Energy Aware Scheduling of HPC Tasks in Decentralised Cloud Systems

The increased computational needs in many sectors place huge demands on cloud computing. Power consumption and resource pool capacity are two of the challenges faced by the next generation of high performance computing (HPC). This paper aims at minimising the computing-energy consumption in decentralised multi-cloud systems using Dynamic Voltage and Frequency Scaling (DVFS) when scheduling dependent HPC tasks under deadline constraints. We propose an energy-aware scheduling algorithm EAGS. To demonstrate the efficiency of our algorithm EAGS, we compare it with the Cloud min-min Scheduling (CMMS) algorithm in different experiments. The simulation results show that our algorithm can produce energy consumption lower than CMMS by an average of 63.9%.

[1]  Gabor Kecskemeti,et al.  Strategies for Increased Energy Awareness in Cloud Federations , 2014, HiPC 2014.

[2]  El-Ghazali Talbi,et al.  A Pareto-based metaheuristic for scheduling HPC applications on a geographically distributed cloud federation , 2013, Cluster Computing.

[3]  Albert Y. Zomaya,et al.  A Taxonomy and Survey of Energy-Efficient Data Centers and Cloud Computing Systems , 2010, Adv. Comput..

[4]  Sandy Irani,et al.  Algorithmic problems in power management , 2005, SIGA.

[5]  Bharadwaj Veeravalli,et al.  On the Design of Adaptive and Decentralized Load Balancing Algorithms with Load Estimation for Computational Grid Environments , 2007, IEEE Transactions on Parallel and Distributed Systems.

[6]  Debasish Ghose,et al.  ELISA: An estimated load information scheduling algorithm for distributed computing systems , 1999 .

[7]  Dejan S. Milojicic,et al.  Open Cirrus: A Global Cloud Computing Testbed , 2010, Computer.

[8]  Alan Jay Smith,et al.  Operating systems techniques for reducing processor energy consumption , 2001 .

[9]  Neven Abou Gazala.  Power management techniques for conserving energy in multiple system components , 2008 .

[10]  Jean-Marc Pierson,et al.  Cooperative Scheduling Anti-load Balancing Algorithm for Cloud: CSAAC , 2013, 2013 IEEE 5th International Conference on Cloud Computing Technology and Science.

[11]  Ricardo Bianchini,et al.  Power and energy management for server systems , 2004, Computer.

[12]  Fei Cao,et al.  Energy-Aware Workflow Job Scheduling for Green Clouds , 2013, 2013 IEEE International Conference on Green Computing and Communications and IEEE Internet of Things and IEEE Cyber, Physical and Social Computing.

[13]  Minjoong Kim,et al.  A Simple Model for Estimating Power Consumption of a Multicore Server System , 2014, MUE 2014.

[14]  Meikang Qiu,et al.  Online optimization for scheduling preemptable tasks on IaaS cloud systems , 2012, J. Parallel Distributed Comput..

[15]  Nik Bessis,et al.  Towards Inter-cloud Schedulers: A Survey of Meta-scheduling Approaches , 2011, 2011 International Conference on P2P, Parallel, Grid, Cloud and Internet Computing.

[16]  Rajkumar Buyya,et al.  Energy-Efficient Scheduling of HPC Applications in Cloud Computing Environments , 2009, ArXiv.