| Titre : | QoS-driven Self-Adaptive IoT system |
| Auteurs : | Raouane DEHIMI, Auteur |
| Type de document : | Mémoire magistere |
| Editeur : | Biskra [Algérie] : Faculté des Sciences Exactes et des Sciences de la Nature et de la Vie, Université Mohamed Khider, 2021 |
| Format : | 1 vol. (70 p.) / ill. / 29 cm |
| Langues: | Anglais |
| Mots-clés: | IoT, Uncertainties, QoS, Self-adaptation, Machine Learning, Deep Learning. |
| Résumé : | IoT applications are subject to a variety of uncertainties, such as sudden changes in traffic load, communication interference. this has given rise to a big challenge to provide consistent quality of service in the network. The self-adaptation was finding to provides the means to automate tasks that humans would otherwise perform, without errors, and varying and potentially inconsistent expertise. Self-adaptation is considered to be the best solution to dynamically manage a system in the occurrence of deviations from the expected quality of service (QoS) parameters. Currently, the Machine learning and Deep Learning techniques can be used to facilitate adaptation because they ensure that the system can learn from multiple data and improve over a period of time. What we are suggesting is a model to be able to count on changes earlier than a QoS gap occurs. The approach constantly monitors QoS parameters and predicts capacity differences from QoS parameters primarily based entirely on old statistics, by change the values of old QoS parameter that was may cause derivation in QoS to the new values that improve the QoS. |
| Sommaire : |
GENERAL INTRODUCTION 2
1-GENERAL CONTEXT 2 2-PROBLEMATIC AND OBJECTIVES 3 3-OUTLINES 4 CHAPTER 01: INTERNET OF THINGS 6 1-INTRODUCTION 6 2-THE INTERNET OF THINGS 6 2.1-Characteristics of IoT 8 2.2-Architecture of IoT 9 2.2.1- Three Layer Architectures 9 2.2.2-Five Layer Architectures 10 2.3-Application of IoT 10 2.3.1-Smart Cities Domain 10 2.3.2-Smart Energy Domain 11 2.3.3-Smart Healthcare Domain 12 2.3.4-Smart Homes Domain 13 2.3.5- Internet of Things in Agriculture Domain 14 2.4- Challenges and recent research of IoT 14 2.4.1-Networking 14 2.4.2-Routing 14 2.4.3-Heterogeneity 15 2.4.4- Interoperability 15 2.4.5-Cloud Computing 15 2.4.6- Security and privacy 15 2.4.7- Quality of Service 16 2.5- Technologies 16 2.5.1- Radio Frequency Identification (RFID) 16 2.5.2- Wireless Sensor Network (WSN) 17 2.5.3- Networking Technologies 17 2.5.4-Nano Technologies 17 3-IOT DISTRIBUTION PATTERNS 18 4-A QOS IN IOT 19 5-CONCLUSION 20 CHAPTER 02: SELF-ADAPTATION 20 1-INTRODUCTION 20 2-SELF ADAPTATION 20 2.1-Conceptual Model of a Self-adaptive System 21 2.2 Waves of a Self-adaptive System 22 3- THE IBM AUTONOMIC FRAMEWORK 24 4- SELF-ADAPTATION PATTERNS 25 5- UNCERTAINTIES 26 6- CONCLUSION 27 CHAPTER 03: DEEP LEARNING 28 1-INTRODUCTION 28 2- MACHINE LEARNING 29 2.1- Machine Learning Classification 29 2.2- Types of Learning 30 2.2.1-Supervised Learning 30 2.2.2-Unsupervised Learning 31 2.2.3- Semi - Supervised Learning 31 2.2.4- Reinforcement Learning 32 3-DEEP LEANING 33 3.1-Datasets for Deep Learning 34 4-NEURAL NETWORK 35 4.1- Neural Network Types 36 4.1.1- Deep Neural Networks (DNN) 36 4.1.2-Convolutional Neural Networks (CNN) 36 4.1.3- Recurrent Neural Networks (RNN) 37 4.1.4- Long Short-Term Memory (LSTM) 37 4.1.5- Probabilistic Neural Network (PNN) 37 4.2- Neural network applications 37 4.3- Neural network Components 38 5-CONCLUSION 40 CHAPTER 04: DESIGN 41 1-INTRODUCTION 41 2-OBJECTIVE 41 3-RELATED WORK 41 3- THE APPROACH 43 4-DETAILED DESCRIPTION FOR THE APPROACH 46 5- FUNCTIONAL OVERVIEW OF THE SYSTEM 48 6-CONCLUSION 50 CHAPTER 05: IMPLEMENTATION 51 1-INTRODUCTION 51 2-USED SOFTWARE AND MATERIALS 51 2.1- Materials 51 2.2- Programming language 51 2.2.1- Java 51 2.2.2- Python 52 2.3- Development tools and frameworks 52 2.3.1-Eclipce 52 2.3.2-Anaconda 53 2.3.3- TensorFlow 54 2.3.4-Numpy 54 2.3.5-Seaborn 54 2.3.6-Pandas 54 2.3.7-matplotlib 54 2.3.8-Ipython 55 2.3.9-Keras 55 2.3.10- Statsmodel 55 3- SIMULATOR 56 4- BUILDING MODEL 59 5- Obtained Results 63 6- CONCLUSION 67 CONCLUSION 69 1-GENERAL CONTEXT 69 2-FUTURE WORK 70 3-CHALLENGES 70 REFERENCES VIII |
| Type de document : | Mémoire master |
Disponibilité (1)
| Cote | Support | Localisation | Statut |
|---|---|---|---|
| MINF/608 | Mémoire master | bibliothèque sciences exactes | Consultable |
