Enhancing decentralized energy storage investments with artificial intelligence-driven decision models

IF 10.7 2区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Artificial Intelligence Review Pub Date : 2025-04-16 DOI:10.1007/s10462-025-11204-y

Gang Kou, Hasan Dinçer, Edanur Ergün, Serkan Eti, Serhat Yüksel, Ümit Hacıoğlu

{"title":"Enhancing decentralized energy storage investments with artificial intelligence-driven decision models","authors":"Gang Kou, Hasan Dinçer, Edanur Ergün, Serkan Eti, Serhat Yüksel, Ümit Hacıoğlu","doi":"10.1007/s10462-025-11204-y","DOIUrl":null,"url":null,"abstract":"<div><p>Decentralized energy storage investments play a crucial role in enhancing energy efficiency and promoting renewable energy integration. However, the complexity of these projects and the limited resources of the companies make it necessary to determine strategic priorities. This paper tries to define effective investment strategies for the improvements of the decentralized energy storage projects. In the first stage, the selection of mass experts is made via information gain-based mass expert selection. Next, the assessments of the experts are balanced based on the opinion of the best expert by using q-learning algorithm. Moreover, determinants of decentralized energy storage investments are examined with molecular fuzzy (MF) cognitive maps. Finally, strategy alternatives for decentralized energy storage investments are ranked with MF multi-objective particle swarm optimization (MOPSO). The main contribution of this study is the identification of the most effective decentralized energy storage investment alternatives by establishing a novel model. The main novelty of the proposed model is that considering information gain-based mass expert selection technique allows for higher consistency and decision efficiency. Owing to this issue, the decision-making process is accelerated, and the applicability of the results increases. The findings indicate that customer expectations (weight: 0.2577) and financial issues (weight: 0.2513) are the most essential criteria in improving the performance of decentralized energy storage investments. Furthermore, hydrogen-based energy storage (average value: 0.1878) and distributed battery swapping stations (average value: 0.1877) are the most important decentralized energy storage investment alternatives.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 7","pages":""},"PeriodicalIF":10.7000,"publicationDate":"2025-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11204-y.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Artificial Intelligence Review","FirstCategoryId":"94","ListUrlMain":"https://link.springer.com/article/10.1007/s10462-025-11204-y","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}

引用次数: 0

Abstract

Decentralized energy storage investments play a crucial role in enhancing energy efficiency and promoting renewable energy integration. However, the complexity of these projects and the limited resources of the companies make it necessary to determine strategic priorities. This paper tries to define effective investment strategies for the improvements of the decentralized energy storage projects. In the first stage, the selection of mass experts is made via information gain-based mass expert selection. Next, the assessments of the experts are balanced based on the opinion of the best expert by using q-learning algorithm. Moreover, determinants of decentralized energy storage investments are examined with molecular fuzzy (MF) cognitive maps. Finally, strategy alternatives for decentralized energy storage investments are ranked with MF multi-objective particle swarm optimization (MOPSO). The main contribution of this study is the identification of the most effective decentralized energy storage investment alternatives by establishing a novel model. The main novelty of the proposed model is that considering information gain-based mass expert selection technique allows for higher consistency and decision efficiency. Owing to this issue, the decision-making process is accelerated, and the applicability of the results increases. The findings indicate that customer expectations (weight: 0.2577) and financial issues (weight: 0.2513) are the most essential criteria in improving the performance of decentralized energy storage investments. Furthermore, hydrogen-based energy storage (average value: 0.1878) and distributed battery swapping stations (average value: 0.1877) are the most important decentralized energy storage investment alternatives.

查看原文本刊更多论文

用人工智能驱动的决策模型加强分散式储能投资

分散式储能投资在提高能源效率和促进可再生能源整合方面发挥着至关重要的作用。然而，这些项目的复杂性和公司有限的资源使得有必要确定战略优先级。本文试图为分散式储能项目的改进确定有效的投资策略。第一阶段，采用基于信息增益的海量专家选择方法进行海量专家的选择。然后，根据最佳专家的意见，使用q-learning算法对专家的评估进行平衡。此外，分散储能投资的决定因素进行了分子模糊（MF）认知图检查。最后，利用MF多目标粒子群优化（MOPSO）对分散储能投资的策略选择进行排序。本研究的主要贡献是通过建立一个新的模型来确定最有效的分散储能投资替代方案。该模型的主要新颖之处在于考虑了基于信息增益的海量专家选择技术，使得该模型具有更高的一致性和决策效率。由于这个问题，加快了决策过程，提高了结果的适用性。研究结果表明，客户期望（权重：0.2577）和财务问题（权重：0.2513）是提高分散式储能投资绩效的最重要标准。此外，氢基储能（平均值：0.1878）和分布式电池交换站（平均值：0.1877）是最重要的分散式储能投资方案。

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

Artificial Intelligence Review 工程技术-计算机：人工智能

CiteScore

22.00

自引率

3.30%

发文量

194

审稿时长

5.3 months

期刊介绍： Artificial Intelligence Review, a fully open access journal, publishes cutting-edge research in artificial intelligence and cognitive science. It features critical evaluations of applications, techniques, and algorithms, providing a platform for both researchers and application developers. The journal includes refereed survey and tutorial articles, along with reviews and commentary on significant developments in the field.