• CHEBOLU SRIVALLI
• K. T. KRISHNA KUMAR

This project aims to improve the accuracy of Short-Term Load Forecasting (STLF) by evaluating and comparing machine learning algorithms such as Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Logistic Regression (LR), Decision Tree Classifier (DTC), and Neural Networks (NN), while addressing the limitations of conventional decision trees, which often face overfitting and poor generalization in large or noisy datasets. To overcome these challenges, an Enhanced Decision Tree Classifier (EDTC) integrating Gradient Boosting techniques is proposed, combining the interpretability of decision trees with the powerful learning capacity of boosting for more accurate and stable predictions across varying load patterns. The models are trained and validated on real-world electricity consumption data enriched with temporal and seasonal features, with performance measured using metrics such as RMSE, MAPE, and R², along with assessments of robustness and efficiency. Results show that the EDTC consistently outperforms baseline models in both accuracy and reliability, highlighting its potential as a practical tool for short-term energy demand forecasting that supports cost reduction, operational stability, and data-driven decision-making in modern power systems.

Short-Term Load Forecasting, Machine Learning, Gradient Boosting, Enhanced Decision Tree, Energy Demand.

"A Performance Comparison of Machine Learning Algorithms for Load Forecasting in Smart Grid", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 9, page no.e785-e793, September-2025, Available :http://www.jetir.org/papers/JETIR2509494.pdf

"A Performance Comparison of Machine Learning Algorithms for Load Forecasting in Smart Grid", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 9, page no. ppe785-e793, September-2025, Available at : http://www.jetir.org/papers/JETIR2509494.pdf