Abstract
High Performance Computing Clusters (HPCCs) are common platforms for solving both up-to-date challenges and high-dimensional problems faced by IT service providers. Nonetheless, the use of HPCCs carries a substantial and growing economic and environmental impact, owing to the large amount of energy they need to operate. In this paper, a two-stage holistic optimisation mechanism is proposed to manage HPCCs in an eco-efficiently manner. The first stage logically optimises the resources of the HPCC through reactive and proactive strategies, while the second stage optimises hardware allocation by leveraging a genetic fuzzy system tailored to the underlying equipment. The model finds optimal trade-offs among quality of service, direct/indirect operating costs, and environmental impact, through multiobjective evolutionary algorithms meeting the preferences of the administrator. Experimentation was done using both actual workloads from the Scientific Modelling Cluster of the University of Oviedo and synthetically-generated workloads, showing statistical evidence supporting the adoption of the new mechanism.
Highlights
High Performance Computing Clusters (HPCCs) are the core infrastructure of modern supercomputers (see Top500 and The Green500), given both the availability of tools for distributed and parallel computing, and the performance/price ratio of modern commodity microprocessors [1]
There are substantial environmental-related impacts such as the greenhouse gases emitted over the HPCC’s entire life cycle: from the carbon footprint of the manufacturing process to that associated with the generation of the large amount of electricity consumed during operation
We introduce a novel mechanism to optimise hardware allocation, implemented by means of a genetic fuzzy system tailored to the underlying equipment of the HPCC, explicitly accounting for its power efficiency and reliability
Summary
High Performance Computing Clusters (HPCCs) are the core infrastructure of modern supercomputers (see Top500 (http://www.top500.org/) and The Green500 This work, focuses on adaptive resource clusters, a method that consists of automatically reshaping the cluster resources to fit the current demand by powering on or off its compute nodes, saving energy whenever these are underused This method has already been applied to load-balancing clusters [13,14,15,16,17,18], in virtual data centres running VMware vSphere Http://www.citrix.com/products/xenserver/overview.html hypervisors, and in HPC clusters [19,20,21,22] These proposals only target the high operating costs and carbon footprints of HPCCs as consequence of their high power consumptions, and do not address the life cycle-related effects.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
