Development of Regression Models for Prediction of Electricity by Considering Prosperity and Climate

This paper uses multiple regression analysis method to establish customer' s load regression models, which consider economic indicators, air temperature and rainfall. Furthermore, the proposed models are used to study the forecasting feasibility of the future energy sales and summer peak load demand. The least-squares technique is applied to derive regression models of 34 customer energy sales and total energy sales by considering economic indicators and air temperature. EViews software is used to verify the feasibility of the research framework. The study found that energy intensive customers and all high voltage customers are not sensitive to air temperature, and the accuracy of the forecasting model only mixing with air temperature and high voltage demand accuracy is low. In the majority of its energy sales forecasting model, the average error is ±3%. These results can be provided to power companies as their future references in system planning.