Agent-based modeling of the demand-side flexibility

B. Kladnik, A. Gubina, G. Artac, K. Nagode, I. Kockar

Research output: Contribution to conferencePaper

13 Citations (Scopus)

Abstract

The paper presents an agent-based approach to model the flexibility of the demand-side. It uses Q-learning algorithm to model a behavior of a demand-side agent, so to investigate the elasticity of the demand to the change in price. Often, market simulation models assume that the demand elasticity is known, however due the lack of data this elasticity is not easy to determine. The objective of this paper is to evaluate the flexibility of the total system demand, and the shift in the consumption with the price, i.e. increase in the demand when the price is low, and a decrease in the demand when the price is high. The here presented model of a demand-side agent is incorporated into the market simulator with double-sided auctions, and is tested on the Slovenian market. However, this approach can be used to estimate flexibility in any system for which the forecasted demand data and generation offers are know.
Original languageEnglish
Pages1 -8
Number of pages8
DOIs
Publication statusPublished - 1 Jul 2011
EventIEEE Power and Energy Society General Meeting 2011 - Ljubljana, Slovenia
Duration: 24 Jul 2011 → …

Conference

ConferenceIEEE Power and Energy Society General Meeting 2011
CountrySlovenia
CityLjubljana
Period24/07/11 → …

Fingerprint

Agent-based modeling
Elasticity
Simulation model
Demand systems
Learning algorithm
Auctions
Agent-based
Demand elasticity

Keywords

  • Q-learning algorithm
  • Slovenian market
  • agent-based modeling
  • demand data forecasting
  • demand elasticity
  • demand-side flexibility
  • double-sided auctions
  • market simulation models
  • learning (artificial intelligence)
  • power engineering computing
  • power generation economics
  • power markets
  • pricing

Cite this

Kladnik, B., Gubina, A., Artac, G., Nagode, K., & Kockar, I. (2011). Agent-based modeling of the demand-side flexibility. 1 -8. Paper presented at IEEE Power and Energy Society General Meeting 2011, Ljubljana, Slovenia. https://doi.org/10.1109/PES.2011.6039772
Kladnik, B. ; Gubina, A. ; Artac, G. ; Nagode, K. ; Kockar, I. / Agent-based modeling of the demand-side flexibility. Paper presented at IEEE Power and Energy Society General Meeting 2011, Ljubljana, Slovenia.8 p.
@conference{474b015c61a1440e9fb1b3f17e031c7f,
title = "Agent-based modeling of the demand-side flexibility",
abstract = "The paper presents an agent-based approach to model the flexibility of the demand-side. It uses Q-learning algorithm to model a behavior of a demand-side agent, so to investigate the elasticity of the demand to the change in price. Often, market simulation models assume that the demand elasticity is known, however due the lack of data this elasticity is not easy to determine. The objective of this paper is to evaluate the flexibility of the total system demand, and the shift in the consumption with the price, i.e. increase in the demand when the price is low, and a decrease in the demand when the price is high. The here presented model of a demand-side agent is incorporated into the market simulator with double-sided auctions, and is tested on the Slovenian market. However, this approach can be used to estimate flexibility in any system for which the forecasted demand data and generation offers are know.",
keywords = "Q-learning algorithm, Slovenian market, agent-based modeling, demand data forecasting, demand elasticity, demand-side flexibility, double-sided auctions, market simulation models, learning (artificial intelligence), power engineering computing, power generation economics, power markets, pricing",
author = "B. Kladnik and A. Gubina and G. Artac and K. Nagode and I. Kockar",
year = "2011",
month = "7",
day = "1",
doi = "10.1109/PES.2011.6039772",
language = "English",
pages = "1 --8",
note = "IEEE Power and Energy Society General Meeting 2011 ; Conference date: 24-07-2011",

}

Kladnik, B, Gubina, A, Artac, G, Nagode, K & Kockar, I 2011, 'Agent-based modeling of the demand-side flexibility' Paper presented at IEEE Power and Energy Society General Meeting 2011, Ljubljana, Slovenia, 24/07/11, pp. 1 -8. https://doi.org/10.1109/PES.2011.6039772

Agent-based modeling of the demand-side flexibility. / Kladnik, B.; Gubina, A.; Artac, G.; Nagode, K.; Kockar, I.

2011. 1 -8 Paper presented at IEEE Power and Energy Society General Meeting 2011, Ljubljana, Slovenia.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Agent-based modeling of the demand-side flexibility

AU - Kladnik, B.

AU - Gubina, A.

AU - Artac, G.

AU - Nagode, K.

AU - Kockar, I.

PY - 2011/7/1

Y1 - 2011/7/1

N2 - The paper presents an agent-based approach to model the flexibility of the demand-side. It uses Q-learning algorithm to model a behavior of a demand-side agent, so to investigate the elasticity of the demand to the change in price. Often, market simulation models assume that the demand elasticity is known, however due the lack of data this elasticity is not easy to determine. The objective of this paper is to evaluate the flexibility of the total system demand, and the shift in the consumption with the price, i.e. increase in the demand when the price is low, and a decrease in the demand when the price is high. The here presented model of a demand-side agent is incorporated into the market simulator with double-sided auctions, and is tested on the Slovenian market. However, this approach can be used to estimate flexibility in any system for which the forecasted demand data and generation offers are know.

AB - The paper presents an agent-based approach to model the flexibility of the demand-side. It uses Q-learning algorithm to model a behavior of a demand-side agent, so to investigate the elasticity of the demand to the change in price. Often, market simulation models assume that the demand elasticity is known, however due the lack of data this elasticity is not easy to determine. The objective of this paper is to evaluate the flexibility of the total system demand, and the shift in the consumption with the price, i.e. increase in the demand when the price is low, and a decrease in the demand when the price is high. The here presented model of a demand-side agent is incorporated into the market simulator with double-sided auctions, and is tested on the Slovenian market. However, this approach can be used to estimate flexibility in any system for which the forecasted demand data and generation offers are know.

KW - Q-learning algorithm

KW - Slovenian market

KW - agent-based modeling

KW - demand data forecasting

KW - demand elasticity

KW - demand-side flexibility

KW - double-sided auctions

KW - market simulation models

KW - learning (artificial intelligence)

KW - power engineering computing

KW - power generation economics

KW - power markets

KW - pricing

UR - http://www.scopus.com/inward/record.url?scp=82855168095&partnerID=8YFLogxK

U2 - 10.1109/PES.2011.6039772

DO - 10.1109/PES.2011.6039772

M3 - Paper

SP - 1

EP - 8

ER -

Kladnik B, Gubina A, Artac G, Nagode K, Kockar I. Agent-based modeling of the demand-side flexibility. 2011. Paper presented at IEEE Power and Energy Society General Meeting 2011, Ljubljana, Slovenia. https://doi.org/10.1109/PES.2011.6039772