Intelligent forecasting method of distributed energy load based on least squares support vector machine

Yingwei Chen and Zhikui Chang

International Journal of Global Energy Issues, 2023, vol. 45, issue 4/5, 383-394

Abstract: Aiming at the problems of long prediction time and low prediction accuracy of traditional distributed energy load intelligent prediction methods, a distributed energy load intelligent prediction method based on least squares support vector machine is proposed. The method of linear interpolation is used to process the missing load data of distributed energy, and the wrong load data of distributed energy are processed horizontally and vertically. On this basis, the t-test standard in probability and statistics method is used to identify the abnormal load of distributed energy. Using least squares support vector machine, a distributed energy load forecasting model is constructed to realise the intelligent forecasting of distributed energy load. The experimental results show that the average MAPE and RMSE of the proposed method are 1.008% and 1048 respectively, and the time of distributed energy load forecasting is 15.8 s. The proposed method can effectively improve the accuracy and efficiency of distributed energy load forecasting.

Keywords: least squares support vector machine; linear interpolation; t-test criterion; distributed energy; load forecasting. (search for similar items in EconPapers)
Date: 2023
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.inderscience.com/link.php?id=132013 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ids:ijgeni:v:45:y:2023:i:4/5:p:383-394

Access Statistics for this article

More articles in International Journal of Global Energy Issues from Inderscience Enterprises Ltd
Bibliographic data for series maintained by Sarah Parker ().