Edge computing server placement with capacitated location allocation

The deployment of edge computing infrastructure requires a careful placement of the edge servers. The aim is to improve application latencies and reduce data transfer load in the opportunistic Internet of Things systems. Practical limitations are faced in the available deployment budget, capacity and hardware requirements of the edge servers and the underlying backbone network topology. In this paper, we survey the existing literature in edge server placement and identify gaps and an extensive set of parameters to be considered. Then, we develop a novel algorithm, called PACK, for server placement as a capacitated location-allocation problem. PACK minimizes the distances between servers and their associated access points, while taking into account capacity constraints for load balancing and enabling workload sharing between servers. Moreover, PACK allows consideration of practical issues, including prioritized locations and reliability concerns. The algorithm is evaluated in two distinct scenarios, with high capacity servers for edge computing in general and low capacity servers for Fog computing. In the evaluation, we utilize a data set collected in a real-world network, consisting of both dense and sparse deployments of access points across a city area. Lastly, PACK is published as an open source software.