<p>Multi-agent systems have been adopted to build intelligent environment in recent years. Previous work has claimed that energy efficiency and occupants’ comfort were the most important factors for evaluating the performance of a modern work environment, and multi-agent systems present a viable solution to handling the complexity of such a dynamic building environment. Experiments have been carried on to gather expertise from both building construction and agent technology society by other researchers (see references) to create such a work environment, where energy efficiency is achieved without compromising occupants’ comfort. </p> <p> While previous research has made significant advance in some aspects, most of them did not focus on providing a satisfactory system or model for learning individual preferences in a “shared environment”, which, however in our opinion, is the core issue of personalisation in intelligent buildings. This document introduces what CMIPS can provide to achieve intelligent control and personal preferences in a shared environment. </p> <p>The key objectives of this document are: <ul> <li>The design of MASBO (Multi-Agent System for Building cOntrol)</li> <li>Policy management</li> <li>Wireless sensor network interface</li> <li>Smart-card based profiling and testbed</li> </ul> </p> <p>This document is the result of a joint effort from project partners. Section 2, contributed by the School of Systems Engineering of the University of Reading (SSE), Thales Research and Technology (UK) Ltd., and Arup, is a discussion on how previous research can relate to our work in CIMPS.</p> <p>SSE leads the building control activity for D3 of CMIPS, which involves the following tasks: <ul> <li>development of agent knowledge structures (Section 3)</li> <li>development of personal profiling mechanisms (Section 3 by SSE and 6 by Arup)</li> <li>design of intelligent personalised agents (Section 3)</li> </ul> </p> <p> Thales Research and Technology (UK) Ltd. have proposed a semantic-level interface to a Wireless Sensor Network and proposed how policy-based management will interact with the multi-agent system (Section 4 and 5). ARUP contributed to the building control work through their expertise in Smartcard-based personalisation techniques (Section 6).</p>
Home
|
Introduction
|
Members
|
Resources
|
Contact Information
© Copyright
Last updated: 19 August 2007.
