A Short-Term Hybrid Forecasting Approach for Regional Electricity Consumption Based on Grey Theory and Random Forest

Electricity consumption reflects the development level of a certain region to a great extent, and it is always in a changing process with fluctuation. Entities or agencies who provide the electricity power supply services are always eager to know the data of regional electricity consumption, and hope to obtain the accurate forecast of future power consumption from these data, so that more appropriate and reasonable power supply service arrangement can be implemented. Till now, many scholars have reported their research on doing forecasting work by employing algorithms for regression such as Grey Theory or Random Forest, however, there are some drawbacks in both algorithms in using available data for prediction. In this paper, a short-term hybrid forecasting approach has been proposed based on both algorithms, it can not only realize the prediction from relatively less available data, but ensure high accuracy in prediction as well. By an empirical study on the electricity power consumption of a certain region in central western China, the effectiveness of the proposed method is verified.