Gaming on the Edge: Performance Issues of Distributed Online Gaming

We study the performance of online games played over a platform that implements gaming as a service (GaaS) in a mobile network slice that hosts concatenated virtual network functions (VNFs) at the edge. The distributed gaming architecture is based on edge computing facilities, whose utilization must be carefully planned and managed, so as to satisfy the stringent performance requirements of game applications. The game manager must consider the latency between players and edge server VNFs, the capacity and load of edge servers, and the latency between edge servers used by interacting players. This calls for a careful choice about the allocation of players to edge server VNFs, aiming at extremely low latency in interactions resulting from player's commands. We develop an analytical model, which we validate with experiments in the wild, and show that, under several combinations of system parameters, deploying gaming VNFs at the edge can deliver better performance with respect to cloud gaming, in spite of the complexities arising from the distribution of gaming VNFs over edge servers. Our analytical model provides a useful tool for edge gaming systems performance prediction, thus supporting the management of GaaS applications.