Short-Term Load Demand Forecasting using Chaos Theory and ANFIS
DOI:
https://doi.org/10.37591/.v6i2.3115Abstract
In the electrical power sector, forecasting of load demand is an important process for effective planning of future expansion and periodical operations including unit commitments, fuel scheduling, short-term maintenance, security assessments, reducing spinning reserve, reliability analysis etc. Accurate load predictions are also necessary to utilize the electrical energy efficiently and to minimize the conflicts between the demand and supply of electricity. As electric load pattern of a region is very complex and is affected by many factors (such as economic, temperature, etc.) hence, it is necessary to develop new and effective methods for its prediction. In this paper, a method based on ANFIS (adaptive neuro-fuzzy inference system) and chaos theory has been utilized for short-term prediction (hourly) of electrical load. Daily load demand real data of Delhi region has been used as a case study. Largest Lyapunov exponent of the load demand time series, as calculated by using the method of phase space reconstruction, is found to be positive. This indicates the chaotic nature (hence, short time predictability) of the load demand time series. A part of the load demand data is used for training the ANFIS and rest of it is used to test the effectiveness of the proposed method for load prediction. Prediction performance is quantized in terms of a number of performance measures. Low values of mean absolute percentage error, relative error percentage and root mean square relative errors verify the accuracy of the proposed method and thus indicate its effectiveness for load demand prediction.
Keywords: Load forecasting, chaos theory, time delay reconstruction, time series and ANFIS
Downloads
Published
Issue
Section
License
Journal Title:
Title of the Paper:
Corresponding Author’s Information:
Name: Address:
E-mail:
Contact Number:
It is herein agreed that: The copyright to the above-listed unpublished and original article is transferred to STM Journals.
This copyright transfer covers the exclusive right to reproduce and distribute the contribution, including reprints, translations, photographic reproductions, microform, electronic form (offline, online), or any other reproductions of similar nature.
I/We declare that above manuscript is not published already in part or whole (except in the form of abstract) in any journal or magazine for private or public circulation, and, is not under consideration of publication elsewhere.
I/ We warrant(s) that his/her/their contribution is original, except for such excerpts from copyrighted works as may be included with the permission of the copyright holder and author thereof, that it contains no libelous statements, and does not infringe on any copyright, trademark, patent, statutory right, or propriety right of others.
I/We will not publish his/her/their above said contribution anywhere else without the prior written permission of the publisher unless it has been changed substantially. I/We also agree to the authorship of the article in the following order: Author(s) Name Signature(s)
1. ________________
2. ________________
3. ________________
4. ________________
The author(s) agree to the terms of this Copyright Notice, which will apply to this submission if and when it is published by this journal (comments if any to the editor can be added below).
