Metalearning to support competitive electricity market players' strategic bidding

Tiago Pinto, Tiago M. Sousa, Hugo Morais, Isabel Praca, Zita Vale

Research output: Contribution to journalJournal articleResearchpeer-review

127 Downloads (Pure)

Abstract

Electricity markets are becoming more competitive, to some extent due to the increasing number of players that have moved from other sectors to the power industry. This is essentially resulting from incentives provided to distributed generation. Relevant changes in this domain are still occurring, such as the extension of national and regional markets to continental scales. Decision support tools have thereby become essential to help electricity market players in their negotiation process. This paper presents a metalearner to support electricity market players in bidding definition. The proposed metalearner uses a dynamic artificial neural network to create its own output, taking advantage on several learning algorithms already implemented in ALBidS (Adaptive Learning strategic Bidding System). The proposed metalearner considers different weights for each strategy, based on their individual performance. The metalearner's performance is analysed in scenarios based on real electricity markets data using MASCEM (Multi-Agent Simulator for Competitive Electricity Markets). Results show that the proposed metalearner is able to provide higher profits to market players when compared to other current methodologies and that results improve over time, as consequence of its learning process. (C) 2016 Elsevier B.V. All rights reserved.
Original languageEnglish
JournalElectric Power Systems Research
Volume135
Pages (from-to)27-34
Number of pages8
ISSN0378-7796
DOIs
Publication statusPublished - 2016

Keywords

  • Adaptive learning
  • Artificial neural network
  • Electricity markets
  • Metalearning
  • Multi-agent simulation

Cite this

Pinto, Tiago ; Sousa, Tiago M. ; Morais, Hugo ; Praca, Isabel ; Vale, Zita. / Metalearning to support competitive electricity market players' strategic bidding. In: Electric Power Systems Research. 2016 ; Vol. 135. pp. 27-34.
@article{0bea56a9643a4e28b0176231284a3747,
title = "Metalearning to support competitive electricity market players' strategic bidding",
abstract = "Electricity markets are becoming more competitive, to some extent due to the increasing number of players that have moved from other sectors to the power industry. This is essentially resulting from incentives provided to distributed generation. Relevant changes in this domain are still occurring, such as the extension of national and regional markets to continental scales. Decision support tools have thereby become essential to help electricity market players in their negotiation process. This paper presents a metalearner to support electricity market players in bidding definition. The proposed metalearner uses a dynamic artificial neural network to create its own output, taking advantage on several learning algorithms already implemented in ALBidS (Adaptive Learning strategic Bidding System). The proposed metalearner considers different weights for each strategy, based on their individual performance. The metalearner's performance is analysed in scenarios based on real electricity markets data using MASCEM (Multi-Agent Simulator for Competitive Electricity Markets). Results show that the proposed metalearner is able to provide higher profits to market players when compared to other current methodologies and that results improve over time, as consequence of its learning process. (C) 2016 Elsevier B.V. All rights reserved.",
keywords = "Adaptive learning, Artificial neural network, Electricity markets, Metalearning, Multi-agent simulation",
author = "Tiago Pinto and Sousa, {Tiago M.} and Hugo Morais and Isabel Praca and Zita Vale",
year = "2016",
doi = "10.1016/j.epsr.2016.03.012",
language = "English",
volume = "135",
pages = "27--34",
journal = "Electric Power Systems Research",
issn = "0378-7796",
publisher = "Elsevier",

}

Metalearning to support competitive electricity market players' strategic bidding. / Pinto, Tiago; Sousa, Tiago M.; Morais, Hugo; Praca, Isabel; Vale, Zita.

In: Electric Power Systems Research, Vol. 135, 2016, p. 27-34.

Research output: Contribution to journalJournal articleResearchpeer-review

TY - JOUR

T1 - Metalearning to support competitive electricity market players' strategic bidding

AU - Pinto, Tiago

AU - Sousa, Tiago M.

AU - Morais, Hugo

AU - Praca, Isabel

AU - Vale, Zita

PY - 2016

Y1 - 2016

N2 - Electricity markets are becoming more competitive, to some extent due to the increasing number of players that have moved from other sectors to the power industry. This is essentially resulting from incentives provided to distributed generation. Relevant changes in this domain are still occurring, such as the extension of national and regional markets to continental scales. Decision support tools have thereby become essential to help electricity market players in their negotiation process. This paper presents a metalearner to support electricity market players in bidding definition. The proposed metalearner uses a dynamic artificial neural network to create its own output, taking advantage on several learning algorithms already implemented in ALBidS (Adaptive Learning strategic Bidding System). The proposed metalearner considers different weights for each strategy, based on their individual performance. The metalearner's performance is analysed in scenarios based on real electricity markets data using MASCEM (Multi-Agent Simulator for Competitive Electricity Markets). Results show that the proposed metalearner is able to provide higher profits to market players when compared to other current methodologies and that results improve over time, as consequence of its learning process. (C) 2016 Elsevier B.V. All rights reserved.

AB - Electricity markets are becoming more competitive, to some extent due to the increasing number of players that have moved from other sectors to the power industry. This is essentially resulting from incentives provided to distributed generation. Relevant changes in this domain are still occurring, such as the extension of national and regional markets to continental scales. Decision support tools have thereby become essential to help electricity market players in their negotiation process. This paper presents a metalearner to support electricity market players in bidding definition. The proposed metalearner uses a dynamic artificial neural network to create its own output, taking advantage on several learning algorithms already implemented in ALBidS (Adaptive Learning strategic Bidding System). The proposed metalearner considers different weights for each strategy, based on their individual performance. The metalearner's performance is analysed in scenarios based on real electricity markets data using MASCEM (Multi-Agent Simulator for Competitive Electricity Markets). Results show that the proposed metalearner is able to provide higher profits to market players when compared to other current methodologies and that results improve over time, as consequence of its learning process. (C) 2016 Elsevier B.V. All rights reserved.

KW - Adaptive learning

KW - Artificial neural network

KW - Electricity markets

KW - Metalearning

KW - Multi-agent simulation

U2 - 10.1016/j.epsr.2016.03.012

DO - 10.1016/j.epsr.2016.03.012

M3 - Journal article

VL - 135

SP - 27

EP - 34

JO - Electric Power Systems Research

JF - Electric Power Systems Research

SN - 0378-7796

ER -