Presentation 2021-04-15
Estimation of server power consumption using machine learning
Katsumi Fujita, Eriko Iwasa, Masashi Kaneko,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) A server power consumption is one of the problem in a data center. There are virtualization and DVFS approaches to address this problem. Estimating power consumption of servers is necessary for these approaches. Previous works presented server power models for CPU and memory intensive workloads. In this paper, we focused on disk intensive workloads and built the server power model by machine learning. Our method used processor performance events as input data. This model is applicable to a server power estimation for disk intensive workload. Moreover we analyzed the feature importance and found that different server power models are needed depending on the type of workloads.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) server / power consumption / machine learning
Paper # NS2021-6
Date of Issue 2021-04-08 (NS)

Conference Information
Committee NS
Conference Date 2021/4/15(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Online
Topics (in Japanese) (See Japanese page)
Topics (in English) Traffic, Network evaluation, Performance, Resource control and management, Traffic engineering, Network reliability and resilience, Network Intelligence and AI, etc.
Chair Akihiro Nakao(Univ. of Tokyo)
Vice Chair Tetsuya Oishi(NTT)
Secretary Tetsuya Oishi(NTT)
Assistant Shinya Kawano(NTT)

Paper Information
Registration To Technical Committee on Network Systems
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Estimation of server power consumption using machine learning
Sub Title (in English) In the case of disk intensive workload
Keyword(1) server
Keyword(2) power consumption
Keyword(3) machine learning
1st Author's Name Katsumi Fujita
1st Author's Affiliation NTT(NTT)
2nd Author's Name Eriko Iwasa
2nd Author's Affiliation NTT(NTT)
3rd Author's Name Masashi Kaneko
3rd Author's Affiliation NTT(NTT)
Date 2021-04-15
Paper # NS2021-6
Volume (vol) vol.121
Number (no) NS-2
Page pp.pp.31-36(NS),
#Pages 6
Date of Issue 2021-04-08 (NS)