Electric vehicle energy consumption prediction using stacked generalization: an ensemble learning approach

Ullah, Irfan; Liu, Kai; Yamamoto, Toshiyuki; Zahid, Muhammad; Jamal, Arshad

doi:10.1080/15435075.2021.1881902

Cited by 77 publications

(26 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The lowest MAE, RMSE, and MAPE values preferred the better model efficacy. 56 The highest value of R 2 (closer to 1) exhibits an accurate prediction model. 57 4 | MODELING RESULT…”

Section: Algorithm' Accuracy Measurementsmentioning

confidence: 89%

Prediction of electric vehicle charging duration time using ensemble machine learning algorithm and Shapley additive explanations

Ullah

Liu

Yamamoto

et al. 2022

Intl J of Energy Research

Self Cite

View full text Add to dashboard Cite

Summary Electric vehicles (EVs) are the most important components of smart transportation systems. Limited driving range, prolonged charging times, and inadequate charging infrastructure are the key barriers to EV adoption. To address the problem of prolonged charging time, the simple approach of developing a new charging station to enhance the charging capacity may not work due to the limitation of physical space and strain on power grids. Prediction of precise EV charging time can assist the drivers in effective planning of their trips to alleviate range anxiety during trips. Therefore, this study employed four different ensemble machine learning (EML) algorithms: random forest, extreme gradient boosting (XGBoost), categorical boosting, and light gradient boosting machine, for predicting EVs' charging time. The prediction experiments were based on 2 years of real‐world charging event data from 500 EVs in Japan's private and commercial vehicles. The study emphasized predicting charging time for different charging modes, that is, normal and fast charging operations. The results indicate that EML models performed well under various scenarios, with the XGBoost model having the highest accuracy. Moreover, we also employ the newly developed Shapley additive explanation (SHAP) approach to tackle the non‐interpretability issues of the ML algorithm by interpreting the XGBoost model outputs. The obtained SHAP value plots demonstrated the nonlinear relationship between explanatory variables and EV charging time.

show abstract

“…The lowest MAE, RMSE, and MAPE values preferred the better model efficacy. 56 The highest value of R 2 (closer to 1) exhibits an accurate prediction model. 57 4 | MODELING RESULT…”

Section: Algorithm' Accuracy Measurementsmentioning

confidence: 89%

Prediction of electric vehicle charging duration time using ensemble machine learning algorithm and Shapley additive explanations

Ullah

Liu

Yamamoto

et al. 2022

Intl J of Energy Research

Self Cite

View full text Add to dashboard Cite

show abstract

“…Nevertheless, this development is not sustainable in the absence of social and environmental problems caused by CO 2 and global warming (Jayaraman et al, 2012). Companies nowadays are implementing environmentally friendly practices in their operational systems, such as green storage, green sourcing, green transportation, ecological product design and green distribution to enhance economic, social and environmental sustainability (Ullah et al, 2021a(Ullah et al, , 2021bRehman Khan and Yu, 2021). Under the Supply chain, there has been much discussion about the correlation between energy demand and logistics.…”

Section: Literature Review and Hypothesesmentioning

confidence: 99%

Dynamic association between socio-economic, environmental and logistic operations: Evidence from SSA BRI host countries

Aden

Zheng²,

Almoshaogeh³

et al. 2022

Front. Environ. Sci.

Self Cite

View full text Add to dashboard Cite

This study examines the connection among green logistic operations, countries-level economic, environmental, and social indicators in Sub-Saharan Africa (SSA) Belt and Road Countries. Using the system generalized method of moments (S-GMM) estimator, this study analyses annual data from 2008 to 2018 and offers three key findings. First, economic indicators China’s foreign direct investment (FDI), trade openness and economic output) are positively associated with green logistic operations. Second, logistics are positively correlated with renewable energy while inversely correlated with carbon emissions. Third, social indicators are also directly associated with green logistic operations measured through health expenditure and institutional quality. Lastly, information communication technology also spurs green logistic operations. Manifestly, Chinese outbound FDI in SSA substantially improved the quality of their logistics in terms of infrastructure, cost, time, customs services, tracking, and the consistency of international shipments. These findings show that green logistics provide adequate infrastructure, and supply chain partners share information more frequently, increasing trade volume, growth potential, and environmental sustainability. Similar results are also endorsed using a feasible generalized least square (FGLS) estimator and suggest that SSA should take effective measures to improve their logistics operation.

show abstract

“…Frendo et al [23] take this process one step further and examine the behaviour of an entire fleet and additionally provide an extensive literature review in their particular field. The complimentary challenge of trying to predict energy consumption while the vehicle is on the road is also being tackled using very similar methods [24,25].…”

Section: Literature Reviewmentioning

confidence: 99%

Predicting Electric Vehicle Charging Station Availability Using Ensemble Machine Learning

2021

View full text Add to dashboard Cite

Electric vehicles may reduce greenhouse gas emissions from individual mobility. Due to the long charging times, accurate planning is necessary, for which the availability of charging infrastructure must be known. In this paper, we show how the occupation status of charging infrastructure can be predicted for the next day using machine learning models— Gradient Boosting Classifier and Random Forest Classifier. Since both are ensemble models, binary training data (occupied vs. available) can be used to provide a certainty measure for predictions. The prediction may be used to adapt prices in a high-load scenario, predict grid stress, or forecast available power for smart or bidirectional charging. The models were chosen based on an evaluation of 13 different, typically used machine learning models. We show that it is necessary to know past charging station usage in order to predict future usage. Other features such as traffic density or weather have a limited effect. We show that a Gradient Boosting Classifier achieves 94.8% accuracy and a Matthews correlation coefficient of 0.838, making ensemble models a suitable tool. We further demonstrate how a model trained on binary data can perform non-binary predictions to give predictions in the categories “low likelihood” to “high likelihood”.

show abstract

Electric vehicle energy consumption prediction using stacked generalization: an ensemble learning approach

Cited by 77 publications

References 65 publications

Prediction of electric vehicle charging duration time using ensemble machine learning algorithm and Shapley additive explanations

Prediction of electric vehicle charging duration time using ensemble machine learning algorithm and Shapley additive explanations

Dynamic association between socio-economic, environmental and logistic operations: Evidence from SSA BRI host countries

Predicting Electric Vehicle Charging Station Availability Using Ensemble Machine Learning

Contact Info

Product

Resources

About