Partial Least Squares regression load forecasting model based on the combination of grey Verhulst and equal-dimension and new-information model

At present, China's electric power development is faced with the new situation of continuous economic downturn, industrial restructuring, tensions in Sino-US relations and longterm epidemic prevention, which has reduced the accuracy of the existing medium and long-term load forecasting models. In this context, this paper proposes a medium and long-term load forecasting model based on improved grey forecasting model combination method and partial least squares regression equation. Firstly, grey Verhulst model is suitable for forecasting data with saturated development trend, and the equal-dimension and new-information grey model is suitable for forecasting data with exponential development trend. The above two models are combined to obtain a new load influencing factor index forecasting model. Then, the PLS method is used to establish the prediction model when the independent variables had serious multiple correlations by extracting the principal components. Finally, the proposed model is used to forecast the annual electricity consumption of region A from 2016 to 2019, and the results are compared with the actual values, which verifies the validity of the model in this paper.