DANCER

Title: DANCER – Digital Agent Networking for Customer Energy Reduction

PI: Prof. Riccardo Russo University of Essex

Fund: £1.65m BuildTEDDI

Project lifespan: Aug 2012 to Aug 2016

Contact: rrusso@essex.ac.uk

Website: www.dancer-project.co.uk


Aims:

The DANCER project will develop and test the extent to which a wireless sensor network augmented with Ultra Wideband (UWB) localisation technology and a decision-making agent can ‘invisibly’ reduce energy use in the home.

Methodology:

The wireless sensor networks will employ novel sensing and communication mechanisms that will monitor users’ movements and the energy use of a range of appliances. These data, together with information collected either directly from end users via their smart phone application (e.g. indications to reduce energy use by 10%) or inferred indirectly from user habits, will be fed into a decision making agent LESDMA) that will decide when to switch on/off certain appliances and for how long. The agent’s goal will be to substantially reduce energy use a) with minimal user input and b) with minimal impact to the user’s comfort and habits.

The system will be piloted in a small number of dwellings and then tested in a matched intervention-control style trial over an extended period of time to assess the effectiveness of the system in reducing energy use ‘in the background’.


Academic partners:

University of Essex

Prof Riccardo Russo

Prof Kun Yang

London South Bank University

Dr Sandra Dudley

Dr Alan Dunn

Prof Mohammad Ghavami

University of Southampton

Dr Ben Anderson

Commercial partners:

Croydon Council

British Gas


Key Outputs:

Buchana, K., Russo, R., & Anderson B. (in press) Feeding back about eco-feedback: How do consumers use and respond to energy monitors? Energy Policy http://dx.doi.org/10.1016/j.enpol.2014.05.008

C. Koch, N. Islam, O. Onalaja, M. Adjrad and S. Dudley (2013). Cloud-based M2M Platforms to Promote Individualised Home Energy Management Systems. Presented at the 4th International Conference on Smart Communications in Network Technologies (SaCoNeT 2013 – IEEE conf.), Paris, France, June 2013.

Zhang J., Yang K., et al. (2013). A Self-Adaptive Regression Based Multivariate Data Compression Scheme with Error Bound in Wireless Sensor Networks. International Journal of Distributed Sensor Networks, Article ID 913497, 12 pages, http://dx.doi.org/10.1155/2013/913497