JavaScript is disabled for your browser. Some features of this site may not work without it.
| dc.contributor.author | Puso, Nomsa | |
| dc.contributor.author | Sigwele, Tshiamo | |
| dc.date.accessioned | 2024-08-16T11:56:53Z | |
| dc.date.available | 2024-08-16T11:56:53Z | |
| dc.date.issued | 2023-09-18 | |
| dc.identifier.citation | Puso M. and Sigwele T. (2023) Energy efficiency for cloud data centers using machine learning in Botswana. In Jamisola, Rodrigo S. Jr (ed.) Proceedings of BIUST Teaching, Research, and Innovation Symposium (TRDAIS),18-19 September 2023, Palapye, Botswana International University of Science and Technology, 28-33. | en_US |
| dc.identifier.issn | 2521-2293 | |
| dc.identifier.uri | https://repository.biust.ac.bw/handle/123456789/593 | |
| dc.description.abstract | Botswana is adopting cloud computing technology, and in the future, it will be dominated by more cloud data centers that will require more power supply from the grid. Botswana Fibre Networks (BoFinet) has planned to build the biggest cloud data center in the capital city with at least 400 racks, requiring more than 8MW from the power grid. Botswana government services will be hosted in this data center as virtual machines. Currently, Botswana’s power supply is less than the demand, leading to power blackouts that have disrupted the subscribers like industrial and healthcare. These power blackouts have negatively impacted the economy of the country. More cloud data centers in Botswana will draw more electricity from the grid, which will cause more power blackouts unless sustainable sources like solar power are used. However, solar power adoption is shallow despite Botswana’s high ultraviolet (UV) index of 9, indicating sufficient sunlight. There is a need for sustainable energy-efficient methods in cloud data centers. This paper proposes the most suitable machine learning approach to minimize energy consumption in cloud data centers which is applicable to Botswana. The proposed framework involves virtual machine placement optimization and shutting down low utilization data center servers to save energy while maintaining the quality of service (QoS). Machine Learning is a cutting-edge Industry 5.0 technology that can be applied to optimization for more accurate outcome predictions without being explicitly programmed to do so. The proposed framework will significantly reduce energy consumption and greenhouse gas emissions. | en_US |
| dc.description.sponsorship | Department of Computer Science and Information Systems, Botswana International University of Science and Technology (BIUST) | en_US |
| dc.language.iso | en | en_US |
| dc.publisher | Botswana International University of Science and Technology | en_US |
| dc.subject | Energy Efficiency | en_US |
| dc.subject | Cloud computing | en_US |
| dc.subject | Cloud data centers | en_US |
| dc.subject | Virtual machine | en_US |
| dc.subject | Quality of service (QoS) | en_US |
| dc.subject | Machine Learning | en_US |
| dc.title | Energy efficiency for cloud data centers using machine learning in Botswana | en_US |
| dc.description.level | phd | en_US |
| dc.description.accessibility | unrestricted | en_US |
| dc.description.department | cis | en_US |
Files in this item
This item appears in the following Collection(s)
-
BIUST Teaching, Research, and Innovation Symposium (TRDAIS)
The collection is made up of BIUST Teaching, Research, and Innovation Symposium (TRDAIS) paper presentations.).