An intelligent broker agent for energy trading: an MDP approach

Rodrigue Talla Kuate; Minghua He; Maria Chli; Hai Wang

An intelligent broker agent for energy trading: an MDP approach

Rodrigue Talla Kuate
, Minghua He
, Maria Chli
, Hai Wang

Research output: Chapter in Book/Published conference output › Conference publication

31 Citations (Scopus)

276 Downloads (Pure)

Abstract

This paper details the development and evaluation of AstonTAC, an energy broker that successfully participated in the 2012 Power Trading Agent Competition (Power TAC). AstonTAC buys electrical energy from the wholesale market and sells it in the retail market. The main focus of the paper
is on the broker’s bidding strategy in the wholesale market. In particular, it employs Markov Decision Processes (MDP) to purchase energy at low prices
in a day-ahead power wholesale market, and keeps energy supply and demand balanced. Moreover, we explain how the agent uses Non-Homogeneous Hidden Markov Model (NHHMM) to forecast energy
demand and price. An evaluation and analysis of the 2012 Power TAC finals show that AstonTAC is the only agent that can buy energy at low price in
the wholesale market and keep energy imbalance low.

Original language	English
Title of host publication	Proceedings of the twenty-third International Joint Conference on Artificial Intelligence
Publisher	AAAI
Pages	234-240
Number of pages	7
ISBN (Print)	978-1-57735-633-2
Publication status	Published - 2013
Event	23rd International Joint Conference on Artificial Intelligence - Beijing, China Duration: 3 Aug 2013 → 9 Aug 2013

Conference

Conference	23rd International Joint Conference on Artificial Intelligence
Abbreviated title	IJCAI 2013
Country/Territory	China
City	Beijing
Period	3/08/13 → 9/08/13

Access to Document

An Intelligent Broker Agent for Energy Trading: an MDP ApproachAccepted author manuscript, 539 KB

Cite this

@inproceedings{03941546f142453a9a31207cbdd2da26,

title = "An intelligent broker agent for energy trading: an MDP approach",

abstract = "This paper details the development and evaluation of AstonTAC, an energy broker that successfully participated in the 2012 Power Trading Agent Competition (Power TAC). AstonTAC buys electrical energy from the wholesale market and sells it in the retail market. The main focus of the paper is on the broker{\textquoteright}s bidding strategy in the wholesale market. In particular, it employs Markov Decision Processes (MDP) to purchase energy at low prices in a day-ahead power wholesale market, and keeps energy supply and demand balanced. Moreover, we explain how the agent uses Non-Homogeneous Hidden Markov Model (NHHMM) to forecast energy demand and price. An evaluation and analysis of the 2012 Power TAC finals show that AstonTAC is the only agent that can buy energy at low price in the wholesale market and keep energy imbalance low.",

author = "Kuate, \{Rodrigue Talla\} and Minghua He and Maria Chli and Hai Wang",

year = "2013",

language = "English",

isbn = "978-1-57735-633-2",

pages = "234--240",

booktitle = "Proceedings of the twenty-third International Joint Conference on Artificial Intelligence",

publisher = "AAAI",

address = "United States",

note = "23rd International Joint Conference on Artificial Intelligence, IJCAI 2013 ; Conference date: 03-08-2013 Through 09-08-2013",

}

TY - GEN

T1 - An intelligent broker agent for energy trading

T2 - 23rd International Joint Conference on Artificial Intelligence

AU - Kuate, Rodrigue Talla

AU - He, Minghua

AU - Chli, Maria

AU - Wang, Hai

PY - 2013

Y1 - 2013

N2 - This paper details the development and evaluation of AstonTAC, an energy broker that successfully participated in the 2012 Power Trading Agent Competition (Power TAC). AstonTAC buys electrical energy from the wholesale market and sells it in the retail market. The main focus of the paper is on the broker’s bidding strategy in the wholesale market. In particular, it employs Markov Decision Processes (MDP) to purchase energy at low prices in a day-ahead power wholesale market, and keeps energy supply and demand balanced. Moreover, we explain how the agent uses Non-Homogeneous Hidden Markov Model (NHHMM) to forecast energy demand and price. An evaluation and analysis of the 2012 Power TAC finals show that AstonTAC is the only agent that can buy energy at low price in the wholesale market and keep energy imbalance low.

AB - This paper details the development and evaluation of AstonTAC, an energy broker that successfully participated in the 2012 Power Trading Agent Competition (Power TAC). AstonTAC buys electrical energy from the wholesale market and sells it in the retail market. The main focus of the paper is on the broker’s bidding strategy in the wholesale market. In particular, it employs Markov Decision Processes (MDP) to purchase energy at low prices in a day-ahead power wholesale market, and keeps energy supply and demand balanced. Moreover, we explain how the agent uses Non-Homogeneous Hidden Markov Model (NHHMM) to forecast energy demand and price. An evaluation and analysis of the 2012 Power TAC finals show that AstonTAC is the only agent that can buy energy at low price in the wholesale market and keep energy imbalance low.

UR - https://www.scopus.com/pages/publications/84896062350

UR - http://www.aaai.org/Press/Proceedings/ijcai13.php

M3 - Conference publication

AN - SCOPUS:84896062350

SN - 978-1-57735-633-2

SP - 234

EP - 240

BT - Proceedings of the twenty-third International Joint Conference on Artificial Intelligence

PB - AAAI

Y2 - 3 August 2013 through 9 August 2013

ER -

An intelligent broker agent for energy trading: an MDP approach

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Short-term wind power forecasting using Gaussian processes

Cite this