Driving Behavior Evaluation Model Base on Big Data From Internet of Vehicles

Driving Behavior Evaluation Model Base on Big Data From Internet of Vehicles

Ruru Hao (Chang'an University, Xi'an, China), Hangzheng Yang (Chinaunicom Software Xi'an Branch, Xi'an, China) and Zhou Zhou (Chang'an University, Xi'an, China)
Copyright: © 2019 |Pages: 18
DOI: 10.4018/IJACI.2019100105

Abstract

This article attempts to evaluate whether a driving behavior is fuel-efficient. To solve this problem, a driving behavior evaluation model was proposed in this article. First, the operating data and fuel consumption data of five trucks were obtained from the vehicle networking system. Four characteristic parameters, which are closely related to fuel consumption, were extracted from 19 sets of vehicle operating data. Then, K-means clustering combined with DBSCAN was adopted to cluster the four characteristic parameters into different driving behaviors. Three types of driving behavior were labeled respectively as low, medium and high fuel consumption driving behavior after clustering analysis. The clustering accuracy rate reached 79.7%. Finally, a fuel consumption-oriented driving behavior evaluation model was established. The model was trained with the labeled samples. The trained model can evaluate the driving behavior online and gives an evaluation of whether the driving behavior is fuel-efficient. The test results show that the prediction accuracy rate of the proposed model can reach to 77.13%.
Article Preview
Top

Introduction

As emissions from road freight account for a large proportion of emissions from global transportation, reducing the fuel consumption of trucks has become an urgent problem to be solved (Zavalko, 2018). There is documented evidence that driver driving behavior has a significant impact on fuel consumption in the 1980s (Wasielewski, 1980; Siero, 1989). Studies show that the influence of driving behavior on fuel consumption is up to 30%. A reckless driver can wipe out all the benefits of vehicle technology advancements such as tires, engines, low air resistance design, synthetic lubricants, etc. (Wang, 2010). Even for professional drivers, different driving behaviors can cause a difference of 7% to 25% in fuel consumption (Zen, 2010).

At present, there are about 15 million trucks and more than 30 million truck drivers in China. The truck drivers are responsible for 76% of the national logistics. Compared with the average level, the best-driving truck drivers can save 30 liters of fuel per thousand kilometers and 3,285 liters a year, which if used to generate electricity, can provide one Beijing citizen with power consumption for more than 12 years. If the 15 million trucks of China were all driven by such excellent drivers, the saved diesel fuel of one year would provide Beijing residents with 8 years of living power consumption. According to the statistics, fuel consumption accounts for about 26% of the cost for road transport logistics, which is the highest among all cost components (G7, 2017). Take Germany for example, in long-distance transportation, fuel costs account for nearly one-third of the total cost of a heavy truck (Daun, 2013).

Both automotive manufacturers and research institutes are working hard to improve technologies to make more fuel-efficient vehicles. As another option, the eco-driving technology proposed by many researchers can also improve the fuel- efficient of existing vehicles, which has been proven in many research literatures (Saboohi, 2009; Saerens & Mensing, 2013; Gamage, Xu, Boriboonsomsin, & Jeffreys, 2016; Díaz-Ramirez & Barla, 2017; Ma, 2018). In the 1970s, the US Department of Energy (DOE) carried out a project called Driver Energy Conservation Awareness Training (DECAT) (Barkenbus, 2010). In 2008, Ford launched Eco-driving operations in Europe (Hennig, 2008). Barth (2009) studied the effects of dynamic Eco-driving systems on energy consumption and emissions on highways. The results showed that the fuel savings reached nearly 10-20% without significantly increasing travel time by providing dynamic guidance to drivers. In 2012, the Royal Automobile Club of Queensland (RACQ) launched the EcoDrive program, which aims to reduce vehicle fuel consumption by developing a good driving behavior for the driver (Graves, 2012). In the same year, the National Renewable Energy Laboratory carried out the researches on the effects of different driving behaviors on fuel consumption. The results show that the reasonable and effective driving behavior can reduce fuel consumption by about 20%. Therefore, the Eco-Driving Strategy was proposed to require drivers to drive the vehicle in a more economical and environmentally friendly manner without driving situations such as sudden acceleration, deceleration, empty throttle and long idle speed (Gonder, 2012). To promote the Eco-driving, Ando (2012) developed some driver assistance systems to improve the drivers’ techniques by providing information, which can help the drivers drive more economically. The tracking results of these driver training programs indicate that eco-driving strategies can save fuel consumption by about 10%on average (Zavalko, 2018; Mcilroy, 2017).

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 11: 4 Issues (2020): 1 Released, 3 Forthcoming
Volume 10: 4 Issues (2019)
Volume 9: 4 Issues (2018)
Volume 8: 4 Issues (2017)
Volume 7: 2 Issues (2016)
Volume 6: 2 Issues (2014)
Volume 5: 4 Issues (2013)
Volume 4: 4 Issues (2012)
Volume 3: 4 Issues (2011)
Volume 2: 4 Issues (2010)
Volume 1: 4 Issues (2009)
View Complete Journal Contents Listing