2023 Fiscal Year Final Research Report
Mitigation of highway traffic congestion using short-term traffic flow prediction from car probe information and velocity control
| Project/Area Number |
19K11930
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Review Section |
Basic Section 60060:Information network-related
|
|---|
| Research Institution | Shibaura Institute of Technology |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2019-04-01 – 2024-03-31
|
| Keywords | IoT(Internet of Things) / スマートネットワーク / スマートセンシング / 交通流制御 / V2X |
|---|
| Outline of Final Research Achievements |
This study evaluated performance of a deceleration control including variable speed limit (VSL) which is configured to start at that time when a traffic jam is predicted to occur in a few tens of seconds using short-term time series forecasting. Multivariate LSTM is employed for forecasting, with time-series data of vehicle speed collected from probe cars used as input data. The traffic flow simulation revealed that the traffic jam mitigation effect is higher than that of the conventional VSL where it starts at the time when a traffic jam actually occurs. The study also confirmed that the configuration using velocity time series of a target vehicle and a group of vehicles travelling 30 seconds ahead of the target vehicle is used for input variates of LSTM yields better performance than the configuration using only velocity time-series data of the target vehicle is used for input variable of LSTM.
|
| Free Research Field |
情報ネットワーク工学
|
| Academic Significance and Societal Importance of the Research Achievements |
都市部および周辺部での交通渋滞は今後も社会問題として継続すると考えられるが，無線通信機能を前提とした遠隔制御車両や貨物車両の隊列走行を始めとする自動運転車両など，Connected Vehiclesは用途を明確化した形で今後台数が増加していくと考えられる．本課題の成果は，これらの車両の一部が交通流制御に参加することで大きな渋滞緩和効果が得られることを示しており，渋滞に伴う経済損失の回避も含めて社会的な意義は大きいと考える．
|
