Multi-Agent Energy Market Simulations With Machine Learning Integration: A Systematic Literature Review

The transition to green energy requires advanced models to analyze complex energy systems. Among these models, agent-based modeling (ABM) or multi-agent systems represents the most pivotal simulation techniques. Machine learning (ML) methods are integrated into ABM to accurately simulate real-world...

Full description

Saved in:
Bibliographic Details
Main Authors: Burak Gokce, Gulgun Kayakutlu
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11039625/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850168914463424512
author Burak Gokce
Gulgun Kayakutlu
author_facet Burak Gokce
Gulgun Kayakutlu
author_sort Burak Gokce
collection DOAJ
description The transition to green energy requires advanced models to analyze complex energy systems. Among these models, agent-based modeling (ABM) or multi-agent systems represents the most pivotal simulation techniques. Machine learning (ML) methods are integrated into ABM to accurately simulate real-world scenarios and the behavior of emerging energy market agents, such as renewable power plants, incentive schemes, electric vehicles, and battery energy storage systems. Initially, ML methods were primarily used to improve agent learning using a reinforcement learning (RL) method. However, the need to estimate external data has motivated the broader adoption of various ML methods. This paper reviews the integration of ML within ABM frameworks, by examining articles from 2014 to 2024. The review methodology utilized self-organizing map (SOM) based clustering using the market data types, simulation periods, and ML contribution types as the clustering attributes. The study provides an overview of the current state of the field and identifies potential research gaps. The findings indicate that agent learning and traditional RL methods dominate; however, significant gaps are evident in terms of the inclusion of long-term and data prediction studies, and future studies should integrate more observations from other energy markets along with electricity.
format Article
id doaj-art-deaecd7a91bc4f4498ab3eec7bcd221a
institution OA Journals
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-deaecd7a91bc4f4498ab3eec7bcd221a2025-08-20T02:20:51ZengIEEEIEEE Access2169-35362025-01-011310600310601810.1109/ACCESS.2025.358073511039625Multi-Agent Energy Market Simulations With Machine Learning Integration: A Systematic Literature ReviewBurak Gokce0https://orcid.org/0000-0002-4223-8434Gulgun Kayakutlu1Energy Institute, Istanbul Technical University, İstanbul, TürkiyeEnergy Institute, Istanbul Technical University, İstanbul, TürkiyeThe transition to green energy requires advanced models to analyze complex energy systems. Among these models, agent-based modeling (ABM) or multi-agent systems represents the most pivotal simulation techniques. Machine learning (ML) methods are integrated into ABM to accurately simulate real-world scenarios and the behavior of emerging energy market agents, such as renewable power plants, incentive schemes, electric vehicles, and battery energy storage systems. Initially, ML methods were primarily used to improve agent learning using a reinforcement learning (RL) method. However, the need to estimate external data has motivated the broader adoption of various ML methods. This paper reviews the integration of ML within ABM frameworks, by examining articles from 2014 to 2024. The review methodology utilized self-organizing map (SOM) based clustering using the market data types, simulation periods, and ML contribution types as the clustering attributes. The study provides an overview of the current state of the field and identifies potential research gaps. The findings indicate that agent learning and traditional RL methods dominate; however, significant gaps are evident in terms of the inclusion of long-term and data prediction studies, and future studies should integrate more observations from other energy markets along with electricity.https://ieeexplore.ieee.org/document/11039625/Agent-based modelingenergy marketsmachine learningmulti-agent systemsself-organizing map
spellingShingle Burak Gokce
Gulgun Kayakutlu
Multi-Agent Energy Market Simulations With Machine Learning Integration: A Systematic Literature Review
IEEE Access
Agent-based modeling
energy markets
machine learning
multi-agent systems
self-organizing map
title Multi-Agent Energy Market Simulations With Machine Learning Integration: A Systematic Literature Review
title_full Multi-Agent Energy Market Simulations With Machine Learning Integration: A Systematic Literature Review
title_fullStr Multi-Agent Energy Market Simulations With Machine Learning Integration: A Systematic Literature Review
title_full_unstemmed Multi-Agent Energy Market Simulations With Machine Learning Integration: A Systematic Literature Review
title_short Multi-Agent Energy Market Simulations With Machine Learning Integration: A Systematic Literature Review
title_sort multi agent energy market simulations with machine learning integration a systematic literature review
topic Agent-based modeling
energy markets
machine learning
multi-agent systems
self-organizing map
url https://ieeexplore.ieee.org/document/11039625/
work_keys_str_mv AT burakgokce multiagentenergymarketsimulationswithmachinelearningintegrationasystematicliteraturereview
AT gulgunkayakutlu multiagentenergymarketsimulationswithmachinelearningintegrationasystematicliteraturereview