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{174405,
        author = {A. Poorna Sharmila},
        title = {Adversarial Autoencoder-Based Cyber-Attack Detection in Smart Power Distribution Grids with Renewable Energy Integration},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {10},
        pages = {4038-4043},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=174405},
        abstract = {The key aspect for sustainable development comes from implementing renewable energy while handling urban planning projects. The research introduces an information-based machinery that uses neural networks and deep learning approaches to optimize urban-based power distribution networks. Before identifying cyber-attack patterns against power systems, the study implements a CNN-LSTM model to encode traffic networks. Its ability to find weaknesses in smart grids coupled with enhanced cyber security protection enables the suggested framework to achieve effective energy control functions. This research explores blockchain through its ability to protect energy transactions and deny unauthoritative access. The detailed urban energy planning approach exists from combining smart grid monitoring systems with real-time analysis of data through AI- based forecasting tools as explained throughout this paper. Furthermore, the integration of deep learning models enhances anomaly detection by capturing spatial and temporal dependencies within network traffic data. The adversarial autoencoder (AAE)-based framework strengthens cybersecurity by reconstructing input patterns and identifying deviations caused by malicious intrusions. By leveraging CNN for spatial feature extraction and LSTM for sequential pattern recognition, the system effectively detects False Data Injection Attacks (FDIAs) and other cyber threats in real time.},
        keywords = {Renewable energy, urban planning, smart grids, deep learning, CNN-LSTM, cyber-attack detection, Hybrid Deep Learning Models, False Data Injection Attacks, Energy Management Systems.},
        month = {March},
        }