Research And System Development Of Short-Term Wind Power Forecasting Based On Machine Learning

In recent years,with the rapid global warming and environmental pollution,as a kind of clean and renewable energy,wind energy has been paid more and more attention.However,the randomness and volatility of wind energy will bring a significant impact on the reliability and power quality of the power system,and become more and more prominent as the scale of wind power.Therefore,the study of wind power forecasting is of great significance to the development of wind power industry in China.In order to improve the stability of wind power.In this paper,we improve the prediction accuracy of wind power.The prediction of wind power probability interval was given to characterize the potential randomness in wind power.Specifically as follows:Firstly,a method based on Improvement Artificial Fish Swarm Algorithm(IAFSA)-BP neural network algorithm is presented for improving the accuracy of short-term wind power forecasting.It optimizes the weights and thresholds of BPNN and improves the BPNN generalization capacity and the rate of convergence.By using the historical data of a wind farm of Shanghai in 2014,IAFSA is proposed to overcome the defects of traditional Artificial Fish Swarm Algorithm such as the blindness of searching,slow convergence speed and low searching precision at the later stage.The simulation result compared with BPNN and AFSA-BPNN algorithm shows that the IAFSA-BPNN algorithm can not only improve the prediction accuracy and stability,but also shorten the model’s rate of convergence,and improve the precision and stability in short-term wind power forecasting.Then,in order to characterize the randomness of wind power,Gaussian Process Regression(GPR)is introduced to predict the short-term wind power probability interval.Using the Variational Modal Decomposition(VMD)-Sample Entropy(SE)algorithm to reduce the nonstationarity of the wind power signal.The GPR model is established for the reconstructed sub-sequences.Finally,the prediction results are superimposed to obtain the probability interval of the given confidence level,and the probability Predictive evaluation index evaluation model.The results show that the new algorithm proposed in this paper has high accuracy and coverage and narrow interval width.Finally,combined with the above wind power prediction algorithm,the design and development of wind power forecasting system,has a very important practical significance and practical value.