Institut de Génie Electrique et d'Electronique

Permanent URI for this communityhttps://dspace.univ-boumerdes.dz/handle/123456789/2344

Browse

Filters

2015 - 20192372020 - 2025377

Settings

Search Results

Now showing 1 - 10 of 618
  • Thumbnail Image
    Item
    AI-Driven intrusion detection system (IDS) for network traffic
    (University of M'Hamed Bougara Boumerdes : Institute of Electrical and Electronic Engineering (IGEE), 2025) Terki, Ali; Mouhouche, Faiza
    This thesis presents a real-time network intrusion detection system that integrates live flow capture via CICFlowMeter with a hybrid CNN–LSTM model. We apply Variance Inflation Factor (VIF) analysis to reduce an initial 83-feature set to 33 uncorrelated predictors, improving stability without loss of accuracy. The resulting CNN-LSTM achieves 98.75 % detection accuracy and 0.9993 AUC in benchmark fl ows, and processes live HTTP, SSH, DoS, and slowloris traffic with millisecond latency. Our work demonstrates practical deployment of machine learning–based intrusion detection system (IDS) in real networks, contributing a streamlined feature selection method and an end-to-end Python application for continuous monitoring.
  • No Thumbnail Available
    Item
    Comparative study of different configurations of a long haul optical fiber link
    (Université M’Hamed Bougara de Boumerdes : Institut de génie electrique et electronique (IGEE), 2025) Drihem, Samy
    Nowadays, with all the advanced technologies that we use, we need a secure, high-data transmission system to safely transfer data. The optical communication system serves this purpose. However, it has dispersion that leads to a loss of data. One way to eliminate this loss is to add optical amplifiers to the optical communication circuit, which are essential for boosting signal strength. However, we can’t add too many amplifiers due to their high cost. In this project, my goal was to explore the possibility of reducing the number of optical amplifiers in the circuit and how this would affect the overall performance of the optical fiber communication system. To do so, I focused on reducing chromatic dispersion using Dispersion Compensating Fibers (DCF). I tested a 120 km link-to-link circuit by dividing it by four, three, and two optical amplifiers at six transmission bit rates (5Gbps, 10Gbps, 15Gbps, 20Gbps, 30Gbps and 40Gbps) using three configurations (Pre-compensation, Post-compensation, and Symmetric-compensation). The results are presented in terms of Q-factor, Bit Error Rate tables, and eye diagrams. MATLAB and OptiSystem version 7.0 were used as the software tools for validating the proposed approach. After analyzing the simulations, results suggests that there is potential to reduce the number of amplifiers in the system and the optimal solution for a 120 km long-haul optical fiber link is to divide it into three evenly spaced amplifier segments. Utilizing the post-compensation technique in t
  • No Thumbnail Available
    Item
    A Comparative analysis of flight control for an autonomous aerial delivery vehicle
    (Université M'hamed Bougara Boumerdès: Institue de génie electronic et electric, 2024) Riabi, Hanane; Cherifi, Dalila (supervisor)
    This work explores a comparative analysis of fligh tcontro lfo ra nautonomou saeria ldelivry vehicle, specificall yapplie dt omedica lassistanc ei nemergenc yan dnatura ldisaste rscenarios. The study begins with an overview of drone technology, including classification san dapplications. It then delves into mathematical modeling, focusing on quadcopter dynamics and control systems. Two distinct control methodologies, linear PID control and 5th generation of Sliding mode control(Continuous Nonsingular Terminal Sliding Mode contoller), are synthesized and simulated. The comparative analysis evaluated the performance of the linear PID controller and the CNSMC approach for the QBall 2 quadrotor system. We assessed their behavior under normal conditions, and the CNSMC controller demonstrated superior resilience to perturbations compared to the PID controller. This makes CNSMC the preferred choice for real-world applications where stability and adaptability are crucial.
  • No Thumbnail Available
    Item
    Implementation of low band booster on LTE 900MHz network for enhanced edge user experience
    (Université M’hamed Bougara de Boumerdes : Institut de Genie Electrique et Electronique, 2024) Bouloum, Sofiane; Boursas, Idir; Smailii, Nesrine ( Supervisor)
    Mobile telephone operators, in functions of the network load, are always looking for innovative solutions in order to improve the quality of service(QoS) given the non-availability or the limitation of the band spectral bandwidth. On the EGSM band, Djezzy has decided to activate 4G (L900) on 3 MHz as bandwidth. Given the spectral limitation of the band, the Qos is more than essential in order to offer the best 4G experience to our clients. The objective of our thesis is to improve the performance of the 4G network (L900 3MHz) in terms of throughput and make the best use of these spectral resources limited by the deployment and optimization of the “Low band booster” solution. This will be done by firs tstudyin gth earchitectur eo f a4 GLT Enetwork ,th edifferen tQo sparameter sa swell as reviewing the strategy adopted in implementation of carrier aggregation, mid and low band coordination and scheduling of data transmission. The contribution of our work in this project is to optimise the overall Djezzy radio access network to meet the high demand of a good quality service particularly the high demand for network capacity.
  • No Thumbnail Available
    Item
    PLC and HMI based monitoring and control of an induction motor using VFD drive and profinet protocol
    (Université M’Hamed Bougara de Boumerdes : Institut de génie electrique et electronique (IGEE), 2024) Zerrouki, Abderrezak; Ouadi, Abderrahmane (Supervisor)
    Various applications in industrial automation require accurate and effective motor speed control. This project addresses this need by developing a motor speed control system utilizing a variable frequency drive (VFD), programmable logic controller (PLC), and human-machine interface (HMI). To achieve variable speed control, the study examines the operating characteristics of AC motors and their fundamental concepts, as well as the way VFDs manipulate the provided AC power. It delves into the capabilities of PLCs, highlighting how they receive control signals and direct the VFD to perform the desired motor functions. The integration of an HMI offers a user-friendly interface for system monitoring, speed set point adjustments, and fault identification. Additionally, the project incorporates the PROFINET protocol to ensure efficient and reliable communication between the PLC, VFD, and HMI. The implementation includes detailed system design, programming, and configuration. Results demonstrate the effectiveness of the integrated system in achieving accurate and responsive motor speed control, underscoring the advantages of using VFD, PLC, HMI, and PROFINET technologies in industrial automation.
  • No Thumbnail Available
    Item
    Microgrids resiliency using multi-agent system communication technology
    (Université M’hamed Bougara de Boumerdes : Institut de Genie Electrique et Electronique, 2024) Attou, Lina; Belaidi, Hadjira (Superviseur)
    Nowadays, communication and data exchange are key factors for the resilience improvement of a microgrid (MG) against natural disasters and play a pivotal role in the energy management (EM) fields .Hence ,the main objective of this project is to improve MGresilience and control its energy management system (EMS) using a multi-agent system (MAS) communication approach. First, the proposed work optimizes the load power consumption inside one MG based on the available power resources; then, the strategy is expanded to optimize power usage to improve resilience when dealing with many MG systems. The simulation of the multi-microgrid (MMG) system is done using both MATLAB Simulink and Cisco packet tracers. Various scenarios are simulated to evaluate the performance of the MAS in maintaining flexibility, stability, an dresiliency. The Cisco packet traceris used to model the communication network to ensure a robust and secure data exchange between agents. The results demonstrate that the integration of MAS communication technology significantly improves MGs’ power management.
  • No Thumbnail Available
    Item
    Simulation study of model predictive control applied to binary distillation column
    (Université M'hamed Bougara Boumerdès: Institue de génie electronic et electric, 2024) Taouli, Houria Ghoufranellah; Asselah, Lamia; Rouani, Lahcene (supervisor)
    Distillation columns are essential in many industries for separating liquids based on the volatility of their components. However, traditional control methods often struggle to achieve high component purity due to the process's complexity. This project investigates the use of Model Predictive Control (MPC) on a binary distillation column, comparing its performance to conventional control techniques. Guidelines for tuning the MPC controller are also provided. Simulation results show that MPC greatly improves setpoint tracking and disturbance rejection compared to traditional methods, demonstrating its potential to enhance process efficiency and product quality.
  • No Thumbnail Available
    Item
    Design of a smart PLC-based fire safety system using fuzzy logic
    (Université M’Hamed Bougara de Boumerdes : Institut de génie electrique et electronique (IGEE), 2024) Chelbi, Ahmed El-Hadi; Kaced, R. (Supervisor)
    This project aims to develop a smart fire detection and fire-fighting system to enhance fire safety measures of a three fire zone industrial facility. An intelligent fire detection algorithm based on fuzzy logic is proposed, integrating four sensor inputs (smoke obscuration rate, temperature, flame radiance and carbon monoxide concentration) for accurate fire identification and classification. Additionally, a PLC-based automation of the fire-fighting pumping system of each fire zone is developed aiming to optimize fire suppression resource deployment. The integration of these intelligent systems is achieved via a SCADA system, enabling real-time monitoring, control, and decision support. The fire detection algorithm was implemented using the MATLAB software and rigorously tested with simulations performed with the industry-standard NIST Fire Dynamics Simulator yielding highly promising results which demonstrated and validated the detection algorithm's effectiveness and robust performance. These application results demonstrate the potential of intelligent fire detection to significantly improve fire safety, a minimize damage, and protect lives through accurate, rapid response times, and optimized resource allocation.
  • No Thumbnail Available
    Item
    Feedback motion planning for car-like robots
    (Université M'hamed Bougara Boumerdès: Institue de génie electronic et electric, 2024) Derar, Iyed; Khoumari, Malik; Guernane, Reda (supervisor)
    In this study, we address the problem of feedback motion planning for a car-like robot de-scribed by a kinematic model, navigating through obstacles. For this purpose, we designed two sampling-based algorithms equipped with the feedback property, a Modifie dRapidly Exploring Random Tree Star (RRT*) algorithm and a Funnel-Graph algorithm. Both al-gorithms generate collision-free paths while accounting for non-holonomic constraints and uncertainties. These generated paths are then fed to the pure pursuit controller which han-dles the robot motion execution. Our approach is validated by testing the algorithms’ ability to handle differen tuncertaintie san dadaptability to environmental changes,including a performance comparison between them. The results show the superiority of the funnel-graph algorithm across all tests, which makes it best suited for real-time applications.
  • No Thumbnail Available
    Item
    Automation and supervision of the boiler sootblwing system using S7-300
    (Université M'hamed Bougara Boumerdès: Institue de génie electronic et electric, 2024) Toumi, Nesrine; Sirine, Samah; Benzaoui, M. (supervisor)
    This project addresses a critical issue identified by the refinery of Algiers regarding the absence of a program for the sootblowing system. The sootblowing system is essential for maintaining operational efficiency in industrial settings. It employs steam technology across three distinct sequences; pre-heating, manual and automatic. Our project not only delivers the Step 7 program required for the effective operation of the sootblowing system but also incorporates a human machine interface HMI. This last one facilitates system supervision enhancing user experience and ensuring coherent monitoring and control. Through the integration of both software and user interface design, this project offers a comprehensive solution to optimize the functionality and performance of the sootblowing system at the refinery of Algiers.