Electric Vehicle Charging Station Load Forecasting and Impact of the Load Curve

Jian, Wang; Wu, Kui; Wang, Feng; Li, Zhi Hui; Niu, Qing Song; Liu, Zhi Zhen

doi:10.4028/www.scientific.net/amm.229-231.853

Cited by 5 publications

(6 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The OCC can reduce the peak-valley difference and improve voltage quality [10]. However, since the EV charging load fluctuates greatly and is related to the temperature and weather factors of the day, this makes the OCC difficult [11]. Therefore, it is necessary to study the load prediction method of the charging station, which provides support for OCC.…”

mentioning

confidence: 99%

RETRACTED: Blockchain-Enabled Charging Right Trading Among EV Charging Stations

et al. 2019

View full text Add to dashboard Cite

Increasing penetration of electric vehicles (EVs) gives rise to the challenges in the secure operation of power systems. The EV charging loads should be distributed among charging stations in a fair and incentive-compatible manner while ensuring that power transmission and transformation facilities are not overloaded. This paper first proposes a charging right (or charging power ration) trading mechanism and model based on blockchain. Considering all kinds of random factors of charging station loads, we use Monte Carlo modeling to determine the charging demand of charging stations in the future. Based on the charging demand of charging stations, a charging station needs to submit the charging demand for a future period. The blockchain first distributes initial charging right in a just manner and ensures the security of facilities. Given that the charging urgency and elasticity differences vary by charging stations, all charging stations then proceed with double auction and peer-to-peer (P2P) transaction of charging right. Bids and offers are cleared via double auctions if bids are higher than offers. The remaining bids and offers are cleared via the P2P market. Then, this paper designs the charging right allocation and trading platform and smart contract based on the Ethernet blockchain to ensure the safety of the distribution network (DN) and the transparency and efficiency of charging right trading. Simulation results based on the Ethereum private blockchain show the fairness and efficiency of the proposed mechanism and the effectiveness of the method and the mechanism.

show abstract

mentioning

confidence: 99%

RETRACTED: Blockchain-Enabled Charging Right Trading Among EV Charging Stations

et al. 2019

View full text Add to dashboard Cite

show abstract

“…References [19] and [20] discuss the prediction of the EV charging profile while taking into account various sources of data, such as vehicle driving and usage data. The authors in [21] and [22] consider forecasting at the charging station level based on the EV user classification and Monte Carlo simulations method. Reference [33] discusses an energy management system for EVs that takes advantage of prediction in different levels through hierarchical model predictive control.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Extensive research has focused on EV charging algorithms and charging station infrastructures [7]- [10], and as a next step, EV-related research has started to utilize forecasting algorithms [16]- [22]. Some papers apply forecasting algorithms to EV driving habits and predict the state of charge (SOC) of a particular EV and when it needs to be charged [17], [18].…”

Section: Literature Reviewmentioning

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.

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

“…There is a rich literature on different methods of time series prediction evolved from statistics, mathematics, computer science, economics, and engineering [9]- [11]. EV related research has started to utilize the forecasting algorithms [12]- [18]. Some papers apply forecasting algorithms to EV driving habits and predict the State of Charge (SOC) of a particular EV and when it needs to be charged [13], [14].…”

Section: Introductionmentioning

confidence: 99%

“…Reference [15] and [16] discuss the prediction of the EV charging profile while taking into account various sources of data, such as vehicle driving/usage data. Authors in [17], [18] consider forecasting at the charging station level based on the EV user classification and Monte Carlo simulations method.…”

Section: Introductionmentioning

confidence: 99%

Fast demand forecast of Electric Vehicle Charging Stations for cell phone application

Majidpour

Qiu

Chung

et al. 2014

2014 IEEE PES General Meeting | Conference &Amp; Exposition

View full text Add to dashboard Cite

This paper describes the core cellphone application algorithm which has been implemented for the prediction of energy consumption at Electric Vehicle (EV) Charging Stations at UCLA. For this interactive user application, the total time of accessing database, processing the data and making the prediction, needs to be within a few seconds. We analyze four relatively fast Machine Learning based time series prediction algorithms for our prediction engine: Historical Average, kNearest Neighbor, Weighted k-Nearest Neighbor, and Lazy Learning. The Nearest Neighbor algorithm (k Nearest Neighbor with k=1) shows better performance and is selected to be the prediction algorithm implemented for the cellphone application. Two applications have been designed on top of the prediction algorithm: one predicts the expected available energy at the station and the other one predicts the expected charging finishing time. The total time, including accessing the database, data processing, and prediction is about one second for both applications.

show abstract

Electric Vehicle Charging Station Load Forecasting and Impact of the Load Curve

Cited by 5 publications

References 7 publications

RETRACTED: Blockchain-Enabled Charging Right Trading Among EV Charging Stations

RETRACTED: Blockchain-Enabled Charging Right Trading Among EV Charging Stations

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

Fast demand forecast of Electric Vehicle Charging Stations for cell phone application

Contact Info

Product

Resources

About