Home / Current Issue / Paper 1717866
A Random Forest-Based Approach for Hourly Electric Vehicle Charging Energy Consumption Forecasting
Subject area: Science,Engineering and Technology · Area of research: Computer Science /Machine Learning
DOI: https://doi.org/10.64388/IREV9I11-1717866
Abstract
The rapid growth in the adoption of electric vehicles (EVs) has increased the need for efficient management of EV charging demand and stable power grid operation. accurate forecasting of EV charging energy consumption is essential for smart grid management and charging infrastructure planning. existing forecasting approaches are commonly based on statistical techniques or deep learning models; however, many of these methods require large datasets, high computational resources, or lack interpretability. this paper presents a random forest-based approach for forecasting hourly EV charging energy consumption. the implemented framework utilizes temporal features and vehicle count information to predict hourly charging demand. the dataset was preprocessed and aggregated at an hourly level to capture variations in charging behavior over time. experimental results demonstrate that the random forest model is capable of capturing EV charging demand patterns and provides reasonable prediction accuracy for hourly energy consumption forecasting.
Keywords
Electric Vehicles, Charging Demand Forecasting, Machine Learning, Random Forest, Energy Consumption Prediction, Vehicle Count Feature, Hourly Load Forecasting, Smart Grid
How to cite this paper
@article{1717866,
author = {Mazama-Esso Yaovi Moddoh Ocloo, Dr. V Haripriya},
title = {A Random Forest-Based Approach for Hourly Electric Vehicle Charging Energy Consumption Forecasting},
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {9},
number = {11},
pages = {2185-2192},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1717866.pdf},
abstract = {The rapid growth in the adoption of electric vehicles (EVs) has increased the need for efficient management of EV charging demand and stable power grid operation. accurate forecasting of EV charging energy consumption is essential for smart grid management and charging infrastructure planning. existing forecasting approaches are commonly based on statistical techniques or deep learning models; however, many of these methods require large datasets, high computational resources, or lack interpretability. this paper presents a random forest-based approach for forecasting hourly EV charging energy consumption. the implemented framework utilizes temporal features and vehicle count information to predict hourly charging demand. the dataset was preprocessed and aggregated at an hourly level to capture variations in charging behavior over time. experimental results demonstrate that the random forest model is capable of capturing EV charging demand patterns and provides reasonable prediction accuracy for hourly energy consumption forecasting.},
keywords = {Electric Vehicles, Charging Demand Forecasting, Machine Learning, Random Forest, Energy Consumption Prediction, Vehicle Count Feature, Hourly Load Forecasting, Smart Grid},
month = {May},
doi = {https://doi.org/10.64388/IREV9I11-1717866}
}