Cyber-physical network architecture for data stream provisioning in complex ecosystems

Abstract

Intelligent fog cyber-physical social systems (iFog CPSS) is a novel smart city project that uses intrinsic processes to automate microservices such as edge-to-fog or fog-to-cloud monitoring of complex real-time activities. This article presents a dynamic cyber-physical architecture that leverages iFog layers to map location-based services (LBS) on a spine-leaf datacenter clos topology. Individual edge clusters are connected to the edge-fog layer, which communicates with iFog gateways for processing streams' requests. Use-case application of artificial intelligence (AI) in vehicular ad-hoc networks (VANETs) is introduced for data stream provisioning. In the validation study, a secure docker-based iFog CPS experiment is carried out using traffic trace files from C++ modeller. iFog spine-leaf architecture for fog-computing and cloud-computing are compared using two key metrics. For traffic workload utilization, the results show that 83.33% of the traffic workload is utilized at the Fog layer while 16.67% is consumed in the cloud layer. For latency profile, the results indicate that Fog and cloud streams had 20.31% and 77.69%, respectively. In terms of iFog VANET spine-leaf congestion control, three distinct algorithms are studied, namely the proposed linear routing algorithm (LRA), LEACH, and collection tree protocol (CTP). In each case, the resource utilization for VANET gave 34.45%, 32.18%, and 33.37%, respectively. Latency response gave 11.76%, 82.35%, and 5.89%, respectively. Also, the throughput scenario offered 19.61%, 39.22%, and 41.17%, respectively. Consequently, the iFog scenario offers satisfactory LBS provisioning for VANETs clusters.