Search

With the increase of solar photovoltaic (PV) penetration in power system, the impact of random fluctuation of PV power on the secure operation of power grid becomes more and more serious. High-precision PV power forecasting can effectively promote the grid's accommodation of PV power generation. Cloud is the most important factor affecting the surface irradiance and PV power. For the ultra-short-term solar PV power forecast considering the influence of cloud movement, it is necessary to be able to obtain the surface irradiance according to the sky cloud observation data. Therefore, in order to accurately achieve the real-time mapping relationship between sky image and surface irradiance, a hybrid mapping model based on deep learning applied for solar PV power forecasting is proposed in this article. First, the sky image data are clustered based on the feature extraction of convolutional autoencoder and K-means clustering algorithm after preprocess stage. Second, a hybrid mapping model based on deep learning methods are established for surface irradiance. Finally, the simulation results are compared and evaluated with different deep learning methods (CNN, LSTM, and ANN). The results show that the proposed model in this article has higher accuracy and can maintain robustness under different weather conditions. [ABSTRACT FROM AUTHOR]

The motion of cloud over a photovoltaic (PV) power station will directly cause the change of solar irradiance, which indirectly affects the prediction of minute-level PV power. Therefore, the calculation of cloud motion speed is very crucial for PV power forecasting. However, due to the influence of complex cloud motion process, it is very difficult to achieve accurate result using a single traditional algorithm. In order to improve the computation accuracy, a pattern classification and particle swarm optimization optimal weights based sky images cloud motion speed calculation method for solar PV power forecasting (PCPOW) is proposed. The method consists of two parts. First, we use a k-means clustering method and texture features based on a gray-level co-occurrence matrix to classify the clouds. Second, for different cloud classes, we build the corresponding combined calculation model to obtain cloud motion speed. Real data recorded at Yunnan Electric Power Research Institute are used for simulation; the results show that the cloud classification and optimal combination model are effective, and the PCPOW can improve the accuracy of displacement calculation. [ABSTRACT FROM AUTHOR]

Regional photovoltaic(PV) power forecasting provides a foundation for grid management and trading in the power markets. To tackle the deficiency of conventional regional PV power modeling methods, such as the problem of challenging to select useful meteorological information and the problem that a single model cannot fully learn the complex and diverse fluctuation characteristics of power curves, an ultrashort-term regional PV power forecasting framework assembled by fusing fluctuation pattern recognition (FPR) and deep learning modeling under a fluctuation pattern prediction (FPP) model was proposed. First of all, the fluctuation characteristics of the regional PV power curves were extracted, including sampling loss area, mean value, standard deviation, and third derivative. Then, a K-means algorithm based FPR model was established to obtained three kinds of patterns. FPP model based on convolutional neural network is used to predict future PV power fluctuation patterns with historical satellite images as input. Finally, the convolutional autoencoder is used to extract cloud distribution features, and a long- and short-term memory network based on the combination of cloud distribution features and historical output is proposed to construct prediction models of the three models. Through the analysis of the simulation data, the prediction method proposed in this article has higher prediction accuracy than the traditional prediction model. [ABSTRACT FROM AUTHOR]

Ultra-short-term photovoltaic (PV) power forecasting can support the real-time dispatching of the power grid. However, PV power has great fluctuations due to various meteorological factors, which increase energy prices and cause difficulties in managing the grid. This article proposes an ultra-short-term PV power forecasting model based on the optimal frequency-domain decomposition and deep learning. First, the optimal frequency demarcation points for decomposition components are obtained through frequency-domain analysis. Then, the PV power is decomposed into the low-frequency and high-frequency components, which supports the rationality of decomposition results and solves the problem that the current decomposition model only uses the direct decomposition method and the decomposition components are not physical. Then, a convolutional neural network (CNN) is used to forecast the low-frequency and high-frequency components, and the final forecasting result is obtained by addition reconstruction. Based on the actual PV data in heavy rain days, the mean absolute percentage error (MAPE) of the proposed forecasting model is decreased by 52.97%, 64.07%, and 31.21%, compared with discrete wavelet transform, variational mode decomposition, and direct prediction models. In addition, compared with recurrent neural network and long–short-term memory model, the MAPE of the CNN forecasting model is decreased by 23.64% and 46.22%, and the training efficiency of the CNN forecasting model is improved by 85.63% and 87.68%. The results fully show that the proposed model in this article can improve both forecasting accuracy and time efficiency significantly. [ABSTRACT FROM AUTHOR]

The precise minute time scale forecasting of an individual PV power station output relies on accurate prediction of cloud distribution, which can lead to dramatic fluctuation of PV power generation. Precise cloud distribution information is mainly achieved by ground-based total sky imager, then the future cloud distribution can also be achieved by sky image prediction. In previous studies, traditional digital image processing technology (DIPT) has been widely used in predicting sky images. However, DIPT has two deficiencies: relatively limited input spatiotemporal information and linear extrapolation of images. The first deficiency makes the input spatiotemporal information not rich enough, while the second creates the prediction error from the beginning. To avoid these two deficiencies, convolutional autoencoder (CAE) based sky image prediction models are proposed due to the spatiotemporal feature extraction ability of two-dimensional (2-D) CAEs and 3-D CAEs. For 2-D CAEs and 3-D CAEs, four architectures are given respectively. To verify the effectiveness of the proposed models, two typical DIPT methods, including particle image velocimetry and Fourier phase correlation theory are introduced to build the benchmark models. Besides, five different scenarios are also set and the results show that the proposed models outperform the benchmark models in all scenarios. [ABSTRACT FROM AUTHOR]

Accurate monthly electricity consumption forecasting (MECF) is important for electricity retailers to mitigate trading risks in the electricity market. Clustering is commonly used to improve the accuracy of MECF. However, in the existing clustering-based forecasting methods, clustering and forecasting are independently performed and lack coordination, which limits the further improvement of forecasting accuracy. To address this issue, an adaptive optimal greedy clustering-based MECF method is proposed in this article. First, a metric of predictability is defined based on the goodness of fit and the cluster's average electricity consumption. Under a predefined number of clusters, the greedy clustering algorithm achieves the optimal division of individuals with the goal of maximizing predictability. Then, an adaptive method is designed to select the optimal number of clusters from a variety of clustering scenarios according to the prediction accuracy on the validation dataset. The effectiveness and superiority of the proposed method have been verified on a real-world dataset. [ABSTRACT FROM AUTHOR]

Residential customers account for an indispensable part in the demand response (DR) program for their capability to provide flexibility when the system required. However, their available DR capacity has not been fully comprehended by the aggregator, who needs the information to bid accurately on behalf of the residential customers in the market transaction. To this end, this article devised an optimal bidding strategy for the aggregator considering the bottom-up responsiveness of residential customers. First, we attempt to establish the customers’ responsiveness function in relation to different incentives, during which a home energy management system is introduced to implement load adjustment for electrical appliances. Second, the functional relation is applied to the aggregator's decision-making process to formulate the optimal bidding strategy in the day-ahead market and the optimal scheduling scheme for the energy storage system with the aim to maximize its own revenue. Finally, the validity of the proposed method is verified using the dataset from the Pecan Street experiment in Austin. The obtained outcome demonstrates the practical rationality of the proposed method. [ABSTRACT FROM AUTHOR]