Exploiting user behaviour for context-aware power management

Abstract

Abstract-With more and more computing devices being deployed in buildings there has been a steady rise in buildings' electricity consumption. At the same time there is a pressing need to reduce overall building energy consumption. Pervasive computing could further exacerbate this problem but it could also provide a solution. Context information (e.g., user location) likely to be available in pervasive computing environments could enable highly effective device power management. The objective of such context-aware power management (CAPM) is to minimise the overall electricity consumption of a building while maintaining acceptable user-perceived device performance.To investigate the potential of CAPM we conducted experimental trials for two simple location-aware power management policies. Our results highlight the presence of two distinct user behaviour patterns but also show that location alone is not enough for effective power management.We therefore propose a CAPM framework that employs Bayesian Networks to support prediction of user behaviour patterns from multi-modal sensor data for effective power management. We further propose the use of acoustic data as an interesting context for predicting finer-grained user behaviour. The paper presents an initial evaluation of the resulting framework.Index Terms-Context-aware, power management, user behaviour, Bayesian Network.

Adding GPS-Control to Traditional Thermostats: An Exploration of Potential Energy Savings and Design Challenges

“…An alternative is to infer typical return-time behavior automatically from prior behavior. Inferring intentionality may be valuable for energy savings [7], but it is also prone to error. An alternative that may lead to a more predictable user experience would be to simply recognize one particular behavior -when someone has stopped traveling --and then present an easy-to-ignore prompt on the phone.…”

“…Harris et al [7], for example, argue that context-aware power management (CAPM) could use multi-modal sensor data to optimally control the standby states of home devices to optimize energy use, reducing so-called vampire power consumption [8]. They conclude that to optimally save energy, in addition to predicting what someone is currently doing, a system should predict what someone is about to do.…”

A Review of Smart House Analysis Methods for Assisting Older People Living Alone

“…Harris and Cahill [112] implemented a context-aware power management (CAPM) framework. CAPM effective power management relied on Bayesian networks that collected data from multi-modal sensors and then predicted the person's behavioural patterns.…”

An Empirical Study of the Potential for Context-Aware Power Management

“…Our previous work [5] evaluates the use of location as a key piece of context for CAPM of desktop PCs in an oce environment. A simple location-aware policy was implemented that uses location context derived from detecting the user's Bluetooth-enabled mobile phone.…”

“…We dened the population of the study to be all workers in an oce environment that use a desktop PC. Our previous work [5] shows that the performance of the location-aware SWOB policy depends primarily on whether the user is LightUse or HeavyUse. A random sample of twenty users from the academic, administrative, technical and postgraduate sta and also oce users from outside the college were selected for the trial.…”