Online optimization of integrated energy systems based on deep learning predictive control

IF 4.2 3区工程技术 Q2 ENGINEERING, ELECTRICAL & ELECTRONIC Electric Power Systems Research Pub Date : 2025-06-01 Epub Date: 2025-02-13 DOI:10.1016/j.epsr.2025.111510

Yuefen Gao , Yiying Zhang , Chengbo Yun , Lizhuang Huang

{"title":"Online optimization of integrated energy systems based on deep learning predictive control","authors":"Yuefen Gao , Yiying Zhang , Chengbo Yun , Lizhuang Huang","doi":"10.1016/j.epsr.2025.111510","DOIUrl":null,"url":null,"abstract":"<div><div>With the large-scale grid connection of new energy sources, their high randomness and volatility bring great challenges to the grid. Using deep learning to predict uncertain renewable energy resources has emerged as a promising technology. This paper presents a deep learning-based approach to forecast the power generation of wind and photovoltaic power with the aim of reducing the adverse effects of uncertainty in optimal scheduling problems. Meanwhile, the multi-objective optimization model of the regionally integrated energy system is established by combining the system operation and maintenance cost and system revenue. The system is optimized online by an accelerated particle swarm optimization. The results show that compared to the online optimization with the single APSO method, the operation and maintenance costs are reduced by 60.8 CNY on a typical cooling day and 52.01 CNY on a typical heating day. The utilization rate of renewable energy in the cooling and heating periods is improved by 5.88 % and 0.65 % and the CO2 emission reduction rate is 6.99% in the system. The integrated energy system online optimization method proposed in this study based on deep learning and accelerated particle swarm optimization can reduce operation and maintenance costs, improve the utilization rate of renewable energy.</div></div>","PeriodicalId":50547,"journal":{"name":"Electric Power Systems Research","volume":"243 ","pages":"Article 111510"},"PeriodicalIF":4.2000,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Electric Power Systems Research","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0378779625001026","RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/2/13 0:00:00","PubModel":"Epub","JCR":"Q2","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}

引用次数: 0

Abstract

With the large-scale grid connection of new energy sources, their high randomness and volatility bring great challenges to the grid. Using deep learning to predict uncertain renewable energy resources has emerged as a promising technology. This paper presents a deep learning-based approach to forecast the power generation of wind and photovoltaic power with the aim of reducing the adverse effects of uncertainty in optimal scheduling problems. Meanwhile, the multi-objective optimization model of the regionally integrated energy system is established by combining the system operation and maintenance cost and system revenue. The system is optimized online by an accelerated particle swarm optimization. The results show that compared to the online optimization with the single APSO method, the operation and maintenance costs are reduced by 60.8 CNY on a typical cooling day and 52.01 CNY on a typical heating day. The utilization rate of renewable energy in the cooling and heating periods is improved by 5.88 % and 0.65 % and the CO2 emission reduction rate is 6.99% in the system. The integrated energy system online optimization method proposed in this study based on deep learning and accelerated particle swarm optimization can reduce operation and maintenance costs, improve the utilization rate of renewable energy.

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

基于深度学习预测控制的综合能源系统在线优化

随着新能源的大规模并网，其高度的随机性和波动性给电网带来了巨大的挑战。利用深度学习来预测不确定的可再生能源已经成为一项很有前途的技术。本文提出了一种基于深度学习的风电和光伏发电预测方法，以减少最优调度问题中不确定性的不利影响。同时，结合系统运维成本和系统收益，建立了区域一体化能源系统的多目标优化模型。采用加速粒子群算法对系统进行在线优化。结果表明，与单一APSO方法在线优化相比，典型制冷日运行维护成本降低60.8元，典型采暖日运行维护成本降低52.01元。制冷和供热时段可再生能源利用率分别提高5.88%和0.65%，系统CO2减排率达到6.99%。本文提出的基于深度学习和加速粒子群优化的综合能源系统在线优化方法可以降低运维成本，提高可再生能源的利用率。

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分钟内获得全文去求助

来源期刊

Electric Power Systems Research 工程技术-工程：电子与电气

CiteScore

7.50

自引率

17.90%

发文量

963

审稿时长

3.8 months

期刊介绍： Electric Power Systems Research is an international medium for the publication of original papers concerned with the generation, transmission, distribution and utilization of electrical energy. The journal aims at presenting important results of work in this field, whether in the form of applied research, development of new procedures or components, orginal application of existing knowledge or new designapproaches. The scope of Electric Power Systems Research is broad, encompassing all aspects of electric power systems. The following list of topics is not intended to be exhaustive, but rather to indicate topics that fall within the journal purview. • Generation techniques ranging from advances in conventional electromechanical methods, through nuclear power generation, to renewable energy generation. • Transmission, spanning the broad area from UHV (ac and dc) to network operation and protection, line routing and design. • Substation work: equipment design, protection and control systems. • Distribution techniques, equipment development, and smart grids. • The utilization area from energy efficiency to distributed load levelling techniques. • Systems studies including control techniques, planning, optimization methods, stability, security assessment and insulation coordination.