Convolutional neural network–bagged decision tree: a hybrid approach to reduce electric vehicle’s driver’s range anxiety by estimating energy consumption in real-time

Modi, Shatrughan; Bhattacharya, Jhilik; Basak, Prasenjit

doi:10.1007/s00500-020-05310-y

Cited by 17 publications

(7 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, we choose the discharge segment with SOC from 80% to 10% as the research object. The remaining driving range (denoted as r_mileage) is the difference between the cumulative mileage with a SOC of 10% and the cumulative mileage of each vehicle operation record (SOC = t%), as shown in Equation (1). r_mileage = mileage soc=t % − mileage soc=10%…”

Section: Construction Of Remaining Driving Mileage Fieldmentioning

confidence: 99%

“…New energy vehicles represented by electric vehicles (EVs) are developing rapidly, but power battery technology has not yet made major breakthroughs, which limits EV development. Accurately predicting the remaining driving range of EVs effectively alleviates the problem of mileage anxiety caused by relatively long charging time and insufficient charging pile density for EV users [1]. At the same time, it also enables vehicle developers to develop more refined EVs energy management strategies to improve vehicle performance.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Method for predicting the remaining mileage of electric vehicles based on dimension expansion and model fusion

Sheng

et al. 2022

IET Intelligent Trans Sys

View full text Add to dashboard Cite

Accurately predicting the remaining mileage of electric vehicles (EVs) can effectively alleviate user's mileage anxiety and develop refinement of energy management strategy. However, traditional prediction methods not only consume time and resources, but also accumulate errors and lack interpretability. In this paper, we proposed a model based on dimension expansion and model fusion strategy, which uses the extreme gradient boosting (XGBoost) algorithm to directly predict the remaining mileage of EVs. After pre‐processing the real running data of EVs, we constructed the field of remaining driving range and analyzed the relationship between features and remaining driving range, and then directly predicted the remaining driving mileage. Compared with other machine learning methods, XGBoost model has the highest accuracy. Then dimensional extended data set was obtained based on prior knowledge and symbol conversion, which improved the model performance. Finally, the model fusion strategy was adopted to further improve the generalization ability and stability of the model. The experimental results show that the Bootstrap aggregating (Bagging) fusion model has the highest predictive performance on the test set and outperformed other methods. The maximum RAE is not more than 3.5%, RMSE is less than 3km and MAE is about 2 km.

show abstract

Section: Construction Of Remaining Driving Mileage Fieldmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Method for predicting the remaining mileage of electric vehicles based on dimension expansion and model fusion

Sheng

et al. 2022

IET Intelligent Trans Sys

View full text Add to dashboard Cite

show abstract

“…It is calculated that the current global petroleum resources could be depleted within 50years if consumed at present utilization rates. Hence, researchers encourage power generation through renewable energy sources (RES) like solar, wind, biomass, and hydro (Modi et al 2021).…”

Section: Introductionmentioning

confidence: 99%

Novel Harmonic Prediction and Power Quality Improvementusing Intelligent Hybrid Strategies for Grid Coordinated System

Sachdev¹

2023

Preprint

View full text Add to dashboard Cite

In recent times, the power demand has been increased worldwide due to industrialization and urbanization using Plug-in Hybrid Electric Vehicles (PHEVs). To improve Harmonic Distortion, a Hybrid Solar and Small Hydro (HSSH) based hybrid form of the renewable energy system has been developed. However, the high penetration of varying nonlinear PHEVs loads on the grid system can impact the system's performance in terms of power loss, voltage fluctuations, power quality, and harmonic distortion. In this article, Kalman Decoupled Harmonic Power Flow (KDHPF) technique is proposed primarily to calculate the harmonic current in the grid system. Consequently, the Bessel Filter Sallen Key (BFSK) and Multiobjective Firefly Algorithm (MOFA) are projected to control the bidirectional converter's voltage and current to improve the quality of power in the coordinated grid system. The power loss, error rate, and Total Harmonic Distortion (THD) have been optimized by the MOFA optimization method. The implementation of this work is done in the MATLAB/Simulink platform. Moreover, the observed simulation results are compared with various existing techniques for validating the efficiency of the proposed method in terms of reduced 3.5% of THD and 0.000142 MW of power loss. The consequences proved that the projected grid coordinated system had achieved the finest performance under diverse cases.

show abstract

“…For this, the coulomb counting technic is used to estimate the battery SOC. Another study [29] had treated the battery SOC as the one point which influence on the energy consumption of electrical vehicle. To estimate the battery SOC, the used equation is function of the fine-tuned estimated power consumption of the electrical vehicle (for more details, the reader can see [30]).…”

Section: Introductionmentioning

confidence: 99%

Coulomb Counting Estimator of Battery State of Charge Under Variable Discharge Current

Zine¹,

BIA²,

Benmouna

et al. 2022

Preprint

View full text Add to dashboard Cite

Battery state of charge assumes a critical part in advancing electric vehicle energy management, improving battery capacity and energy utilization, keeping batteries from overcharging and over-discharging, for the purpose to guarantee the security and long-term use of batteries lifespan and the expected vehicle autonomy with the indicated battery state of charge. This study presents a battery state of charge estimation using coulomb counting technique with a constant and variable discharging current for Lead-acid battery. In this way, the current, voltage, and temperature are measured during the battery cycle of charge and discharge and contrasted with the estimated value depending on the battery generic model. Additionally, exploratory outcomes are done to approve this investigation.

show abstract

Convolutional neural network–bagged decision tree: a hybrid approach to reduce electric vehicle’s driver’s range anxiety by estimating energy consumption in real-time

Cited by 17 publications

References 39 publications

Method for predicting the remaining mileage of electric vehicles based on dimension expansion and model fusion

Method for predicting the remaining mileage of electric vehicles based on dimension expansion and model fusion

Novel Harmonic Prediction and Power Quality Improvementusing Intelligent Hybrid Strategies for Grid Coordinated System

Coulomb Counting Estimator of Battery State of Charge Under Variable Discharge Current

Contact Info

Product

Resources

About