Multi-Objective Optimization and its Application in Cloud Computing

Abstract

As an emerging technology, cloud computing which processes a huge amount of data as well as requires a large amount of resource cost and a large part of the user’s budget cost. Job arrangement is significant in cloud computing, since it openly disturbs a systems burden and enactment. An actual job scheduling technique needs not only conference the user’s wants but also improves the output of the entire system. So, scheduling mechanism works as a dynamic part in the cloud computing. Thus, my protocol is planned to minimize the switching time, increase the resources’ utilization and also increase the server performance and throughput. Here we allocate the import to the job which gives better performance to the computer and try the best to reduce the waiting and switching time. The cloud services comprise of altered functionalities at variable costs, and changeable reliability. So the customer’s main purposes are to maximize their usefulness, and decrease their costs and risks. For job scheduling problems in cloud computing, a multi objective optimization technique is required to be projected here. An effective job scheduling not only minimizes the load of the resources but also eliminates the budget cost constraints of the users completing multi objective optimization of both performance and cost. We proposed ant colony optimization algorithm here to resolve this tricky. The ant colony algorithm is a probabilistic and indeterminate world-wide optimization algorithm, so it’s easy to find an over-all optimal solution. Moreover, it does not depend on accurate optimization and organizational features of the tricky itself. Two constraints roles were used to calculate and view the utility performance and cost. Based on the feedback these two restriction functions ready the algorithm correct the scheduling to process in a timely manner.