Research On Short-Term Photovoltaic Power And Power Load Forecasting And Optimal Scheduling Of Microgrid

Social and economic development cannot be separated from the supply of energy.With the rapid development of society,the demand for energy is gradually increasing.Photovoltaic power generation has the advantages of clean and renewable,and has been highly concerned by the society in recent years.However,due to the random and intermittent photovoltaic power output,the grid connection will affect the dispatching and stability of the microgrid.Accurate short-term photovoltaic power prediction can provide certain guarantee for the safe and stable dispatching of the microgrid.Microgrid is the main form of power generation using new energy,which has the advantages of high safety,low environmental pollution and low cost.Therefore,it is of great theoretical value to study the optimal scheduling of microgrid.Load prediction is the premise of optimal dispatching of microgrid,so it has important significance for economic dispatching and stable operation of microgrid.To this end,this paper studies short-term photovoltaic power prediction,short-term power load prediction and economic optimal dispatching of micro-grid,and the main research contents are as follows:(1)In order to improve the accuracy of short-term photovoltaic power prediction,a combined prediction model based on feature extraction and optimized LSSVM was proposed.Firstly,the CNN-LSTM feature extraction model is constructed by combining the advantages of CNN and LSTM,which is used to extract spatial features and temporal features in data.Then the extracted feature vectors are input into the LSSVM model for prediction.Secondly,the shortcomings of Sparrow algorithm are improved,and the improved sparrow algorithm is used to optimize the parameters of LSSVM.Finally,by comparing the prediction results with those of other models,the validity and superiority of the model proposed in this chapter are verified.(2)In order to improve the accuracy of short-term power load prediction,a combined prediction model based on variational mode decomposition and optimized KELM is proposed.Firstly,the load sequence was decomposed into multiple subsequences by the variational mode decomposition method in view of the nonstationary property of the load sequence.Then the KELM model is constructed for different subsequences,and the regularization coefficient and kernel function parameters of KELM are optimized by the improved Pelican optimization algorithm.Finally,the prediction results of different subsequences were superimposed and reconstructed to obtain the final prediction results.Compared with the prediction results of other models,the proposed model has higher accuracy.(3)In order to reduce the comprehensive operation cost of microgrid system,the economic optimal dispatching of microgrid system is studied.Firstly,the operation characteristics and mathematical model of distributed power supply in microgrid are introduced.Then,taking the lowest total operation cost of the microgrid system as the objective function,reasonable constraint conditions are constructed according to the operation characteristics of the microgrid and the operation characteristics of each distributed power source.Finally,the improved grey Wolf algorithm is used to solve the above established microgrid system.On the premise of meeting the load demand,the distributed power output in the system is reasonably scheduled,and the optimal scheduling result is obtained to minimize the total operation cost of the system.By comparing with the scheduling result of the grey Wolf algorithm,the improved grey Wolf algorithm can effectively reduce the comprehensive operation cost of the system.