Location aware resource management in smart homes

Designing Smart Environments: A Paradigm Based on Learning and Prediction

“…A smart home environment can then act on this information by activating resources in an efficient manner (for example, by turning on the lights lying only on these routes). Our experiments [28] demonstrate that the predictive framework can save up to 70% electrical energy in a typical smart home environment. The prediction accuracy is up to 86% while only 11% of routes constitute the typical set.…”

“…The prediction also helps in optimal allocation of resources and activation of effectors in location-aware applications [11,24]. In [2], we proposed a model-independent algorithm for location prediction in wireless cellular networks, which we later adopted for indoor location tracking and predicting inhabitant's future locations [15,28]. Our approach uses symbolic representation of location information that is relative to the access infrastructure topology (e.g., sensor ids or zones through which the inhabitant passes), making the approach universal or model-independent.…”

“…While the basic LeZi-Update algorithm was used to predict only the current location from past movement patterns, this approach has also been extended in [28] to predict the likely future routes (or trajectories) of inhabitants in smart homes and also for heterogeneous environments [23]. The route prediction exploits the asymptotic equi-partition property in information theory [8], which implies the algorithm predicts a relatively small set (called typical set) of routes that the user is likely to take.…”

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

“…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. Reliable detection of intentionality to control appliance energy use indoors is a difficult problem that is the subject of ongoing research [9]. Nonetheless, Harle and Hopper [10] showed that even without such prediction, in one office building using location of occupants would have permitted energy expended on lighting and "fast-response" electrical systems to be reduced by 50%.…”

“…The concept, therefore, is to layer the GPS thermostat (GPS-Therm) capability on top of existing thermostats, so that the GPS system engages only when users are not using a more efficient setback strategy. This work is inspired by solutions for controlling appliance use in the home or office based on indoor location [9,10,24], but the proposed system does not require an extensive sensor or distributed appliance control network to be installed in the home to achieve savings. We make only the following assumptions: (1) that mobile phone adoption trends continue so that in many households everyone who travels alone will have a phone, (2) that within a few years nearly all new phones will have location-finding and Internet data transfer capabilities, and (3) that many homes will have Internet access and home wireless networks.…”