AgentSwitch: Towards smart energy tariff selection

Sarvapali D. Ramchurn, Michael A. Osborne, Oliver Parson, Talal Rahwan, Sasan Maleki, Steve Reece, Trung D. Huynh, Mudasser Alam, Joel E. Fischer, Tom Rodden, Luc Moreau, Stephen Roberts

Research output: Contribution to conferencePaper

Abstract

In this paper, we present AgentSwitch, a prototype agent-based platform to solve the electricity tariff selection problem. Agent-Switch incorporates novel algorithms to make predictions of hourly energy usage as well as detect (and suggest to the user) deferrable loads that could be shifted to off-peak times to maximise savings. To take advantage of group discounts from energy retailers, we develop a new scalable collective energy purchasing mechanism, based on the Shapley value, that ensures individual members of a collective (interacting through AgentSwitch) fairly share the discounts. To demonstrate the effectiveness of our algorithms we empirically evaluate them individually on real-world data (with up to 3000 homes in the UK) and show that they outperform the state of the art in their domains. Finally, to ensure individual components are accountable in providing recommendations, we provide a novel provenance-tracking service to record the flow of data in the system, and therefore provide users with a means of checking the provenance of suggestions from AgentSwitch and assess their reliability.

Original languageEnglish (US)
Pages981-988
Number of pages8
StatePublished - Jan 1 2013
Event12th International Conference on Autonomous Agents and Multiagent Systems 2013, AAMAS 2013 - Saint Paul, MN, United States
Duration: May 6 2013May 10 2013

Other

Other12th International Conference on Autonomous Agents and Multiagent Systems 2013, AAMAS 2013
CountryUnited States
CitySaint Paul, MN
Period5/6/135/10/13

Fingerprint

Purchasing
Electricity
Switches

Keywords

  • Electricity
  • Group Buying
  • Optimisation
  • Provenance
  • Recommender Systems
  • Smart Grid

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

Ramchurn, S. D., Osborne, M. A., Parson, O., Rahwan, T., Maleki, S., Reece, S., ... Roberts, S. (2013). AgentSwitch: Towards smart energy tariff selection. 981-988. Paper presented at 12th International Conference on Autonomous Agents and Multiagent Systems 2013, AAMAS 2013, Saint Paul, MN, United States.

AgentSwitch : Towards smart energy tariff selection. / Ramchurn, Sarvapali D.; Osborne, Michael A.; Parson, Oliver; Rahwan, Talal; Maleki, Sasan; Reece, Steve; Huynh, Trung D.; Alam, Mudasser; Fischer, Joel E.; Rodden, Tom; Moreau, Luc; Roberts, Stephen.

2013. 981-988 Paper presented at 12th International Conference on Autonomous Agents and Multiagent Systems 2013, AAMAS 2013, Saint Paul, MN, United States.

Research output: Contribution to conferencePaper

Ramchurn, SD, Osborne, MA, Parson, O, Rahwan, T, Maleki, S, Reece, S, Huynh, TD, Alam, M, Fischer, JE, Rodden, T, Moreau, L & Roberts, S 2013, 'AgentSwitch: Towards smart energy tariff selection' Paper presented at 12th International Conference on Autonomous Agents and Multiagent Systems 2013, AAMAS 2013, Saint Paul, MN, United States, 5/6/13 - 5/10/13, pp. 981-988.
Ramchurn SD, Osborne MA, Parson O, Rahwan T, Maleki S, Reece S et al. AgentSwitch: Towards smart energy tariff selection. 2013. Paper presented at 12th International Conference on Autonomous Agents and Multiagent Systems 2013, AAMAS 2013, Saint Paul, MN, United States.
Ramchurn, Sarvapali D. ; Osborne, Michael A. ; Parson, Oliver ; Rahwan, Talal ; Maleki, Sasan ; Reece, Steve ; Huynh, Trung D. ; Alam, Mudasser ; Fischer, Joel E. ; Rodden, Tom ; Moreau, Luc ; Roberts, Stephen. / AgentSwitch : Towards smart energy tariff selection. Paper presented at 12th International Conference on Autonomous Agents and Multiagent Systems 2013, AAMAS 2013, Saint Paul, MN, United States.8 p.
@conference{6eaabb6e977a485bb1943f27126ea726,
title = "AgentSwitch: Towards smart energy tariff selection",
abstract = "In this paper, we present AgentSwitch, a prototype agent-based platform to solve the electricity tariff selection problem. Agent-Switch incorporates novel algorithms to make predictions of hourly energy usage as well as detect (and suggest to the user) deferrable loads that could be shifted to off-peak times to maximise savings. To take advantage of group discounts from energy retailers, we develop a new scalable collective energy purchasing mechanism, based on the Shapley value, that ensures individual members of a collective (interacting through AgentSwitch) fairly share the discounts. To demonstrate the effectiveness of our algorithms we empirically evaluate them individually on real-world data (with up to 3000 homes in the UK) and show that they outperform the state of the art in their domains. Finally, to ensure individual components are accountable in providing recommendations, we provide a novel provenance-tracking service to record the flow of data in the system, and therefore provide users with a means of checking the provenance of suggestions from AgentSwitch and assess their reliability.",
keywords = "Electricity, Group Buying, Optimisation, Provenance, Recommender Systems, Smart Grid",
author = "Ramchurn, {Sarvapali D.} and Osborne, {Michael A.} and Oliver Parson and Talal Rahwan and Sasan Maleki and Steve Reece and Huynh, {Trung D.} and Mudasser Alam and Fischer, {Joel E.} and Tom Rodden and Luc Moreau and Stephen Roberts",
year = "2013",
month = "1",
day = "1",
language = "English (US)",
pages = "981--988",
note = "12th International Conference on Autonomous Agents and Multiagent Systems 2013, AAMAS 2013 ; Conference date: 06-05-2013 Through 10-05-2013",

}

TY - CONF

T1 - AgentSwitch

T2 - Towards smart energy tariff selection

AU - Ramchurn, Sarvapali D.

AU - Osborne, Michael A.

AU - Parson, Oliver

AU - Rahwan, Talal

AU - Maleki, Sasan

AU - Reece, Steve

AU - Huynh, Trung D.

AU - Alam, Mudasser

AU - Fischer, Joel E.

AU - Rodden, Tom

AU - Moreau, Luc

AU - Roberts, Stephen

PY - 2013/1/1

Y1 - 2013/1/1

N2 - In this paper, we present AgentSwitch, a prototype agent-based platform to solve the electricity tariff selection problem. Agent-Switch incorporates novel algorithms to make predictions of hourly energy usage as well as detect (and suggest to the user) deferrable loads that could be shifted to off-peak times to maximise savings. To take advantage of group discounts from energy retailers, we develop a new scalable collective energy purchasing mechanism, based on the Shapley value, that ensures individual members of a collective (interacting through AgentSwitch) fairly share the discounts. To demonstrate the effectiveness of our algorithms we empirically evaluate them individually on real-world data (with up to 3000 homes in the UK) and show that they outperform the state of the art in their domains. Finally, to ensure individual components are accountable in providing recommendations, we provide a novel provenance-tracking service to record the flow of data in the system, and therefore provide users with a means of checking the provenance of suggestions from AgentSwitch and assess their reliability.

AB - In this paper, we present AgentSwitch, a prototype agent-based platform to solve the electricity tariff selection problem. Agent-Switch incorporates novel algorithms to make predictions of hourly energy usage as well as detect (and suggest to the user) deferrable loads that could be shifted to off-peak times to maximise savings. To take advantage of group discounts from energy retailers, we develop a new scalable collective energy purchasing mechanism, based on the Shapley value, that ensures individual members of a collective (interacting through AgentSwitch) fairly share the discounts. To demonstrate the effectiveness of our algorithms we empirically evaluate them individually on real-world data (with up to 3000 homes in the UK) and show that they outperform the state of the art in their domains. Finally, to ensure individual components are accountable in providing recommendations, we provide a novel provenance-tracking service to record the flow of data in the system, and therefore provide users with a means of checking the provenance of suggestions from AgentSwitch and assess their reliability.

KW - Electricity

KW - Group Buying

KW - Optimisation

KW - Provenance

KW - Recommender Systems

KW - Smart Grid

UR - http://www.scopus.com/inward/record.url?scp=84899433158&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84899433158&partnerID=8YFLogxK

M3 - Paper

SP - 981

EP - 988

ER -