Presentation 2018-01-18
Numerical Evaluation of Cooperative Edge System for Realtime Predictive Information Delivery
MAsahiro Kanbayashi, Shingo Kato, Ryoichi Shinkuma,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Traffic congestion is still a serious social problem in the recent years.Predictive road traffic information delivery is expected as a promising solution for the problem.When machine learning is used to predict road traffic, computing resources in edge and cloud servers should be cooperatively leveraged to ensure realtime delivery of information.However, prior works related to edge-cloud cooperation did not consider the fact that the amount of sensor data collected and processed at edge servers is geographically different area-by-area.Therefore, this report proposes an edge cooperation system for realtime delivery of predictive road traffic information.We tackle a mathematical problem formulation as a generalized mutual assignment problem for maximizing prediction accuracy while considering the latency requirement for realtime delivery . As the first step of our work, we consider the system that consists of two edge servers and discuss the performance evaluation with the scenario where roadside cameras work for collecting road-traffic information as sensors in the system.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) edge computing / road traffic prediction / machine learning / realtime delivery / generalized mutual assignment problem
Paper # MoNA2017-42
Date of Issue 2018-01-11 (MoNA)

Conference Information
Committee MoNA
Conference Date 2018/1/18(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Campus Plaza Kyoto
Topics (in Japanese) (See Japanese page)
Topics (in English) Mobile Network, Application of Machine Learning, Mobile Data, etc.
Chair Ryoichi Shinkuma(Kyoto Univ.)
Vice Chair Shigeaki Tagashira(Kansai Univ.) / Gen Kitagata(Tohoku Univ.)
Secretary Shigeaki Tagashira(Kyushu Univ.) / Gen Kitagata(NTT)
Assistant Takayuki Nishio(Kyoto Univ.) / Takato Saito(NTT)

Paper Information
Registration To Technical Committee on Mobile Network and Applications
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Numerical Evaluation of Cooperative Edge System for Realtime Predictive Information Delivery
Sub Title (in English)
Keyword(1) edge computing
Keyword(2) road traffic prediction
Keyword(3) machine learning
Keyword(4) realtime delivery
Keyword(5) generalized mutual assignment problem
1st Author's Name MAsahiro Kanbayashi
1st Author's Affiliation Kyoto University(Kyoto Univ.)
2nd Author's Name Shingo Kato
2nd Author's Affiliation Kyoto University(Kyoto Univ.)
3rd Author's Name Ryoichi Shinkuma
3rd Author's Affiliation Kyoto University(Kyoto Univ.)
Date 2018-01-18
Paper # MoNA2017-42
Volume (vol) vol.117
Number (no) MoNA-390
Page pp.pp.7-12(MoNA),
#Pages 6
Date of Issue 2018-01-11 (MoNA)