Study of the short-term electric load forecast based on ANFIS

Short-term electric load forecast is extremely important for the security management and cost control of the electric power industry, and thus it is of great significance to improve the forecast accuracy. Adaptive network-based fuzzy inference system (ANFIS) model, which combines the self-learning ability of neural network and the logical reasoning ability of fuzzy system, has some advantages in performance when compared with neural network and fuzzy system. In this study, an adaptive network-based fuzzy inference system (ANFIS) model was used to construct the short-term load forecasting model based on factors such as weather and date types, etc. Then, the model was trained by the historical electric load data of eastern Czechoslovakia, and the prediction performance of the model is demonstrated. As shown in the simulation results, the proposed model can efficiently complete the mission of short-term electric load forecast.