An agent-based fuzzy-neural approach for precise energy consumption forecasting

Tin-Chih Chen, Yu Cheng Wang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Precise energy consumption forecasting is of major importance to define the future energy consumption of a given region. However, it is not easy to contend with the uncertainty of the long-term energy consumption. In order to effectively forecast the long-term energy consumption, an agent-based fuzzy-neural approach is proposed in this study. In the proposed methodology, a group of agents is formed. These agents configure their own fuzzy neural networks to forecast the long-term energy consumption based on the settings. A collaboration mechanism governed by the centralized efficient P2P communication is therefore established. To facilitate the collaboration process and to derive a single representative value from these forecasts, the fuzzy group learning tree technique is used. The agent-based fuzzy-neural approach takes into account the different points of view in a more efficient way, and therefore the results obtained are more comprehensive and more in-depth. The effectiveness of the proposed methodology is illustrated with a case study.

Original languageEnglish
Title of host publication2012 IEEE Online Conference on Green Communications, GreenCom 2012
Pages56-61
Number of pages6
DOIs
StatePublished - 1 Dec 2012
Event2012 IEEE Online Conference on Green Communications, GreenCom 2012 - Piscataway, NJ, United States
Duration: 25 Sep 201228 Sep 2012

Publication series

Name2012 IEEE Online Conference on Green Communications, GreenCom 2012

Conference

Conference2012 IEEE Online Conference on Green Communications, GreenCom 2012
CountryUnited States
CityPiscataway, NJ
Period25/09/1228/09/12

Keywords

  • agent
  • collaborative intelligences
  • energy consumption
  • forecasting
  • fuzzy neural network

Fingerprint Dive into the research topics of 'An agent-based fuzzy-neural approach for precise energy consumption forecasting'. Together they form a unique fingerprint.

Cite this