Integrated computational and network QOS in grid computing

Abstract

In this thesis, we look into a method for providing QoS through learning and autonomic methods. The learning methodology we use is known as Reinforcement Learning (RL). An autonomous method is one in which no manual intervention is required, and the aim in this thesis is to provide QoS in such a manner. RL based systems will help achieve this, since they are model free, and require no supervision to learn. An autonomous system will not require constant monitoring, and if well designed, will be able to maximize the utility of the grid.We explore two RL methods, known as Watkinsa?? Q(I>) and Semi-Markovian Average Reward Technique (SMART), to perform resource allocation on computing and network resources. We also explore two alternatives to resource allocation, provisioning and reservation. Our proposed solution was tested in simulation on a grid simulation software called GridSim, and also implemented and tested on a testbed.