Y.-w. Park, K. Casey, and S. Baskiyar (USA)
Dynamic scheduling, support vector machine, adaptive scheduling, heterogeneous computing, distributed computing
In this paper, we propose a novel instance based Support Vector based machine learning approach to task scheduling in heterogeneous computational grids. The system is composed of two components: a Support Vector Machine (SVM) scheduler and a dynamic learner. The scheduler is a multiclass SVM which maps any task to a machine based on the current load on the machines and the queue of tasks waiting to be dispatched. To support dynamic adaptation of the scheduler, we have designed a dynamic learning system which incorporates new knowledge into the scheduler. It allows the scheduler to update the training set and adapt to changing conditions. As newer and better scheduling strategies are discovered, they are incorporated into the training set and thereby used for scheduling tasks in the future. We demonstrate that our SVM scheduler has comparable performance to conventional task scheduling heuristics. Our approach allows for dynamic and adaptive behavior of the system. For grid based systems, where the pattern of tasks is unpredictable, such a technique may be superior to specific heuristic methods and fulfill a much needed instance based learner approach.
Important Links:
Go Back
