Eco-Route: Recommending Economical Driving Routes For Plug-in Hybrid Electric Vehicles

TL;DR

Eco-Route is a two-phase framework that recommends the most economical driving routes for PHEVs by modeling route costs and utilizing real-time traffic data, leading to significant cost savings.

Contribution

The paper introduces a novel two-phase eco-route planning framework that combines cost modeling with real-time traffic data for PHEVs, improving cost efficiency.

Findings

Achieves less than 8% mean cost error for routes over 5 km.

Enables drivers to save about 9% in fuel costs on average.

Validates effectiveness using simulations and real-world taxi data.

Abstract

High fuel consumption cost results in drivers' economic burden. Plug-In Hybrid Electric Vehicles (PHEVs) consume two fuel sources (i.e., gasoline and electricity energy sources) with floating prices. To reduce drivers' total fuel cost, recommending economical routes to them becomes one of the effective methods. In this paper, we present a novel economical path-planning framework called Eco-Route, which consists of two phases. In the first phase, we build a driving route cost model (DRCM) for each PHEV (and driver) under the energy management strategy, based on driving condition and vehicles' parameters. In the second phase, with the real-time traffic information collected via the mobile crowdsensing manner, we are able to estimate and compare the driving cost among the shortest and the fastest routes for a given PHEV, and then recommend the driver with the more economical one. We evaluate the two-phase framework using 8 different PHEVs simulated in Matlab/Simulink, and the real-world datasets consisting of the road network, POI and GPS trajectory data generated by 559 taxis in seven days in Beijing, China. Experimental results demonstrate that the proposed model achieves good accuracy, with a mean cost error of less 8% when paths length is longer than 5 km. Moreover, users could save about 9% driving cost on average if driving along suggested routes in our case studies.