Ali Teta

Occupancy detection plays a pivotal role in optimizing energy consumption, enhancing occupant comfort, and enabling intelligent decision-making in smart building environments. While traditional centralized learning methods often compromise user privacy and scalability, federated learning (FL) offers a promising privacy-preserving alternative. In this study, we propose Federated Cascade Learning with Long Short-Term Memory and Attention (FCL-LSTMA), a novel decentralized architecture that synergistically combines FL and cascade learning to enable accurate and efficient occupancy detection across distributed environments. The FCL-LSTMA framework operates through a two-stage training process: initially, Block B1 leverages 1D convolution, batch normalization, and a parallel LSTM layer for foundational feature learning. Once stabilized, the block is frozen and extended to Block B2, which incorporates attention mechanisms and an additional LSTM layer to refine temporal feature extraction. This progressive training ensures improved stability, model depth, and generalization without compromising data privacy. Experimental results on four benchmark datasets demonstrate the superiority of the proposed framework. FCL-LSTMA achieves outstanding accuracy for binary occupancy detection: 99.99% on the Living Room dataset, 98.95% on the UCI Occupancy Detection dataset, 99.95% on both the UCI Room Occupancy Estimation and IEQ datasets. For multi-class tasks, the model achieves 99.98% and 99.95% on the Living Room and UCI Room Occupancy Estimation datasets, respectively. Furthermore, it demonstrates computational efficiency with inference times ranging from 0.2028 to 0.562 milliseconds and memory usage between 0.17 MB and 0.49 MB. These results confirm the robustness, scalability, and privacy-preserving capabilities of FCL-LSTMA, making it a compelling solution for real-time occupancy detection in smart building systems.

Early fault detection and diagnosis of grid-connected photovoltaic systems (GCPS) is imperative to improve their performance and reliability. Low-cost edge devices have emerged as innovative solutions for real-time monitoring, reducing latency, and improving response times. In this work, a lightweight Convolutional Neural Network (CNN) is designed and fine-tuned using Energy Valley Optimizer (EVO) for fault diagnosis. The CNN input consists of two-dimensional scalograms generated using Continuous Wavelet Transform (CWT). The proposed diagnosis technique demonstrated superior performance compared to benchmark architectures, namely MobileNet, NASNetMobile, and InceptionV3, achieving higher test accuracies and lower losses on binary and multi-fault classification tasks on balanced, unbalanced, and noisy datasets. Further, a quantitative comparison is conducted with similar recent studies. The obtained results indicate good performance and high reliability of the proposed fault diagnosis method.

This paper proposes a new multifunctional control technique for a grid-connected hybrid distributed generation system composed of a photovoltaic system and a wind power system based on a voltage source converter (VSC). Indeed, aside from the generation and the injection of energy into the grid, the proposed system deals with power quality issues caused by harmonics generated by non-linear loads in order to keep the source current uncontaminated. The VSC serves to first ensure that the power generated from the hybrid renewable energy source is fed to the utility grid and acts as a shunt active power filter in case an abnormal increase in the THD of the source current above the standard permissible values is detected due to the non-linear load connection. The two sources of the hybrid system are connected to a common DC bus to simplify the control and reduce the cost of the system, and a maximum power point tracking controller is used for both sources. The major advantage of this novel proposed multifunctional control technique is its ability to inject harvested power into the grid while simultaneously ensuring the compensation of the harmonics and reactive power. The proposed multifunctional control technique is validated through an extensive simulation analysis using MATLAB/Simulink.