Ant Colony Algorithm For Task Scheduling In Grid Computing Application

Grid computing is a new technology in the network utilization.Grid computing and calculating resources are used to solve some complicated calculating problems by balancing the task loading.Grid computing is a new computing-framework to meet the growing computational demands.So grid scheduling which aims at improving resource utilization and grid application performance is a key concern in grid.Currently,much research can be found about grid scheduling and some algorithms on it were proposed. Grid resources have the characters of autonomic,development and distributed.The scheduling algorithms are able to fit into these characters well.However,task scheduling in grid computing has been proved to be a NP complete problem.It can't be solved well in the polynomial.So people begin to probe the calculation method to solve the task scheduling.In the passage,the task scheduling is analyzed in detail.Several main kinds of algorithms for task scheduling on grid are introduced,which are:Genetic Algorithm, Neural Net Algorithm,Min-min,Max-min and First come first serve.Based on previous research,the major research jobs in this article are:pheromone rule was elucidated and an improved ant colony algorithm was presented.It agrees with the optimalize in big and small scale.The pheromone amending strategy adopts the method of roulette.It is quicker than the Pseudo-random Proportional rule in the big scale optimalize.At the same time, the pheromone volatilization coefficient in the way is set up to zero.The complete reserve of the pheromone gives the ants direction well.It agrees with the optimalize in small scale better.Founded on this,a algorithm for task scheduling on grid will be founded upon MATLAB toolkits,using C++ to code,referring to relative researches.It was proved by simulation experiment that ant colony algorithm is feasible in algorithm for bask scheduling on grid.The pheromone left in the best way in much more than that in traditional ways.