CHASE: Context-Aware Heterogenous Adaptive Smart Environments Using Optimal Tracking for Resident’s Comfort

Abstract

An information-theoretic, optimal framework is developed for tracking the residents in a Context-aware Heterogenous Adaptive Smart Environments (CHASE). The framework envisions that each individual sensor-system operates fairly independently, and does not require public knowledge of individual topologies. The resident-tracking problem is formulated in terms of weighted entropy. The framework is truly universal and provides an optimal, online learning and prediction of inhabitants movement (location) profiles from the symbolic domain. Since the optimal tracking in heterogeneous smart homes is a NP-complete problem, a greedy heuristic for near-optimal tracking is proposed. The concept of Asymptotic Equipartition Property (AEP) is also explored to predict the inhabitants most likely path-segments (comprising of coverage areas of different sensor-systems) with very good accuracy. Successful prediction helps in on-demand operations of automated indoor devices along the inhabitants future paths and locations, thus providing the necessary comfort at a near-optimal cost. Simulation results on a typical smart home corroborate this high prediction success, thereby providing sufficient resident-comfort while reducing the daily energy consumption and manual operations.KeywordsMultiagent SystemSmart HomeTemperature Control SystemDaily Energy ConsumptionLocation UncertaintyThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.