Task Allocation Model Based on Hierarchical Clustering and Impact of Different Distance Measures on the Performance

Abstract

This article observed a new strategy to the problem of tasks clustering and allocation for very large distributed real-time problems, in which software is consolidated hierarchically and hardware potentially spans various shared or dedicated links. Here, execution and communication times have been considered as a number. Existing strategies for tasks clustering and allocation are based on either executability or communication. This study's analytical model is a recurrence conjuration of two stages: formation of clusters and clusters allocation. A modified hierarchical clustering (MHC) algorithm is derived to cluster high communicated tasks and also an algorithm is developed for proper allocation of task clusters onto suitable processors in order to achieve optimal fuzzy response time and fuzzy system. Yang's and Hamming's distances are taken to demonstrate the impact of distance measures on the performance of the proposed model.

Hybrid technique for optimal task scheduling in cloud computing environments

“…Hybrid weighted ant colony optimisation (HWACOA) optimizes job scheduling and minimizes cloud computing costs [27]. Kumar and Tyagi [28] distances assign task clusters to processors to demonstrate fuzzy system performance and optimal response time. Two hybrid genetic algorithms (HGAs) improve GA convergence, system cost, response time, and distributed real-time system reliability via new encoding, population initialization, and genetic operations [29] convergence rate of the proposed PSO-based strategy for solving a distributed computing system assignment problem [30].…”

“…Lower the makespan and cost of cloud computing while optimizing performance. Kumar and Tyagi [28] (2020)…”