Power system load forecasting based on BEMPSO chaotic neural network

Considering the chaotic characteristic of power system load, a method based on bee evolution modifying particle swarm optimization (BEMPSO) and chaotic neural network is presented for power system load forecasting to improve precision. In this paper, builds the chaotic neural network model and integrates bee evolution modifying with particle swarm optimization. The novel BEMPSO algorithm is proposed. It is used to train connection weights of multi-layer feed forward neural network until the learning error tends to be stable. Using the basic PSO algorithm and proposed BEMPSO algorithm, we simulate the prediction of power system load, the results shows that forecasting model based on the BEMPSO algorithm proposed in this paper have strong capacity of generalization and relatively high precision compared with the basic PSO algorithm.