Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{177638,
        author = {Aadarsh K Hareendran and Dr. Devaraj Verma C and Vyshnav Kumar P and Vinayak CM and Deepshik Sharma},
        title = {AI-DRIVEN LOAD FORECASTING IN SMART GRIDS},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {1148-1153},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=177638},
        abstract = {Effective predictions are essential to ensure operational stability, economic efficiency and stability of modern intellectual networks. Traditional predictive models often have no opportunity to accurately capture complex patterns in energy consumption data, especially dynamic and nonlinear conditions. This article takes into account the use of a machine learning method (ML) including a network including a linear regression, a support for vector regression (SVR), a network of short -term memory (LSTM) for predicting loads of random forests and electricity. The performance of each model using a set of data consumption of household energy is evaluated using standard accuracy indicators. The result shows that the LSTM network exceeds the traditional approach, especially when recognizing temporary models and peak requirements. These results emphasize the potential of a method based on artificial intelligence, enhancing the decision -making and reliability of the intellectual network, and packing the route that is more adaptive and controlled by the energy consumption management strategy.},
        keywords = {Smart Grid, Load Forecasting, Machine Learning (ML), Long Short-Term Memory (LSTM), Energy Consumption Prediction},
        month = {May},
        }