Safety and feasibility of a cloud-based architecture for multi-vehicle system

Abstract

Cloud computing is widely adopted in industry sectors of finance, energy and transportation. Public cloud service providers are able to consistently deliver solutions that meet demanding needs of security, availability, scalability of mission-critical applications. The low cost of compute and storage, combined with expanding coverage of high speed cellular networks, have enabled a wide expansion of telemetry services and consumer applications in automobiles, but safety applications are not leveraging these benefits. The majority of traffic fatalities happens in high-speed multi-vehicle crashes. Causal analysis of multi-vehicle crashes reveal process model inconsistencies that lead the drivers to make wrong assumptions about vehicle capabilities and lead-vehicle separation distances during adverse road conditions. The Spot Weather Impact Warning (SWIW) is a connected vehicle application concept proposed by the US Department of Transportation (DOT) that alerts drivers to unsafe conditions at specific points on the downstream roadway as a result of weather-related impacts. The application is designed to warn drivers about inclement weather conditions that may impact travel conditions using real-time weather information that is collected from roadway infrastructure and vehicle based probe data. The information is processed to determine the nature of the alert or warning to be delivered and then communicated to connected vehicles. The effectiveness of SWIW connected vehicle application depends on the probe coverage and the speed that probe data can be collected, analyzed, and broadcasted to relevant vehicles and roadway signage. To reach a sufficient coverage without high investment in new infrastructure, SWIW applications can be architected to use existing mobile operators and cloud service providers. A deeper Systems Theoretic Process Analysis of the application reveals that varying levels of vehicle-to-cloud communication performance may lead to process model inconsistencies for drivers, resulting in unsafe control actions from driver that ignore warnings and lead to accidents. To validate the vehicle to cloud communication performance, the SWIW application prototype is built using existing cloud service and vehicle platform. The performance of the application is validated across all tier-one cloud and mobile service providers in 10,000 miles of US roadways. The test results reveal the presence of low latency corridors in the US that may support the initial deployment of low latency solution. String stability model showed that significant reduction in probability of accidents is possible even at low penetration rates of the solution. The solution's operational cost analysis also concludes that a limited deployment on commercial vehicles has the potential of saving high value corridors such as the 402-mile Wyoming I-80 corridor as much as $1.5 million per day of socio-economic losses in accidents with an operational cost of $763 per day. This thesis concludes that connected vehicle programs that are addressing multi-vehicle accidents in low latency corridors should consider commercial fleet deployments that use mobile and public cloud service providers to quickly reach minimal penetration rate and socio-economic benefits.