Cloud Resource Management to Improve Energy Efficiency Based on Local Nodes Optimizations

Abstract The energy consumption of Cloud Computing systems is one of the current concerns of systems architects. In order to reduce the energy consumption, they have provided techniques which go through the design of locations for data centres, together with techniques for the proper management of resources, taking into account the energy consumption of the system. This paper presents a resource allocation technique that maximizes the system efficiency. This technique is based on taking decisions at two levels: physical machine level and overall system level. Each of the levels ensure its own proper performance. To test that the technique complies with the initial hypothesis, simulations through the CloudSim tool have been developed. Also, we compared the results with a resource allocation technique based on a full knowledge of the system. As a result, we obtained a better solution time with the proposed technique that the other technique. Moreover, we obtained a lesser use of intra cluster network and a more energetically efficient cloud system.