A Novel Particle Swarm Optimization Approach Combined with Fuzzy Neural Networks for Short-Term Load Forecasting

To resolve the short-term load forecasting (STLF) tasks, this paper proposes to use a new method, namely, particle swarm optimization (PSO) merged with fuzzy neural networks (FNNs), here after called the PSO-FNN method. With the PSO method, we encode all the networks' weights and biases into several artificial neural network (ANN) system particle swarms, and then we train the network parameter values using the particle swarm optimization method proposed in this paper to locate the networks' optimal parameter solution. Next, we resolve the optimal STLF with the FNNs derived. The results by the proposed method are compared with that by other commonly-used load forecasting methods, such as the artificial neural network (ANN), the evolutionary programming combined with ANN (EP-ANN) and the genetic algorithm combined with ANN (GA-ANN). The comparisons indicate that the proposed method renders smaller load forecasting discrepancies, with significant improvement rates ranging from 24.7% to 41.7%, signifying the proposed method's advantage in load forecasting.

I. Introduction

S tlf is vital to an electric power system's thermal power generation planning, thermal-hydro power generation coordination, power generation units' economic dispatch and power exchange planning. The traditional electric power forecasting often uses vital linear factors which will influence the load; such forecasting's advantage lies at its simplicity with the forecasting model. However, since the system load is multi-dimensional and there exists nonlinearity among the influential factors, the traditional method hardly can forecast the load series with enough accuracy.