Site menu:

Links:

News:

MyJoulo wins British Gas Connecting Homes Startup Competition and Best Paper at BuildSys 2013.

Updated:

October 2013

Research within the iDEaS project has covered the following areas:

Home Energy Management
Smart Meters and Energy Feedback
Electric Vehicle Charging
Cooperative Virtual Power Plants
Decentralised Micro-Storage
Decentralised Grid Control

See below for more details:

Home Energy Management

Domestic homes account for 25% of the UK's total CO2 emissions, and the majority of this goes toward space and water heating. We have developed an intelligent home heating agent that models and predicts heating costs and provides live feedback to the home owner.

Software demonstration of a home energy management agent.


See the related research project Intelligent Agents for Home Energy Management and the following publications for more details:

Rogers, A., Maleki, S., Ghosh, S. and Jennings, N. R. (2011) Adaptive Home Heating Control Through Gaussian Process Prediction and Mathematical Programming. In: Second International Workshop on Agent Technology for Energy Systems (ATES 2011), Taipei, Taiwan. pp. 71-78.

TOP

Smart Meters and Energy Feedback

The installation of smart meters provides a platform on which a number energy services can be built. We have developed solutions including mechanisms to allow household energy agents can provide improved predictions of energy consumption, and energy disaggregation algorithms that can provide householders with contextualised energy consumption feedback.


See the following publications for more details:

Rose, H., Rogers, A. and Gerding, E. H. (2012) A Scoring Rule-Based Mechanism for Aggregate Demand Prediction in the Smart Grid. In: The Eleventh International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2012), Valencia, Spain. (In Press)

Parson, O., Ghosh, S., Weal, M. and Rogers, A. (2011) Using Hidden Markov Models for Iterative Non-intrusive Appliance Monitoring. In: Neural Information Processing Systems workshop on Machine Learning for Sustainability, Sierra Nevada, Spain.

TOP

Electric Vehicle Charging

The rapid increase in the popularity of electric vehicles (EVs) and plug-in hybrid electric vehicles (PHEVs) is expected to place a considerable strain on the existing electricity grids, due to the high charging rates these vehicles require. In many places, the limited capacity of the local electricity distribution network will be exceeded if many such vehicles are plugged in and left to charge their batteries simultaneously. Thus, it will become increasingly important to schedule the charging of these vehicles, taking into account the vehicle owners' preferences, and the local constraints on the network. We have used tecniques from online mechanism design to address this setting and have developed allocation mechanisms that incentivises agents (representing vehicle owners) to truthfully reveal their values for getting electricity, as well as when the times their vehicle is available for charging.


See the following publications for more details:

Gerding, E., Robu, V., Stein, S., Parkes, D., Rogers, A. and Jennings, N. (2011) Online Mechanism Design for Electric Vehicle Charging. In: The Tenth International Joint Conference on Autonomous Agents and Multi-Agent Systems (AAMAS 2011), Taipei, Taiwan. pp. 811-818.

Robu, V., Stein, S., Gerding, E., Parkes, D., Rogers, A. and Jennings, N. (2011) An Online Mechanism for Multi-Speed Electric Vehicle Charging. In: Second International Conference on Auctions, Market Mechanisms and Their Applications (AMMA'11), New York, USA.

Stein, S., Gerding, E., Robu, V. and Jennings, N. (2012) A model-based online mechanism with pre-commitment and its application to electric vehicle charging. In: The Eleventh International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS 2012), Valencia, Spain. (In Press)

TOP

Cooperative Virtual Power Plants

With the increasing number of small to medium capacity renewable energy generators in the Grid, maintaining the reliability of supply becomes an important challenge. Our work has focussed on promoting the formation of cooperatives of a large number of such distributed energy resources - so that together they act as a Virtual Power Plant. We have developed pricing mechanisms and payment functions to aid in the functioning of such cooperatives.


See the following publications for more details:

Chalkiadakis, G., Robu, V., Kota, R., Rogers, A. and Jennings, N. R. (2011) Cooperatives of Distributed Energy Resources for Efficient Virtual Power Plants. In: The Tenth International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2011), Taipei, Taiwan. pp. 787-794.

TOP

Decentralised Micro-Storage

Recent developments in low-cost efficient battery solutions suggest that the use of distributed electricity storage within the grid is becoming a reality. Our work has addressed the optimisation of these devices within a single home to reduce carbon and cost, and also the coordination and stability of the grid when large numbers of such devices are widely deployed.


See the following publication for more details:

Voice, T., Vytelingum, P., Ramchurn, S., Rogers, A. and Jennings, N. (2011) Decentralised Control of Micro-Storage in the Smart Grid. In: AAAI-11: Twenty-Fifth Conference on Artificial Intelligence, San Francisco, USA. pp. 1421-1426.

Vytelingum, P., Voice, T. D., Ramchurn, S. D., Rogers, A. and Jennings, N. R. (2010) Agent-Based Micro-Storage Management for the Smart Grid. In: The Ninth International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2010), Toronto, Canada. pp. 39-46. [AAMAS 2010 Best Paper Award]

TOP

Decentralised Grid Control

With the advent of embedded generation, increased use of renewable resources and advances in energy storage technology, new challenges are arising for control and coordination in energy management. Traditional top-down approaches may not be flexible enough to deal with these future demands, and developing tools for decentralised management at the local level is of vital importance. We are developing an autonomous multi-agent system for decentralised grid management. Under which, energy resources are managed and generation devices are controlled through local interactions with other devices on the grid. Although these interactions are local, global system integrity is maintained, and resources are made use of efficiently.


See the following publication for more details:

Miller, S., Ramchurn, S. D., Rogers, A. (2012) Optimal Decentralised Dispatch of Embedded Generation in the Smart Grid. In: The Eleventh International Conference on Autonomous Agents and Multiagent Systems (AAMAS-2012), Valencia, Spain. To appear.