stability than other single forecasting models, which is of great significance to guide wind power dispatching operation and improve wind power consumption capacity. [ABSTRACT FROM AUTHOR]

Wind power is associated with uncertainties in scheduling and dispatching to the power grid, because the availability of wind speed is unknown in advance, and precise wind power forecasts are crucial to reducing these uncertainties. However, the accuracy of the wind power prediction, which is driven by average wind speed forecasting, is influenced by the spatial variability of the wind field. In this paper, the mechanisms of how wind power prediction errors are caused by the spatial heterogeneity of wind speeds and wind turbine power curves are analyzed. The degree of spatial heterogeneity of wind farms and errors caused by this are defined, and the relationships between various errors are revealed. We choose wind data collected from one observation site in northeast China as a sample; the results indicate that the short-term wind power prediction error is mainly caused by the inhomogeneity of the power curves. Moreover, these forecast errors can vary with season and installed wind farm capacity. [ABSTRACT FROM AUTHOR]

Wind energy assessment at multi-time scale is essential for the effective utilization of offshore wind resources. Conventionally, energy assessment factors are estimated based on parametric models under the assumption of wind speed stationarity. However, given the subjection of seasonal variability and long-term trends, the hypothesis is violated, especially in the context of climate change. In this paper, to advance the conventional approach, wind speeds were modelled using the decomposition-based method to consider the non-stationarity, and a novel framework for the estimation of energy factors at multi-time scale was designed. Using long-term ERA5 data, wind energy potential across the sea area along Chinese continental coastline was investigated. It is demonstrated that the established non-stationary models are superior to commonly used stationary models, allowing the estimation of energy assessment factors at arbitrary time scales after one-time parametrization of parametric distributions. Results confirmed that wind energy exhibits apparently temporal and spatial variability. The difference between annual averaged wind power density at different nodes exceeds 1000 W/m2. Moreover, significant long-term trends of wind energy characteristics were detected. The increase can be up to 16 W/m2/year in Taiwan Strait, emphasizing that an adequate consideration of the non-stationarity of wind speed in future research is required. [ABSTRACT FROM AUTHOR]

Estimating the total wind power output from the meteorological information at a province level (called Provincial Regional Wind Power Conversion Model, PRWPCM) plays vital and fundamental roles in energy modeling community and regional wind power forecasting. How to construct a reliable PRWPCM is a real challenge, since PRWPCM involves a large number of widely distributed wind turbines, massive meteorological data across the whole province, and complex nonlinear correlations. This paper proposes a lightweight PRWPCM by integrating Geographic Information System (GIS) analysis technology and Convolutional Neural Network (CNN). First, we conduct the land suitability analysis for wind turbine sites through the multi-criteria GIS layer overlay method to make the provincial wind turbine land suitability map (WTLSM) with scored divisions from the least suitable to the most suitable areas. On this basis, a new fusion mechanism for geographic and meteorological information is proposed, through which the raw meteorological data matrix can be reconstructed to filter and amplify the meteorological information that is more relevant to the total wind power output of the province, and avoid the time-consuming and labor-intensive data collection and processing, large-size model construction and validation. Second, a CNN-based regression architecture is designed to further capture the mapping relationship between the reconstructed meteorological data and total wind power output of the province; each type of meteorological factor is considered as an input channel and the attention modules are introduced to adaptively enhance useful channels and suppress less useful ones. Numerical experiments based on the wind power operation data of Yunnan Province, China, are conducted to validate the superiority of the proposed PRWPCM via benchmarking against 13 classical methods. • Mapping relationship between wind power output and meteorological information at a province level is recognized by integrating GIS and CNN. • A new fusion mechanism for geographic and meteorological information is proposed to achieve lightweight modeling. • Comparative experimental studies are conducted in Yunnan province, China. [ABSTRACT FROM AUTHOR]

Accurate and robust wind power forecasting (WPF) is great significance to ensure the safe and stable operation of the power system and promote the transformation of low-carbon energy. However, the high randomness and intermittency of wind power bring great challenges when designing reliable forecasting models. In this paper, a novel spatial-temporal attention graph convolutional network model is proposed. Firstly, the spatial attention mechanism is used to aggregate and extract the spatial correlations of the raw wind power data. Secondly, the temporal attention mechanism is applied to capture the temporal correlations. Then, the extracted spatial-temporal correlations were put into the temporal convolution network and the spatial convolution network to further obtain the temporal and spatial dependencies. Finally, the wind power forecasting results is output through the full connection layer. The proposed method is verified by using wind power data from real wind farm in China. The experimental results reveal that the proposed depth spatiotemporal prediction model has more significant advantages than other advanced models in terms of prediction accuracy and stability. • The spatiotemporal attention mechanism is used to learn the dynamic spatiotemporal correlations. • The spatiotemporal convolution mechanism is applied to enhance feature extraction of wind power. • The proposed model can improve the accuracy of wind power prediction by experiments. • Real datasets from wind farm in China is employed for the modeling study. [ABSTRACT FROM AUTHOR]

Accurate forecasting of the agricultural power load is important for rural electricity networks' safe and stable operation. But it is more uncertain and difficult to forecast than industrial, commercial, and residential loads. Multivariate time series prediction methods have problems such as poor refinement of weather services and difficulty in quantifying the influencing factors. Univariate time series prediction methods should be emphasized, and the characteristic information in the historical load data should be fully exploited. Therefore, this paper systematically investigates the decomposition strategy and attention-based recurrent neural network for univariate time-series multi-step prediction. The decomposition strategy is employed to generate derived variable sequences from the target sequence as inputs for the model, while the dual-stage attention mechanism is used for dynamically selecting features. A one-year real-world dataset of agricultural power loads in southern China is used for validation. The effectiveness of two different decomposition algorithms on dual-stage attention-based recurrent neural network (DARNN) is discussed, then the proposed ensemble empirical mode decomposition and dual-stage attention-based recurrent neural network (EEMD-DARNN) is compared with four univariate time series prediction models and three ablation models. The proposed model is optimal in four evaluation indicators, with R 2 , R M S E , M A P E , and M A E of 0.970, 12.298, 0.040, and 7.335 respectively in the shortest forecast horizon (15 min), and 0.941, 17.305, 0.065 and 11.347 respectively in the longest forecast horizon (1 h). It is a significant improvement over the existing models. In conclusion, EEMD-DARNN can achieve more accurate ultra-short-term agricultural power load forecasting. [ABSTRACT FROM AUTHOR]

Wind speed accurate forecasting plays an important role in preserving the stability of offshore wind power. Most of current predictions are based on a single wind node. It is difficult for this methods to capture wind high dimensional features and latent spatio-temporal dependencies. In this paper, we propose a general graph optimization neural network specifically for multi-node offshore wind speed prediction named spatio-temporal correlation graph neural network. The proposed model firstly employs graph convolution, which performs Laplace transforms instead of the traditional convolution, to capture the potential spatial dependencies from the nodes' relationship and historical time series better. The channel-wise attention makes the original concentrated weights within a region constructed by adjacency matrix disperse to all input nodes, which distinguishes the nodes' contributions and generates high dimensional spatial features. Long short-term memory is applied to extract temporal correlation from the high dimensional spatial features. The model has ability to excavate the full potential of spatial-temporal dependencies from multiple wind nodes to the utmost. Experiments select 120 wind nodes in the China sea for prediction. The results show that the proposed model can be very competitive with state-of-the-art methods and holds great performance on multi-node and multi-step wind speed forecasting. • A graph optimization model is proposed for multi-node offshore wind speed prediction. • The GCN module can capture multiple wind nodes relationships' spatial correlation. • Channel-wise attention distinguishes the nodes' contributions to spatial dimensions. • The parallel LSTMs is specifically adopted to further integrate time dependencies. • The proposed STGN can track actual wind speed tendencies and maintain stability. [ABSTRACT FROM AUTHOR]

• A hybrid prediction system is proposed to provide technical support for achieving energy sustainable development goals. • Extract original complex time series features using CEEMDAN. • Optimize Extreme Learning Machine using particle swarm optimization algorithm. • Experiments are conducted for four seasons of wind speed to verify that the model can effectively predict year-round data. • Experiments demonstrate that CEEMDAN-PSO-ELM can predict complex energy data efficiently and accurately. As environmental concerns and the energy crisis intensify, advancing the use of new energy sources such as wind and photovoltaic is an important means to achieve sustainable energy development. However, the random fluctuation characteristics and seasonality of wind and light make them difficult to predict, which brings many operational risks to grid security and power dispatch. Therefore, this paper uses the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) as the decomposition algorithm, which can effectively avoid the problems of modal confusion and noise residuals and better identify the trend, seasonality and nonlinear characteristics of the series. The Particle Swarm Optimization (PSO) algorithm is also utilized to improve the prediction accuracy and stability of the Extreme Learning Machine (ELM). Combining CEEMDAN and PSO-ELM models, a high-precision hybrid forecasting system that can effectively reduce the effects of stochastic fluctuations is proposed. In this paper, wind speed data from four different seasons at Changma wind farm in China are selected to verify the effectiveness and generalization ability of this hybrid prediction system. The results show that the improvement of ELM by PSO and CEEMDAN significantly improves the prediction accuracy of the model, and the hybrid prediction system can be applied to time series with different data characteristics and variation patterns in each season, and its prediction accuracy and model performance are significantly better than other comparative models. [ABSTRACT FROM AUTHOR]

In wind power prediction, the input probability distributions in the different sub-periods are shifted owing to the strong randomness of the input features, such as wind speed and direction. This may violate the assumption for machine learning that the training and test data meet the condition of being independent and identically distributed, resulting in an insufficient generalization ability of the prediction model that is trained with the training data and applied to unknown test data. To address this problem, this study proposes an adaptive temporal transformer method for short-term wind power forecasting. First, a temporal transformer model with a gate recurrent unit and multi-head attention layers was used to extract the short- and long-term temporal information of the multiple input variables. Then, an adaptive learning strategy consisting of two stages—temporal distribution characterization and temporal distribution matching—was developed to explore the common knowledge hidden in each sub-period. The case results for an actual wind farm in northwest China showed that the proposed method could effectively weaken the adverse effects of the shifts in time series distribution on forecasting and improve the accuracy and generalization of short-term wind power prediction. [ABSTRACT FROM AUTHOR]

Spatiotemporal forecasting involves generating temporal forecasts for system state variables across spatial regions. Data‐driven methods such as Convolutional Long Short‐Term Memory (ConvLSTM) are effective in capturing both spatial and temporal correlations, but they suffer from error accumulation and accuracy loss as forecasting time increases due to the nonlinearity and uncertainty in physical processes. To address this issue, we propose to combine data‐driven and data assimilation (DA) methods for spatiotemporal forecasting. The accuracy of the data‐driven ConvLSTM model can be improved by periodically assimilating real‐time observations using the ensemble Kalman filter (EnKF) approach. This proposed hybrid ConvLSTM‐EnKF method is demonstrated through PM2.5 forecasting in China, which is a challenging task due to the complexity of topographical and meteorological conditions in the region, the need for high‐resolution forecasting over a large study area, and the scarcity of observations. The results show that the ConvLSTM‐EnKF method outperforms conventional methods and can provide satisfactory operational PM2.5 forecasts for up to 1 month with spatially averaged RMSE below 20 μg/m3 and correlation coefficient (R) above 0.8. In addition, the ConvLSTM‐EnKF method shows a substantial reduction in CPU time when compared to the commonly used NAQPMS‐EnKF method, up to three orders of magnitude. Overall, the use of data‐driven models provides efficient forecasts and speeds up DA. This hybrid ConvLSTM‐EnKF is a novel operational forecasting technique for spatiotemporal forecasting and is used in real spatiotemporal forecasting for the first time. Plain Language Summary: This study introduces an advanced method (ConvLSTM‐EnKF) for PM2.5 forecasting in China, which is a challenging task due to its large area coverage, and complex topographical and meteorological conditions. This innovative approach combines two techniques: one looks at historical data to make forecasts, while the other periodically incorporates new information from observations to improve forecasts over time. This combination significantly improves forecasting accuracy and provides reliable operational PM2.5 forecasts for up to 1 month. Notably, this method is more efficient than traditional approaches. Beyond air pollution, the method holds promise for improving predictions in other areas, including weather, climate, and environmental systems, marking a substantial step forward in our ability to anticipate and understand complex spatiotemporal phenomena. Key Points: A hybrid data‐driven (ConvLSTM) and data assimilation (EnKF) method is proposed for accurate and efficient spatiotemporal forecasting. A pre‐trained ConvLSTM is used for both the forecasting and assimilation processes, enabling fast online operational forecastingThe ConvLSTM‐EnKF demonstrates high efficiency by reducing CPU time by three orders of magnitude compared to the NAQPMS‐EnKF, a widely used air quality forecasting model in ChinaThe ConvLSTM‐EnKF enables online data assimilation (DA) for high‐dimensional systems and improves DA accuracy by allowing the use of a large ensemble size [ABSTRACT FROM AUTHOR]

Wind energy has become a kind of attractive alternative energy in power generation field due to its nonpolluting and renewable properties. Wind speed forecasting acts an important role in programming and operation of power systems. However, achieving high precision wind speed forecasts is still consider as an arduous and challenging issue with the randomization and transient exist in wind speed time series. For this reason, this paper proposed two novel de-noising-reconstruction-based hybrid models which consist of novel signal decomposed methods, feature selection approaches and predictors based on quantile regression and optimization algorithm to achieve more accurate short term wind speed forecasting. The developed hybrid models firstly eliminate inherent noise from the wind speed sequences via decomposed method and subsequently construct the appropriate datasets for the forecasting engines by adopting the feature selection method; finally, establish the predictors for the forecasting task. To verify the effectiveness of proposed forecasting models, 1-h and 2-h wind speed data collected from Yumen, Gansu province of China mainland is used as case studies. The computational results demonstrated that the developed hybrid models yield better performance contrast with those of other models involved in this research in terms of both wind speed deterministic and probabilistic forecasting. • Two hybrid strategies with four modules are developed for wind speed forecasting. • A modified signal decomposition method is proposed for wind speed noise reduction. • A novel correlation-analysis-based approach is proposed to feature selection. • The proposed QRNN-based model can obtain forecasting results in different quantile. • The hybrid models perform well in both deterministic and probabilistic forecasting. [ABSTRACT FROM AUTHOR]

• An advanced forecasting system is proposed for short-term wind speed prediction. • The data pre-processing technique can extract effective information from the raw sequences and eliminate the volatility and uncertainty of the data. • Choose the appropriate benchmark models in different situations based on optimal benchmark model selection strategy. • A multi-objective optimizer is applied to find the optimal weights and a theoretical proof indicates that the weights assigned by this optimizer are Pareto optimal solutions. • Our proposed forecasting system can quantify the uncertainty of the wind speed sequences. Facing the increasing depletion of traditional energy resources and the worsening environmental issues, wind energy sources have been widely considered. As an essential renewable energy resource, wind energy features abundant deposits, extensive distribution, non-pollution, etc. In recent years, wind power generation occupies a non-negligible position in the electric power industry. Stable and reliable power system operation demands accurate wind speed prediction (WSP), but the inherent randomness of wind speed sequences complicates their fluctuations and causes them to be uncontrollable. In this paper, an innovative WSP system is proposed, which combines data pre-processing technique, benchmark model selection, an advanced optimizer for point forecast and interval forecast. Furthermore, this paper theoretically demonstrates that the weights allocated by this optimizer are Pareto optimal solutions. Six interval data from two sites in China are utilized to validate the forecasting performance of our developed model. The experimental results indicate that the developed model can achieve superior accuracy compared to the tested models in all cases for point forecast, and also obtains the forecasting interval with high coverage and low width error, which is an extremely crucial instruction to guarantee the security and stability of the power system. [ABSTRACT FROM AUTHOR]

The volatility and uncertainty of wind energy has brought great challenges to its accommodation in electric power systems. To determine a wind power trading strategy in the real-time power market, the accurate assessment of wind energy accommodation capability (WAC) is of great significance. However, most current studies investigate the wind energy accommodation potential from the perspective of dispatch, but rarely provide quantitative assessment results. Additionally, the non-anticipativity of decisions has not been considered in the assessment yet. This paper proposes a novel quantitative assessment method for WAC based on the multi-stage robust optimization (RO), which addresses the anticipativity issues in the traditional two-stage method while maintaining the decision-making process' robustness. In the assessment method, the operational risk is integrated via a tractable scheme to obtain dynamic admissible WAC boundaries. To obtain the optimal solution of the proposed multi-stage RO problem, a fast robust dual dynamic programming (FRDDP) algorithm is employed, where the adaptive techniques are developed to accelerate the computation. Numerical studies on the modified IEEE 14-Bus system and a real-world system in Zhejiang Province of China validate the effectiveness of the proposed assessment model and adaptive acceleration techniques. The simulation results demonstrate the presented method brings a 18.87% reduction in operational cost, and reduces 29.34% curtailment of wind energy. Compared with the original FRDDP, the adaptive technique significantly reduces the computational consumption by 73.34% on the real-world test system. • A novel assessment method for WAC is proposed based on the multi-stage robust optimization. • Tractable risk evaluation method is integrated in the multi-stage framework. • Adaptive techniques are designed for FRDDP method to accelerate the optimal solution. • The proposed method achieves both non-anticipative and robust assessment decisions. [ABSTRACT FROM AUTHOR]

Faced with the growing renewable energy requirements, there is increased interest in cross-region of large-scale renewable energy market, which provides an alternative path for building sustainable power systems. Critically, the development of a renewable energy-dominated electricity market is an important way to achieve global climate goals and energy conversion. Despite improved achievement of electricity demand response (EDR) market, only limited development in the coordination capacity and development scale of EDR are dominated by renewable energy. Moreover, the normal operation and work efficiency of the system is greatly affected due to data transmission errors and other human factors. Thus, it is of great importance for the State Grid to accurately identify the data sources and realize the interactive development of cross-region power systems. This paper presents a new cross-region (province) electricity demand response (CR-EDR) model in China for large-scale renewable energy participating in EDR market. This model is applied to three provinces in China based on renewable energy, and fully consider how wind power is integrated with EDR in terms of operation, grid connection and optimization. Presently, China is in the initial stage of development, and the identification of data anomalies is inevitable for the CR-EDR. To solve this problem, a novel machine learning (ML)-based approach is proposed for effective identification of EDR. By calculating wind power output and customers' EDR results, reliable feature sequences can be obtained. Finally, all the feature sequences are uploaded to cross-region system operators (CR-SO) for classification and identification by ML. In the case studies and discussions, we integrated all feature sequences to CR-SO for identification and present a novel process approach to implement EDR, the random forest (RF) enables 100% accuracy for training set and 99.7685% for testing set with small training samples. Compared with RF, support vector machine only achieves 79.1667% for testing set with small training samples. With accurate RF identification results, the stable operation capability and management level of the system can be effectively improved. The proposed methodology creates a new provincial perspective of China and the establishment of CR-EDR, which provides a theoretical and methodological guidance for all countries and regions to develop CR-EDR. • A new cross-region (province) electricity demand response management is proposed. • Large-scale renewable energy participating in demand response is fully considered. • Machine learning-based approach is adopted for data integration and identification. [ABSTRACT FROM AUTHOR]

• Using intelligent algorithms to forecast wind sequences in wind-fire coupling scenario. • Using the VMD technology to reduce the complexity of the wind speed sequence. • The optimal parameter combination of the VMD method is obtained by HS algorithm. In this study, an effective model for wind speed prediction in a coupled wind-fire scenario is proposed. (a) The original wind speed sequence is decomposed using the variational mode decomposition (VMD) algorithm to describe the different scales of perturbations to the wind speed caused by various physicochemical processes in terms of the decomposed modal components. (b) To avoid the limitations of VMD decomposition caused by manual parameter settings, the optimal parameter combinations [ k , α ] for VMD are determined by using the harmony search (HS) algorithm. (c) Train k attention mechanism-long short-term memory (AM-LSTM) models to predict each subsequence separately, and finally obtain the predicted value of the original wind speed by reconstructing the prediction results of each subsequence. To train the HS-VMD-AM-LSTM model and verify its validity, a medium-scale point-burning experiment was conducted in Heilongjiang Province, China, and the corresponding dataset was established. In comparing the models, five error statistics are used, and box-and-line plots, Taylor diagrams, and ANOVA tests are employed to compare the model performance from multiple perspectives. The experimental results show that the average absolute percentage error of the model proposed in this paper is 8.08% on the test set data, which is a great advantage over other models. This study can guide the multi-time step prediction of fire spread and fire control decisions. [ABSTRACT FROM AUTHOR]

In the context of carbon neutrality, renewable energy, especially wind power, solar PV and hydropower, will become the most important power sources in the future low-carbon power system. Since wind power and solar PV are specifically intermittent and space-heterogeneity, an assessment of renewable energy potential considering the variability of wind power and solar PV with high temporal resolution in different regions will facilitate more accurate identification of the decarbonization pathway of power system. In this paper, the complementary output potential of wind-solar-hydro power every 15 min in 31 Chinese provinces is evaluated by developing a multi-objective optimization model based on Nondominated Sorting Genetic Algorithm II. The results show that the total annual complementary power generation potential in China is 17.57 PWh, of which the three components account for 47.8%, 25.3% and 26.9%, respectively. Inner Mongolia and Tibet are the major renewable energy source provinces with annual complementary power generation potential of 5330 TWh and 3907 TWh, accounting for 30.3% and 13.7% of the total power generation potential, respectively. The temporal potential of wind-solar-hydro power varies greatly, with daily potential is more volatile than monthly. Seasonal and spatial heterogeneity of the complemental renewable potential makes some provinces suffer power shortage during long-hours period especially in winter. Our findings will encourage a higher penetration of renewable energy, the promotion of multi-energy complementarity, and the development of inter-provincial power transmission and energy storage infrastructure in China's future power sector. • A multi-objective wind-solar-hydro complementary optimization model is developed. • Electricity supply and demand have gaps at different temporal and spatial scales. • Wind-solar-hydro complementary potential shows great temporal and spatial variation. • Renewable complementarity can improve China's future power system stability. [ABSTRACT FROM AUTHOR]