Abstract In order to fully consider the diversity of urban development and the various influencing factors in the process of power load forecasting, and improve the forecast accuracy of power network plan, a method of multivariate power load forecasting based on the econometrics and grey theory is proposed. Firstly, this method determines strong correlation factors of the power load in the forecasting process through the correlation analysis between the power load and the variables. Then we find the connection between each other through the econometric theory of statistics, and establish the mathematical model for forecasting between the power load and the variables. Finally, we predict the value of each variable in the target year in order to solve the problems caused by the lack of data and the uncertainty of fluctuation. and brought them into the mathematical model in order to complete the load forecasting. An engineering example shows that the method is correct and effective.
2017, Vol. 18 
