Research on BiLSTM Model-Based IoT Device Fingerprint Recognition in Power Grid Systems

The Internet of Things (IoT) smart devices IoT devices are widely used in power grid systems. Combining IoT with fingerprint recognition enhances device security, personalizes authentication, and improves user experience, ensuring authorized access and protecting sensitive data in the interconnected landscape. However, traditional approaches based on machine learning or deep learning for IoT device traffic identification suffer from various issues, such as the need for manual feature extraction, resulting in low training and detection efficiency. To address these challenges, this paper proposes a traffic recognition scheme based on BiLSTM (Bidirectional Long Short-Term Memory) method. This approach leverages temporal features and fully considers bidirectional temporal information, significantly improving the identification performance of IoT devices. By using this method, the traffic generated by IoT devices during operation can be effectively recognized, providing strong support for the further development and application of smart devices. Compared to mainstream deep learning algorithms, the BiLSTM algorithm achieves favorable detection results in terms of precision, recall, and F1-Score.