Edge computing server placement with capacitated location allocation

The deployment of edge computing infrastructure requires a careful placement the servers, with an aim to improve application latencies and reduce data transfer load in opportunistic Internet Things systems. In server placement, it is important consider capacity, available budget, hardware requirements for servers underlying backbone network topology. this paper, we thoroughly survey existing literature identify gaps present extensive set parameters be considered. We then develop novel algorithm, called PACK, as capacitated location–allocation problem. PACK minimizes distances between their associated access points, while taking into account capacity constraints balancing enabling workload sharing servers. Moreover, considers practical issues such prioritized locations reliability. evaluate algorithm two distinct scenarios: one high general, low Fog computing. Evaluations are performed collected real-world network, consisting both dense sparse deployments points across city area. resulting related tools publicly open source software.