Scheduled System Maintenance:
On Monday, April 27th, IEEE Xplore will undergo scheduled maintenance from 1:00 PM - 3:00 PM ET (17:00 - 19:00 UTC). No interruption in service is anticipated.
By Topic

Time-variant slide fuzzy time-series method for short-term load forecasting

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

4 Author(s)
Xiaojuan Liu ; Coll. of Inf. Sci. & Technol., Donghua Univ., Shanghai, China ; Enjian Bai ; Jian'an Fang ; Lunhan Luo

Power load forecasting is important in energy management with great influence on generation scheduling, operation and controlling electric power systems. Economic and precise short-term load forecasting is needed in power system planning and distribution and it can result in costing saving and better operation conditions. In order to reduce the load forecasting error, the concept of fuzzy time series is introduced in the short term load forecasting. The proposed forecasting method adapts an analysis slide window of fuzzy time series to train the trend predictor in the training phase, and uses these trend predictor to generate forecasting values in the forecasting phase. By using the data from the National Electric Power Company in Jordan (used in), the numerical examples are employed to illustrate the proposed method, as well as to compare the training accuracy of the proposed method with the fuzzy inference model. The results show that the maximum the mean absolute percentage(MAPE) in proposed method is less than 1%, which produces more accurate training results as compared to the fuzzy inference model. The MAPE in forecasting phase in our proposed model is less than 10%.

Published in:

Intelligent Computing and Intelligent Systems (ICIS), 2010 IEEE International Conference on  (Volume:1 )

Date of Conference:

29-31 Oct. 2010