Power and performance management for parallel computations in clouds and data centers
作者：
Highlights：
• Address task scheduling in a data center as combinatorial optimization problems.
• Use level-by-level scheduling algorithms to deal with precedence constraints.
• Use a simple system partitioning and processor allocation scheme.
• Use two heuristic algorithms for scheduling independent tasks in the same level.
• Adopt a two-level energy/time/power allocation scheme.
摘要
•Address task scheduling in a data center as combinatorial optimization problems.•Use level-by-level scheduling algorithms to deal with precedence constraints.•Use a simple system partitioning and processor allocation scheme.•Use two heuristic algorithms for scheduling independent tasks in the same level.•Adopt a two-level energy/time/power allocation scheme.
论文关键词：Cloud computing,Data center,Energy-efficient scheduling,Parallel task,Performance analysis,Precedence constraint,Simulation
论文评审过程：Received 24 December 2014, Revised 27 June 2015, Accepted 1 July 2015, Available online 21 July 2015, Version of Record 27 November 2015.
论文官网地址：https://doi.org/10.1016/j.jcss.2015.07.001
