Investigation on Occupancy Detection Techniques for Internet of Things Enabled Home Energy Management System

Abstract

Buildings have become a major source of electricity related greenhouse gas emissions owing to the rising energy requirements for space heating and cooling, lighting and plug loads. Residential electricity utilization constitutes more than a quarter of the global electricity consumption. An important step in reducing the energy consumption in buildings, including residential spaces, is the design of efficient building energy management systems. Smart scheduling of domestic appliances based on user demand is an important aspect of any home energy management system. Such a demand driven operation can be performed by accurately detecting the presence, activities and location of users at their residence. Internet of things (IoT) and other enabling technologies can transform a smart home into an energy aware entity by judicious utilization of the data available from various sensors present in a smart home. This includes data from wireless devices, smartphone inertial units, smart meters and environmental sensors. The pervasiveness of WiFi access points in urban buildings render it as a preferred candidate for occupant activity and location monitoring. Design of device-free sensing techniques by passive sensing of WiFi received signal strength indicator (RSSI) and channel state information (CSI) signals, extracted from commercially available WiFi devices, can offer an affordable solution with minimum disturbance to the inhabitants and is adopted in this thesis for occupancy driven building energy management.