Абстрактный

Truthful Dynamic Scheduling Algorithm Based on Multi objective for Multi cloud Environments

M.Geethanjali, J.Angela Jennifa Sujana T.Revathi

Job scheduling is a complex problem for large environments like Clouds.Profit maximization for the Cloud Service Provider (CSP) is a key objective in the large-scale, heterogeneous, and multi cloud environments. In these types of environments, the service providers want to increase their profit but the customers (end-users) want to minimize the costs. Therefore the goal of selfish providers contradicts with the user’s objective. So we design a new model based on multi cloud environment. In the proposed system, we try to negotiate with the different cloud service provider’s services. In the negotiation process, we consider two main criteria: the time taken for executing the job and the cost the user has to pay for the job. Considering these two main objectives for our model, we incorporate a truthful algorithm for scheduling the job with respect to task completion time and monetary cost. The truthful algorithm uses game theory for deciding the winner. The experiments conducted using randomly generated workflows and real world workflows. We discovered that the generated solutions of the proposed mechanism are effective with multi-objective optimization.