Load Prediction in Power System with Grey Theory and its Diagnosis of Stabilization

With the advancement of power system, the prediction of load series in power system has received a lot of attention from industry and research communities in the recent years. The prediction of load series plays an important part in the field of scheduling, the analysis of the contingency and load flow, planning and maintenance of power system. For a prediction model, besides the prediction accuracy, the stability of the prediction model is a very important issue. In this paper, we focus on the stability of the GM(1,1) model, which is widely utilized for the load prediction. Using the matrix condition number, the stabilization of the GM(1,1) model, as well as the detailed constraint conditions causing the morbidity of the model are theoretically derived. Moreover, when the model is unstable, how to solve the morbidity is also discussed in detail. The experimental results demonstrated and validated the correctness of the theoretical derivations.