TOPSIS inspired cost-efficient concurrent workflow scheduling algorithm in cloud

Abstract

Scheduling is a decision-making mechanism that enables the sharing of resources among several activities by determining their execution order on the set of available resources. In distributed systems, it is a great challenge to schedule multiple workflows submitted at different times. In particular, concurrent workflow scheduling with time constraints makes the problem more complex in the cloud due to the dynamics of the cloud such as elasticity, non-homogeneous resource types, various pricing schemes, and virtualization. A well-managed deadline workflow scheduling is required to improve end-user satisfaction and system performance. In the meantime, the intrinsic uncertainty in the cloud increases the difficulties of scheduling problems. Therefore, it is a great challenge to improve system performance and optimize several scheduling criteria simultaneously. To address the above issues, a novel concurrent workflow scheduling method for heterogeneous distributed environments based on the new Multi-Criteria Decision Making (MCDM) method i.e., TOPSIS (Technique of Order Preference by Similarity to Ideal Solution) is presented. A weighted sum of execution time, cost and communication time are used to find out the optimal resource among the existing resources as per the workflow task requirements. The proposed method minimizes the makespan and execution cost of the workflow and improves the resource efficiency under uncertain environment. The performance of the proposed work is compared with the state-of-the-art algorithms such as Cloud-based Workflow Scheduling Algorithm (CWSA), Earliest Finish Time-Maximum Effective Reduction (EFT-MER) and Heterogeneous Earliest-Finish-Time (HEFT) algorithms based on deadline constraint and resource utilization. Our experimental results demonstrate that the proposed T-CCWSA outperforms current state-of-the-art heuristics with the criteria of achieving the deadline constraint, minimizing the cost of execution and resource efficiency.