Prediction by Integration of Phase Space Reconstruction and a Novel Evolutionary System under Deregulated Power Market

Abstract

In deregulated power markets, forecasting electricity loads is one of the most essential tasks for system planning, operation and decision making. Based on an integration of two machine learning techniques: a hybrid evolutionary algorithm which combines PSO and Artificial Fish Swarm Algorithm Search approach based on test-sample error estimate criterion (PSO-AFSAS-TEE) and support vector regression (SVR), this paper proposes a novel evolutionary model for future electricity load forecasting. The proposed evolutionary model adopts an integrated architecture to optimize the prediction of time series. Firstly, the theory of Phase Space Reconstruction (PSR) technique was used for nonlinear dynamic system analysis and prediction with the chaotic load series. Then, a PSO-AFSAS-TEE evolutionary system is proposed to choose the parameters of SVR automatically in time series prediction. The effectiveness of the proposed model is demonstrated with actual data taken from the Australia Power Grid.