This paper concerns guarantees on system performance through Service Level Agreement (SLA) compliance and focuses on devising energy aware resource management techniques based on Dynamic Voltage and Frequency Scaling (DVFS) used by resource management middleware in clouds that handle MapReduce jobs. This research formulates the resource management problem as an optimization problem using Constraint Programming (CP). Experimental results presented in the paper demonstrate the effectiveness of the technique.

Additional Metadata
Keywords Big data, Constraint Programming, Energy management, MapReduce with deadlines, Resource management on clouds
Persistent URL dx.doi.org/10.1145/2859889.2859892
Conference 7th ACM/SPEC International Conference on Performance Engineering, ICPE 2016
Citation
Gregory, A. (Adam), & Majumdar, S. (2016). A constraint programming based energy aware resource management middleware for clouds processing MapReduce jobs with deadlines. Presented at the 7th ACM/SPEC International Conference on Performance Engineering, ICPE 2016. doi:10.1145/2859889.2859892