Abstract:
There is a non-optimal solution problem when optimizing the Least Square Support Vector Machine(LSSVM) for Particle Swarm Optimization(PSO). A short-term load prediction method based on Chaos theory for optimizing LSSVM parameters is proposed. The prediction model first introduces chaos theory, improves the particle swarm algorithm. Then it allows the PSO combined with chaos theory to optimize the LSSVM regression estimate to obtain CPSO-LSSVM. Finally, the method is applied to short-term load prediction, and the prediction results are obtained by Matlab simulation training. The simulation results show that this method can not only reduce the probability of the algorithm falling into local extremum, but also improve the learning ability, thus improving the accuracy of prediction.