Research on Wind Power Prediction Method Based on Convolutional Neural Network and Genetic Algorithm

With the vigorous development of renewable energy, large-scale wind power is connected to the power grid. Compared with conventional energy sources, wind power generation has the stochastic and intermittent characteristics, which brings great challenges to the safe and stable operation of power grids. Forecasting is essential for the rational, safe and effective use of wind power. Thus, the ability to predict wind power in a timely and accurate manner is particularly significant.The short-term prediction error of wind power is mainly caused by inherent stochastic factors and extrinsic stochastic factors. The inherent stochastic factor refers to the defect or imperfection of the prediction system itself. The external stochastic factor refers to the imperfect data input by the system or the error of the input data. Artificial neural network (ANN) algorithms are supposed to be with better performance to solve such problems. This paper reviews the development of wind power generation and the research status of wind power prediction technology. On this basis, a wind power prediction model of convolutional neural network (CNN) and genetic algorithm (GA) is constructed to predict the short-term wind power. The learning accuracy, the number of hidden nodes, and the training function are discussed. The selection of the optimal neural network and GA prediction model are presented. The simulation results show that the prediction accuracy and stability of the proposed prediction system are improved, compared with the BP neural network and CNN.

[1]  Jie Zhang,et al.  A Copula-Based Conditional Probabilistic Forecast Model for Wind Power Ramps , 2019, IEEE Transactions on Smart Grid.

[2]  Gongjian Wen,et al.  A deep neural network for real-time detection of falling humans in naturally occurring scenes , 2017, Neurocomputing.

[3]  Jie Zhang,et al.  A Data-Driven Methodology for Probabilistic Wind Power Ramp Forecasting , 2019, IEEE Transactions on Smart Grid.

[4]  C. Y. Chung,et al.  Novel Multi-Step Short-Term Wind Power Prediction Framework Based on Chaotic Time Series Analysis and Singular Spectrum Analysis , 2018, IEEE Transactions on Power Systems.

[5]  Zhang Li.  Wind speed forecast model for wind farms based on time series analysis , 2005 .

[6]  Luiz G. Hafemann.  Learning features for offline handwritten signature verification , 2019 .

[7]  Shuang Gao,et al.  Studies on wind farms ultra-short term NWP wind speed correction methods , 2013, 2013 25th Chinese Control and Decision Conference (CCDC).

[8]  Yakup S. Ozkazanç,et al.  Wind Pattern Recognition and Reference Wind Mast Data Correlations With NWP for Improved Wind-Electric Power Forecasts , 2016, IEEE Transactions on Industrial Informatics.

[9]  Gilson A. Giraldi,et al.  Convolutional Neural Network approaches to granite tiles classification , 2017, Expert Syst. Appl..

[10]  Gyogwon Koo,et al.  End-to-end recognition of slab identification numbers using a deep convolutional neural network , 2017, Knowl. Based Syst..

[11]  Rashmi P. Shetty,et al.  Optimized Radial Basis Function Neural Network model for wind power prediction , 2016, 2016 Second International Conference on Cognitive Computing and Information Processing (CCIP).

[12]  Erik Cambria,et al.  Ensemble application of convolutional neural networks and multiple kernel learning for multimodal sentiment analysis , 2017, Neurocomputing.

[13]  Tuo Xie,et al.  Prediction of short-term wind power in wind power plant based on BP-ANN , 2016, 2016 IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC).

[14]  Jie Zhang,et al.  Wind Power Ramp Event Forecasting Using a Stochastic Scenario Generation Method , 2015, IEEE Transactions on Sustainable Energy.