cost-aware and energy-efficient task scheduling based on grey wolf optimizer

One of the principal challenges in the cloud is the task scheduling problem. appropriate task scheduling algorithms are needed to achieve goals such as load balancing, minimum cost, minimum energy consumption, etc. using meta-heuristic algorithms is a good way to solve scheduling problems in the cloud because scheduling is an np-hard problem. in recent years, various meta-heuristic algorithms have been introduced, one of the most popular meta-heuristic algorithms to deal with optimization problems is the grey wolf optimizer (gwo) algorithm. this paper introduces a novel gwo-based task scheduling (gwots) algorithm to map tasks over the available resources. the principal goal of this paper is to decrease execution cost, energy consumption, and makespan. the efficiency of the gwots algorithm is compared with the well-known meta-heuristic algorithms, namely genetic algorithm (ga), dragonfly algorithm (da), particle swarm optimization (pso), whale optimization algorithm (woa), ant colony optimization (aco), gravitational search algorithm (gsa), sooty tern optimization algorithm (stoa), artificial hummingbird algorithm (aha), multi-verse optimizer (mvo), and sine cosine algorithm (sca). in addition, the performance of gwots is compared with three recently scheduling algorithms, namely soats, iwc, and cetsa. experimental results show that the gwots algorithm improves performance in terms of makespan, cost, energy consumption, total execution time, resource utilization, throughput, and degree of resource load balance compared to other algorithms.