01628747

Component

Based on the Connected Vehicle (CV) technology, a number of Eco-Approach and Departure (EAD) strategies have been designed to guide vehicles to travel through signalized intersections in an eco-friendly way, avoiding unnecessary idling and minimizing acceleration/deceleration events. Most of the existing EAD applications were developed and tested in traffic-free scenarios or in a fully connected environment where presence and behavior of surrounding vehicles are detectable and predictable. In this study, the authors propose a prediction-based EAD strategy for more realistic scenarios, where there is a preceding vehicle, which can be either a connected or non-connected vehicle. Unlike in highway scenarios, predicting vehicle speed trajectory along signalized corridors is much more challenging due to the disturbances from signals, traffic queues and pedestrians. Based on vehicle activity data available via inter-vehicles communication or onboard sensing (e.g., by radar), the authors developed several artificial neural network (ANN)-based algorithms to perform short-term speed prediction of the preceding vehicle. Using signal phase and timing (SPaT) information and predicted state of the preceding vehicle, the authors improve the existing EAD algorithm to achieve better fuel economy and emissions reduction in the presence of preceding traffic and queues at intersections. Results from the numerical simulation show that the proposed prediction-based EAD system achieve 4.0% energy savings and 5.2%~41.7% air pollutant emission reduction compared to a conventional car following strategy. The proposed system saves 1.9% energy and reduces 3.1%~33.4% air pollutant emission compared to the existing EAD without prediction in congested urban traffic.

This paper was sponsored by TRB committee AHB15 Standing Committee on Intelligent Transportation Systems.

01618707

17-05809

English

20p

2017

Transportation Research Board 96th Annual Meeting

Digital/other

Figures; References; Tables

Algorithms; Ecodriving; Mathematical prediction; Pollutants; Speed; Traffic congestion; Urban areas

Speed prediction models

Environment; Highways; Operations and Traffic Management; Planning and Forecasting

Transportation Research Board Annual Meeting 2017 Paper #17-05809

TRIS, TRB, ATRI

Dec 8 2016 12:20PM