Research On Improved Ant Colony Optimization For Task Scheduling In Cloud Computing

With the development of Internet technology,the amount of information on the Internet is explosive growth every day.Nowadays,with its high reliability,high scalability and flexible billing,cloud computing has attracted more and more attention in the efficient processing of massive information.Cloud computing is essentially a kind of distributed computing.Users can get services on demand anytime,anywhere according to their own situation.With the continuous expansion of the scale of users,the cloud platform needs to deal with more and more tasks,so the current research focuses on the design and improvement of task scheduling algorithm.Ant colony optimization(ACO)is a heuristic global optimization algorithm,which is inspired by the observation of ant foraging behavior.It is found that ants release pheromones in the process of crawling,and they can communicate with each other through pheromones.In the whole path from ant nest to food source,if one path is short,the number of ants passing through the path in unit time is more,and the concentration of pheromone on the path is higher,so it is more attractive to ants,forming a positive feedback loop,and finally all ants will choose this short path.ACO is often used to solve cloud computing task scheduling problem because of its good performance in finding the optimal path.Considering the limitations of ACO in system load balancing and task execution efficiency,this paper improves it in heuristic information calculation and pheromone update rules,introduces the virtual machine evaluation factor and pheromone correction coefficient,and proposes an Improved Ant Colony Optimization(IACO),and then it is tested on the cloud simulation platform CloudSim.Before the experiment,this paper introduces CloudSim in detail.In the process of the experiment,first configure the running environment,then determine the parameters needed in the experiment,and set other task scheduling algorithms as the control group.Experimental results show that the IACO has a good improvement in system load balancing and task execution efficiency,which proves the feasibility of the algorithm.