Cooperative grid jobs scheduling with multi-objective genetic algorithm

Job scheduling on computational grids is a key problem in large scale grid-based applications for solving complex problems. The aim is to obtain an efficient scheduler able to allocate dependable jobs originated from large scale applications on hierarchy based grid computing platforms with heterogeneous resources. In contrast to satisfying multi objectives of different levels, which is NP-hard in most formulations, a set of cooperative multi-objective genetic algorithm (MOGA) is presented. Using this scheme, the application level generates multiple local schedules based on local nodes and objectives to a schedule pool, from which the system level can assemble a set of global schedules according to global objectives. The MOGA scheduling scheme is shown to perform well on the experimental scenario, which shows its flexibility and possible application to more complex job scheduling scenarios with multiple and diverse tasks and nodes.