Using a sparse promoting method in linear programming approximations to schedule parallel jobs

Abstract

Summary In this paper, we tackle the well‐known problem of scheduling a collection of parallel jobs on a set of processors either in a cluster or in a multiprocessor computer. For the makespan objective, that is, the completion time of the last job, this problem has been shown to be NP‐hard, and several heuristics have already been proposed to minimize the execution time. In this paper, we consider both rigid and moldable jobs. Our main contribution is the introduction of a new approach to the scheduling problem, based on the recent discoveries in the field of compressed sensing. In the proposed approach, all possible positions and shapes of the jobs are encoded into a matrix, and the scheduling is performed by selecting the best columns under natural constraints. Thus, the solution to the new scheduling formulation is naturally sparse, and we may use appropriate relaxations to achieve the optimization task in the quickest possible way. Among many possible relaxation strategies, we choose to minimize the ℓp‐quasi‐norm for p∈(0,1). Minimization of the ℓp‐quasi‐norm is implemented via a successive linear programming approximation heuristic. We propose several new algorithms based on this approach, and we assess their efficiency through simulations. The experiments show that the scheme outperforms the classic Largest Task First list based algorithm for scheduling small to medium instances but needs improvements to compete on larger numbers of jobs. Copyright © 2014 John Wiley & Sons, Ltd.

Green power aware approaches for scheduling independent tasks on a multi-core machine

“…LP T (Largest Processing Time) sorts tasks by decreasing processing times. This solution fosters long tasks which are more difficult to place and usually gives good results for the makespan minimization on parallel identical machines when the number of tasks exceeds 50, as shown in [5]. SP T (Shortest Processing Time) sorts tasks by increasing processing times p i , as for flowtime minimization an increasing p i order must be preferred.…”

Scheduling Independent Tasks in Parallel under Power Constraints

“…LP T (Largest Processing Time) sorts tasks by decreasing processing times. This solution fosters long tasks which are more difficult to place and usually gives good results for the makespan minimization on parallel identical machines when the number of tasks exceeds 50, as shown in [9]. SP T (Shortest Processing Time) sorts tasks by increasing processing times p i , as for flowtime minimization an increasing p i order must be preferred.…”

Research on social network discovery algorithm in pervasive sensing environment

“…Social sensing is also known as crowd sensing. This is mainly derived from the idea of crowd sourcing, so it is known as the crowd‐sourced sensing . The crowdsourcing is a professional term to describe a new distributed computing mode, which uses the Internet to work, find creative, or solve technical problems.…”