Distributed resource management for QoS-aware service provision

Provision of quality of service (QoS) is of significant importance to service providers, where QoS is a function of resource availability. When resources are insufficient at a particular service provider, two approaches to mitigating this problem can be considered by that service provider (a) limit the amount of resources allocated to its users, and (b) cooperate with other resource holders and find a reasonable way to share resources. For instance, a private cloud could reject its customers’ requests or forward some requests to a public cloud (e.g., Amazon) to achieve satisfactory QoS. To this end, in addition to designing resource allocation approaches, service providers should also consider how to maximize their utilities when cooperating with other resource holders. ❧ Motivated by cooperation among resource holders and related resource allocation problems, in this thesis, we focus on several services and study how to allocate resources efficiently while maximizing all participants’ benefits: For P2P video streaming, where the resource is the download rate for video playback, we eliminate the problem of playback pauses by adopting reduced advertisement viewing duration as a positive incentive for peers to contribute their unused download rates. For provision of on-demand compute capacity in the cloud service, where virtual machines are the main resources, we study the incentives motivating small-scale clouds to share their virtual machines in a cooperative manner in order to achieve profitable service while maintaining customer service-level agreements. For co-locating machine learning training jobs, where the resource is the CPU core or GPU, we investigate the throughput improvement of a distributed training job when optimizing its resource allocation by integrating our throughput estimation technique with scheduling mechanisms.