By Topic

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

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Wei Sun ; Dept. of Econ. & Manage., North China Electr. Power Univ., Baoding ; Jian-Chang Lu ; Ming Meng

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

Published in:

Machine Learning and Cybernetics, 2006 International Conference on

Date of Conference:

13-16 Aug. 2006