A novel forecasting algorithm for electric vehicle charging stations

Majidpour, Mostafa; Qiu, Charlie; Chu, Pao-Hsien; Gadh, Rajit; Pota, H. R.

doi:10.1109/iccve.2014.7297504

Cited by 24 publications

(18 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The predictive model was integrated to a cell phone application that can predict the end time of charging and the available energy in about 1 second. Various ML algorithms were utilized in [62] with the goal of predicting the energy needs at a charging outlet in the next 24 hours. Among the ML algorithms used was pattern sequence-based forecasting (PSF) [63], which works by first classifying the days using clustering before making predictions for that day.…”

Section: Supervised Learning For Analysis and Prediction Of Charmentioning

confidence: 99%

“…Ensembled model using RF, Naïve Bayes, AdaBoost and Gradient boosting TPR for predicting whether the EVs will be charged: 0.996, Accuracy for predicting the hours when the EVs will be charged: 0.724 [61] Predict energy consumption at a charging outlet in a university campus (non-residential) KNN, Best model was with k set to 1 (1-NN) SMAPE: 15.27%. The predictive model integrated to a mobile application can predict the end charging time and energy in 1 second [62] Predict the energy needs at a charging outlet in the next 24 hours for a university campus…”

Section: Svmsmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning Approaches for EV Charging Behavior: A Review

et al. 2020

View full text Add to dashboard Cite

As the smart city applications are moving from conceptual models to development phase, smart transportation is one of smart cities applications and it is gaining ground nowadays. Electric Vehicles (EVs) are considered one of the major pillars of smart transportation applications. EVs are ever growing in popularity due to their potential contribution in reducing dependency on fossil fuels and greenhouse gas emissions. However, large-scale deployment of EV charging stations poses multiple challenges to the power grid and public infrastructure. To overcome the issue of prolonged charging time, the simple solution of deploying more charging stations to increase charging capacity does not work due to the strain on power grids and physical space limitations. Therefore, researchers have focused on developing smart scheduling algorithms to manage the demand for public charging using modeling and optimization. More recently, there has been a growing interest in data-driven approaches in modeling EV charging. Consequently, researchers are looking to identify consumer charging behavior pattern that can provide insights and predictive analytics capability. The purpose of this paper is to provide a comprehensive review for the use of supervised and unsupervised Machine Learning as well as Deep Neural Networks for charging behavior analysis and prediction. Recommendations and future research directions are also discussed.

show abstract

Section: Supervised Learning For Analysis and Prediction Of Charmentioning

confidence: 99%

Section: Svmsmentioning

confidence: 99%

Machine Learning Approaches for EV Charging Behavior: A Review

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Other state-of-the-art methods which have been applied on this same data take substantially more time. Specifically, depending on the parameter selection process, support vector regression and random forest take, respectively, 3900 and 306 s to produce the results [38].…”

Section: Introductionmentioning

confidence: 99%

Fast Prediction for Sparse Time Series: Demand Forecast of EV Charging Stations for Cell Phone Applications

Majidpour

Qiu

Chu

et al. 2015

IEEE Trans. Ind. Inf.

Self Cite

View full text Add to dashboard Cite

This paper proposes a new cellphone application algorithm which has been implemented for the prediction of energy consumption at electric vehicle (EV) charging stations at the University of California, Los Angeles (UCLA). For this interactive user application, the total time for accessing the database, processing the data, and making the prediction needs to be within a few seconds. We first analyze three relatively fast machine learning-based time series prediction algorithms and find that the nearest neighbor (NN) algorithm (k NN with k = 1) shows better accuracy. Considering the sparseness of the time series of the charging records, we then discuss the new algorithm based on the new proposed time-weighted dot product (TWDP) dissimilarity measure to improve the accuracy and processing time. Two applications have been designed on top of the proposed prediction algorithm: one predicts the expected available energy at the outlet and the other one predicts the expected charging finishing time. The total time, including accessing the database, data processing, and prediction is approximately 1 s for both applications. The granularity of the prediction is 1 h and the horizon is 24 h; data have been collected from 20 EV charging outlets.

show abstract

“…To this end, we have chosen Symmetric Mean Absolute Percentage Error (SMAPE). For day i, the SMAPE is defined as: (2) where is the horizon of prediction in a given day ( =24 in this paper).…”

Section: Problem Formulationmentioning

confidence: 99%

“…These data, when used for different analysis in utility or public charging station operation or planning, might expose information such as the pattern of entrance and exit times of the customers from charging lots or their home, hence risking their privacy. To exemplify the battery size, consider Chevrolet Volt, Nissan Leaf, and Tesla, with a battery size of 16.5 kWh, 24kWh, and up to 85kWh, respectively [2]. With Level 1 household chargers (16A at 230VAC which delivers 3.3 kW) it will take the Nissan Leaf around 8 hours, and Tesla (Model S85) around 25 hours to charge completely.…”

Section: Introductionmentioning

confidence: 99%

Forecasting the EV charging load based on customer profile or station measurement?

et al. 2016

Self Cite

View full text Add to dashboard Cite

In this paper, forecasting of the Electric Vehicle (EV) charging load has been based on two different datasets: data from the customer profile (referred to as charging record) and data from outlet measurements (referred to as station record). Four different prediction algorithms namely Time Weighted Dot Product based Nearest Neighbor (TWDP-NN), Modified Pattern Sequence Forecasting (MPSF), Support Vector Regression (SVR), and Random Forest (RF) are applied to both datasets. The corresponding speed, accuracy, and privacy concerns are compared between the use of the charging records and station records. Real world data compiled at the outlet level from the UCLA campus parking lots are used. The results show that charging records provide relatively faster prediction while putting customer privacy in jeopardy. Station records provide relatively slower prediction while respecting the customer privacy. In general, we found that both datasets generate comparable prediction error.

show abstract

A novel forecasting algorithm for electric vehicle charging stations

Cited by 24 publications

References 17 publications

Machine Learning Approaches for EV Charging Behavior: A Review

Machine Learning Approaches for EV Charging Behavior: A Review

Fast Prediction for Sparse Time Series: Demand Forecast of EV Charging Stations for Cell Phone Applications

Forecasting the EV charging load based on customer profile or station measurement?

Contact Info

Product

Resources

About