Task schedule optimization enables to attain high performance in both homogeneous and heterogeneous computing environments. The primary objective of task scheduling is to minimize the execution time of an application graph. However, this is an NP-complete (non-deterministic polynomial) undertaking. Additionally, task scheduling is a challenging problem due to the heterogeneity in the modern computing systems in terms of both computation and communication costs. An application can be considered as a task graph represented using Directed Acyclic Graphs (DAG). Due to the heterogeneous system, each task has different execution time on different processors. The primary concern in this problem domain is to reduce the schedule length with minimum complexity of the scheduling procedure. This work presents a couple of hybrid heuristics, based on a list and guided random search to address this concern. The proposed heuristic, i.e., Hybrid Heuristic and Genetic-based Task Scheduling Algorithm for Heterogeneous Computing (HHG) uses Genetic Algorithm and a list-based approach. This work also presents another heuristic, namely, Hybrid Task Duplication, and Genetic-based Task Scheduling Algorithm for Heterogeneous Computing (HTDG). The present work improves the quality of initial GA population by inducing two diverse guided chromosomes. The proposal is compared with four state-of-the-art methods, including two evolutionary algorithms for the same task, i.e., New Genetic Algorithm (NGA) and Enhanced Genetic Algorithm for Task Scheduling (EGA-TS), and two list-based algorithms, i.e., Heterogeneous Earliest Finish Time (HEFT), and Predict Earliest Finish Time (PEFT). Results show that the proposed solution performs better than its counterparts based on occurrences of the best result, average makespan, average schedule length ratio, average speedup, and the average running time. HTDG yields 89% better results and HHG demonstrates 56% better results in comparisons to the four state-of-the-art task scheduling algorithms.

任务计划优化可以在同构和异构计算环境中实现高性能。任务调度的主要目标是最大程度地减少应用程序图的执行时间。但是，这是一个NP完全（不确定性多项式）任务。另外，由于现代计算系统在计算和通信成本方面的异质性，任务调度是一个具有挑战性的问题。可以将应用程序视为使用有向无环图（DAG）表示的任务图。由于系统的异构性，每个任务在不同的处理器上具有不同的执行时间。该问题域中的主要关注点在于以最小的调度过程复杂度来减少调度长度。这项工作提出了两种混合启发式方法，基于列表和引导式随机搜索来解决此问题。所提出的启发式，即基于混合启发式和基于遗传的异构计算任务调度算法（HHG）使用了遗传算法和基于列表的方法。这项工作还提出了另一种启发式方法，即混合任务复制和基于遗传的异构计算任务调度算法（HTDG）。目前的工作通过诱导两个不同的指导染色体，提高了初始遗传算法种群的质量。将该提案与四种最新方法进行了比较，其中包括用于同一任务的两种进化算法，即新遗传算法（NGA）和用于任务调度的增强遗传算法（EGA-TS），以及两种基于列表的方法。算法，即异构最早完成时间（HEFT）和预测最早完成时间（PEFT）。结果表明，基于最佳结果，平均完成时间，平均计划长度比率，平均加速和平均运行时间的出现，所提出的解决方案比同类解决方案具有更好的性能。与四种最新的任务调度算法相比，HTDG的结果要好89％，HHG的结果要好56％。