Discovering emergence and bidding behaviour in competitive electricity market using agent-based simulation

Ly-Fie Sugianto; Zhigang Liao

doi:10.1007/978-3-319-57421-9_12

Discovering emergence and bidding behaviour in competitive electricity market using agent-based simulation

Ly-Fie Sugianto, Zhigang Liao

Department of Accounting

Research output: Chapter in Book/Report/Conference proceeding › Chapter (Book) › Research › peer-review

Abstract

The aim of this paper is to explore the implication of multi agent interaction, learning and competing in a repetitive trading environment. Using the complex systems paradigm, the study attempts to observe the behavior of the agents and the emergence phenomena resulting from the multi agent interaction. Using Q-learning, generator agents can rapidly learn the market mechanism and auction rules as they seek to maximize their revenue by modifying their bidding strategies. In this paper, we experiment with different pricing rule to observe the impact on agents' behavior. The paper also describes the types of agents in each domain, together with the properties, relationships, processes and events associated with the agents. Emergence from this study includes collusion and capacity withholding to inflate price. The emergence is evidence that we can gain new knowledge from the Sciences of the Artificial.

Original language	English
Title of host publication	Proceedings of ELM-2016
Editors	Jiuwen Cao, Erik Cambria, Amaury Lendasse, Yoan Miche, Chi Man Vong
Place of Publication	Cham Switzerland
Publisher	Springer
Pages	145-158
Number of pages	14
ISBN (Electronic)	9783319574219
ISBN (Print)	9783319574202
DOIs	https://doi.org/10.1007/978-3-319-57421-9_12
Publication status	Published - 2018
Event	Extreme Learning Machines 2016 - Expo and Convention Centre, Marina Bay Sands, Singapore, Singapore Duration: 13 Dec 2016 → 15 Dec 2016 http://www.ntu.edu.sg/home/egbhuang/ELM2016/index.html

Publication series

Name	Proceedings in Adaptation, Learning and Optimization
Publisher	Springer
Volume	9
ISSN (Print)	2363-6084
ISSN (Electronic)	2363-6092

Conference

Conference	Extreme Learning Machines 2016
Abbreviated title	ELM2016
Country/Territory	Singapore
City	Singapore
Period	13/12/16 → 15/12/16
Internet address	http://www.ntu.edu.sg/home/egbhuang/ELM2016/index.html

Keywords

Agent-based modelling
Auction
Artificial intelligence (AI)
Complex Adaptive Systems (CAS)

Access to Document

10.1007/978-3-319-57421-9_12

Cite this

Sugianto, L.-F., & Liao, Z. (2018). Discovering emergence and bidding behaviour in competitive electricity market using agent-based simulation. In J. Cao, E. Cambria, A. Lendasse, Y. Miche, & C. M. Vong (Eds.), Proceedings of ELM-2016 (pp. 145-158). Article 12 (Proceedings in Adaptation, Learning and Optimization; Vol. 9). Springer. https://doi.org/10.1007/978-3-319-57421-9_12

@inbook{3a8fe1bd7a1c4229b6fac5b99037312c,

title = "Discovering emergence and bidding behaviour in competitive electricity market using agent-based simulation",

abstract = "The aim of this paper is to explore the implication of multi agent interaction, learning and competing in a repetitive trading environment. Using the complex systems paradigm, the study attempts to observe the behavior of the agents and the emergence phenomena resulting from the multi agent interaction. Using Q-learning, generator agents can rapidly learn the market mechanism and auction rules as they seek to maximize their revenue by modifying their bidding strategies. In this paper, we experiment with different pricing rule to observe the impact on agents' behavior. The paper also describes the types of agents in each domain, together with the properties, relationships, processes and events associated with the agents. Emergence from this study includes collusion and capacity withholding to inflate price. The emergence is evidence that we can gain new knowledge from the Sciences of the Artificial.",

keywords = "Agent-based modelling, Auction, Artificial intelligence (AI), Complex Adaptive Systems (CAS)",

author = "Ly-Fie Sugianto and Zhigang Liao",

year = "2018",

doi = "10.1007/978-3-319-57421-9_12",

language = "English",

isbn = "9783319574202",

series = "Proceedings in Adaptation, Learning and Optimization",

publisher = "Springer",

pages = "145--158",

editor = "Jiuwen Cao and Erik Cambria and Amaury Lendasse and Yoan Miche and Vong, {Chi Man}",

booktitle = "Proceedings of ELM-2016",

note = "Extreme Learning Machines 2016, ELM2016 ; Conference date: 13-12-2016 Through 15-12-2016",

url = "http://www.ntu.edu.sg/home/egbhuang/ELM2016/index.html",

}

Sugianto, L-F & Liao, Z 2018, Discovering emergence and bidding behaviour in competitive electricity market using agent-based simulation. in J Cao, E Cambria, A Lendasse, Y Miche & CM Vong (eds), Proceedings of ELM-2016., 12, Proceedings in Adaptation, Learning and Optimization, vol. 9, Springer, Cham Switzerland, pp. 145-158, Extreme Learning Machines 2016, Singapore, Singapore, 13/12/16. https://doi.org/10.1007/978-3-319-57421-9_12

Discovering emergence and bidding behaviour in competitive electricity market using agent-based simulation. / Sugianto, Ly-Fie; Liao, Zhigang.
Proceedings of ELM-2016. ed. / Jiuwen Cao; Erik Cambria; Amaury Lendasse; Yoan Miche; Chi Man Vong. Cham Switzerland: Springer, 2018. p. 145-158 12 (Proceedings in Adaptation, Learning and Optimization; Vol. 9).

Research output: Chapter in Book/Report/Conference proceeding › Chapter (Book) › Research › peer-review

TY - CHAP

T1 - Discovering emergence and bidding behaviour in competitive electricity market using agent-based simulation

AU - Sugianto, Ly-Fie

AU - Liao, Zhigang

PY - 2018

Y1 - 2018

N2 - The aim of this paper is to explore the implication of multi agent interaction, learning and competing in a repetitive trading environment. Using the complex systems paradigm, the study attempts to observe the behavior of the agents and the emergence phenomena resulting from the multi agent interaction. Using Q-learning, generator agents can rapidly learn the market mechanism and auction rules as they seek to maximize their revenue by modifying their bidding strategies. In this paper, we experiment with different pricing rule to observe the impact on agents' behavior. The paper also describes the types of agents in each domain, together with the properties, relationships, processes and events associated with the agents. Emergence from this study includes collusion and capacity withholding to inflate price. The emergence is evidence that we can gain new knowledge from the Sciences of the Artificial.

AB - The aim of this paper is to explore the implication of multi agent interaction, learning and competing in a repetitive trading environment. Using the complex systems paradigm, the study attempts to observe the behavior of the agents and the emergence phenomena resulting from the multi agent interaction. Using Q-learning, generator agents can rapidly learn the market mechanism and auction rules as they seek to maximize their revenue by modifying their bidding strategies. In this paper, we experiment with different pricing rule to observe the impact on agents' behavior. The paper also describes the types of agents in each domain, together with the properties, relationships, processes and events associated with the agents. Emergence from this study includes collusion and capacity withholding to inflate price. The emergence is evidence that we can gain new knowledge from the Sciences of the Artificial.

KW - Agent-based modelling

KW - Auction

KW - Artificial intelligence (AI)

KW - Complex Adaptive Systems (CAS)

U2 - 10.1007/978-3-319-57421-9_12

DO - 10.1007/978-3-319-57421-9_12

M3 - Chapter (Book)

SN - 9783319574202

T3 - Proceedings in Adaptation, Learning and Optimization

SP - 145

EP - 158

BT - Proceedings of ELM-2016

A2 - Cao, Jiuwen

A2 - Cambria, Erik

A2 - Lendasse, Amaury

A2 - Miche, Yoan

A2 - Vong, Chi Man

PB - Springer

CY - Cham Switzerland

T2 - Extreme Learning Machines 2016

Y2 - 13 December 2016 through 15 December 2016

ER -