GreenRoute: A Generalizable Fuel-Saving Vehicular Navigation Service

Yiran Zhao, Shuochao Yao, Dongxin Liu, Huajie Shao, Shengzhong Liu, Tarek Abdelzaher

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper presents GreenRoute, a fuel-saving vehicular navigation system whose contribution is motivated by one of the key challenges in the design of autonomic services: Namely, designing the service in a manner that reduces operating cost. GreenRoute achieves this end, in the specific context of fuel-saving vehicular navigation, by significantly improving the generalizability of fuel consumption models it learns (in order to recommend fuel-saving routes to drivers). By learning fuel consumption models that apply seamlessly across vehicles and routes, GreenRoute eliminates one of the key incremental costs unique to fuel-saving navigation: Namely, the cost of upkeep with ever-changing fuel-consumption-specific route and vehicle parameters globally. Unlike shortest or fastest routes (that depend only on map topology and traffic), minimum-fuel routes depend additionally on the vehicle engine. This makes fuel-efficient routes harder to compute in a generic fashion, compared to shortest and fastest routes. The difficulty results in two additional costs. First, more route features need to be collected (and updated) for predicting fuel consumption, such as the nature of traffic regulators. Second, fuel prediction remains specific to the individual vehicle type, which requires continual upkeep with new car types and parameters. The contribution of this paper lies in deriving and implementing a fuel consumption model that avoids both of the above two sources of cost. To measure route recommendation quality, we test the system (using 21 vehicles and over 2400 miles driven in seven US cities) by comparing fuel consumption on our routes against both Google Maps' routes and the shortest routes. Results show that, on average, our routes save 10.8% fuel compared to Google Maps' routes and save 8.4% compared to the shortest routes. This is roughly comparable to services that maintain individualized vehicle models, suggesting that our low-cost models do not come at the expense of quality reduction.

Original languageEnglish (US)
Title of host publicationProceedings - 2019 IEEE International Conference on Autonomic Computing, ICAC 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-10
Number of pages10
ISBN (Electronic)9781728124117
DOIs
StatePublished - Jun 2019
Event16th IEEE International Conference on Autonomic Computing, ICAC 2019 - Umea, Sweden
Duration: Jun 16 2019Jun 20 2019

Publication series

NameProceedings - 2019 IEEE International Conference on Autonomic Computing, ICAC 2019

Conference

Conference16th IEEE International Conference on Autonomic Computing, ICAC 2019
CountrySweden
CityUmea
Period6/16/196/20/19

Fingerprint

Navigation
Fuel consumption
Costs
Navigation systems
Operating costs
Traffic
Railroad cars
Topology
Engines
Cost Model
Navigation System
Regulator
Model
Driver
Recommendations
Engine
Eliminate

Keywords

  • eco drive
  • fuel consumption model
  • Fuel saving routing

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Hardware and Architecture
  • Control and Optimization

Cite this

Zhao, Y., Yao, S., Liu, D., Shao, H., Liu, S., & Abdelzaher, T. (2019). GreenRoute: A Generalizable Fuel-Saving Vehicular Navigation Service. In Proceedings - 2019 IEEE International Conference on Autonomic Computing, ICAC 2019 (pp. 1-10). [8831213] (Proceedings - 2019 IEEE International Conference on Autonomic Computing, ICAC 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICAC.2019.00011

GreenRoute : A Generalizable Fuel-Saving Vehicular Navigation Service. / Zhao, Yiran; Yao, Shuochao; Liu, Dongxin; Shao, Huajie; Liu, Shengzhong; Abdelzaher, Tarek.

Proceedings - 2019 IEEE International Conference on Autonomic Computing, ICAC 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 1-10 8831213 (Proceedings - 2019 IEEE International Conference on Autonomic Computing, ICAC 2019).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Zhao, Y, Yao, S, Liu, D, Shao, H, Liu, S & Abdelzaher, T 2019, GreenRoute: A Generalizable Fuel-Saving Vehicular Navigation Service. in Proceedings - 2019 IEEE International Conference on Autonomic Computing, ICAC 2019., 8831213, Proceedings - 2019 IEEE International Conference on Autonomic Computing, ICAC 2019, Institute of Electrical and Electronics Engineers Inc., pp. 1-10, 16th IEEE International Conference on Autonomic Computing, ICAC 2019, Umea, Sweden, 6/16/19. https://doi.org/10.1109/ICAC.2019.00011
Zhao Y, Yao S, Liu D, Shao H, Liu S, Abdelzaher T. GreenRoute: A Generalizable Fuel-Saving Vehicular Navigation Service. In Proceedings - 2019 IEEE International Conference on Autonomic Computing, ICAC 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 1-10. 8831213. (Proceedings - 2019 IEEE International Conference on Autonomic Computing, ICAC 2019). https://doi.org/10.1109/ICAC.2019.00011
Zhao, Yiran ; Yao, Shuochao ; Liu, Dongxin ; Shao, Huajie ; Liu, Shengzhong ; Abdelzaher, Tarek. / GreenRoute : A Generalizable Fuel-Saving Vehicular Navigation Service. Proceedings - 2019 IEEE International Conference on Autonomic Computing, ICAC 2019. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 1-10 (Proceedings - 2019 IEEE International Conference on Autonomic Computing, ICAC 2019).
@inproceedings{2c3945a6d4fc4ebc97dfaa3e5fcfb2fa,
title = "GreenRoute: A Generalizable Fuel-Saving Vehicular Navigation Service",
abstract = "This paper presents GreenRoute, a fuel-saving vehicular navigation system whose contribution is motivated by one of the key challenges in the design of autonomic services: Namely, designing the service in a manner that reduces operating cost. GreenRoute achieves this end, in the specific context of fuel-saving vehicular navigation, by significantly improving the generalizability of fuel consumption models it learns (in order to recommend fuel-saving routes to drivers). By learning fuel consumption models that apply seamlessly across vehicles and routes, GreenRoute eliminates one of the key incremental costs unique to fuel-saving navigation: Namely, the cost of upkeep with ever-changing fuel-consumption-specific route and vehicle parameters globally. Unlike shortest or fastest routes (that depend only on map topology and traffic), minimum-fuel routes depend additionally on the vehicle engine. This makes fuel-efficient routes harder to compute in a generic fashion, compared to shortest and fastest routes. The difficulty results in two additional costs. First, more route features need to be collected (and updated) for predicting fuel consumption, such as the nature of traffic regulators. Second, fuel prediction remains specific to the individual vehicle type, which requires continual upkeep with new car types and parameters. The contribution of this paper lies in deriving and implementing a fuel consumption model that avoids both of the above two sources of cost. To measure route recommendation quality, we test the system (using 21 vehicles and over 2400 miles driven in seven US cities) by comparing fuel consumption on our routes against both Google Maps' routes and the shortest routes. Results show that, on average, our routes save 10.8{\%} fuel compared to Google Maps' routes and save 8.4{\%} compared to the shortest routes. This is roughly comparable to services that maintain individualized vehicle models, suggesting that our low-cost models do not come at the expense of quality reduction.",
keywords = "eco drive, fuel consumption model, Fuel saving routing",
author = "Yiran Zhao and Shuochao Yao and Dongxin Liu and Huajie Shao and Shengzhong Liu and Tarek Abdelzaher",
year = "2019",
month = "6",
doi = "10.1109/ICAC.2019.00011",
language = "English (US)",
series = "Proceedings - 2019 IEEE International Conference on Autonomic Computing, ICAC 2019",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "1--10",
booktitle = "Proceedings - 2019 IEEE International Conference on Autonomic Computing, ICAC 2019",
address = "United States",

}

TY - GEN

T1 - GreenRoute

T2 - A Generalizable Fuel-Saving Vehicular Navigation Service

AU - Zhao, Yiran

AU - Yao, Shuochao

AU - Liu, Dongxin

AU - Shao, Huajie

AU - Liu, Shengzhong

AU - Abdelzaher, Tarek

PY - 2019/6

Y1 - 2019/6

N2 - This paper presents GreenRoute, a fuel-saving vehicular navigation system whose contribution is motivated by one of the key challenges in the design of autonomic services: Namely, designing the service in a manner that reduces operating cost. GreenRoute achieves this end, in the specific context of fuel-saving vehicular navigation, by significantly improving the generalizability of fuel consumption models it learns (in order to recommend fuel-saving routes to drivers). By learning fuel consumption models that apply seamlessly across vehicles and routes, GreenRoute eliminates one of the key incremental costs unique to fuel-saving navigation: Namely, the cost of upkeep with ever-changing fuel-consumption-specific route and vehicle parameters globally. Unlike shortest or fastest routes (that depend only on map topology and traffic), minimum-fuel routes depend additionally on the vehicle engine. This makes fuel-efficient routes harder to compute in a generic fashion, compared to shortest and fastest routes. The difficulty results in two additional costs. First, more route features need to be collected (and updated) for predicting fuel consumption, such as the nature of traffic regulators. Second, fuel prediction remains specific to the individual vehicle type, which requires continual upkeep with new car types and parameters. The contribution of this paper lies in deriving and implementing a fuel consumption model that avoids both of the above two sources of cost. To measure route recommendation quality, we test the system (using 21 vehicles and over 2400 miles driven in seven US cities) by comparing fuel consumption on our routes against both Google Maps' routes and the shortest routes. Results show that, on average, our routes save 10.8% fuel compared to Google Maps' routes and save 8.4% compared to the shortest routes. This is roughly comparable to services that maintain individualized vehicle models, suggesting that our low-cost models do not come at the expense of quality reduction.

AB - This paper presents GreenRoute, a fuel-saving vehicular navigation system whose contribution is motivated by one of the key challenges in the design of autonomic services: Namely, designing the service in a manner that reduces operating cost. GreenRoute achieves this end, in the specific context of fuel-saving vehicular navigation, by significantly improving the generalizability of fuel consumption models it learns (in order to recommend fuel-saving routes to drivers). By learning fuel consumption models that apply seamlessly across vehicles and routes, GreenRoute eliminates one of the key incremental costs unique to fuel-saving navigation: Namely, the cost of upkeep with ever-changing fuel-consumption-specific route and vehicle parameters globally. Unlike shortest or fastest routes (that depend only on map topology and traffic), minimum-fuel routes depend additionally on the vehicle engine. This makes fuel-efficient routes harder to compute in a generic fashion, compared to shortest and fastest routes. The difficulty results in two additional costs. First, more route features need to be collected (and updated) for predicting fuel consumption, such as the nature of traffic regulators. Second, fuel prediction remains specific to the individual vehicle type, which requires continual upkeep with new car types and parameters. The contribution of this paper lies in deriving and implementing a fuel consumption model that avoids both of the above two sources of cost. To measure route recommendation quality, we test the system (using 21 vehicles and over 2400 miles driven in seven US cities) by comparing fuel consumption on our routes against both Google Maps' routes and the shortest routes. Results show that, on average, our routes save 10.8% fuel compared to Google Maps' routes and save 8.4% compared to the shortest routes. This is roughly comparable to services that maintain individualized vehicle models, suggesting that our low-cost models do not come at the expense of quality reduction.

KW - eco drive

KW - fuel consumption model

KW - Fuel saving routing

UR - http://www.scopus.com/inward/record.url?scp=85073146005&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85073146005&partnerID=8YFLogxK

U2 - 10.1109/ICAC.2019.00011

DO - 10.1109/ICAC.2019.00011

M3 - Conference contribution

AN - SCOPUS:85073146005

T3 - Proceedings - 2019 IEEE International Conference on Autonomic Computing, ICAC 2019

SP - 1

EP - 10

BT - Proceedings - 2019 IEEE International Conference on Autonomic Computing, ICAC 2019

PB - Institute of Electrical and Electronics Engineers Inc.

ER -