Prediction of energy consumption for new electric vehicle models by machine learning

Fukushima, Arika; Yano, Tōru; Imahara, Shuichiro; Aisu, Hideyuki; Shimokawa, Yusuke; Shibata, Yasuhiro

doi:10.1049/iet-its.2018.5169

Cited by 33 publications

(22 citation statements)

References 17 publications

(22 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To minimize the prediction error, i.e., min υ ρ j (υ), we also apply the Adam optimizer and update the global model υ (φ+1) as expressed in Eqs. (5)- (7). This υ (φ+1) is then pushed back to the CS-j, ∀j ∈ J for the next local learning process.…”

Section: Csmentioning

confidence: 99%

“…In [6], the authors proposed a reinforcement learning-based demand response scheme to optimize the amount of energy charging for an individual EV based on daily forecasted price policy. Furthermore, the authors in [7] developed a driving activity-based recommendation system applying a multiple regression-based learning approach, aiming at improving the energy consumption prediction accuracy for EVs. In [8], an online learning to optimize EVs' charging demands using previous-day pricing profiles from the distribution company was proposed.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Energy Demand Prediction with Federated Learning for Electric Vehicle Networks

Saputra

Hoang

Nguyen

et al. 2019

2019 IEEE Global Communications Conference (GLOBECOM)

177

View full text Add to dashboard Cite

In this paper, we propose novel approaches using state-of-the-art machine learning techniques, aiming at predicting energy demand for electric vehicle (EV) networks. These methods can learn and find the correlation of complex hidden features to improve the prediction accuracy. First, we propose an energy demand learning (EDL)-based prediction solution in which a charging station provider (CSP) gathers information from all charging stations (CSs) and then performs the EDL algorithm to predict the energy demand for the considered area. However, this approach requires frequent data sharing between the CSs and the CSP, thereby driving communication overhead and privacy issues for the EVs and CSs. To address this problem, we propose a federated energy demand learning (FEDL) approach which allows the CSs sharing their information without revealing real datasets. Specifically, the CSs only need to send their trained models to the CSP for processing. In this case, we can significantly reduce the communication overhead and effectively protect data privacy for the EV users. To further improve the effectiveness of the FEDL, we then introduce a novel clustering-based EDL approach for EV networks by grouping the CSs into clusters before applying the EDL algorithms. Through experimental results, we show that our proposed approaches can improve the accuracy of energy demand prediction up to 24.63% and decrease communication overhead by 83.4% compared with other baseline machine learning algorithms.

show abstract

Section: Csmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Energy Demand Prediction with Federated Learning for Electric Vehicle Networks

Saputra

Hoang

Nguyen

et al. 2019

2019 IEEE Global Communications Conference (GLOBECOM)

177

View full text Add to dashboard Cite

show abstract

“…19,20 The estimation of future energy consumption is frequently performed using ML algorithms. [21][22][23] Thereby, information from the vehicle, such as mass or current tractive energy consumption, is used together with predictive information about the selected route. This information comprises the map data on each link of the route (e.g., legal speed limit, curvature, slope) as well as live traffic data from other connected vehicles.…”

Section: Range Estimation Routing and Charge Planningmentioning

confidence: 99%

“…Of the four module placement variants analyzed, cloud-based inference is clearly superior. Our proposed system architecture can enable driving range estimation concepts such as those of Fukushima et al, 22 Grubwinkler et al 25,28 and Lee et al 30,31 to perform efficiently.…”

Section: Inferencementioning

confidence: 99%

Evaluating system architectures for driving range estimation and charge planning for electric vehicles

Thorgeirsson

Vaillant²,

Scheubner

et al. 2020

Softw Pract Exp

View full text Add to dashboard Cite

Due to sparse charging infrastructure and short driving ranges, drivers of battery electric vehicles (BEVs) can experience range anxiety, which is the fear of stranding with an empty battery. To help eliminate range anxiety and make BEVs more attractive for customers, accurate range estimation methods need to be developed. In recent years, many publications have suggested machine learning algorithms as a fitting method to achieve accurate range estimations. However, these algorithms use a large amount of data and have high computational requirements. A traditional placement of the software within a vehicle's electronic control unit could lead to high latencies and thus detrimental to user experience. But since modern vehicles are connected to a backend, where software modules can be implemented, high latencies can be prevented with intelligent distribution of the algorithm parts. On the other hand, communication between vehicle and backend can be slow or expensive. In this article, an intelligent deployment of a range estimation software based on ML is analyzed. We model hardware and software to enable performance evaluation in early stages of the development process. Based on simulations, different system architectures and module placements are then analyzed in terms of latency, network usage, energy usage, and cost. We show that a distributed system with cloud-based module placement reduces the end-to-end latency significantly, when compared with a traditional vehicle-based placement. Furthermore, we show that network usage is significantly reduced. This intelligent system enables the application of complex, but accurate range estimation with low latencies, resulting in an improved user experience, which enhances the practicality and acceptance of BEVs.

show abstract

“…Range extender research is not only limited to the optimization of the mechanical strategy, but it also covers on the sophisticated algorithm development by considering a large amount of real-world driving data of the EV system [27], [28]. Various external factors can potentially affect the driving performance of the EV system such as the driving behavior, weather condition, road and traffic conditions [29].…”

Section: Introductionmentioning

confidence: 99%

Electric Motorcycle Modeling for Speed Tracking and Range Travelled Estimation

et al. 2019

View full text Add to dashboard Cite

With the massive interest in electric vehicle technology, all different types of vehicles are moving toward green awareness, including the motorcycle. As time progresses, the investigations on the motorcycle developed to an even more complex model as the model need to be able to include the dynamics of the motorcycle at high speed. Relatively, few works of the literature found on an electric motorcycle (MC) modeling. Therefore, this paper aims to develop an E-MC model that represents a realistic model of the motorcycle with both kinematics and dynamics of the motorcycle incorporated in the model. The developed model is then tested for the speed tracking and the range travelled to evaluate the performance. Two different driving cycles that commonly applied in the commercial motorcycle evaluation test are used as the driving profiles in the simulation, namely, the Worldwide Motorcycle Test Cycle and New European Driving Cycle profiles. The results show an evident ability for the developed model of the E-MC to track the speed profile. It is also noted that the distance travelled by the E-MC model can be effectively determined. INDEX TERMS Modeling, electric motorcycle, simulation, speed tracking.

show abstract

Prediction of energy consumption for new electric vehicle models by machine learning

Cited by 33 publications

References 17 publications

Energy Demand Prediction with Federated Learning for Electric Vehicle Networks

Energy Demand Prediction with Federated Learning for Electric Vehicle Networks

Evaluating system architectures for driving range estimation and charge planning for electric vehicles

Electric Motorcycle Modeling for Speed Tracking and Range Travelled Estimation

Contact Info

Product

Resources

About