Energy aware management framework for HPC systems

High Performance Computing (HPC) Systems provide access to high end resources for parallel jobs execution. Resource monitoring and management are the most important aspects of providing a successful HPC environment. Improving performance, reducing energy consumption and operating costs for HPC environment is crucial. There can be different management strategies to manage HPC resources like energy, performance and operating cost based on the overall system's state, the nature of the workload queued and the administrator's choice. As per the current research trends, there is a need to put all these strategies under one umbrella. This paper presents a design of an energy aware framework which bundles all these strategies to autonomically identifying the best suitable resource management strategy. This framework works with the help of multiple intelligent agents and also uses the past knowledge of the application behavior to decide the strategy. We have explained how this framework intends to reduce the energy consumption and operating cost of HPC Systems by selecting the proposed energy management strategy.