FAILURE-RELATED ENERGY WASTE IN WIDE-RANGE CLOUD ENVIRONMENT
Journal Title: International Journal of Engineering Sciences & Research Technology - Year 0, Vol 4, Issue 8
Abstract
Cloud computing providers are under great pressure to reduce operational costs through improved energy utilization while provisioning dependable service to clients; it is therefore extremely important to understand and enumerate the explicit impact of failures within a system in terms of energy costs. This paper presents the first inclusive analysis of the impact of failures on energy consumption in a real-world large-scale cloud system (comprising over 12,500 servers), including the study of failure and energy trends of the spatial and temporal environmental characteristics. Our results show that 88% of task failure events occur in lower priority tasks producing 13% of total energy waste, and 1% of failure events occur in higher priority tasks due to server failures producing 8% of total energy waste. These results highlight an unintuitive but significant impact on energy consumption due to failures, providing a strong foundation for research into dependable energy-aware cloud computing.
Authors and Affiliations
Pruthvin. R*
Keywords
Related Articles
- EP ID EP163812
- DOI -
- Views 62
- Downloads 0
Analysis and Design of Different Flip Flops, Extensions of Conventional JK-Flip Flops
The analysis and design of a 100% and 87.5% high-performance and efficient memory element (Flip-Flop) capable of being selected for the purpose of reading from and writing into it, is of crucial importance in mode...
CASTOR SEED BIO -TRANSFORMER OIL AS AN ALTERNATIVE TO CONVENTIONAL TRANSFORMER OIL
In search of solution to the harmful ecological problems due to toxicity and non-biodegradability posed by conventional transformer insulation oil (mineral oil), the production of transformer oil from castor s...
DETECTION OF COMPUTER VIRUSES USING WELM_ABC
Computer viruses are big threat for our society .The expansion of various new viruses of varying forms make the prevention quite tuff. Here we proposed WELM_ABC to detect computer viruses. The proposed method efficient...
Evaluation and Performance Analysis of Machine Learning Algorithms
Prediction is widely researched area in data mining domain due to its applications. There are many traditional quantitative forecasting techniques, such as ARIMA, exponential smoothing, etc. which achieved higher succe...
A FRAMEWORK FOR COMMUNITY IDENTIFICATION IN DYNAMIC SOCIAL NETWORKS
A unified framework is provided for tracking the evolution of hierarchical and overlapping communities in dynamic online social networks. HOCTracker is used for tracking such communities. HOCTracker adapts a preli...