Roth-Erev Reinforcement Learning Approach for Smart Generator Bidding towards Long Term Electricity Market Operation Using Agent Based Dynamic Modeling

Purushothaman, Kiran; Chandrakala, Vijaya

doi:10.1080/15325008.2020.1758840

Cited by 17 publications

(5 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[26], [27], [28] Artificial Neural Networks [11], [29], [30], [31], [32], [33], [34] [35], [12], [36], [37], [38], [39], [40] Reinforcement Learning [41], [42], [43], [44], [45] [46], [47], [48], [49], [50], [51], [52], [10], [53] Nature-Inspired Intelligence [54] [55]…”

Section: Overview Of Algorithmic Approaches For Electricity and Flexibility Tradingmentioning

confidence: 99%

“…[35] explore a RL approach with a hybrid stochastic model coupled with a Stackelberg game for bidding on a day-ahead market. [39] employ a RL approach with a Roth-Erev learning strategy to improve the bidding of GENCOs on a wholesale electricity market. Further, [41] and [43] apply a deep deterministic policy gradient algorithm, i.e., an actor-critic approach, to combine the functionalities of RL and ANN, maximizing profits of electricity suppliers by selling their generated electricity.…”

Section: Overview Of Algorithmic Approaches For Electricity and Flexibility Tradingmentioning

confidence: 99%

See 1 more Smart Citation

How to trade electricity flexibility using artificial intelligence - An integrated algorithmic framework

Hanny¹,

Körner²,

Leinauer³

et al. 2022

Proceedings of the Annual Hawaii International Conference on System Sciences

View full text Add to dashboard Cite

In course of the energy transition, the growing share of Renewable Energy Sources (RES) makes electricity generation more decentralized and intermittent. This increases the relevance of exploiting flexibility potentials that help balancing intermittent RES supply and demand and, thus, contribute to overall system resilience. Digital technologies, in the form of automated trading algorithms, may considerably contribute to flexibility exploitation, as they enable faster and more accurate market interactions. In this paper, we develop an integrated algorithmic framework that finds an optimal trading strategy for flexibility on multiple markets. Hence, our work supports the trading of flexibility in a multi-market environment that results in enhanced market integration and harmonization of economically traded and physically delivered electricity, which finally promotes resilience in highly complex electricity systems.

show abstract

Section: Overview Of Algorithmic Approaches For Electricity and Flexibility Tradingmentioning

confidence: 99%

Section: Overview Of Algorithmic Approaches For Electricity and Flexibility Tradingmentioning

confidence: 99%

How to trade electricity flexibility using artificial intelligence - An integrated algorithmic framework

Hanny¹,

Körner²,

Leinauer³

et al. 2022

Proceedings of the Annual Hawaii International Conference on System Sciences

View full text Add to dashboard Cite

show abstract

“…Purushothaman et al [65] model the learning capabilities of power generators through the use of the Roth-Erev RL algorithm. They find that the agents are able to exhibit market power through this approach.…”

Section: Literature Review 41 Reinforcement Learningmentioning

confidence: 99%

“…[43] Local energy market Bidding strategies DQN 2020 Nunna H.S.V.S.K. [56] Microgrid Bidding strategies Q-Learning 2020 Purushothaman K. [65] International/National Bidding strategies Roth-Erev 2020 Mbuwir B.V. [48] Microgrid Scheduling of flexibility Policy Iteration (PI), Fitted Q-iteration (FQI) 2020 Kiran P. [36] International/National Bidding strategies Variant Roth-Erev 2019 Lin F. [41] International/National Bidding strategies Roth-Erev 2019 Wang J. [84] International/National Bidding strategies Roth-Erev 2019 Machado M.R.…”

Section: Year First Authormentioning

confidence: 99%

Machine learning applications for electricity market agent-based models: A systematic literature review

Kell¹,

McGough²,

Forshaw³

2022

Preprint

View full text Add to dashboard Cite

The electricity market has a vital role to play in the decarbonisation of the energy system. However, the electricity market is made up of many different variables and data inputs. These variables and data inputs behave in sometimes unpredictable ways which can not be predicted a-priori. It has therefore been suggested that agentbased simulations are used to better understand the dynamics of the electricity market. Agent-based models provide the opportunity to integrate machine learning and artificial intelligence to add intelligence, make better forecasts and control the power market in better and more efficient ways. In this systematic literature review, we review 55 papers published between 2016 and 2021 which focus on machine learning applied to agent-based electricity market models. We find that research clusters around popular topics, such as bidding strategies. However, there exists a long-tail of different research applications that could benefit from the high intensity research from the more investigated applications. CCS CONCEPTS• Computing methodologies → Modeling and simulation; Machine learning; Artificial intelligence.

show abstract

“…Regarding the algorithms, classical RL algorithms mainly include Roth-Erev (RE) learning [21], Q-learning [22], deep Q-learning (DQN), deep deterministic policy gradient (DDPG), etc. RE learning has been often used in the simulations of the day-ahead electricity market [23], forward electricity market [24], long-term electricity market [25], etc. Reference [26] applied RE to simulate the bidding decision-making of generators in the demand response market with commercial buildings.…”

Section: Introductionmentioning

confidence: 99%

MRL-Based Model for Diverse Bidding Decision-Makings of Power Retail Company in the Wholesale Electricity Market of China

Wang

Liu

Yuan

et al. 2023

Axioms

View full text Add to dashboard Cite

Power retail companies in the electricity market make profits through buying and selling power energy in the wholesale and retail markets, respectively. Traditionally, they are assumed to bid in the wholesale market with the same objective, i.e., maximize the profit. This paper proposes a multiagent reinforcement learning (MRL)-based model to simulate the diverse bidding decision-making concerning various operation objectives and the profit-sharing modes of power retail companies in China’s wholesale electricity market, which contributes to a more realistic modeling and simulation of the retail companies. Specifically, three types of operation objectives and five types of profit-sharing modes are mathematically formulated. After that, a complete electricity market optimization model is established, and a case study with 30 retail companies is carried out. The simulation results show that the proposed method can effectively model the diverse bidding decision-making of the power retail companies, which can further assist their decision-making and further contribute to the analysis and simulations of the electricity market.

show abstract

Roth-Erev Reinforcement Learning Approach for Smart Generator Bidding towards Long Term Electricity Market Operation Using Agent Based Dynamic Modeling

Cited by 17 publications

References 23 publications

How to trade electricity flexibility using artificial intelligence - An integrated algorithmic framework

How to trade electricity flexibility using artificial intelligence - An integrated algorithmic framework

Machine learning applications for electricity market agent-based models: A systematic literature review

MRL-Based Model for Diverse Bidding Decision-Makings of Power Retail Company in the Wholesale Electricity Market of China

Contact Info

Product

Resources

About