Economic Based Scheduling and Load Balancing Algorithms in Cloud Computing Using Learning Automata

Abstract

Cloud computing is a distributed computing model in which access is based on demand. A cloud computing environment includes a wide variety of resource suppliers and demanders. Hence, efficient and effective methods for task scheduling and load balancing are required. This paper presents a new approach to task scheduling and load balancing in the cloud computing environment with an emphasis on the cost-efficiency of task execution through resources. The proposed algorithms are based on the fair distribution of work between machines, which will prevent the unconventional increase in the price of a machine and the unemployment of other machines. The two parameters Total Cost and Final Cost are designed with certain criteria to achieve the mentioned goal. Applying these two parameters will create a fair basis for load balancing and scheduling. To implement the proposed approach, learning automata were used as an effective and efficient technique in reinforcement learning. In this paper, the input flow of tasks was considered in batches. Finally, to show the effectiveness of the proposed algorithms we conducted simulations using CloudSim toolkit and compared proffered algorithms with other existing algorithms, like BCO, MCT, MET And KPB. Proffered methods can balanced the Final Cost and Total Cost of machines.