An Improved Short-Term Load Forecasting Method Considering Thermal Inertia Effect

摘要

Due to the thermal inertia of the mass temperature and the inertia of human temperature perception, the load is affected by the temperatures with the coupling of multiple timescales, and load variation tends to lag behind temperature variation. In the proposed method, the temperature variable used in the short-term load forecasting model is modified as a function of present and historical temperatures. To enhance the prediction power of the modified temperature, genetic algorithm is adopted to get the optimal parameters of the thermal inertia effect modification function. The testing results show that the proposed method can improve the accuracy of short-term load forecasting.