Enhancing frequency response using artificial intelligence techniques in the power system with renewable energy resources

IF 4.9 2区社会学 Q2 ENVIRONMENTAL SCIENCES

Sustainable Futures Pub Date : 2025-06-14 DOI:10.1016/j.sftr.2025.100848

M. Elzalik , Abouelmaaty M. Aly , Amir Y. Hassan , M.A. Abdelghany

{"title":"Enhancing frequency response using artificial intelligence techniques in the power system with renewable energy resources","authors":"M. Elzalik , Abouelmaaty M. Aly , Amir Y. Hassan , M.A. Abdelghany","doi":"10.1016/j.sftr.2025.100848","DOIUrl":null,"url":null,"abstract":"<div><div>This article aims to improve the performance of the modern electric power system with renewable energy resources, which have fluctuating power and low inertia contribution, by designing a control system based on different artificial intelligent (AI) techniques. Because of this power fluctuation, there is a constant mismatch between generation and load, which causes the power system's frequency to vary. Low-inertia operation amplifies the frequency fluctuation at the same time. Due to the stochastic variation of load and renewable resources in the system, an effective load frequency control (LFC) technique is therefore required. When working conditions change, LFC based on a fixed controller may perform unsatisfactorily even though it may respond optimally at a specific operating point. With the constraints and nonlinearities of the system taken into account, the controllers are applied to the secondary loop LFC of a multi-source generating system. The power system’s mathematical model was obtained using a transfer function approach, and the AI controllers were optimized using a particle swarm optimization technique (PSO) algorithm. Utilizing the FOPID reduces the settling time by 50.5 %, 64.6 % while FFOPID reduces it by 74.0 %, 81.4 % compared to optimal PID and FPID, respectively. Also, they reduces the system nadir for excessive load conditions. The results demonstrated that the power system's LFC is combined with AI controllers, the fuzzy fractional order proportional integral derivative (FFOPID) controller performs better than the other AI controllers.</div></div>","PeriodicalId":34478,"journal":{"name":"Sustainable Futures","volume":"10 ","pages":"Article 100848"},"PeriodicalIF":4.9000,"publicationDate":"2025-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Sustainable Futures","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2666188825004137","RegionNum":2,"RegionCategory":"社会学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENVIRONMENTAL SCIENCES","Score":null,"Total":0}

引用次数: 0

Abstract

This article aims to improve the performance of the modern electric power system with renewable energy resources, which have fluctuating power and low inertia contribution, by designing a control system based on different artificial intelligent (AI) techniques. Because of this power fluctuation, there is a constant mismatch between generation and load, which causes the power system's frequency to vary. Low-inertia operation amplifies the frequency fluctuation at the same time. Due to the stochastic variation of load and renewable resources in the system, an effective load frequency control (LFC) technique is therefore required. When working conditions change, LFC based on a fixed controller may perform unsatisfactorily even though it may respond optimally at a specific operating point. With the constraints and nonlinearities of the system taken into account, the controllers are applied to the secondary loop LFC of a multi-source generating system. The power system’s mathematical model was obtained using a transfer function approach, and the AI controllers were optimized using a particle swarm optimization technique (PSO) algorithm. Utilizing the FOPID reduces the settling time by 50.5 %, 64.6 % while FFOPID reduces it by 74.0 %, 81.4 % compared to optimal PID and FPID, respectively. Also, they reduces the system nadir for excessive load conditions. The results demonstrated that the power system's LFC is combined with AI controllers, the fuzzy fractional order proportional integral derivative (FFOPID) controller performs better than the other AI controllers.

查看原文本刊更多论文

利用人工智能技术增强可再生能源电力系统的频率响应

本文旨在通过设计一种基于不同人工智能（AI）技术的控制系统，提高现代可再生能源电力系统的性能，使其具有波动功率和低惯性贡献。由于这种功率波动，发电和负荷之间存在不断的不匹配，从而导致电力系统的频率变化。低惯性运行同时放大了频率波动。由于系统中负荷和可再生资源的随机变化，需要一种有效的负荷频率控制技术。当工作条件发生变化时，基于固定控制器的LFC即使在某一特定工作点上可能达到最优响应，也可能表现不理想。考虑到系统的约束和非线性，将该控制器应用于多源发电系统的二次回路LFC。采用传递函数法建立了电力系统的数学模型，并采用粒子群优化算法对人工智能控制器进行了优化。与最优PID和FPID相比，使用FOPID分别减少了50.5%、64.6%和74.0%、81.4%的沉淀时间。此外，他们减少了系统的最低点过度负载条件。结果表明，将电力系统LFC与人工智能控制器相结合，模糊分数阶比例积分导数（FFOPID）控制器的性能优于其他人工智能控制器。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Sustainable Futures Social Sciences-Sociology and Political Science

CiteScore

9.30

自引率

1.80%

发文量

审稿时长

71 days

期刊介绍： Sustainable Futures: is a journal focused on the intersection of sustainability, environment and technology from various disciplines in social sciences, and their larger implications for corporation, government, education institutions, regions and society both at present and in the future. It provides an advanced platform for studies related to sustainability and sustainable development in society, economics, environment, and culture. The scope of the journal is broad and encourages interdisciplinary research, as well as welcoming theoretical and practical research from all methodological approaches.