Multi-Network Provisioning for Perpetual Operations in IoT-Enabled Smart Spaces

Abstract

The IoT revolution has enabled perpetual continuous monitoring of spaces, people and events. Data thus generated can be used to create knowledge for diverse ubiquitous services. Today, IoT platforms are key technology substrate for smart homes/buildings that are equipped with heterogeneous devices and diverse (often multiple) network interfaces. In this paper, we address a key challenge in perpetual smartspace applications, i.e. that of energy cost associated with continuous sensing and communication. Diverse applications utilize data at different levels of quality; we exploit these quality tolerances by modeling them as “space-states” and intelligently leverage the dynamic space-states to select and provision resources (access networks, device capabilities) to reduce energy overhead while ensuring application quality. We propose efficient IoT provisioning algorithms that trigger actions and space-state shifts to drive energy-optimized sensor/network activations. To validate our approach, we derive use-cases from real-world assisted living smarthomes with multiple personal and in-situ devices and target applications such as elderly fall detection. Through detailed testbed measurements and larger simulated scenarios, we show that adaptive provisioning techniques that use state-spaces and their semantics can achieve greater than 3X reductions in energy dissipation and reduce active devices without loss of sensing accuracy.