文献类型：期刊文献

英文题名：Distributed Data Center Bandwidth Allocation for Cloud-Based Streaming

作者：Kong, Fanxin[1];Lu, Xingjian[2];Liu, Xue[3,4]

机构：[1]Univ Penn, Dept Comp & Informat Sci, Philadelphia, PA 19104 USA;[2]East China Univ Sci & Technol, Sch Informat Sci & Engn, Shanghai, Peoples R China;[3]Shanghai Jiao Tong Univ, Smart City Collaborat Innovat Ctr, Shanghai, Peoples R China;[4]McGill Univ, Sch Comp Sci, Montreal, PQ H3A 0G4, Canada

年份：2019

卷号：4

期号：2

起止页码：263

外文期刊名：IEEE TRANSACTIONS ON SUSTAINABLE COMPUTING

收录：;EI(收录号：20192407051744);WOS:【SCI-EXPANDED(收录号:WOS:000719473900012)】；

基金：The authors would like to thank the anonymous reviewers for the constructive comments. This work was partially supported by the NSF of China under grant No. 61602175. A preliminary version of this paper was published in [1].

语种：英文

外文关键词：Cloud-based streaming; dynamic streaming; data centers; energy cost; quality of experience; bandwidth allocation; distributed algorithms

摘要：Cloud-based video streaming systems such as YouTube and Netflix are usually supported by the content delivery networks and data centers that can consume many megawatts of power. Most existing work independently studies the issues of improving quality of experience (QoE) for viewers and reducing the cost and emissions associated with the enormous energy usage of data centers. By contrast, this paper addresses them both, and jointly optimizes the QoE, the energy cost and emissions by intelligently allocating data center bandwidth among different client groups. Specially, we propose a distributed algorithm to achieve the optimal bandwidth allocation, given the prediction of future workload. The algorithm novelly decomposes the optimization process into separate ones, which are solved iteratively across data centers and clients. Further, the algorithm has robust performance guarantee in terms of the variance of the prediction error. We demonstrate its convergence and robustness by both proofs using theoretical analysis and validation based on trace-driven simulations. The results further show that the proposed algorithm converges very fast and achieves much better QoE-cost balance than existing approaches.