Distributed service placement in hierarchical fog environments*

The fog computing paradigm emerged as a promising solution to realize deployment of large-scale Internet of Things (IoT) environments and low latency real-time services. It leverages a large number of resource constrained, heterogeneous compute nodes distributed across vast geographical areas and located closer to users and data sources, as compared to the cloud which is usually located at large data centers, far from users and IoT devices. In an infrastructure environment with the interplay of cloud and fog nodes, there is a need for efficient placement of services to satisfy resource requirements as well as improve various factors such as node utilization, network utilization, computation cost, communication cost, energy consumption, response time, availability, and load balancing. In this paper, we propose a scalable, low-overhead, fully distributed approach to select a cost-efficient fog node, considering both computation and communication costs, from the set of prospective fog nodes to host the given application service. We have implemented the solution in a simulation environment and compared its performance with several approaches along with a centralized approach. (c) 2022 Elsevier Science. All rights reserved.