Application of Time Series Based SVM Model on Next-Day Electricity Price Forecasting Under Deregulated Power Market

With the development of power markets, electricity price especially the market clearing price (MCP) forecasting is becoming more and more important in such new competitive markets since the MCP forecasting is 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 time series is provided. Except considering MCP price influential factors such as previous competitive load, making-up price, competitive generating capacity etc, the past price data which are time series style or not have been included as attributes in input parameters. That is to introduce the concept of time series into our presented model. Based on these influential factors, the corresponding SVM forecasting model is presented. 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