Genetic algorithm solution for scheduling jobs in multiprocessor environment

Abstract

Multiprocessor task scheduling is considered to be the most important and very difficult issue in High Performance Computing. Task scheduling is performed to match the resource requirement of the job with the available resources resulting in effective utilization of multiprocessor systems. In this paper, a Genetic algorithm (GA) is proposed for static, non-preemptive scheduling problem in homogeneous fully connected multiprocessor systems with the objective of minimizing the job completion time. The proposed GA is used to determine suitable priorities that lead to a sub-optimal solution. To compare the performance of proposed algorithm, Static algorithms of BNP (Bounded Number of Processors) scheduling class i.e. HLFET (Highest Level with First Estimated Time) and MCP (Modified Critical Path) are implemented. HLFET, MCP and proposed GA are tested by mapping our tasks in a directed acyclic graph (DAG). Performance analysis of HLFET, MCP and proposed GA for a given job scheduling problem proves that GA results in better sub-optimal solutions.

An Evolutionary Approach for the Hierarchical Scheduling of Safety- and Security-Critical Multicore Architectures

“…Hence, a 2 × 1D method is chosen because it lessens the dimensionality burden while allowing the solution space for cores, partitions, and tasks to be searched simultaneously. Kaur and Singh [51] provide an encoding example that is adapted to our research. We leverage the idea of chromosomal encoding that provides a processor-to-task assignment and expand it to account for task-to-partition-to-core assignment.…”

“…Wall [38] points out that genetic algorithms are well suited for the complex combinatorial nature that most scheduling problems exhibit. Genetic algorithms are used in a variety of different scheduling systems; for example, job shop scheduling systems [36][37][38][39][40][41], real-time systems [42][43][44][45], distributed and grid computing systems [15,46,47], and multiprocessor systems [48][49][50][51].…”

“…Kaur et al [51] illustrated the complexities of multiprocessor task scheduling in high-performance computing environments. The authors used a genetic algorithm for static nonpreemptive scheduling problems in an online fashion.…”

A Comprehensive Review of Evolutionary Algorithms for Multiprocessor DAG Scheduling

“…In this table, we also present how the work was published, that is, if it is a journal article ("Jour") or a conference paper ("Conf"); in this last case, the publication year refers to the publication date of the conference proceedings. [26] 2012 Conf 10 Woo et al [27] 1997 Conf 38 Panwar et al [28] 2012 Conf 11 Tsuchiya et al [29] 1998 Jour 39 Singh and Singh [30] 2012 Jour 12 Corrêa et al [31] 1999 Jour 40 Xu et al [32] 2012 Conf 13 Jezic et al [33] 1999 Conf 41 Dhingra and Gupta [34] 2013 Jour 14 Zomaya et al [35] 1999 Jour 42 Guzek et al [36] 2014 Jour 15 Liu et al [37] 2002 Conf 43 Singh and Pillai [38] 2014 Conf 16 Topcuoglu and Sevilmis [39] 2002 Conf 44 Xu et al [40] 2014 Jour 17 Zhong and Yang [41] 2003 Note that only one paper was published in 1990 [9], and, after this, two others appeared in 1994 [11,13]. Closing the collection, three papers were published in 2019 [60,62,64].…”

Task Scheduling and Idle-Time Balancing in Homogeneous Multi Processors: A Comparison between GA and SA

“…The task scheduling problem is to assign a number of jobs onto the set of available processors in such a way that precedence constraints are maintained with the objective to minimize the completion time [11]. In addition, another objective function as balancing the processors idle time is used in this paper which should be less than a predetermined value (Beta).…”