Task Scheduling Policy Based on Ant Colony Optimization in Cloud Computing Environment

A PSO‐based task scheduling algorithm improved using a load‐balancing technique for the cloud computing environment

“…However, solutions generated by heuristic methods are often trapped in local optima, which is not near global optima . Accordingly, meta‐heuristic algorithms, such as the genetic algorithm (GA), ant colony, and particle swarm optimization (PSO), are the best candidates for task scheduling problems, specifically when we face a diversity of requests and VMs . It has been proven that meta‐heuristic algorithms are the most effective approach to escaping the local optima .…”

“…5 Accordingly, meta-heuristic algorithms, such as the genetic algorithm (GA), ant colony, and particle swarm optimization (PSO), are the best candidates for task scheduling problems, specifically when we face a diversity of requests and VMs. [6][7][8] It has been proven that meta-heuristic algorithms are the most effective approach to escaping the local optima. 9,10 In addition, heuristic algorithms are problem-dependent techniques while meta-heuristic ones are problem-independent techniques.…”

“…In the proposed method, we considered utilization of the resources in addition to compatibility between the requested resources and the available resources of VMs. Thus, we select an underloaded VM with the best compatibility for task T k using Equation 7 where value α is set to 0.5 in this paper. We obtain the value of the angle in each execution period of our algorithm.…”

Scheduling Jobs on Cloud Computing using Firefly Algorithm

“…The author in [9] proposed a policy on task scheduling based on the concept of Ant Colony Optimization. The original ACO was designed to resolve the traveling salesman problem, by altering some aspects of the ACO to be accustomed to task scheduling problem and using simulator CloudSim.…”

Virtual Resource Allocation based on Improved Particle Swarm Optimization in Cloud Computing Environment

“…In a previous study [3], a modified particle swarm optimisation (MPSO) algorithm was applied for task scheduling in a cloud computing environment with the introduction of dynamic multi-group collaboration and a reverse of the flight of a mutation particle to coordinate the global search and local search, resulting in improved resource use. Another study proposed a resource allocation model based on ant colony optimisation that introduced the concept of entropy into the model to measure the uncertainty of the cloud resource [4]. In addition, a traditional genetic algorithm has been integrated into the task scheduling model in the cloud computing environment to improve the quality of service and the fitness function; however, it is common to encounter issues such as local optimisation [5].…”