Hybrid Heuristic-Based Artificial Immune System for Task Scheduling

TL;DR

This paper introduces a hybrid heuristic-based Artificial Immune System (AIS) algorithm that effectively solves task scheduling in heterogeneous systems by balancing exploration and exploitation, outperforming existing methods.

Contribution

The paper presents a novel hybrid AIS algorithm combining heuristics and SNS for improved task scheduling in heterogeneous environments.

Findings

Demonstrates the method's validity through experimental comparison.

Shows superior performance over state-of-the-art algorithms.

Achieves better scheduling efficiency and solution quality.

Abstract

Task scheduling problem in heterogeneous systems is the process of allocating tasks of an application to heterogeneous processors interconnected by high-speed networks, so that minimizing the finishing time of application as much as possible. Tasks are processing units of application and have precedenceconstrained, communication and also, are presented by Directed Acyclic Graphs (DAGs). Evolutionary algorithms are well suited for solving task scheduling problem in heterogeneous environment. In this paper, we propose a hybrid heuristic-based Artificial Immune System (AIS) algorithm for solving the scheduling problem. In this regard, AIS with some heuristics and Single Neighbourhood Search (SNS) technique are hybridized. Clonning and immune-remove operators of AIS provide diversity, while heuristics and SNS provide convergence of algorithm into good solutions, that is balancing between exploration and exploitation. We have compared our method with some state-of-the art algorithms. The results of the experiments show the validity and efficiency of our method.