Skip to Main Content
With the development of power markets, the market clearing price (MCP) forecasting is becoming the basis of decision making for participants in electricity market. In this paper the problem of modeling market clearing price forecasting in deregulated markets is studied. And electricity price forecasting with support vector machines based on data mining technology is provided. MCP price influential factors such as weather factors, day type, previous competitive load and recent dayspsilas electricity price are considered in this paper. Based on these influential factors, the training samples are formed, then using them to train the corresponding SVM forecasting model. Finally, using the forecasting results which got by the upper four SVMs and real values of the forecasting days to train the No.5 SVM forecasting model. The proposed algorithm is more robust and reliable as compared to traditional approach and neural networks. The performance of our proposed modeling approach has been tested using practical electricity market and compared with traditional neural network. The satisfactory results with better generalization capability and lower prediction error can be obtained.