Price forecasting algorithm for coal and electricity based on PSO and RBF neural network

The price of coal and electricity depends on various indeterminate factors, and there is a very complicated coupling relationship among them. The forecasting model becomes more complex for their strong nonlinear features that bring lots of difficulties in constructing a precise forecasting model with the traditional methods. This paper proposes a new method, on the basis of PSO and RBF neural network, to predict the price of the coal and electricity. In the model, the PSO algorithm is applied to optimize the parameters of RBS and weights of neural network. The method is verified with a simulation program developed on Matlab and the results show that the convergence speed and the prediction precision are both improved with satisfactorily.