The Industrial Internet of Things (IIoT) revolutionizes both industrial and residential operations by integrating AI (artificial intelligence)-driven analytics with real-time monitoring, optimizing energy usage, and significantly enhancing energy efficiency. This study proposes a secure IIoT framework that simultaneously predicts both active and reactive loads while also incorporating anomaly detection. The system is optimized for real-time deployment on an edge server, such as a single-board computer (SBC), as well as on a cloud or centralized server. It ensures secure and reliable industrial operations by integrating smart data acquisition systems with real-time monitoring, control, and protective measures. We propose a Temporal Convolutional Networks-Gated Recurrent Unit-Attention (TCN-GRU-Attention) model to predict both active and reactive loads, which demonstrates superior performance compared to other conventional models. The performance metrics for active load forecasting are 0.0183 Mean Squared Error (MSE), 0.1022 Mean Absolute Error (MAE), and 0.1354 Root Mean Squared Error (RMSE), while for reactive load forecasting, the metrics are 0.0202 (MSE), 0.1077 (MAE), and 0.1422 (RMSE). Furthermore, we introduce an optimized Isolation Forest model for anomaly detection that considers the transient conditions of appliances when identifying irregular behavior. The model demonstrates very promising performance, with the average performance metrics for all appliances using this Isolation Forest model being 95% for Precision, 98% for Recall, 96% for F1 Score, and nearly 100% for Accuracy. To secure the entire system, Transport Layer Security (TLS) and Secure Sockets Layer (SSL) security protocols are employed, along with hash-encoded encrypted credentials for enhanced protection.

With the increasing use of lithium-ion (Li-ion) batteries in electric vehicles (EVs), accurately measuring the state of charge (SoC) has become crucial for ensuring battery reliability, performance, and safety. In addition, EVs operate in different environmental conditions with different driving styles, which also cause inaccurate SoC estimation resulting in reduced reliability and performance of battery management systems (BMSs). To address this issue, this work proposes a new hybrid method that integrates a gated recurrent unit (GRU), temporal convolution network (TCN), and attention mechanism. The TCN and GRU capture both long-term and short-term dependencies and the attention mechanism focuses on important features within input sequences, improving model efficiency. With inputs of voltage, current, and temperature, along with their moving average, the hybrid GRU-TCN-Attention (GTA) model is trained and tested in a range of operating cycles and temperatures. Performance metrics, including average RMSE (root mean squared error), MAE (mean absolute error), MaxE (maximum error), and $R^2$ score indicates the model is performing well, with average values of 0.512%, 0.354%, 1.98%, and 99.94%, respectively. The proposed model performs well under both high and low noise conditions, with an RMSE of less than 2.18%. The proposed hybrid approach is consistently found to be superior when compared against traditional baseline models. This work offers a potential method for accurate SoC estimation in Li-ion batteries, which has an important impact on clean energy integration and battery management systems in EVs.

Visible light communication (VLC) has emerged as a promising wireless communication technology, utilizing light-emitting diodes for high-speed data transmission. While VLC offers advantages such as high bandwidth, energy efficiency, and enhanced security, it faces several limitations, including noise, environmental interference, signal blockage, and the requirement for a direct line of sight. Machine learning (ML) and deep learning (DL) have been widely explored in VLC applications to address these challenges and improve system adaptability. This survey comprehensively reviews ML and DL techniques in VLC systems, focusing on key areas such as channel estimation, noise mitigation, modulation classification, and symbol detection. Furthermore, the contributions of DL in advanced VLC systems, such as intelligent reflecting surface-assisted MIMO and non-orthogonal multiple access-aided VLC systems, are described. Additionally, this review highlights the role of ML and DL in hybrid VLC/RF systems, focusing on resource management and dynamic network selection. The details of DL-based localization for indoor VLC systems are also discussed. The implementation of DL in image sensor-based VLC systems is highlighted for both indoor and outdoor vehicular applications. Four major search engines—Google Scholar, Science Direct, Web of Science, and IEEE Xplore—were used to identify and evaluate quantitative studies. This review emphasizes five key aspects: model architectures, modulation techniques, channel models, model performance, and the contributions or applications of each algorithm. Finally, we highlight future research directions and unresolved challenges, emphasizing the integration of ML/DL for security in the VLC systems, intelligent networking, and real-time adaptive control. This survey aims to provide valuable insights into the role of ML and DL in enhancing the efficiency and reliability of next-generation VLC systems.

The Internet of Things (IoT) is transforming industries by integrating sensors and connectivity into everyday objects, enabling enhanced monitoring, management, and automation through Machine-to-Machine (M2M) communication. Despite these advancements, the IoT faces limitations in accurately predicting environmental conditions and power consumption. This study proposes an advanced IoT platform that combines real-time data collection with secure transmission and forecasting using a hybrid Long Short-Term Memory (LSTM)–Gated Recurrent Unit (GRU) model. The hybrid architecture addresses the computational inefficiencies of LSTM and the short-term dependency challenges of GRU, achieving improved accuracy and efficiency in time-series forecasting. For all prediction use cases, the model achieves a Maximum Mean Absolute Error (MAE) of 3.78%, Root Mean Square Error (RMSE) of 8.15%, and a minimum $R^2$ score of 82.04%, the showing proposed model’s superiority for real-life use cases. Furthermore, a comparative analysis also shows the performance of the proposed model outperforms standalone LSTM and GRU models, enhancing the IoT’s reliability in real-time environmental and power forecasting.