Maximal Profit Service Task Partition and Allocation in Computer Grid Considering Service Reliability and Security
The paper considers grid computing systems in which the Resource Management Systems (RMS) divides a service tasks into Execution Blocks (EBs) and sends these blocks to different available resources. The service cost comprises the task execution cost, communication cost and security measures cost and depends on the resources assigned to execute the EBs. The service price is determined according to a fixed tariff. The pricing approach is considered: price based on service time and penalties for service reliability and security failures price depending on service and expected security level. The optimal task partition and distribution should maximize the provider's profit, which is equal to the difference between the service price and its cost for the provider.