Job batch generation and scheduling in distributed computing environments

The paper considers approaches to ranked jobs system generation in the model of cyclic scheduling in the virtual organizations of distributed computing environments. Two different methodologies of job selection for scheduling are proposed and compared: the first one is based on the solution of knapsack problem, the second one utilizes a heuristic "compatibility" indicator of jobs and computing domains. Experimental results that allow estimating of the proposed solutions efficiency are presented, the solutions are compared to random job selection.