Phase level energy aware map reduce scheduling for big data applications
2016 International Conference on Signal Processing, Communication, Power and Embedded System (SCOPES), 2016
The preponderance of large scale data radical applications executed by various business areas for... more The preponderance of large scale data radical applications executed by various business areas for performing data preparation and data analytics based on Map Reduce paradigm which can be better implemented on Hadoop. Such data driven applications which are executed on large clusters set up in data centers hike the energy cost which imposes burden on overall data center cost. Thus minimizing parameter that guides energy consumption becomes paramount requisite to be considered. In this paper we propose a framework for improving energy efficiency of Map Reduce applications. We propose phase level energy aware map reduce scheduling algorithms that assign map and reduce task to system on the basis of maximum node availability. We perform various extensive experiments on Hadoop cluster to determine execution time and energy consumption for several workloads from Hadoop including Terasort and K-means clustering and results evaluated that proposed algorithm consume less energy than various heuristic algorithms and minimizes execution time.
Uploads
Papers by RAJEEV PANDEY