Optimal performance evaluation of thermal AGC units based on multi-dimensional feature analysis

Li, Bin, Wang, Shuai, Li, Botong, Li, Hongbo and Wu, Jianzhong ORCID: https://orcid.org/0000-0001-7928-3602 2023. Optimal performance evaluation of thermal AGC units based on multi-dimensional feature analysis. Applied Energy 339 , 120994. 10.1016/j.apenergy.2023.120994

Preview

PDF - Accepted Post-Print Version Available under License Creative Commons Attribution Non-commercial No Derivatives. Download (1MB) | Preview

Abstract

In modern energy system, automatic generation control (AGC) is the core technology of real-time output regulation for thermal power generator. The performance of thermal AGC units must be accurately evaluated to measure their actual contribution to the energy system. However, based on current conventional evaluation methods, the difficulty of the tasks undertaken by AGC units has not been distinguished and quantified. An optimal performance evaluation method based on multi-dimensional feature analysis is proposed. Firstly, a performance index describing the difference between the expected regulating energy and the actual regulated energy of AGC units is designed, which improves the universality of the evaluation to the actual engineering scenarios. Additionally, after data preprocessing and data cleaning, a sample space is constructed to significantly distinguish the difficulty of tasks performed by AGC units. Finally, a multi-dimensional feature analysis in the sample space is proposed to find the optimal performance points of AGC units. Based on historical data, the proposed methods were verified on real AGC units. The experimental results show that the proposed method obtains detailed evaluation results of thermal AGC units with different control requirements and solves the problem of evaluation failure in traditional method.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Engineering
Publisher:	Elsevier
ISSN:	0306-2619
Date of First Compliant Deposit:	12 April 2023
Date of Acceptance:	14 March 2023
Last Modified:	11 Nov 2024 03:45
URI:	https://orca.cardiff.ac.uk/id/eprint/158383

Citation Data

Cited 5 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item