On Short Term Photovoltaic Power Prediction Based on ITMBA-BP Algorithm

Photovoltaic power generation, with its clean, low-carbon and sustainable characteristics, is playing an increasingly important role in the formulation of national energy strategies. The photovoltaic power generation is affected by many factors. The traditional prediction method is not accurate to solve the high dimensional optimization problem, and it is easy to fall into the local optimal problem. In this paper, a collaborative algorithm based on improved adaptive T-distribution variation bat algorithm and traditional BP neural network (ITMBA-BP) is proposed. The improved bat algorithm is used to enhance the global coverage and the ability to solve high-dimensional optimization problems. The ITMBA algorithm is used to adjust the structure and parameters of the neural network, which enhances the global search capability of the BP neural network. Use real photovoltaic power plant data to predict and analyze the algorithm proposed in this paper, and compare it with the traditional BP algorithm. The simulation results show that ITMBA-BP algorithm has the advantages of high accuracy and small mean square error. It can effectively predict the change of power generation and has strong practical application value.