Deep Learning Based Electrical Demand Forecasting for Smart Grids

DOI

10.2991/978-94-6239-654-8_34How to use a DOI?

Keywords

Electrical Demand Forecasting; Smart Grids; Convolutional Neural Network; Multi Energy Predictive

Abstract

The Smart Grid plays an important role in global energy demands by participating in multiple power sources across modern transmission networks. Energy forecasting is important in analysing and predicting electrical load demand, and it regularly applies arithmetical models and past data to the grid. Previous Smart Grid-based machine learning approaches face challenges such as power losses in converters and output load distortions. To solve a problem, a novel Convolutional Neural Network (CNN) background and a Multi Energy Predictive (MEP) algorithm for specific energy demand forecasting within Smart Grid environments. The proposed procedure starts with data preprocessing, where the data file from the CSV file is characterized by active, adaptive, and facts-driven based on specific parameters corresponding to different appliances. In the second step, feature selection detects the amount of power, irregular input power, and variations of dependability in grid energy management. These features are independently trained on a dedicated training dataset and validated against a test dataset to ensure performance reliability. In the third step, CNNs continuously evaluate electrical parameters such as load demand and load faults in the innovative grid system, and the MEP approach is used for electricity demand prediction created on the test data. The simulation results validate the test data access in forecasting, enhancing energy distribution, optimizing grid performance, and supporting advanced data in innovative grid management strategies.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - R. Raguraman
AU  - K. Sakthivel
PY  - 2026
DA  - 2026/04/24
TI  - Deep Learning Based Electrical Demand Forecasting for Smart Grids
BT  - Proceedings of the Global Conference on Sustainable Energy Systems, Smart Electronics and Intelligent Computing (GCSESEIC 2025)
PB  - Atlantis Press
SP  - 413
EP  - 428
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6239-654-8_34
DO  - 10.2991/978-94-6239-654-8_34
ID  - Raguraman2026
ER  -