Online prediction of an electric vehicle remaining range based on regression analysis

Bolovinou, Anastasia; Bakas, Ioannis; Amditis, Angelos; Mastrandrea, Francesco; Vinciotti, Walter

doi:10.1109/ievc.2014.7056167

Cited by 50 publications

(32 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The underlying assumption of the conventional historybased estimation is such that the immediate future fuel consumption may be the same as the right past fuel consumption. The advantages of the history-based estimation is model free, but at the same time, the estimation accuracy is far limited though an elaborated history-based estimation attempts more accurate prediction of the future fuel consumption with a regression of the past data [7].…”

Section: Hybrid Model-based Remaining Range Estimationmentioning

confidence: 99%

See 1 more Smart Citation

Accurate remaining range estimation for Electric vehicles

Hong

Park

Chang

2016

2016 21st Asia and South Pacific Design Automation Conference (ASP-DAC)

View full text Add to dashboard Cite

EVs (Electric vehicle) generally have only around 22% driving ranges compared with ICEVs (Internal combustion engine vehicle) with a similar price range. Running out of the EV battery SoC (State of charge) while driving gives the same inconvenience as a vehicle breakdown. In this paper, we emphasize that an accurate remaining range estimation can efficiently mitigate the range anxiety of EV drivers. Most EV drivers reserve 30% of the on-dash estimated remaining range gauge of their EV because they do not trust the current remaining range estimation accuracy of production EVs. In other words, an accurate remaining range estimation is equivalent to increasing the EV battery capacity up to 30%.Just like the analogous concepts used in the power estimation of digital circuits, a model-based remaining range estimation consists of the two consecutive steps, a driving profile estimation and a power consumption estimation using the power model. In this paper, we focus on increasing the accuracy of the power model. We come up with a hybrid modeling methodology combining a physics equation based model with empirical data. We validate the accuracy of the hybrid model in the remaining range estimation with the target EV. We collect the power consumption, velocity, road inclination, etc. of the EV in every half second with an onboard monitoring system, a perform multivariable linear regression and create an accurate EV power model. The proposed remaining range estimation yields only 2.52% error while the state-of-the-art model-based EV remaining range estimation shows 9.33% error when the same future route and speed estimation are given.

show abstract

Section: Hybrid Model-based Remaining Range Estimationmentioning

confidence: 99%

“…We classify this estimation method as a history-based estimation in this paper. A regression-based algorithm improves the prediction accuracy of the conventional range estimation methods [7].…”

Section: Introductionmentioning

confidence: 99%

Accurate remaining range estimation for Electric vehicles

Hong

Park

Chang

2016

2016 21st Asia and South Pacific Design Automation Conference (ASP-DAC)

View full text Add to dashboard Cite

show abstract

“…DTE can be estimated by measuring the mean energy consumption over short and long distances [16]. To account for the deviation between the historical and future energy intensity, a regression model can be used to predict the future energy intensity given future route information [17]. Route features from sensor data can be clustered to identify the driving pattern for EV range estimation [18].…”

Section: Applications Of Vehicle Energy Consumptionmentioning

confidence: 99%

Personalized Prediction of Vehicle Energy Consumption Based on Participatory Sensing

Tseng¹,

Chau²

2017

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

The advent of abundant on-board sensors and electronic devices in vehicles populates the paradigm of participatory sensing to harness crowd-sourced data gathering for intelligent transportation applications, such as distance-to-empty prediction and eco-routing. While participatory sensing can provide diverse driving data, there lacks a systematic study of effective utilization of the data for personalized prediction. There are considerable challenges on how to interpolate the missing data from a sparse dataset, which often arises from participatory sensing. This paper presents and compares various approaches for personalized vehicle energy consumption prediction, including a blackbox framework that identifies driver/vehicle/environment-dependent factors and a collaborative filtering approach based on matrix factorization. Furthermore, a case study of distance-to-empty prediction for electric vehicles by participatory sensing data is conducted and evaluated empirically, which shows that our approaches can significantly improve the prediction accuracy.

show abstract

“…The Mobility2.0 project [1]- [5] has been completed in February, 2015. It has developed and tested an in-vehicle commuting assistant for FEV mobility, enabling more reliable and energy-efficient electro-mobility by controlling available range and proposing as needed a park and ride type of trip.…”

Section: Introductionmentioning

confidence: 99%

“…• the Range Estimator computes the FEV battery energy consumption for a given leg of a journey (see [5]);…”

Section: Introductionmentioning

confidence: 99%

Global On-line Optimization for Charging Station Allocation

Lasgouttes¹

2015

2015 IEEE 18th International Conference on Intelligent Transportation Systems

View full text Add to dashboard Cite

Abstract-The goal of the Mobility2.0 project was to provide full electric vehicles users with a set of tools that reduce range anxiety and favor a partial modal shift towards public transportation. As part of this work, we have designed a so-called global optimization criterion for selecting charging stations where change of mode can occur. The idea is to minimize the mean quadratic travel time of all users, in a way that can be used for on-line allocation with good performance. We show through simulation that this leads to a sizable improvement with respect to a "greedy" station selection.

show abstract

Online prediction of an electric vehicle remaining range based on regression analysis

Cited by 50 publications

References 13 publications

Accurate remaining range estimation for Electric vehicles

Accurate remaining range estimation for Electric vehicles

Personalized Prediction of Vehicle Energy Consumption Based on Participatory Sensing

Global On-line Optimization for Charging Station Allocation

Contact Info

Product

Resources

About