Electric load forecasting by SVR with chaotic ant swarm optimization

Abstract

Support vector regression (SVR) has revealed the strong potential in accurate electric load forecasting, particularly by employing effective evolutionary algorithms to determine suitable values of its three parameters. Based on previous research results, these employed evolutionary algorithms themselves also have drawbacks, such as premature convergence, slowly reaching the global optimal solution, and trapping into a local optimum in parameters determination of a SVR model. This paper presents a short-term electric load forecasting model which applies a novel algorithm, namely chaotic ant swarm optimization (CAS), to improve the forecasting performance by searching suitable parameters combination in a SVR forecasting model. The proposed CAS combines with the chaotic behavior of single ant and self-organization behavior of ant colony in the foraging process to overcome premature local optimum. The empirical results indicate that the SVR model with CAS (SVRCAS) results in better forecasting performance than the other methods, namely SVRCPSO (SVR with chaotic PSO), SVRCGA (SVR with chaotic GA), regression model, and ANN model.