The problem of energy consumption is topical in every sphere of human activity nowadays. This problem is especially important for IT (information technologies), where the amount of data that needs to be processed is growing every day. In this paper PCPB (Power Consumption and Performance Balance) algorithm has been proposed. It is an energy-aware scheduling algorithm which is aimed at reducing power consumption of the computer cluster without its performance reducing. The main idea of the proposed approach is to use energy model (as relation between CPU load of the node and its consumed power) for each node in the cluster and find the balance between power consumption and performance while tasks allocating. To compare PCPB with other algorithms mathematical model was developed. The efficiency of the algorithm is proved experimentally: PCPB algorithm allows increasing performance of a cluster and reducing its power consumption at the same time in comparison with widely used Round Robin algorithm.

No abstract

No abstract

No abstract

No abstract