As urban areas increasingly favor underground cables over traditional overhead transmission lines due to their numerous advantages, such as reduced line losses and better resilience to adverse weather conditions, the need to effectively detect and address potential shortcomings becomes paramount. With India’s rapid progress and growing reliance on underground lines, there arises a pressing need for innovative solutions to streamline fault detection processes. In response, this paper proposes a novel approach that harnesses the power of Internet of Things (IoT) technology in conjunction with Google’s extensive database infrastructure for fault detection in underground cable systems. Our method integrates state-of-the-art deep learning models, including Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), to enhance fault detection accuracy and efficiency. Through extensive experimentation, our results demonstrate that the incorporation of CNNs and RNNs significantly improves both the accuracy and efficiency of fault detection compared to traditional techniques. By leveraging IoT capabilities, Google’s database, and deep learning methodologies, our proposed approach offers a comprehensive solution for fault detection in underground cable systems, thereby contributing to the advancement and reliability of urban infrastructure.