Doctorat

Now showing 1 - 3 of 3

Contribution to the optimization of smart grids
(Université M'Hamed Bougara Boumerdès : Faculté de Technologie, 2025) Faradji, Mohamed; Layadi, Toufik Madani(Directeur de thèse)
The transition toward smart grids demands sophisticated optimization techniques to enhance efficiency, stability, and demand responsiveness. This thesis contributes to smart grid optimization by leveraging advanced optimization and computational intelligence methods, including Particle Swarm Optimization (PSO), Artificial Neural Networks (ANN), and Adaptive Neuro-Fuzzy Inference System (ANFIS). The study focuses on two critical areas: demand-side management (DSM) for peak load reduction and load frequency control (LFC) for grid stability. A hybrid PSO- ANN framework is proposed for DSM to predict and optimize energy consumption patterns, while ANFIS-based controllers are designed for robust LFC under dynamic load conditions. Simulation results demonstrate superior performance compared to conventional methods, with significant improvements in demand response accuracy and frequency regulation. The findings underscore the potential of AI-driven optimization in advancing smart grid resilience and operational efficiency
Detection and identification of defects in gearbox systems using artificial intelligence based techniques
(Université M'Hamed Bougara Boumerdès : Faculté de Technologie, 2023) Ikhlef, Boualem; Benazzouz, Djamel(Directeur de thèse)
Gearboxes are massively utilized in nowadays industries due to their huge importance in power transmission; hence, their defects can heavily affect the machines performance. Therefore, many researchers are working on gearboxes fault detection and classification. However, most of the works are carried out under constant speed conditions, while gears usually operate under varying speed and torque conditions, making the task more challenging. In this work, we propose a new method for gearboxes condition monitoring that is efficiently able to reveal the fault from the vibration signatures under varying operating condition. First, the vibration signal is processed with the Maximal Overlap Discrete Wavelet Packet Transform (MODWPT) to extract the modes. Next, time domain features are calculated from each mode. Then the features set are reduced using the Ant colony optimization algorithm (ACO) by removing the redundant and unimportant parameters that may mislead the classification. Finally, an ensemble learning algorithm Random Forest (RF) is used to train a model able to classify the fault based on the selected features. The innovative aspect about this method is that, unlike other existing methods, ACO is able to optimize not only the features but also the parameters of the classifier in order to obtain the highest classification accuracy. The proposed method was tested on varying operating condition real dataset consisting of six different gearboxes. In the aim to prove the performance of our method, it had been compared to other conventional methods. The obtained results indicate its robustness, and its accuracy stability to handle the varying operating condition issue in gearboxes fault detection and classification with high efficiency
Improvement of vlc technology and deployment in the context of smart city
(Université M'Hamed Bougara : Faculté de Technologie, 2023) Yahia, Selma; Meraihi, Yassine(Directeur de thèse)
The demand for wireless communication systems has increased dramatically due to their ability to enable the exchange of information between various devices, o?ering the potential to enhance safety, manage tra?c and improve convenience. Extensive research and standardization e?orts in wireless communications have focused on radio frequency (RF) technologies. Nevertheless, RF technologies are susceptible to high levels of interference and channel congestion in heavily populated areas, which can adversely a?ect the performance of delay-sensitive applications. To mitigate such problems, researchers from academia and industry started to explore and develop new communication technologies. Visible light communication (VLC) is considered one of the promising technologies. VLC uses the visible part of the electromagnetic spectrum and o?ers an alternative solution to the limitations posed by RF communications. The data transmission through VLC technology depends on the ability to modulate the intensity of the Light-Emitting-Diode (LED), enabling the dual use of LED for illumination and communication purposes. This results in a highly e?cient, low-power, and low-latency communication solution, that is immune to interference from other communication technologies. VLC deploys the existing lighting infrastructures, which o?ers an innovative way to transmit data in widespread areas and for various applications such as indoor communication, vehicular communications, and smart cities. VLC is still new in some applications and requires extensive e?orts to cope with several challenges in di?erent aspects, including system and channel modeling, transceiver modeling and design, optimization of various system parameters, and performance analysis. This thesis provides a comprehensive study of di?erent research topics in VLC technology. The objective is to shed light on the new applications of VLC systems, illustrating the challenges that limit the system performance and introducing novel solutions to improve such performance. In the ?rst part of this dissertation, we provide a comprehensive review of VLC technology, illustrating the existing research e?orts on di?erent prospects. That starts from the system and channel modeling and reaches the performance analysis and system implemen- III ABSTRACT tation. Since channel modeling is critical for system design and performance estimation, we then focus on that and present a comprehensive study of the traditional and advanced channel modeling approaches for VLC systems. We illustrate the advantages and the capabilities of utilizing the advanced non-sequential ray tracing channel modeling approach. These include the ability to incorporate and model practical and commercial light sources with their di?erent radiation patterns and the consideration of many re?ections to provide more accurate results. Therefore, we adopt this channel modeling approach, which forms the foundation of our research, to model and evaluates the performance of di?erent VLC applications and scenarios in the other parts of the thesis. Our work focuses primarily on improving the performance and e?ciency of VLC systems in indoor and outdoor applications. In the second part of this thesis, we consider the outdoor scenarios aiming to improve the system performance through novel receiver designs, including imaging and non-imaging receivers. Utilizing the proposed structure, we investigate the performance of both vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) VLC applications. The third part of this thesis focuses on indoor applications where a novel resource allocation scheme is proposed to enhance the performance of Massive Optical internetof-things (IoT) systems. The proposed technique depends on an improved version of the Aquila Optimization (AO) algorithm, which integrates chaotic maps, Quasi-OppositionBased Learning (QOBL) concept, Fitness-distance balance (FDB) selection methods, and cosine functions into the original AO algorithm to enhance its performance. Extensive simulations and analyses are conducted to compare the system performance using the proposed designs, algorithms, and schemes with the existing literature work. The results demonstrate the e?ectiveness of our proposed work in improving the performance and e?ciency of the VLC system in indoor and outdoor scenarios. To conclude, this dissertation provides a comprehensive study of VLC technology, o?ering new insights into system and channel modeling, receiver design, transmission schemes, and system optimization, paving the way for future research extensions in this area

Doctorat

Browse

Filters

Settings

Sort By

Results per page

Search Results