Mon, Sep 11, 2017 @ 01:00 PM - 03:00 PM
Thomas Lord Department of Computer Science
PhD Candidate: Sung-Han Lin
Committee: Leana Golubchik (Chair), Fei Sha and Konstantinos Psounis
Title: Distributed Resource Management for QoS-Aware Service Provision
Time: September 11 (Monday) 1:00-3:00pm
Location: SAL 322
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 are for that service provider to (a) limit the amount of resources allocated to its users, and (b) cooperate with other resource holders and find a reasonable way to share those resources. For instance, a private cloud could can reject its customers\' requests or forward some requests to public clouds (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 document, we focus on several services and study how to allocate resources efficiently while maximizing all participants-benefit: 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 the resources are virtual machines (VMs), we study the incentives motivating the small-scale clouds to share their resources in some cooperative manner in order to achieve profitable service while maintaining customer SLAs. 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 via studying the trade-off of using more resources, and integrate the throughput estimation technique into the scheduling mechanisms for better sharing the limited computing resources.
Audiences: Everyone Is Invited
Contact: Lizsl De Leon