Cooperative group provisioning with latency guarantees in multi-cloud deployments

Abstract

Given a set of datacenters and groups of application clients, well-connected datacenters can be rented as traffic proxies to reduce client latency. Rental costs must be minimized while meeting the application specific latency needs. Here, we formally define the Cooperative Group Provisioning problem and show it is NP-hard to approximate within a constant factor. We introduce a novel greedy approach and demonstrate its promise through extensive simulation using real cloud network topology measurements and realistic client churn. We find that multi-cloud deployments dramatically increase the likelihood of meeting group latency thresholds with minimal cost increase compared to single-cloud deployments.

Cascading impact of lag on Quality of Experience in cooperative multiplayer games

“…Finally, QoE objectives could be taken into account when managing lag of multiple game session using solutions such as Ensemble Routing [48]. Our recent work proposes mechanisms for resource management in widely distributed deployments that meet group QoE constraints [49]. These and other game architecture advances could effectively mitigate the impact of lagged users on group QoE in cooperative applications and potentially bridge the gap between current lag mitigation approaches and user frustration.…”

The Server Allocation Problem for Session-Based Multiplayer Cloud Gaming

“…In addition to the game servers, the rendering servers for the clients also need to be deployed in cloud gaming, which makes the problem much more challenging. There is also some work [25] focusing on exploiting well-provisioned inter-datacenter connections to reduce the communication latency from clients to servers. In contrast, the purpose of cloud gaming is to leverage the rich computing resources in the clouds for clients to play high-quality games without dedicated hardware equipped.…”