Abstract
(Aim) A short-term load forecast is an arduous problem due to the nonlinear characteristics of the load series. (Method) The artificial neural network (ANN) was employed. To train the ANN, a novel hybridization of Tabu Search and Particle Swarm Optimization (TS-PSO) methods was introduced. TS-PSO is a novel and powerful global optimization method, which combined the merits of both TS and PSO, and removed the disadvantages of both. (Results) Experiments demonstrated that the proposed TS-PSO-ANN is superior to GA-ANN, PSOANN, and BFO-ANN with respect to a mean squared error (MSE). (Conclusion) The TS-PSO-ANN is effective in a short-term load forecast.