A Survey on Hadoop MapReduce Energy Efficient techniques for Intensive Workload
Manal Alalawi, Herbert Daly · 2017
Apache Hadoop is one of the widely adopted frameworks for big data processing in several applications. MapReduce is one of the key components of this Hadoop framework that helps in executing tasks of a large cluster in parallelised and distributive manner. Despite Hadoop MapReduce being efficient in processing huge voluminous data, it requires high energy resources in order to carry out its data processing activities. The escalating energy costs of Hadoop MapReduce made contemporary organisations look for different techniques that can help in reducing the energy consumption and thereby energy costs. This resulted in the development of several strategic techniques with the main intention of changing the way data processing is done in order to minimise the energy costs. This paper intends in surveying the state-of-art energy efficient techniques that are applicable for reducing the energy consumption and energy costs of using Hadoop MapReduce framework. The comparative analysis and the evaluation of the state-of-art energy efficient techniques can help the contemporary organisations chose the best suitable technique.