Power Load Forecasting Using Data Mining and Knowledge Discovery Technology

Considering the importance of the peak load to the dispatching and management of the system, the error of peak load is proposed in this paper as criteria to evaluate the effect of the forecasting model. This paper proposes a systemic framework that attempts to used data mining and knowledge discovery (DMKD) pretreatment of the data. And a new model is proposed which combining artificial neural networks with data mining and knowledge discovery for electric load forecasting. With DMKD technology, the system not only could mine the historical daily loading which had the same meteorological category as the forecasting day to compose data sequence with highly similar meteorological features, meanwhile, but also could eliminate the redundant influential factors. Then an artificial neural network is constructed to predict according to its characteristics. Using this new model, it could eliminate the redundant information accelerated the training of neural network and improve the stability of the convergence. Comparing with single SVM and BP neural network, this new method can achieve greater forecasting accuracy.