Abstract
AbstractThe need to reduce data center operational costs has necessitated siting cloud computing platforms in cold locations such as the stratosphere. The stratosphere has also been found to play an important role in understanding life origins as it hosts life forms. The use of stratosphere based computing platforms however requires the hosting of multiple server payloads (requiring high energy consumption) at a higher altitude. In addition, smaller server payloads lead to smaller sized stratospheric computing platforms (SCPs) which limit interaction with stratospheric organisms. However, these challenges are not considered when designing SCPs. Hence, there is a risk of wrongly evaluating the power usage effectiveness (PUE) associated with SCPs. In addition, there is a risk of installing and deploying large sized SCPs thereby leading to contamination and limiting research potential on studying life forms. The research being presented proposes an intelligent architecture enabling the identification, selection and use of only light weight servers aboard SCPs. The incorporation of the intelligent architecture is observed to enhance the PUE by 43.9%. In addition, the use of the intelligent architecture is noted to enhance the overall PUE by 59.6% for hosting altitudes spanning the low to mid stratosphere regions. In addition, the reduction in server weight by an amount exceeding 92% is noted by simulations to enable the realization of a PUE that is close to the ideal value of unity.
Funder
Cape Peninsula University of Technology
Publisher
Springer Science and Business Media LLC
Subject
Electrical and Electronic Engineering,Computer Science Applications
Reference25 articles.
1. Sovacool, B. K., Monyei, C. G., & Upham, P. (2022). ‘Making the internet globally sustainable: technical and policy options for improved energy management, governance, and community acceptance of Nordic datacenters. Renewable and Sustainable Energy Reviews, 154, 111793.
2. Ahmed, K. M. V., Bolton, M. H. J., & Alvarez, M. (2021). A review of data centers energy consumption and reliability modelling. IEEE Access, 9, 152536–152563.
3. Koot, M., & Wjnhoven, F. (2021). usage impact on data center electricity needs: A system dynamic forecasting model. Applied Energy, 291, 116798.
4. Siddik, M. A. B., Shehabi, A., & Marston, L. (2021). The environmental footprint of data centers in the United States. Environmental Research Letters, 16, 064017.
5. Manganelli, M., Soldati, A., Martirano, L., & Ramakrishna, S. (2021). Strategies for Improving the sustainability of data centers via energy mix. Energy Conservation and Circular Energy’, Sustainability, 13(6114), 1–24.
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献