Short-Term Load Forecasting Based On The Hybrid Alrorithm And Radial Basis Function Neural Network

Short-term load forecasting (STLF) in power system is an important part of running and dispatching, and it is an important module of energy management system. The operation of power market requires the accuracy, real-time, reliability and intelligence of load forecasting. The neural networks forecasting model is one of the most normal models used in STLF. On base of improving the shortcomings of Neural Networks Forecasting using the RBF algorithm, this paper aims to introduce a new model in STLF. The main study in this paper is as follows.(1) Particle Swarm Optimization (PSO) is an evolutionary computation technique based on the swarm intelligence, which is originated from artificial life and evolutionary computation. In this paper, a mixed PSO-RBF algorithm is formed, which is the combination of PSO and RBF network. Then, a STLF model involving various influencing factors is built. The STLF of power system is performed using the mixed PSO-RBF algorithm and RBF algorithm. The simulation results indicate that this mixed PSO-RBF algorithm is better than RBF algorithm.(2) In this paper, a mixed artificial fish swarm algorithm (AFSA)-RBF algorithm is formed, which is the combination of AFSA and RBF network. Then, a STLF model involving various influencing factors is built. The STLF of power system is performed using the mixed AFSA-RBF algorithm. The simulation results indicate that this mixed AFSA-RBF algorithm is better than RBF algorithm.(3) Some problems of the particle swarm optimization (PSO), including the local minimum and the convergence of the shortcomings, the AFSA is introduced to the PSO, the AFSA has the advantage of the characteristics of global optimization, can jump out of local excellent. Based on the advantages of both, the hybrid algorithm is formed. The test from four standard functions results show that the hybrid algorithm can avoid falling into local minima, and improve the convergence speed, accuracy. In this paper, a mixed hybrid algorithm (AFSA and PSO)-RBF network is formed, which is the combination of the hybrid algorithm and RBF network. Then, a STLF model involving various influencing factors is built. The STLF of power system is performed for the state of New South Wales, Australia, using the mixed the hybrid algorithm-RBF network. The simulation results indicate that this mixed hybrid algorithm-RBF network is better than PSO-RBF algorithm, can improve the predicting precision and overcome the shortcomings of the RBF network and PSO.