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.

Detection of Man-in-the-Middle (MitM) Cyber-Attacks in Oil and Gas Process Control Networks Using Machine Learning Algorithms

“…Melnick [19] explained the different forms of MitM which include session hijacking, IP spoofing, and replay attack in which any of the attack forms will lead to the attacker taking over the communication between the sensors and the controllers with the intention of disrupting the process control [32]. In [33], the authors explained that fairness, data trustworthiness, reliability, and availability are necessary for the actualization of cyberphysical systems, for example, smart cities with robust system architecture for secured high bandwidth systems and low-latency diffusion [33], whereas supervised machine learning is taught by example and uses labeled data to detect known attacks [34,35], unsupervised machine learning can analyze huge volumes of data to identify hidden patterns, clusters, and outliers, thereby can be very effective in detecting anomalies in datasets which include process upsets, shutdowns or faulty equipment as well as attacks [15,27,31,36,37]. Deep learning algorithms have shown great results in supervised and unsupervised machine learning applications using very large datasets, timely learning ability, produced great accuracy, and increased prediction speed with negligible false alarm rates [38][39][40].…”