In this paper, five imputation methods namely Constant (zero), Mean, Median, Maximum Likelihood, and Multiple Imputation methods have been applied to compensate for missing values in Electric Vehicle (EV) charging data. The outcome of each of these methods have been used as the input to a prediction algorithm to forecast the EV load in the next 24 hours at each individual outlet. The data is real world data at the outlet level from the UCLA campus parking lots. Given the sparsity of the data, both Median and Constant (=zero) imputations improved the prediction results. Since in most missing value cases in our database, all values of that instance are missing, the multivariate imputation methods did not improve the results significantly compared to univariate approaches.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Incomplete data in smart grid: Treatment of missing values in electric vehicle charging data


    Contributors:


    Publication date :

    2014-11-01


    Size :

    175097 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Electric Vehicle Charging Control Based on Smart Grid Big Data

    Chang, Kuo-Chi / Xu, Ze / Chu, Kai-Chun et al. | IEEE | 2020


    Electric Vehicle Smart Charging For Demand Response Participation For An Electric Grid

    WANG ZHENYUAN / LIU KAIYU | European Patent Office | 2025

    Free access

    Electric vehicle charging and discharging facility based on smart power grid

    ZHANG WENLONG | European Patent Office | 2021

    Free access

    ELECTRIC VEHICLE SMART CHARGING STATIONS

    PROSSERMAN JEFFREY / VICARI JOERN / VALLEJO ALEJANDRO | European Patent Office | 2022

    Free access

    Electric Vehicle Smart Charging Stations

    VICARI JOERN / PROSSERMAN JEFFREY / VALLEJO ALEJANDRO | European Patent Office | 2024

    Free access