Intelligent Energy Control of Households based on People Movement Indoors
Location aware computing has become an important area in the field of telecommunications due to the large increase in the number of mobile communications devices. A need has arisen to calculate the position of these devices in all environments. One such system developed at the University of Ulster can probabilistically learns the movement patterns of a person and uses this knowledge to intelligently predict where the person will go. The system models human movement patterns by applying a discrete Bayesian filter to predict the areas that will, or will not, be visited in the future.
A potential useful area to extend the existing system is in control systems, specifically those that are dependent on the movement of people. Lighting and Heating, Ventilation and Air Conditioning (HVAC) account for approximately 60% of a buildings energy costs [1]. Knowledge of where people will travel within a building and when, also gives information regarding where they are not likely to go. This knowledge could be used as input to an intelligent control system for heating and lighting in a large building. In the short term, if a system knew what room or area a person would travel to next, then the lights could already be on or in some standby mode to facilitate quick power up. This way they would not have to stay on standby continuously. Areas which were infrequently travelled could be put into low energy mode or switched off completely, thereby saving energy consumption costs.
With heating systems, a similar but longer term approach could be applied. If the automatically controlled heating system knew that at a certain time of day, e.g. lunch, many people stood in the canteen or corridor then the heat could be adjusted up or down depending on the outside temperature and number of people. Conversely, if the system knew areas were people rarely travelled, then the heating could be turned off and would not be wasted while the area was vacant. While various sensors can currently control this, they only work when activated, i.e. when someone walks past them. A system based on existing work could control the system in advance and could learn when the movement patterns changed.
Brief Methodology
(1) Carry out a literature review in the areas of control systems and location determination indoors
(2) Embark on requirements analysis to determine the current key factors that influence streaming media over wireless networks
(3) Specify a framework which accommodates the efficient control of heating and lighting systems
(4) Once the framework has been developed and refined, evaluation will take place to ensure the improvements of new framework over existing techniques.
The anticipated outcomes relate to the development of a localisation framework to assist in efficient management of heating and lighting systems for intelligent energy control.
References
[1] Bolick, J. (2010). AutomatedBuilding.com Article: A Wireless Solution For Energy Control In Existing Buildings http://www.automatedbuildings.com/news/apr10/arcles/adura/100329095808adura.htm
Personnel Involved
First Supervisor: Curran, K Dr
Second Supervisor: Santos, J Dr
Collaboration: This project does not involve collaboration with another establishment