https://dspace.univ-ouargla.dz/jspui/handle/123456789/206 2026-06-26T13:35:59Z https://dspace.univ-ouargla.dz/jspui/handle/123456789/40787 Titre: Performance Improvement and Complexity Reduction of Massive MIMO Communication System Auteur(s): Smail, LABED Description: Telecommunication Systems 2026-01-01T00:00:00Z https://dspace.univ-ouargla.dz/jspui/handle/123456789/39709 Titre: Intelligent Forecasting and Control Strategies for Multi-Source Renewable Energy Systems Auteur(s): Fares, Bennaceur Résumé: The integration of multi-source renewable energy systems into smart grids remains chal- lenging due to the intermittent nature of renewable sources, load variability, and the need for efficient control and stability. This thesis proposes an intelligent framework integrating forecasting, control, and energy management to enhance the performance and reliability of hybrid renewable systems. The first contribution focuses on solar irradiation forecasting, which provides the foun- dation for intelligent decision-making in hybrid systems. Deep learning and machine learn- ing techniques CNN, LSTM, CNN–LSTM, and SVM are employed to predict short-term solar irradiance with high accuracy, allowing better planning and real-time adaptation of control strategies. The second contribution addresses maximum power point tracking (MPPT), where three intelligent controllers ANFIS with subtractive clustering, a GWO based controller, and an IT2FL controller are developed to maximize PV energy extraction under rapidly changing conditions. The third contribution concerns battery State of Charge (SOC) estimation, achieved through a Cascade Forward Neural Network (CFNN) model capable of handling nonlin- earities and temporal variations. The proposed SOC estimator improves accuracy and ensures optimal energy utilization and battery health. Finally, an Energy Management System (EMS) based on hybrid metaheuristic algo- rithms GWOPSO and ALO is designed to maintain DC bus voltage stability and manage power flow between PV, wind, and storage units. Simulation results demonstrate that the proposed AI-driven framework outperforms conventional approaches in terms of forecasting accuracy, MPPT efficiency, SOC reliabil- ity, and EMS stability, contributing to the realization of intelligent and sustainable smart grids.; L’intégration des systèmes hybrides à sources d’énergie renouvelable dans les réseaux in- telligents demeure un défi en raison du caractère intermittent des ressources renouvelables, de la variabilité de la charge et de la nécessité d’un contrôle efficace et stable. Cette thèse propose un cadre intelligent intégrant la prévision, le contrôle et la gestion énergétique afin d’améliorer les performances et la fiabilité des systèmes hybrides. La première contribution concerne la prévision de l’irradiation solaire, qui constitue la base de la prise de décision intelligente dans les systèmes hybrides. Des techniques d’ap- prentissage profond et d’apprentissage automatique CNN, LSTM, CNN LSTM et SVM sont utilisées pour prédire l’irradiation solaire à court terme avec une grande précision, permettant une meilleure planification et une adaptation en temps réel des stratégies de contrôle. La deuxième contribution traite du suivi du point de puissance maximale (MPPT), où trois contrôleurs intelligents ANFIS avec partitionnement soustractif, un contrôleur basé sur le GWO, et un contrôleur IT2FL sont développés afin de maximiser l’extraction de puissance photovoltaïque sous des conditions rapidement variables. La troisième contribution est liée à l’estimation de l’état de charge (SOC) des batteries, réalisée à l’aide d’un modèle Cascade Forward Neural Network (CFNN) capable de gérer les non-linéarités et les variations temporelles. L’estimateur proposé améliore la précision et garantit une utilisation énergétique optimale et une meilleure durée de vie des batteries. Enfin, un système de gestion de l’énergie (EMS) fondé sur des algorithmes méta- heuristiques hybrides GWOPSO et ALO est conçu pour maintenir la stabilité de la tension du bus CC et gérer les flux d’énergie entre les unités PV, éoliennes et de stockage. Les résultats de simulation montrent que le cadre intelligent proposé dépasse les ap- proches conventionnelles en termes de précision de prévision, d’efficacité MPPT, de fiabi- lité SOC et de stabilité EMS, contribuant ainsi au développement de réseaux intelligents durables et autonomes. Description: Electronic 2025-01-01T00:00:00Z https://dspace.univ-ouargla.dz/jspui/handle/123456789/38254 Titre: Enhanced Neural Network Architectures for Data-Scarce Environments and Multi-Parameter Prediction in Oil and Gas Operations Auteur(s): HARROUZ, Aymen Djamel Eddine Résumé: Neural networks are a crucial component of modern artificial intelligence, demonstrating impressive abilities in understanding complex patterns and relationships in data. However, applying neural networks in real industrial systems, such as Oil and Gas operations, is challenging due to limited his- torical data availability, especially for new machines, and the high cost of obtaining or producing data. As a result, there is a scarcity of public data for the research community. This PhD thesis proposes innovative neural net- work architectures tailored to address the critical challenges in this field. To solve the issue of low prediction accuracy in predicting the health state of tools, a novel neural network architecture is proposed to forecast the Remain- ing Useful Life when limited training data is provided. a feedback mechanism is incorporated into an artificial neural network in a novel manner, using the values of the output layer neurons as inputs. These inputs are utilized as features to generate precise predictions. To validate the effectiveness of the approach, real dataset from oil and gas wells during production is used, this study focuses on a sub dataset of a sub-surface safety valve tool. Addition- ally, a custom neural network architecture is proposed to create a data-driven digital twin based on multi-target regression to mitigate the time delay that impacts decision-making for drillers during directional drilling operations. The architecture combines Long-short Term Memory and Multi-Layer Per- ception branches in a single neural network to forecast and predict important drilling parameters, such as inclination and rate of penetration. To validate this approach a real data collected during a directional drilling operation is used. Furthermore, an incremental learning framework is implemented to simulate the performance of the architectures in real-time, where data is continuously received and the regression models are updated concurrently. The proposed architectures demonstrate superior results compared to exist- ing works in the field. The research conducted in this thesis aims to extend the capabilities of neural network models, uncovering their potential in solv- ing complex problems while contributing to the evolving field of intelligent systems. Description: Automation and Systems Engineering 2024-01-01T00:00:00Z https://dspace.univ-ouargla.dz/jspui/handle/123456789/37631 Titre: Observation à échantillonnage événementiel d'un système cyber-physique Auteur(s): Gasmi, Elhadi; SID Mohamed, Amine; HACHANA, Oussama Résumé: This thesis focuses on event-triggered state estimation problems within the context of cyber-physical systems (CPSs), aiming to develop new event-triggered estimators for nonlinear and Gaussian/nonGaussian systems. Event-triggered state estimation has been a prominent area of systems research for several decades, with successful applications in diverse elds such as signal processing, target tracking, and navigation systems. This approach o ers a promising solution to data tra c congestion by facilitating aperiodic, event-triggered information exchange between sensors and estimators. The motivation for this research stems from the resource limitations inherent in CPS applications, such as wireless sensor networks, and the increased computational burden associated with calculating optimal state estimates under event-triggering conditions. In this work, we address several practical challenges encountered in the eld and endeavor to advance the state of the art in event-triggered state estimation. In the rst part, we provide a brief introduction to the problem of systems under event-triggering conditions and outline the main theory using probabilistic inference, where the problem is addressed with Bayesian state estimation. In the second part, we present the necessary theory for event-triggered state estimation, where the Gaussian assumption are discussed to approximate the posterior Probability Density Function (pdf). Here, the problem is reduced to one of the approximated nonlinear type of Kalman lters. In the next part of this research, we assume that the posterior pdf is no longer to be Gaussian. Therefore, we develop an event-triggered particle lter to approximate the non-Gaussian posterior. The pdfs are approximated based on Monte Carlo simulations using a set of particles and weights. However, computing the particle weights based on the event trigger condition can lead to a computational burden. To address this issue, a Bayesian constraint is developed. Finally, we study the e ect of packet dropouts on the performance of state estimators, speci cally focusing on particle lters. Packet dropouts, caused by imperfect communication channels, are unavoidable when information is transmitted through a communication network. We rst develop a nonlinear particle lter to reduce the estimation error. Using a special form of the sequential Monte Carlo algorithm, the posterior distribution is approximated, and the corresponding minimum meansquared error is derived. By contrasting the error covariance matrix with the posterior Cramér-Rao lower bound, the estimator's performance is assessed. Description: Automatics & systems 2024-01-01T00:00:00Z