What question did this study set out to answer?

This research aims to evaluate the effectiveness of various machine learning models for forecasting electricity demand in a smart grid context.

July 14, 2026Open Access

Machine Learning-Based Electricity Load Forecasting for Smart Grid Energy Management: A Comparative Study Using Austrian Demand Data

View Full Paper

Ask AI

Bookmark

Authors

BEBaudwin Antsebe Aje EzieUniversity of Buea

Discussion

Member takes

Implication

Randomized trial compares machine learning models for electricity demand forecasting in Austria, demonstrating superior accuracy of tree-based methods.

Key Points

This research aims to evaluate the effectiveness of various machine learning models for forecasting electricity demand in a smart grid context.
Developed four machine learning models: Linear Regression, Support Vector Regression, Random Forest, and Extreme Gradient Boosting.
Analyzed four years of hourly demand and generation data from Austria, totaling 35,000 observations.
Evaluated model performance using metrics such as MAE, RMSE, MAPE, and R² across different forecast horizons.
XGBoost demonstrated the best performance with MAE of 195.29 MW, RMSE of 243.71 MW, MAPE of 2.38%, R² of 0.9617.
Random Forest followed with a MAPE of 3.20% and R² of 0.9178.
Linear Regression and SVR had significantly higher errors with MAPEs of 15.90% and 14.98%, indicating ineffective forecasting capabilities.

Cite This Study

Baudwin Antsebe Aje Ezie (2026) studied this question.

synapsesocial.com/papers/6a55d16e5aafca87247f86d3 https://doi.org/10.5281/zenodo.21325065

View Full Paper

Ask AI

Bookmark

Implication

Randomized trial compares machine learning models for electricity demand forecasting in Austria, demonstrating superior accuracy of tree-based methods.

Machine Learning-Based Electricity Load Forecasting for Smart Grid Energy Management: A Comparative Study Using Austrian Demand Data

Discussion

Member takes

Implication

Key Points

Cite This Study

Machine Learning-Based Electricity Load Forecasting for Smart Grid Energy Management: A Comparative Study Using Austrian Demand Data

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider