RESEARCH ON SHORT-TERM PV OUTPUT PREDICTION METHOD BASED ON GCN
To improve the accuracy of short-term photovoltaic output prediction,a photovoltaic short-term output prediction method based on graph convolutional network(GCN)is proposed.Firstly,construct a short-term photovoltaic output model that considers multiple meteorological factors,and conduct an analysis of the influencing factors and output characteristics of photovoltaic system.Secondly,graphical transformation and data reconstruction are performed on the historical time series data of photovoltaic output,and an adjacency matrix is constructed to extract graphical feature data of short-term photovoltaic output.Establish a photovoltaic output prediction model based on GCN in a multi time scale scenario,and compare and analyze it with prediction models based on LSTM,BP,GAT and other algorithms.Finally,simulation validation research is conducted using measured photovoltaic output data from a certain region,and the simulation results show that the proposed method has good predictive performance.
photovoltaic powergraph convolutional neural networkgraph data structuremulti-time scale
NETL
NSTL
万方数据
