A hybrid self-adaptive Particle Swarm Optimization–Genetic Algorithm–Radial Basis Function model for annual electricity demand prediction

•A hybrid self-adaptive PSO–GA-RBF model is proposed for electricity demand prediction.•Each mixed-coding particle is composed by two coding parts of binary and real.•Five independent variables have been selected to predict future electricity consumption in Wuhan.•The proposed model has a simpler structure or higher estimating precision than other ANN models.•No matter what the scenario, the electricity consumption of Wuhan will grow rapidly.

The present study proposes a hybrid Particle Swarm Optimization and Genetic Algorithm optimized Radial Basis Function (PSO–GA-RBF) neural network for prediction of annual electricity demand. In the model, each mixed-coding particle (or chromosome) is composed of two coding parts, binary and real, which optimizes the structure of the RBF by GA operation and the parameters of the basis and weights by a PSO–GA implementation. Five independent variables have been selected to predict future electricity consumption in Wuhan by using optimized networks. The results shows that (1) the proposed PSO–GA-RBF model has a simpler network structure (fewer hidden neurons) or higher estimation precision than other selected ANN models; and (2) no matter what the scenario, the electricity consumption of Wuhan will grow rapidly at average annual growth rates of about 9.7–11.5%. By 2020, the electricity demand in the planning scenario, the highest among the scenarios, will be 95.85 billion kW h. The lowest demand is estimated for the business-as-usual scenario, and will be 88.45 billion kW h.