Optimized Wavelet Transform Neural Networks for Accurat Distributed Renewable Energy Information Prediction
Distributed renewable energy generation is a crucial component of low-carbon power systems.As the proportion of distributed renewable energy in urban power grids is gradually increasing,and the impacts of random load fluctuations and random weather changes on urban power grids are increasing,placing higher demands on the accuracy of distributed renewable energy information forecasting.Currently,the primary generation methods of distributed renewable energy are distributed photovoltaic power generation and distributed wind power generation.The changes of urban electricity load are both cyclical and random,while factors such as wind speed and solar irradiance have significant impacts on distributed wind power generation and distributed photovoltaic power generation,respectively.Therefore,based on wavelet transform neural network,a distributed renewable energy information prediction method is constructed.Firstly,the model of distributed renewable energy is established by analyzing the working principle of distributed renewable energy.Then,the wavelet transform neural network is optimized to predict the parameters that play a significant role in the renewable energy grid,such as the load power change and the irradiation intensity,using wind power generation and photovoltaic power generation as examples.Finally,the example verifies that the proposed model can accurately predict the information of distributed renewable energy.
国家科技期刊平台
NSTL
万方数据
