Short-Term Load Forecasting of Microgrid Based on Chaotic Particle Swarm Optimization
Han Ma, Jing Min Tang
Abstract
In order to solve the problem of non-optimal when Particle Swarm Optimization (PSO) optimizes least square support vector machine (LSSVM), a short-term load forecasting method based on Chaos theory is proposed.Firstly, chaos theory is introduced into the prediction model to improve the particle swarm algorithm, and then PSO combined with chaos theory is used to optimize the parameters of LSSVM. Finally, the method is applied to short-term load forecasting, and the forecasting results are obtained through Matlab simulation training. The experimental simulation shows that the method can not only reduce the possibility of the algorithm falling into local extremum, but also improve the learning ability, thus improving the accuracy of prediction.