Hadoop File System and Fundamental Concept of Mapreduce Interior and Closure Rough Set Approximations

Abstract: The development of computing systems has always been focused on performance improvements driven by the demand of applications from consumer, scientific and business domains, but the ever increasing energy consumption of computing systems has started to limit further performance growth due to overwhelming energy consumption and carbon dioxide footprints. Hence, the goal of the computer system design has been shifted from performance improvements to power and energy efficiency. Techniques like Dynamic Voltage Frequency Scaling, VM consolidation, Server power switching and resource throttling have been made use of to make cloud computing more power aware and energy efficient [2][3][4][5][6][7]. Dynamic Voltage Frequency Scaling is a technique through which the frequency of the CPU can be dynamically adjusted to reduce energy consumption. VM consolidation is technique whereby VMs residing on different nodes (Servers) are consolidated onto a single node for effective resource utilization and power savings. Server power switching refers to the technique wherein the idle servers could be switched off. Resource throttling could also be done in various ways at the hardware or at the software level in-order to meet the performance requirements and minimize the energy consumption [3]. Algorithms for VM allocation and migration like Greedy, Knapsack, Maximum Bin Packing, Power Expand Min-Max [7] and Minimization Migrations, Highest Potential growth, Random Choice [17] have been used respectively to improve energy efficiency and minimize cost and SLA violations. We therefore review the various techniques mentioned above (and a few others) that have been proposed specifically at the data centre level with the help of virtualization technology. This paper would be concluded with the suggestions on the future research directions.

Keywords: Dynamic Voltage Frequency Scaling, Energy Efficiency, Green Cloud, Resource throttling, Server power switching, Soft scaling, VM Consolidation.