CityGuard - A Watchdog for Safety-Aware Conflict Detection in Smart Cities
Abstract: Cities are deploying an increasing number of smart services independently. IoT platforms are available to integrate smart services and city devices, and thus improve city performance in the domains of transportation, emergency, environment, public safety, etc. Despite the increasing intelligence of smart services and the sophistication of platforms, the safety issues in smart cities are not addressed adequately, especially the safety issues arising from the integration of smart services. Therefore, CityGuard, a safety-aware watchdog architecture is developed. To the best of our knowledge, it is the first architecture that detects conflicts among actions of different services considering both safety and performance requirements. Before developing CityGuard, we formalize a set of typical safety and performance requirements from different domains in smart cities (e.g., transportation, emergency, and environment) using Signal Temporal Logic. Sophisticated models are used to analyze secondary effects, and detect device and environmental conflicts. We present a simulated New York city based on a smart city simulator, in which actions of smart services and their predicted effects on city states are converted into signal traces over time and monitored continuously using formal specifications. Three parts of experimental results demonstrate that CityGuard (i) identifies unsafe actions and formally specify safety requirements using temporal logic, (ii) detects and resolves two major types of conflicts, i.e., device and environmental conflicts, and (iii) improves the overall city performance.
Committee Members: John Stankovic (advisor), Alfred Weaver (chair), Kamin Whitehouse and Haiying Shen.