Search

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]

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]

Accurate and credible operation data sets of wind and solar power stations are the basis of many research works. However, such data sets often contain abnormal data due to failure, maintenance, energy curtailment, etc. The existing identification methods fail to consider the operating characteristics of power stations and the forms of abnormal data, resulting in low identification ability. Therefore, an adaptive identification method of abnormal data (AIMAD) in the wind and solar power stations is proposed in this paper, including the bidirectional one-sided quartile method and double DBSCAN method to deal with unevenly distributed abnormal data; the improved K-means clustering method based on the distance between the cluster center and benchmark power curve to process the abnormal data that are densely accumulated and closely connected with normal data in the power scatter diagram. The proposed method can adjust adaptively according to the forms of abnormal data to realize accurate identification and has strong robustness for power stations. The operation data of 30 wind farms and 8 solar plants in China are taken as examples to verify the effectiveness and superiority of the proposed method. • BOQ and d-DBSCAN are proposed to deal with unevenly distributed abnormal data. • Improved K-means method is proposed for identifying stacked abnormal data. • AIMAD is proposed to realize accurate identification of abnormal data. • Operation data in 38 stations are used to verify the effectiveness of AIMAD. [ABSTRACT FROM AUTHOR]

The promotion of wind power is an important strategic measure to promote energy transformation and achieve carbon neutralization in China. Driven by a series of industrial policies, China's wind power industry is still faced with the dilemma of "large quantity yet poor quality". Therefore, the paper considers as research object the wind power industry policies issued by the government of China between 2008 and 2019, and evaluates their impact on the innovation quality of enterprises from the perspective of financing modes. The results show that different categories of industry innovation policies and their combination have an important positive influence on enterprise innovation quality. There are differences in the regulatory effects of different financing modes on wind power industrial policy and enterprise innovation quality: internal financing inhibits the effect of industrial policy on enterprise innovation quality, while external financing promotes the impact of industrial policy on enterprise innovation quality. Further analysis shows that different categories of innovation policies and their combinations have impacts on the innovation quality of both private and state-owned enterprises, and in many regions. Finally, based on the research results, there are recommendations for policy managers and micro enterprises to stimulate the innovation quality of wind power plants. • The paper evaluates wind power industry policies and their combination impact on the innovation quality of enterprises from the perspective of financing modes. • Different categories of wind power industry policies and their combinations have an important positive influence on enterprise innovation quality. • There are conspicuous differences in the regulatory effects of different financing modes on industry policy and enterprise innovation quality. • Different types of industry policies and their combinations have impacts on the innovation quality of both private and state-owned enterprises, and in many regions. • There are differences in the regulatory effects of different financing modes on industry policy and innovation quality of both private and state-owned enterprises, and in many regions. [ABSTRACT FROM AUTHOR]

With the centralization of wind power development, power-prediction technology based on wind power clusters has become an important means to reduce the volatility of wind power, so a large-scale power-prediction method of wind power clusters is proposed considering the prediction stability. Firstly, the fluctuating features of wind farms are constructed by acquiring statistical features to further build a divided model of wind power clusters using fuzzy clustering algorithm. Then the spatiotemporal features of the data of wind power are obtained using a spatiotemporal attention network to train the prediction model of wind power clusters in a large scale. Finally, the stability of predictive performance of wind power is analyzed using the comprehensive index evaluation system. The results show that the RMSE of wind power prediction is lower than 0.079 at large-scale wind farms based on the prediction method of wind power proposed in this paper using experience based on the data of 159 wind farms in the Nei Monggol Autonomous Region in China and the extreme error is better than 25% for the total capacity of wind farms, which indicates high stability and accuracy. [ABSTRACT FROM AUTHOR]

This paper discusses how the incorporation of high-resolution ground coverage dataset ESA WorldCover into a wind flow field and wake simulation calculation, as well as the use of the coupled wake model for wind farm output simulation, can improve the accuracy of wind resource assessment using engineering examples. In the actual case of grid-connected wind farms in central China, SCADA wind speed data is reconstructed to the free flow wind speed in front of the wind turbine impeller using the transfer function of the nacelle, and the wind farm is modeled using OpenWind software, simulating the wind speed at the height of each wind turbine hub and each wind turbine output. The results show that when other initial data are consistent, using ESA's high-precision land cover dataset WorldCover 10 m to make roughness lengths which improves the wind farm output simulation accuracy by 8.91%, showing that it is worth trying to apply WorldCover 10 m to the wind farm simulation design. At the same time, this case is used to compare and analyze the application of the Eddy-Viscosity wake model and the two coupled wake models based on the Eddy-Viscosity wake model. The results show that the coupled wake model will have higher accuracy than the Deep Array Eddy Viscosity wake model and it is 1.24% more accurate than the Eddy Viscosity wake model, and the ASM Eddy Viscosity wake model is 5.21% more accurate than the Eddy Viscosity wake model. [ABSTRACT FROM AUTHOR]

Currently, wind power prediction has so many problems in the ultra-short-term time scale (0–4h), which is difficult to improve the deterministic prediction and probability prediction accuracy of the wind farm cluster because it can not fully explore the spatio-temporal correlation between the physical change process and the wind farm. In this paper, a method of ultra-short-term deterministic and probability prediction of wind farm cluster power based on Graph Convolutional Network (GCN) considering fluctuation correlation (FC) is proposed. Firstly, the adjacency matrix is constructed based on the power sequence fluctuation information of each wind farm, and the GCN is designed. Secondly, the spatio-temporal features of power and Numerical Weather Prediction (NWP) wind speed are extracted and fused based on the network model of dual-channel and dual-adjacency matrix. Thirdly, in order to effectively improve the prediction accuracy, a trend switching mechanism is designed based on the effective trend of NWP. When the fluctuation information of NWP is not accurate, the graph structure is constructed by the adjacency matrix based on geographical location to achieve effective prediction. Finally, the method proposed in this paper is applied to wind farm clusters in three provinces of China, compared with some commonly used methods, the average RMSE is reduced by 1.34 %, 1.62 %, 2.07 %, respectively, and the average CWC is reduced by 6.12 %, 4.49 %, 6.62 %, which verifies the effectiveness of this method. • A method for calculating FCC is proposed. • Combined with FCC, the graph structure of wind farm cluster is constructed. • A two-module GCN is designed. • A trend-switching mechanism is designed. [ABSTRACT FROM AUTHOR]

Compared with the point prediction of the wind power, the interval prediction provides more information to assist power dispatching and optimize quotation strategies in power trading. To improve the accuracy of the prediction intervals, this paper proposes a novel model based on the lower upper bound evaluation (LUBE) by the gate recurrent unit (GRU) network. First, the Pearson correlation coefficient is selected to screen out the variables related to wind power, which can simplify the input variables of the prediction model while preserving the feature information as much as possible. Afterwards, with the consideration of the prediction interval relative deviation (PIRD), the improved objective function is introduced. Based on the GRU network, the prediction intervals of the wind power can be obtained to minimize the new objective function. Finally, by choosing several mainstream neural networks, experiments are conducted towards a certain wind farm in China. The results show that the proposed model has a significant improvement in both prediction interval width and PIRD under the given prediction interval coverage probability (PICP). [ABSTRACT FROM AUTHOR]

[Display omitted] • A liner positive correlation is revealed between wind farm distance and ecological impacts. • The ecological obstacle points increased 350 % after construction of wind farm. • The proportions of forest around weak points raised from 38 % (50 m range) to 49 % (150 m range). • Protection, restoration, and compensation strategies are proposed according to recession degrees. The wind energy industry is developing rapidly in China with a maximum capacity worldwide. Meanwhile, the stability of the ecological network is challenged by extensive renewable energy expansion. There are still research deficiencies in wind farm ecological impacts at project scale from an ecological restoration perspective. It is of great necessity to monitor the ecological impacts with time going and explore ecological restoration strategies for wind power development. The research case of Zhongying Wind Farm is selected based on investigation and interviews regarding its ecological impact in the prior study. It employs a comparative methodology by comparing the ecological quality before and after the construction of Zhongying Wind Farm. Raw data from Landsat 8, the Digital Elevation Model (DEM), the Normalized Difference Vegetation Index (NDVI), and wind turbine statistics originating from open data platforms are analyzed and visually represented with ArcGIS. This paper establishes an ecological network based on morphological spatial pattern analysis (MSPA) and the Minimum Cumulative Resistance (MCR) model to quantify wind farms' impacts on ecological corridors. The circuit theory and Pajek software are used to identify and categorize the ecological nodes into weak and obstacle points. The results reveal that ecological impacts on ecological corridors decay with distance, reflecting changes in length, connection strength and cumulative values of corridors. While the impacts on ecological nodes depend on nodes' attributes: the number of weak points increased by 18.5 %, and obstacle points increased by 350 %, with their locations shifting from the edges of urban construction sites to the edges of wind farm. Differentiated strategies are proposed according to the impact magnitude of each ecological corridor and node: such as dynamic inspection mechanism, construction prohibition for protection; corridor structure and function recovering, stepping stones addition for restoration; buffer belts, warning radar, and monetary schemes for compensation. This research fills the gap of ecological impact assessment under the challenges of wind energy expansion. It helps to balance wind energy development and ecological restoration at the regional level. [ABSTRACT FROM AUTHOR]

Aiming at a large number of decentralized resources such as rural biomass, rooftop photovoltaic, and decentralized wind power, a novel rural virtual power plant (VPP) has been conceptualized. The VPP is integrated by biomass waste conversion system (BWC), carbon to energy (C2P), demand response aggregator (DRA), and distributed renewable energy (DRE), namely, BDCD-VPP. Then, this paper proposes a data-driven two-stage robust optimization dispatching model for BDCD-VPP considering carbon-green certificates equivalent conversion mechanism. This model aims to address the uncertainty of wind power plants (WPP) and photovoltaic (PV) power generation. Strong duality theorem (SDT) and C&CG algorithm are applied to construct this model. Thirdly, the Aumann-Shapley method (A-S) was enhanced by incorporating risk factor, cost factor, and carbon reduction factor. This refinement results in the development of a synergistic scheduling revenue allocation method for electricity‑carbon-green certificates. Finally, the Lankao rural energy revolution pilot program in China is selected as the case study, the results showed: (1) The BDCD-VPP aggregates distributed energy sources such as the rural WPP and the PV to realize electricity‑carbon-electricity cycle effect. The BDCD-VPP generates a green certificate revenue of 47.17¥/MWh and exhibited carbon emissions of 0.37 t/MWh. The proposed Carbon-Green Certificates Equivalent Conversion Mechanism increases BDCD-VPP benefit ratio by 3.52%. (2) The proposed two-stage robust optimization dispatching model enhances the ability of BDCD-VPP to adapt to uncertainty. Compared to the day-ahead stage, biomass power generation (BPG) and waste power generation (WPG) increase upward peaking power by 24.05% and 9.99% in intra-day stage. Flue gas treatment system (FG-TS), gas-power plant carbon capture (GPPCC) and power to gas (P2G) increase downward peaking power by 65.15%, 70.99% and 25.94%. (3) Utilizing the proposed benefit allocation methodology, BPG and WPG need to concede 38.25¥/MWh and 65.02¥/MWh for carbon emissions associated with electricity. WPP and PV need to concede 64.25¥/MWh and 33.71¥/MWh for power generation uncertainty. GPPCC, P2G, DRA, and small hydropower station (SHS) obtain revenues of 24.48 ¥/MWh, 55.07 ¥/MWh, 70.38 ¥/MWh, and 51.30 ¥/MWh. Compared to the A-S, the proposed benefit allocation methodology exhibits 6.92% improvement in satisfaction. Overall, the proposed data-driven two-stage robust optimization dispatching model and benefit allocation strategy facilitates the optimal aggregation and utilization of rural distributed energy resources, considering the interests of various stakeholders. This is conducive to achieving a clean and low-carbon transformation of the overall energy structure. • Proposed a novel rural virtual power plant considering biomass waste conversion and carbon to power. • Designed carbon-green certificate equivalence conversion mechanism. • Proposed a data-driven scenarios generation and reduction strategy for uncertainty factors. • Construct a two-stage robust optimization dispatching model and strong duality C&CG algorithm. • Construct an improved Aumann-Shapley-based benefit allocation strategy [ABSTRACT FROM AUTHOR]

Accurately predicting wind and photovoltaic power is one of the keys to improving the economy of wind-solar complementary power generation system, reducing scheduling costs and no-load losses, and ensuring grid stability. However, the natural properties of energy result in complex fluctuations in their corresponding power sequences, making accurate predictions difficult. Therefore, this paper proposes an intelligent prediction system that combines decomposition algorithms and deep learning for ultra-short-term prediction of wind and photovoltaic power. First, an improved decomposition algorithm is proposed, based on fuzzy entropy's property that its value increases with the increase of sequence uncertainty, particle swarm optimization (PSO) is used to search for the optimal parameter combinations of variational modal decomposition (VMD), so that it can automatically adjust the parameters for energy data with different characteristics to reduce the human error. Then, a convolutional neural network (CNN) architecture that balances operational efficiency and prediction performance is constructed, and the hyperparameters of the CNN are optimized using the wild horse optimization algorithm (WHO) to improve the stability and accuracy of the prediction model. In this paper, real data from wind power plants and photovoltaic power plants in China are used as experimental objects, and experiments are carried out in three aspects, namely, benchmark model selection, decomposition algorithm comparison and combined model comparison. The results show that selecting CNN as the benchmark model is a good choice; the improved VMD has better decomposition performance than other state-of-the-art decomposition algorithms. The system proposed in this paper is highly generalizable and adaptive, and its prediction performance and accuracy greatly outperform that of other comparative models, with prediction accuracies improved by 72% and 79%, respectively, compared to a single CNN model. • The hyperparameters of VMD are determined by using PSO based on fuzzy entropy. • Optimize convolutional neural network using the wild horse optimization algorithm. • The intelligent prediction system can accurately predict wind power and PV power. • Experiments based on power data from actual wind farms and PV plants. • A deep learning prediction method applied to wind and solar complementary systems. [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]

Wind power curve describes the relationship between wind speed and output power of wind turbine. In this paper, we propose a novel image-based abnormal data cleaning algorithm aiming to provide high quality data for wind power curve modeling and relevant applications. For image binarization, a multiscale space is built to determine the optimal scale at which the most stable as well as informative shape representations are extracted. The active shape model is utilized to model the power curve shape and generate a set of segmentation candidates for filtering abnormal data. An energy space is constructed based on class uncertainty map generated from dual feature images and eventually the optimal segmentation boundary is determined by an optimization process. Comparative experiments are conducted over the real-world datasets consisted of 37 wind turbines from two wind farms located in West and East China respectively. The accuracy reaches as high as 0.95, the precision rate P is 0.98, recall rate R is 0.99 and F1-score is 0.96, which demonstrates the superior performance of the proposed method. Besides, the reproducibility and sensitivity analyses are also carried out to assess the algorithm's performance. • A novel image-based abnormal WPC data cleaning algorithm is presented in this paper. • A multi-scale image space is built to determine the optimal scale for WPC data binarization. • Dual feature images are constructed to generate the class uncertainty map. • The Active Shape Model is used to model WPC shapes and filter abnormal data. • Accuracy, reproducibility and sensitive analysis are conducted on real-world datasets. [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]

The rotational inertia and primary frequency response capabilities of power systems are declining as synchronous generators (SGs) are replaced by inverter-based variable renewable energy (VRE) resources. Therefore, when a high VRE proportion is present, it becomes essential to include frequency security constraints in power system planning. Under this circumstance, the decline in SGs would deteriorate the system frequency response performance; thus, inverter-based resources are supposed to provide frequency response support. This paper presents a frequency-constrained stochastic planning method for high VRE share systems. Frequency response support from wind farms is considered in the planning process for the first time, and the unique characteristics of wind power support are addressed. Specifically, the uncertainty of and variations in wind power support capabilities are modeled from the field-measured data, and the optimal combination of various support schemes can be determined by introducing binary variables with novel linear constraints into the planning process. Moreover, the nonlinear frequency constraints are transformed and embedded in the planning model by the proposed computationally efficient adaptive piecewise linearization method. The planning is formulated as a stochastic optimization model to consider the VRE power uncertainty. Finally, case studies on the IEEE 30-bus system validate the proposed method, with results indicating time savings of 22%. Further, compared with the case that only SGs provide frequency support, the results based on the East China system demonstrate that considering wind power support can improve the VRE share from 49.5% to 79.7%. [ABSTRACT FROM AUTHOR]

The widespread implementation of feed-in tariff (FIT) policies has played a crucial role in fostering the development of wind power, with their positive effects firmly established in numerous studies. However, the impact of regionally differentiated FIT policies on the misallocation of wind power resources remains a topic of contention, with limited research dedicated to this area. This paper aims to address this gap by examining the implications of such policies on the intensive and extensive margins of wind power installed capacity in China, shedding light on the underlying mechanisms driving resource misallocation. Empirical findings indicate that, concerning the intensive margin, the policy amplifies the concentration of wind power investments in regions characterized by abundant wind resources but low electricity demand. These regions present favorable conditions for large-scale wind farms with cost advantages, consequently exacerbating the misallocation of wind power resources. However, on the extensive margin, the policy promotes the likelihood of locating small and medium-sized wind farms in regions with poor wind resources but higher tariff rates, thus partially mitigating resource misallocation. In summary, China's policy hampers wind power investments in regions characterized by high electricity demand but limited wind resources. This suggests that the negative impact on the intensive margin outweighs the positive impact on the extensive margin. The findings of this study bear significant implications for the development of renewable energy support policies, particularly in countries grappling with substantial regional disparities in renewable energy resources. • We cope with the controversial effect of FIT policies on the resource misallocation • We provide novel perspectives as the intensive and extensive margins • China's regionally differentiated FIT policy hampers wind power investments • We provide implications for countries implemented regionally differentiated FIT [ABSTRACT FROM AUTHOR]

China is facing the challenge of selecting appropriate policies to implement tradable green certificate (TGC) under the renewable portfolio standards (RPS). This paper proposes a tripartite evolutionary game model among thermal power plants, green power plants and the grid under the RPS and TGC policy to analyze the evolutionary stability strategies (ESSs) of unilateral subjects and systems and use numerical simulation to discuss the influence of different types of TGC purchase ratios and different trading markets on the choice of tripartite strategy. The results are as follows. (1) When the renewable energy consumption quota ratio is 21%, thermal power plants are more and more active in choosing to trade TGC as the ratio of wind power TGC and photovoltaic TGC gradually increases from 1:5 to 5:1. (2) In the TGC market where the price of wind power and photovoltaic TGC is 50 yuan, green power plants are more inclined to hold TGC; in the subsidized TGC market, where the price of wind power TGC is 190 yuan and the price of photovoltaic TGC is 650 yuan, green power plants tend to sell TGC. (3) With the price of excess green electricity consumption gradually decreased from 700 yuan/MWh to 100 yuan/MWh, the activity of three parties participating in TGC trading gradually increased, effectively activating the TGC market. Finally, from the perspective of policy management, we provide suggestions for the long-term sustainable development of the TGC market. • The strategy selection of stakeholders involved in the implementation process of the RPS and TGC policy has been examined. • The evolutionary convergence of tripartite behaviors shows a high dependent degree. • In parity TGC trading markets, the government has the potential to lower the transaction price for excess consumption. • An important policy reference for promoting the balanced development of the RPS and TGC has been provided. [ABSTRACT FROM AUTHOR]

The uncertainty of wind energy due to its non-stationary and random nature poses a major challenge to engineers responsible for power system scheduling. In the present research, a spatio-temporal graph deep neural network is used to learn the spatial characteristics and explore the strong correlation characteristics of wind-farm clusters. The Bagging, long short-term memory (LSTM), and random forest (RF) are superimposed based on the stacking integration algorithm. By analyzing the decomposed wind electron sequence characteristics, two Stacking models are used to predict the wind power of target wind-farms respectively and then a dual stacking model fusion strategy is formed. Finally, a multi-step prediction model with the spatio-temporal characteristics of D-stacking multi-integration fusion is designed for rolling multi-step prediction of wind-farm cluster power to obtain high-precision target wind-farm power. Through the actual wind power generation measured in northwest China to conduct case studies and comparative tests, it concludes that：(1) Spatio-temporal method in this paper can effectively extract the deep spatial features of wind farm clusters. (2) Dual fusion strategy improves Stacking effectively. (3) The proposed model can obtain accurate wind power prediction results, which is superior to 14 comparative algorithms proposed by other researchers. • The spatio-temporal graph network is proposed to capture spatiotemporal features. • An integration algorithm for a multi-integration overlay framework is investigated. • The D-stacking spatio-temporal feature multi-step prediction model is proposed. • The dual Stacking model fusion strategy is proposed to improve the stacking algorithm. • The proposed method provides more accurate predictions than other methods. [ABSTRACT FROM AUTHOR]

Under the carbon peak and neutrality targets, the power generation industry in China is facing an urgent demand for a low carbon transition and participation in the electricity-carbon market. This paper novelty proposes a near-zero carbon emission power plant (NZCEP) integrating gas turbines, wind turbines, power-to-gas and the carbon capture, utilization and storage system. And a two-stage Data-driven Set based robust optimization (DSRO) model, including a day-ahead dispatching phase and a real-time adjustment phase, is conducted to ensure the consumption of renewable energy resources and to develop the optimal operating strategy for NZCEP participation under the electricity-carbon market. The results demonstrated the following outcomes: (1) NZCEP shows better environmental benefits by reducing carbon emissions and consuming renewable energy resources. (2) the DSRO model can resist the interference of wind power output uncertainties and address the issue of traditional robust models being overly conservative. (3) under the electricity-carbon market, NZCEP shows better economic benefits, which can generate additional revenue from selling surplus carbon emission allowances (CEA). Moreover, when the annual average CEA price reaches 355 CNY/t, the NZCEP will achieve full capital cost recovery. • Optimal operation of near-zero carbon emission power plant (NZCEP) is studied. • A Data-driven robust optimization model is proposed for NZCEP operating. • Carbon emissions reduction and wind power accommodation of NZCEP are verified. • The economy of NZCEP participation in the electricity-carbon market is analyzed. [ABSTRACT FROM AUTHOR]

Wind power is just in place for a major improvement to the power grid in security and economy. More accurate forecast methods are emerged to benefit grid operators and their customers. A wind speed behavior prediction method based on multi-feature and multi-scale integrated learning (MFMS) is developed in this paper. The behavior characteristics are proposed to solve the problem of the temporal and spatial feature extraction distinctly of wind speed. Multi-scale feature fusion and spatial pyramid pooling algorithms are proposed to reduce the loss of micro-space-scale and short-time-scale information. Meanwhile, environmental features and background features are applied to consider the influence of the overall wind farm environment on the wind speed of local wind turbines. The wind speed data of sixteen wind turbines in a wind farm at Zhangjiakou in North China are used to verify the method. Results show that MAPE, RMSE and R2 of 4-h ultra-short-term wind speed prediction are 6.164%, 0.275 and 0.966, respectively, which are improved by 1.786%–6.757%, 0.051–0.216 and 0.014–0.074 compared with other methods. The method proposed in this paper can be applied to wind speed prediction and provide a guideline for wind farm power prediction. • A multi-step wind speed prediction model of wind turbine is proposed. • Meteorological factors and wind behavior were used as background/foreground feature. • Features are deeply excavated with the shallow feature loss been overcome. • The model efficiency and accuracy is validated by wind data from a wind farm. • The model shows high accuracy in ultra-short-term wind speed prediction. [ABSTRACT FROM AUTHOR]

• Province-level grid parity potential of wind and solar PV power plants in China. • Techno-economic feasibility of baseload supply in hybrid renewable energy system. • Correlation analysis of system cost and resource potential and complementarity. • Projected Grid parity potential of renewable energy system for baseload supply. To promote the large-scale deployment and grid integration of renewable-based power system, this paper investigates the province-level techno-economic feasibility of wind-photovoltaic-battery hybrid renewable energy system (HRES) for baseload supply application around China. Firstly, the power generation cost and grid parity potential of province-level standalone wind and photovoltaic power plants are assessed. Then, the optimal sizing of province-level HRESs aims to minimize the net present cost and meet the reliability constraint for baseload supply, which is solved by teaching and learning-based optimization. Finally, the techno-economic comparison between different system configurations, the correlation between HRES cost-effectiveness and resource potential as well as resources complementarity, and the grid parity potential of HRES for baseload supply are quantitatively analyzed. The results reveal that: (i) 84.4% of regions in China can achieve solar photovoltaic plant-side grid parity in 2022, while only 15.6% of regions can achieve wind power plant-side grid parity; (ii) HRESs in all regions are technically feasible but not cost-effective for baseload supply; (iii) wind-photovoltaic-battery HRES is the optimal configuration for most regions, indicating that the wind-solar hybridization is more reliable and cost-effective than standalone power plants; (iv) the economic performance of HRES depends mainly on the wind-solar joint resource potentials and the supply-demand relative deviation; (v) investment cost reduction and utilization of energy curtailment are promising to help HRES achieve plant-side grid parity for baseload supply. The findings of this paper can help policy-makers and investors optimally determine the national pathway of renewable energy transition. [ABSTRACT FROM AUTHOR]

• Combined with the error reconstruction rate, an adaptive VMD technology is developed and used for data preprocessing. • Two mainstream deep learning methods (LSTM, DBN) are used as sub-series predictors, and the classic PSO algorithm is utilized to determine the number of neurons in the DBN network. • A novel hybrid prediction model based on the PSO-DBN nonlinear combination mechanism is proposed. Wind power forecasting plays a vital role in enhancing the efficiency of power grid operation and increasing the competitiveness of power market. In this paper, a novel hybrid forecasting model is developed by using the decomposition strategy, nonlinear weighted combination, and two deep learning models to overcome the drawbacks of the linear weighted combination and further enhance wind power forecasting accuracy and stability. Firstly, the variational mode decomposition (VMD) technique is employed to decompose the original wind power series to extract local features. Then, the long short-term memory neural networks (LSTM) and deep belief networks based on particle swarm optimization (PSO-DBN) are utilized to construct sub-series prediction models. Finally, the multiple sub-series forecasting models are integrated by a nonlinear weighted combination method based on PSO-DBN to construct a hybrid model for short-term wind power forecasting. To verify the performance of the developed forecasting model, wind speed data of 10 min from a wind farm in Shaanxi Dingbian, China are selected as case studies. The results show that the proposed method in this paper is more effective than other existing methods. [ABSTRACT FROM AUTHOR]

• The MLM and DAM is coupled and connected by electricity decomposition. • The W-T alliance is conducive to peak load regulation of the system. • The joint participation of W-T alliance in the market can reduce wind curtailment. • The joint participation of W-T alliance in the market increases economic benefits. In 2015, "Several Opinions on Further Deepening the Reform of the Power System" was issued. The new round of power system reforms proposes to give full play to the vitality of the power generation-side bidding market, which will help to establish a fair, reasonable, and active power market. Due to factors such as a lack of peak shaving capacity and imperfect market mechanisms, China's renewable energy participation in the power market faces many problems. To solve these, this paper proposes a two-level optimization model for a wind power plant and thermal power unit to participate in the medium and long-term electricity market, and day-ahead market transactions. First, the paper proposes the electricity quantity and electricity price determination method of annual bilateral negotiated transactions, monthly centralized bidding transactions and listings, and delisting transactions, and briefly describes how to decompose contract electricity into the day-ahead market in the medium and long-term market. Then, two ways for the wind power plant and thermal power unit to participate in the power market are proposed. With maximization of the market benefits as the objective function, and through comprehensive consideration of the system reserve, wind curtailment penalty, green certificate trading, and other issues, the two models of independent participation and joint participation in market transactions were established to study the problem of maximum profit on the power generation side. Finally, the analysis results of the calculation example show that the joint participation of the wind power plant and thermal power unit in the power market has additional benefits compared to independent participation. The wind power plant can complete the assessment index of the renewable energy quota for the thermal power unit, which does not need to purchase green certificates to complete the assessment indicators. The thermal power unit can provide reserve services for the wind power plant, avoiding output whenever necessary, reducing the cost of the curtailment penalty, and overcoming the threat of wind power plant output fluctuations to the system. The two alliances have greater profit margins. [ABSTRACT FROM AUTHOR]

• Typical heating operation mode of hybrid energy storage system is proposed. • Mathematical model of HESS optimal operation is established. • Operation mode of HESS with wind power and electrode operation is proposed. During the heating season in the "Three North" area of China, the wind curtailment has become a serious problem due to the lack of space for grid-connected wind power. Firstly, from the perspective of improving the acceptance capacity of wind power curtailment, this paper establishes a model of hybrid energy storage. Then considering the influence of the frequently changing electrodes of the regenerative electric boiler on its working life, this paper introduces the optimization coefficient of electrodes, and the optimal operation strategy of hybrid energy storage system is put forward. Finally, based on the actual data of 200 MW wind farm, this paper compares and analyzes the advantages and disadvantages of different control methods. The results show that the proposed method can further improve the power system's ability to accept wind power, under the requirements of meeting the heating demand and reducing the number of electrode adjustment of electric boilers. [ABSTRACT FROM AUTHOR]

• A novel CLPU model that considers the impact of outage duration with a minimal number of additional auxiliary variables is proposed. A piecewise linearization technique is developed to linearize the CLPU model as a function of outage duration so that it can be efficiently integrated into the load restoration model. • Scheduling strategies of hybrid WF-ESSs to accelerate the load restoration process are investigated. The ESS can occasionally be operated in the alarm state to accelerate load restoration at the cost of a slight sacrifice to its lifespan. • Linearization methods are developed to formulate the load restoration problem as a mixed-integer linear programming model. A rolling horizon optimization-based framework is adopted to deal with the uncertainty of wind power and reduce computational burden. A common solution to deal with the stochasticity introduced by fast-ramping wind power integration is to equip wind farms (WFs) with energy storage systems (ESSs) to formulate hybrid WF-ESSs. In addition to leveling off wind power fluctuations during normal operations, a hybrid WF-ESS can be a flexible power source to accumulate the power system restoration. In this paper, we propose a rolling optimization model for transmission network recovery and load restoration considering the contributions of WF-ESSs. The proposed model is formulated as a mixed integer linear programming problem that simultaneously optimizes the amount and location of restorable load blocks as well as the restoration lines. The cold load pickup features of interrupted loads considering the outage duration are modeled in detail. A chance-constrained method is employed to deal with the uncertainty of wind power, and a rolling horizon-based framework is adopted to reduce the influence of forecast error. Case studies are conducted on both New England 39-bus system and part of a provincial power system in China. The results show that the load restoration process can be significantly accelerated by employing the proposed method and contributions of hybrid WF-ESSs to power system restoration are validated. [ABSTRACT FROM AUTHOR]

• A wind power prediction method based on ensemble learning and hyper-parameters optimization is proposed. • A wind power sequence segmentation method based on the Swing Window is proposed. • The relationships mapping model between error sequence and NWP sequences are built. • A daily rolling error correction strategy is proposed to correct wind power prediction results. With a high proportion of renewable energy injected into the power grid, the accurate wind power prediction of wind farms is key to improving power quality and ensuring the stable operation of the power grid. In this paper, an ensemble learning prediction model considering the rolling error correction strategy used for short-term wind power prediction is proposed. Firstly, the ensemble learning prediction model integrating multiple Gradient Boosting Trees (GBDTs) based on Bayesian optimization is established, and the characteristics of prediction errors are analyzed. To further improve the prediction accuracy, a daily rolling error correction strategy based on the Swing Window segmentation method, Spearman correlation coefficient and Quantile Regression is established to obtain the optimal compensation amount. Finally, the corrected short-term wind power prediction results are obtained. The two-year dataset collected from a regional wind farm in China is used as the benchmark test. Different prediction models and error correction strategies are compared, and the effectiveness of the proposed method is comprehensively evaluated. The results from different seasons show that the proposed prediction method has good stability, and the proposed error correction strategy has good generalization ability. [ABSTRACT FROM AUTHOR]

As large-scale wind and solar power sharing hydropower transmission channels are put into operation in river basins to lower investment costs in China, joint operations of hydro-wind-solar energy sources have become an effective operating strategy in power systems. However, wind and solar output with uncertainties and volatilities are problematic and pose challenges for power grid optimal scheduling, especially for peak shaving of grid system. In this paper, a novel decision-making model based on the information gap decision theory method is formulated to optimize the complementary operation of multi-energy systems. First, with the objective of minimizing the variance of the residual load, a deterministic short-term peak shaving model for a hydro-wind-solar system as a base case is established. Then, to model uncertainties of wind and solar output in the hybrid system and analyze the impact of grid peak shaving, the risk averse and opportunity seeker strategies of information gap decision theory-based technique are developed. Finally, as a proficient multi-objective optimization method, the normalized normal constraint method is exploited to solve the information gap decision theory-based bilevel optimal problem, and a set of Pareto solutions is obtained for the decision maker. A hydro-wind-solar hybrid system in Guizhou Province in China, with seven hydropower plants, a virtual wind power plant and a virtual solar power plant, is taken as an example to demonstrate the effectiveness of the proposed model. The results indicate that, by considering the uncertainties of wind and solar output, the presented model not only reduces the load fluctuations but also increases the flexibility response to the system against operational risk. In addition, the calculation time and load variance of the system are greatly reduced in comparison with stochastic programming. • A hydro-wind-solar hybrid system alleviates the power grid fluctuation. • The IGDT method handles the uncertainties of wind and solar output. • The usage regions are found by robust averse and opportunity seeker strategies. • Impacts of uncertainty on the power grid peak shaving operations. [ABSTRACT FROM AUTHOR]

• Model-based transfer learning is utilized to construct the multi-layer extreme learning machine (MLELM). • Output mapping factors of MLELM are further optimized through particle swarm optimization (PSO) with the objective of minimizing quantile evaluation indexes. • Joint distribution adaptation (JDA) is utilized to explore historical temporal variation characteristics and update weights of MLELM to accommodate variable wind power output. With the increasing penetration of wind power, probabilistic forecasting becomes critical to quantifying wind power uncertainties and guiding power system operations. This paper proposes a transfer learning based probabilistic wind power forecasting method. Model-based transfer learning is utilized to construct the multi-layer extreme learning machine (MLELM). The output mapping factors of MLELM are further optimized through the particle swarm optimization (PSO) with the objective of minimizing the quantile evaluation indexes. Joint distribution adaptation (JDA) is utilized to update the weights of MLELM to accommodate variable wind power output. Test results on the practical wind farms in China shows that the proposed method can provide more accurate quantile forecasting results with better nonlinear fitting ability compared with other quantile forecasting methods. [ABSTRACT FROM AUTHOR]

• This study comes from the actual needs of USHS in China. • A novel USHS model for cascaded hydropower regulated by MLDCs suppressing WPV. • The model performed well in ensuring the POR rationality and fairness. • The power output of each hydropower station after POR is stable in USHS. • The improved SOS2 method can achieve an exact and efficient solution. In China, cascade hydropower stations are widely used in the ultra-short-term scheduling of power grids to eliminate power fluctuations caused by large-scale wind power grid integration due to their quick load tracking characteristics. They are usually operated jointly by multilevel dispatch centers (MLDCs). However, the ultra-short-term hydropower scheduling (USHS) of cascade hydropower stations controlled by MLDCs faces difficulties in coordinating power output regulation (POR) among stations with different dispatch levels, frequent fluctuations in the station power output, and complex solution difficulties. In this paper, a USHS model for cascade hydropower regulated by MLDCs suppressing wind power volatility is developed to address the above problems based on mixed-integer linear programming. First, a novel objective function that minimizes the POR of cascade hydropower considering the planed load rate and operating state is combined with the coordination strategy to cooperate the POR among MLDC stations. Then, the minimum continuous generating period constraint containing the output ramping limit is proposed to prevent the hydropower station power output from fluctuating frequently. Finally, the power output function of the hydropower station, obtained by aggregation technology from multiple nonlinear characteristic curves, is linearized by improved special ordered sets of type two to achieve an efficient solution. The scheduling results from the Beipan River in southwest China demonstrate the feasibility and validity of the model, and the model can obtain reasonable POR results in an acceptable computational time. [ABSTRACT FROM AUTHOR]

Huaneng Rudong 300 MW offshore wind farm project is located in eastern China. The wake effect is one of the major concerns for wind farm operators, as all 70 units are plotted in ranks, and the sea surface roughness is low. This paper investigated the wake intensity by combining a field test and a numerical simulation. To carry out further yaw optimization, a Gaussian wake model was adopted. Firstly, a 3D Light Detection and Ranging device (LiDAR) was used to capture the features in both horizontal and vertical directions of the wake. It indicated that Gaussian wake model can precisely predict the characteristics under time average and steady state in the wind farm. The predicted annual energy production (AEP) of the whole wind farm by the Gaussian model is compared with the calculation result of the actuator line (AL)-based LES method, and the difference between the two methods is mostly under 10%. [ABSTRACT FROM AUTHOR]

Combined bidding strategies can reduce the imbalance penalty caused by wind power uncertainty. Power generation stakeholders can benefit from the combined bidding with a suitable coalition. However, the coalition formation method for wind farms with other resources is less reported. In this paper, a sequential coalition formation method is studied. The relationship constraint of wind-thermal combined bidding in a day-ahead market is described by the star graph. Technique for order preference by similarity to ideal solution (TOPSIS) is used to rank the thermal power plants considering multiple evaluation criteria. On the basis of the star graph and the TOPSIS, the coalition structure graph (CSG) is simplified. An actual wind farm and five thermal power plants in northeast China are utilized to verify the effectiveness and practicability of the proposed method. The results show that the proposed method can reduce the computational complexity of coalition formation. When wind power deviations are 0.1, 0.2, 0.3, and 0.4, the retrieval coalition structures are only 4.93%, 4.93%, 6.40%, and 7.39% of those in the basic CSG. The utilities of the formed coalitions have increment rates of 1.30%, 2.79%, 4.13%, and 5.45% compared with those under separated bidding in different wind power scenarios. • A sequential coalition formation method is proposed based on TOPSIS. • CSG is simplified with the star graph and sequential coalition formation method. • A fair utility allocation is guaranteed by the nucleolus solution. • Effectiveness and practicability are verified by actual data of northeast China. [ABSTRACT FROM AUTHOR]