Short-term load forecasting based on improved particle swarm neural network
Jiang Yunteng1, Li Ping2
1. School of Physics and Electronic-Electrical Engineering, Ningxia University, Yinchuan 750021 2. Ningxia Key Laboratory of Intelligent Sensing for Desert Information, Yinchuan 750021
Abstract：In the development of the power system, the power load plays a very important role, so the accuracy of power load forecasting is particularly important.In order to improve the accuracy of short-term load forecasting, an improved particle swarm-BP neural network hybrid optimization algorithm is proposed. The particle swarm optimization algorithm with adaptive inertia weight improves the convergence speed and convergence accuracy of PSO. In the process of optimizing the neural network, the initial weights and threshold parameters of the BP neural network are improved, and the IPSO-BP algorithm model is established to forecast the short-term power load. The simulation results how that the convergence speed and prediction accuracy of the model are superior to the traditional particle swarm-BP neural network model based on historical load data from one places. The model improves the shortcomings of particle swarm optimization and neural network, and improves the generalization ability of BP neural network. The model improves the short-term load forecasting accuracy, and the average relative error is about 1%, which can be used for short-term load forecasting of power system.
2018, Vol. 19 
