Combined particle swarm optimization and heuristic fuzzy inference systems for a smart home one-step-ahead load forecasting

This article presents a hybrid approach that combines particle swarm optimization (PSO) and heuristic fuzzy inference system (HFIS) for smart home one-step-ahead load forecasting. Smart home load forecasting is an important issue in the development of smart grids. Generally, the electricity consumption of a household is inherently nonlinear and dynamic and heavily dependent on the habitual nature of power demand, activities of daily living and on holidays or weekends, so it is often difficult to construct an adequate forecasting model for this type of load. To address this problem, a hybrid model, consisting of two phases, is proposed in this article. In the first phase, the popular PSO algorithm is used to determine the locations of fuzzy membership functions. Then, the proposed HFIS technique is used to develop the one-step-ahead load forecasting model in the second phase. Because of the robust nature of the proposed HFIS technique, which does not need to retrain or re-estimate model parameters, it is very suitable for smart home load forecasting. The proposed method was verified using two different households load data. Simulation results indicate that the proposed method produces better forecasting accuracy than existing methods.