An AI-Powered Hybrid Framework for Load Forecasting and Fault Diagnosis in Smart Grids Using LSTM and CNN–LSTM Models

Akshay Suryavanshi; Nivedita Singh

doi:10.36948/ijfmr.2026.v08i01.67101

An AI-Powered Hybrid Framework for Load Forecasting and Fault Diagnosis in Smart Grids Using LSTM and CNN–LSTM Models

Author(s)	Mr. Akshay Suryavanshi, Prof. Dr. Nivedita Singh
Country	India
Abstract	The increasing penetration of renewable energy resources and the growing complexity of distribution networks have significantly challenged the reliability and operational stability of modern smart grids. Traditional analytical and protection mechanisms are often inadequate for handling nonlinear load patterns, evolving transient disturbances, and early-stage grid anomalies. To address these limitations, this paper proposes an integrated AI-powered hybrid framework that combines Long Short-Term Memory (LSTM) networks for short-term load forecasting, a Convolutional Neural Network–Long Short-Term Memory (CNN–LSTM) hybrid model for fault detection and classification, and an Autoencoder for anomaly identification. The proposed system performs multi-stage learning, capturing both temporal dependencies and transient waveform signatures for improved predictive and diagnostic performance. Experimental evaluations conducted using synthetic and MATLAB-generated data demonstrate that the LSTM model achieves an RMSE of 18.35 kW in 24-hour forecasting, outperforming conventional machine learning models. The hybrid CNN–LSTM classifier achieves a fault classification accuracy of 97.68%, significantly improving robustness under noisy and high-impedance conditions. The integrated framework enhances situational awareness and enables early detection of operational risks, thus contributing to improved grid reliability and resilience. The results confirm the feasibility of deploying AI-driven diagnostic architectures in next-generation smart grid ecosystems
Keywords	Smart grid, LSTM, CNN–LSTM, load forecasting, fault diagnosis, anomaly detection, deep learning, renewable energy, hybrid AI model, power system reliability.
Field	Engineering
Published In	Volume 8, Issue 1, January-February 2026
Published On	2026-01-22
DOI	https://doi.org/10.36948/ijfmr.2026.v08i01.67101

View / Download PDF File

E-ISSN 2582-2160

doi

CrossRef DOI is assigned to each research paper published in our journal.

IJFMR DOI prefix is
10.36948/ijfmr

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 8 Isu 2 Cover Page Vol 8 Isu 1 Cover Page Vol 7 Isu 6

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

An AI-Powered Hybrid Framework for Load Forecasting and Fault Diagnosis in Smart Grids Using LSTM and CNN–LSTM Models

Share this