Dynamic Frequency Scaling Algorithms for Improving the CPU’s Energy Efficiency
This paper approaches the problem of improving the service center servers CPU’s energy efficiency by executing dynamic frequency scaling actions and performing tradeoffs between CPU’s computational performance and its energy consumption. Two different algorithms are designed and implemented: an immune inspired algorithm and a fuzzy logic based algorithm. The immune inspired algorithm uses the human antigen as a model to represent the server energy / performance state. Using a set of detectors the antigens are classified as self for optimal energy consumption state or non-self for non-optimal energy consumption state. For the non-self antigens a biologically inspired clonal selection approach is used to determine the actions that need to be executed to bring the server’s CPU in an optimal energy consumption state. The fuzzy logic based algorithm adaptively changes the processor performance states to the incoming workload. The algorithm also filters workload spikes because frequent p-states transition costs can outweight the benefit of adaptation.