Short-term load forecasting using PSO-based phase space neural networks

The nonlinear theories of load forecasting, such as the applications of neural network and chaos, have recently made considerable progress. Generally, it is an effective method to combine phase space restructures theory with artificial neural networks (ANN) model for load forecasting. But, they are not so effective to forecast attractors with higher embedded dimension. The paper proposes a new idea based on incidence-degree to determine the nearest point in phase space. In the mean time, an artificial neural networks model based on particle swarm optimization (PSO) learning algorithm is presented for load forecasting. The proposed method has been examined and tested on a practical power system. The test result shows that the precision of load forecasting is improved by means of the new method when the embedded dimension is higher.