Task Allocation for Computer Service Provider by Optimal CPU Usage Consideration

Abstract

Task allocation algorithm in distributed computing system, such as cloud computing, are now critical issue. Service manager: SM has to consider which Service provider: SP is suitable to service data processing or even data storage from Service request: SR. Normally, SP has to handle its own tasks thus new allocated task should not consume more CPU’s work load status which could make SP decrease its base performance. This research objective is to invent the allocation algorithm by study status of SP’s CPU usages. The less CPU performance usages: LCU of each SP were specified. The status of each SP’s LCU should be used to represent its status which will be a criteria for making a decision by SM whether this SP is suitable to service request from SR or not. The start time and finish time of SR’s task was defined by maximized Lagrange transformation function. The experiment is presented in practical calculation. It could point out that some request of SR is more suitable sending to which SP.