DSpace Collection:http://dspace.ensta.edu.dz/jspui/handle/123456789/862026-10-10T23:50:38Z2026-10-10T23:50:38ZDesign and Implementation of a Real-Time Monitoring and Supervision System for a Grid-Connected Photovoltaic Power PlantKHALED, ChahineADDALA, AbderrahimDERMOUCHE, Reda (Directeur de thèse)CHOUDER, Aissa (Directeur de thèse)DROUICHE, Imane (Directeur de thèse)http://dspace.ensta.edu.dz/jspui/handle/123456789/4412026-10-07T08:51:40Z2025-01-01T00:00:00ZTitle: Design and Implementation of a Real-Time Monitoring and Supervision System for a Grid-Connected Photovoltaic Power Plant
Authors: KHALED, Chahine; ADDALA, Abderrahim; DERMOUCHE, Reda (Directeur de thèse); CHOUDER, Aissa (Directeur de thèse); DROUICHE, Imane (Directeur de thèse)
Abstract: This End-of-Study Project presents the design and implementation of a real-time monitoring
and supervision system tailored for large-scale grid-connected photovoltaic systems. As the integration
of renewable energy into power systems grows, maintaining consistent performance
and ensuring operational reliability becomes essential. The work addresses the need for a robust
and centralized platform—based on SCADA architecture—that enables continuous oversight of
photovoltaic systems, enabling early detection of irregularities, efficient decision-making, and
enhanced energy yield.
The proposed system facilitates real-time data acquisition and visualization, giving operators
access to crucial information such as energy production levels, system efficiency, and the status
of system components. It further supports predictive analysis, and fault detection and diagnosis,
enabling timely intervention and minimizing system downtime. By aligning the system's architecture
with established performance metrics and supervisory principles, the study ensures that
operators can both monitor and evaluate the plant's behaviour in real-time.
Furthermore, the work emphasizes the significance of modular architecture, accessibility, and
clarity in monitoring tools, ensuring they serve as decision-support systems rather than passive
displays. This work ultimately contributes to improving the management of photovoltaic power
plants by offering a scalable and user-focused solution that enhances operational awareness, responsiveness,
and long-term energy performance.
Description: Projet de fin d’étude d'ingeniorat: Systèmes Embarqués:Alger: Ecole Nationale Supérieure des Technologie Avancées: 20252025-01-01T00:00:00ZAutomatic Extraction of the Inference Structure of a CNN as a DAG for Temporal Analysis of Many-Core SystemsLOUNNACI, SarahBENDOUDA, Djamila (Directeur de thèse)HLADIK, Pierre-Emmanuel (Directeur de thèse)MAIZA, Claire (Directeur de thèse)http://dspace.ensta.edu.dz/jspui/handle/123456789/4402026-10-07T08:42:50Z2025-01-01T00:00:00ZTitle: Automatic Extraction of the Inference Structure of a CNN as a DAG for Temporal Analysis of Many-Core Systems
Authors: LOUNNACI, Sarah; BENDOUDA, Djamila (Directeur de thèse); HLADIK, Pierre-Emmanuel (Directeur de thèse); MAIZA, Claire (Directeur de thèse)
Abstract: Convolutional Neural Networks (CNNs) have become indispensable in Artificial In-
telligence applications due to their ability to automatically extract hierarchical features.
However, when deployed in real-time and embedded systems, accuracy is not the only
metric of interest. In such environments, timing predictability and the guarantee of meet-
ing strict deadlines are essential. This work addresses this challenge by bridging Deep
Learning inference with real-time analysis through the systematic transformation of CNN
models into Directed Acyclic Graphs (DAGs).
The primary contribution of this project is the design of MIND Model Inference Net-
work Designer software, which automatically extracts the inference structure of a CNN
and converts it into a DAG compatible with the MIA Multicore Interference Analysis
tool. To capture different execution strategies, we developed a set of novel and innova-
tive regrouping policies, such as Macroscopic Layer-Wise Modeling (MLWM), Structured
Spatial Partitioning (SSP), Redundant Convolution via Channel Tiling (RCCT), and
Dense Fusion (DF). These policies balance computation, memory access, and communi-
cation overheads in parallel, making it possible to analyze their impact on the many-core
Kalray MPPA architectures.
Furthermore, we proposed architecture-aware cost for Kalray’s architectures: Bostan
256 cores and Coolidge 80 cores with TCA co-processor. By formalizing the Worst-Case
Execution Time (WCET) and Worst-Case Memory Access (WCMA) at different preci-
sions FP32, FP16, INT8, we provided a relatively accurate computation model that en-
ables Worst-Case Response Time (WCRT) computation through MIA. The testing phase
validates our methodology with a prototype CNN and multiple parameter variations,
highlighting the trade-offs between speedup, compute efficiency, interference, memory
transfer costs, etc. This work demonstrates the feasibility of systematically analyzing CNNs for Real-
Time Systems on many-core processors, achieving a complete workflow: from CNN to
DAG extraction, to regrouping policy application, cost modeling, YAML generation, and
MIA-based timing analysis. The outcomes not only validate the proposed approach but
also open perspectives for extending analysis to larger models.
Description: Projet de fin d’étude d'ingeniorat: Systèmes Embarqués:Alger: Ecole Nationale Supérieure des Technologie Avancées: 20252025-01-01T00:00:00ZDéveloppement d’un Système Embarqué dans un Tableau de Bord pour ScooterBOUCHIBANE, AmineCHOUAF, Seloua (Directeur de thèse)MAOUCHE, Idris (Directeur de thèse)http://dspace.ensta.edu.dz/jspui/handle/123456789/4392026-10-07T08:15:31Z2025-01-01T00:00:00ZTitle: Développement d’un Système Embarqué dans un Tableau de Bord pour Scooter
Authors: BOUCHIBANE, Amine; CHOUAF, Seloua (Directeur de thèse); MAOUCHE, Idris (Directeur de thèse)
Abstract: Ce projet a pour objectif le développement d’un système embarqué intégré à un
tableau de bord pour scooter. La solution établit une communication bidirec-
tionnelle avec un smartphone via Bluetooth pour l’échange de données, tout en
proposant une interface utilisateur moderne sur un écran tactile.
Description: Projet de fin d’étude d'ingeniorat: Systèmes Embarqués:Alger: Ecole Nationale Supérieure des Technologie Avancées: 20252025-01-01T00:00:00ZTest and Validation of a motorcycle dashboardELABASSI, Mohammed YassineKHOULA, OmarZELLAT, Khadidja (Directeur de thèse)MAOUCHE, Idris (Directeur de thèse)http://dspace.ensta.edu.dz/jspui/handle/123456789/3952025-11-06T10:22:57Z2025-01-01T00:00:00ZTitle: Test and Validation of a motorcycle dashboard
Authors: ELABASSI, Mohammed Yassine; KHOULA, Omar; ZELLAT, Khadidja (Directeur de thèse); MAOUCHE, Idris (Directeur de thèse)
Abstract: It’s a presentation of the design and implementation of a Hardware-in-the-Loop (HIL) bench dedicated to testing a motorcycle dashboard. This project aims to simulate various motorcycle conditions by generating realistic analog and digital signals to verify the proper functioning of the dashboard in a controlled environment using the actual tools of Vector Informatik that are made for automotive test and validation. The bench consists of a microcontroller-based system (ESP32 and Arduino Nano), DAC modules, relays, and signal conditioning circuits, all coordinated together by custom firmware. This work highlights the challenges of embedded systems integration, real-time signal emulation and the importance of verification tools in the development lifecycle of automotive-grade electronics
Description: Projet de fin d’étude d'ingeniorat: Systèmes Embarqués: Alger: Ecole Nationale Supérieure des Technologie Avancées: 20252025-01-01T00:00:00Z