Presentation | 2023-10-20 Proposal of Power Consumption Model Using Decision Trees for Distributed Video Analysis System Shumpei Kawaguchi, Hideyuki Shimonishi, Daichi Kominami, Masayuki Murata, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Traditionally, data such as images and video were assumed to be aggregated and analyzed in the cloud, but there are concerns about transmission delays, increased traffic on the network, and enormous power consumption in the cloud. Recently, edge computing technology has been attracting attention and is expected to reduce the amount of data transmitted to the cloud and reduce power consumption in the network and cloud. In addition, edge computing can shorten the transmission delay and enable the cloud to perform video analysis in a shorter time, thus reducing the overall delay. For such a distributed video analysis system, we minimize power consumption by distributing analysis tasks to the computers that make up the system in an optimal ratio. In this report, we found that the acceptable error in minimizing the power consumption of the distributed video analysis system is within $10%$ in terms of the error between the power consumption model of the computers installed as the internal model and the actual measured values. Then, we constructed a more accurate power consumption model using a decision tree, and found that the RMSE and MAE of the power consumption estimation could be reduced to 17.7W and $3.6%$, respectively, and the target acceptable error of $10%$ could be achieved. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | genetic algorithm / edge computing / cloud computing / power consumption minimization method |
Paper # | IN2023-37 |
Date of Issue | 2023-10-12 (IN) |
Conference Information | |
Committee | IN / ICTSSL / IEE-SMF |
---|---|
Conference Date | 2023/10/19(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Fukuoka University |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Kunio Hato(NTT) / Osamu Uchida(Tokai Univ.) / 石田 隆張(明星大学) |
Vice Chair | Tsutomu Murase(Nagoya Univ.) / Munenari Inoguchi(Toyama Univ.) / Akira Otsuka(Graduate Institute for Entrepreneurial Studies) |
Secretary | Tsutomu Murase(NTT) / Munenari Inoguchi(NTT) / Akira Otsuka(KDDI Research) / (Fukuoka Univ.) |
Assistant | / Makoto Kobayashi(Hiroshima City Univ.) |
Paper Information | |
Registration To | Technical Committee on Information Networks / Technical Committee on Information and Communication Technologies for Safe and Secure Life / Technical Committee on Smart Facilities |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Proposal of Power Consumption Model Using Decision Trees for Distributed Video Analysis System |
Sub Title (in English) | |
Keyword(1) | genetic algorithm |
Keyword(2) | edge computing |
Keyword(3) | cloud computing |
Keyword(4) | power consumption minimization method |
1st Author's Name | Shumpei Kawaguchi |
1st Author's Affiliation | Osaka University(Osaka Univ.) |
2nd Author's Name | Hideyuki Shimonishi |
2nd Author's Affiliation | Osaka University(Osaka Univ.) |
3rd Author's Name | Daichi Kominami |
3rd Author's Affiliation | Osaka University(Osaka Univ.) |
4th Author's Name | Masayuki Murata |
4th Author's Affiliation | Osaka University(Osaka Univ.) |
Date | 2023-10-20 |
Paper # | IN2023-37 |
Volume (vol) | vol.123 |
Number (no) | IN-219 |
Page | pp.pp.21-26(IN), |
#Pages | 6 |
Date of Issue | 2023-10-12 (IN) |