Save or Waste: Real Data Based Energy-Efficient Driving

Abstract

Energy consumption is the key to restrict the development of electric vehicles (EV), which is heavily affected by complex driving behaviors. In this paper, we propose a classified driving behavior based energy consumption prediction model, as well as recommended mechanisms for energy-efficient driving. Firstly, utilizing six EVs, we collect real data related to driving behaviors and energy consumption of vehicle in one year. After clustering behaviors of drivers, we present an energy consumption predication model, which accurately forecast the energy consumption caused by different driving behaviors. Motivated by the model, energy-saving strategies are proposed to recommend suitable driving behaviors. The simulation results further indicate that the accuracy of the proposed model is up to 98%. Specifically, the proposed model is less dependence on data volume, which guarantees the precision of more than 96% when the data volume is very small.

A Scoping Review of Energy-Efficient Driving Behaviors and Applied State-of-the-Art AI Methods

“…For instance, a dataset of 2250 driving tests with an Android smartphone and an OBD-Bluetooth adapter was generated in [54], and two ML models to analyze the dataset from CANbus and a smartphone, respectively, were developed in [50]. Some studies require customized data not covered in the mentioned sources and additional sensors (e.g., the camera [12], pedal force [14], and V2I communication devices [34]) should be installed for data collection.…”

“…Fuel consumption mL/s [13,49] g [7] L/km [8] L/100 km [11,25,31,40] gallon/mile [22] mL [28,29,36] kg [32] gallon [44,45] Electrical energy consumption Wh/km [10,23] J [23] kwh/100 km [14,48] kwh [30,47] Wh [37] kJ/s [42] Fuel economy km/L [24] mile/gallon [39] CO 2 emissions g/km [21,48] g/mile [22] g [46] The variables are mainly divided into energy consumption and energy economy. Energy consumption signifies the amount of fuel or electricity a vehicle utilizes to cover a specific distance.…”

“…The main purpose of energy-efficient driving is to develop a velocity and acceleration recommendation strategy for reducing energy consumption. Deceleration and acceleration are integrated in some studies [12,21,28], and the pedal indexes (e.g., the force, frequency and depth) are also the parameters indicating acceleration [14,40,47].…”

“…The study in [12] utilizes an RL model to generate energy-saving driving behaviors and integrates vision-perceptive methods to achieve higher energy efficiency. Meanwhile, some studies apply classification [13] or clustering [14] algorithms to find out the best practices in driving styles for fuel saving.…”

Identifying the electricity-saving driving behaviors of electric bus based on trip-level electricity consumption: a machine learning approach

“…Many researchers used statistical models and machine learning methods to investigate various driving behavior features (i.e., microscopic and macroscopic levels) that affect Responsible Editor: Philippe Garrigues energy consumption. For example, Lv et al (2019) and Huang et al (2020) used driving behavior features to analyze the EV electricity consumption under different driving styles. Fetene et al (2017) exploited real-world EV driving data to uncover the effect of macroscopic driving behavior patterns (e.g., mean driving speed, mean driving speed square, mean acceleration, and mean acceleration square) and weather conditions on the EB electricity consumption rate.…”