Intelligent Network Management and Control

Badr Benmammar is currently a Professor in the Computer Science department at the Abou Bakr Belkaïd University of Tlemcen, Algeria, having received his PhD in Computer Science from Bordeaux 1 University, France. He is the author of several books, including Radio Resource Allocation and Dynamic Spectrum Access (ISTE-Wiley), and his work has led to many journal publications.

• Introduction xiiiBadr BENMAMMARPart 1. AI and Network Security 1Chapter 1. Intelligent Security of Computer Networks 3Abderrazaq SEMMOUD and Badr BENMAMMAR1.1. Introduction 31.2. AI in the service of cybersecurity 51.3. AI applied to intrusion detection 81.3.1. Techniques based on decision trees 91.3.2. Techniques based on data exploration 91.3.3. Rule-based techniques 101.3.4. Machine learning-based techniques 111.3.5. Clustering techniques 131.3.6. Hybrid techniques 141.4. AI misuse 151.4.1. Extension of existing threats 161.4.2. Introduction of new threats 161.4.3. Modification of the typical threat character 171.5. Conclusion 171.6. References 18Chapter 2. An Intelligent Control Plane for Security Services Deployment in SDN-based Networks 25Maïssa MBAYE, Omessaad HAMDI and Francine KRIEF2.1. Introduction 252.2. Software-defined networking 272.2.1. General architecture 272.2.2. Logical distribution of SDN control 292.3. Security in SDN-based networks 322.3.1. Attack surfaces 332.3.2. Example of security services deployment in SDN-based networks: IPSec service 342.4. Intelligence in SDN-based networks 402.4.1. Knowledge plane 412.4.2. Knowledge-defined networking 412.4.3. Intelligence-defined networks 422.5. AI contribution to security 432.5.1. ML techniques 432.5.2. Contribution of AI to security service: intrusion detection 472.6. AI contribution to security in SDN-based networks 482.7. Deployment of an intrusion prevention service 492.7.1. Attack signature learning as cloud service 502.7.2. Deployment of an intrusion prevention service in SDN-based networks 522.8. Stakes 552.9. Conclusion 562.10. References 56Part 2. AI and Network Optimization 63Chapter 3. Network Optimization using Artificial Intelligence Techniques 65Asma AMRAOUI and Badr BENMAMMAR3.1. Introduction 653.2. Artificial intelligence 663.2.1. Definition 663.2.2. AI techniques 673.3. Network optimization 733.3.1. AI and optimization of network performances 733.3.2. AI and QoS optimization 743.3.3. AI and security 753.3.4. AI and energy consumption 773.4. Network application of AI 773.4.1. ESs and networks 773.4.2. CBR and telecommunications networks 793.4.3. Automated learning and telecommunications networks 793.4.4. Big data and telecommunications networks 803.4.5. MASs and telecommunications networks 823.4.6. IoT and networks 843.5. Conclusion 853.6. References 85Chapter 4. Multicriteria Optimization Methods for Network Selection in a Heterogeneous Environment 89Fayssal BENDAOUD4.1. Introduction 894.2. Multicriteria optimization and network selection 914.2.1. Network selection process 924.2.2. Multicriteria optimization methods for network selection 944.3. “Modified-SAW” for network selection in a heterogeneous environment 994.3.1. “Modified-SAW” proposed method 1004.3.2. Performance evaluation 1044.4. Conclusion 1134.5. References 113Part 3. AI and the Cloud Approach 117Chapter 5. Selection of Cloud Computing Services: Contribution of Intelligent Methods 119Ahmed Khalid Yassine SETTOUTI5.1. Introduction 1195.2. Scientific and technical prerequisites 1205.2.1. Cloud computing 1205.2.2. Artificial intelligence 1265.3. Similar works 1295.4. Surveyed works 1315.4.1. Machine learning 1315.4.2. Heuristics 1335.4.3. Intelligent multiagent systems 1355.4.4. Game theory 1375.5. Conclusion 1405.6. References 140Chapter 6. Intelligent Computation Offloading in the Context of Mobile Cloud Computing 145Zeinab MOVAHEDI6.1. Introduction 1456.2. Basic definitions 1476.2.1. Fine-grain offloading 1476.2.2. Coarse-grain offloading 1496.3. MCC architecture 1516.3.1. Generic architecture of MCC 1516.3.2. C-RAN-based architecture 1546.4. Offloading decision 1546.4.1. Positioning of the offloading decision middleware 1556.4.2. General formulation 1566.4.3. Modeling of offloading cost 1586.5. AI-based solutions 1616.5.1. Branch and bound algorithm 1616.5.2. Bio-inspired metaheuristics algorithms 1646.5.3. Ethology-based metaheuristics algorithms 1656.6. Conclusion 1656.7. References 166Part 4. AI and New Communication Architectures 169Chapter 7. Intelligent Management of Resources in a Smart Grid-Cloud for Better Energy Efficiency 171Mohammed Anis BENBLIDIA, Leila MERGHEM-BOULAHIA, Moez ESSEGHIR and Bouziane BRIK7.1. Introduction 1717.2. Smart grid and cloud data center: fundamental concepts and architecture 1727.2.1. Network architecture for smart grids 1737.2.2. Main characteristics of smart grids 1747.2.3. Interaction of cloud data centers with smart grids 1787.3. State-of-the-art on the energy efficiency techniques of cloud data centers 1807.3.1. Energy efficiency techniques of non-IT equipment of a data center 1807.3.2. Energy efficiency techniques in data center servers 1817.3.3. Energy efficiency techniques for a set of data centers 1827.3.4. Discussion 1847.4. State-of-the-art on the decision-aiding techniques in a smart grid-cloud system 1857.4.1. Game theory 1867.4.2. Convex optimization 1877.4.3. Markov decision process 1877.4.4. Fuzzy logic 1877.5. Conclusion 1887.6. References 189Chapter 8. Toward New Intelligent Architectures for the Internet of Vehicles 193Léo MENDIBOURE, Mohamed Aymen CHALOUF and Francine KRIEF8.1. Introduction 1938.2. Internet of Vehicles 1958.2.1. Positioning 1958.2.2. Characteristics 1968.2.3. Main applications 1978.3. IoV architectures proposed in the literature 1978.3.1. Integration of AI techniques in a layer of the control plane 1998.3.2. Integration of AI techniques in several layers of the control plane 1998.3.3. Definition of a KP associated with the control plane 2008.3.4. Comparison of architectures and positioning 2008.4. Our proposal of intelligent IoV architecture 2018.4.1. Presentation 2028.4.2. A KP for data transportation 2038.4.3. A KP for IoV architecture management 2058.4.4. A KP for securing IoV architecture 2078.5. Stakes 2098.5.1. Security and private life 2108.5.2. Swarm learning 2108.5.3. Complexity of computing methods 2108.5.4. Vehicle flow motion 2118.6. Conclusion 2118.7. References 212Part 5. Intelligent Radio Communications 217Chapter 9. Artificial Intelligence Application to Cognitive Radio Networks 219Badr BENMAMMAR and Asma AMRAOUI9.1. Introduction 2199.2. Cognitive radio 2229.2.1. Cognition cycle 2229.2.2. CR tasks and corresponding challenges 2239.3. Application of AI in CR 2239.3.1. Metaheuristics 2239.3.2. Fuzzy logic 2299.3.3. Game theory 2309.3.4. Neural networks 2319.3.5. Markov models 2319.3.6. Support vector machines 2329.3.7. Case-based reasoning 2339.3.8. Decision trees 2339.3.9. Bayesian networks 2349.3.10. MASs and RL 2349.4. Categorization and use of techniques in CR 2369.5. Conclusion 2379.6. References 237Chapter 10. Cognitive Radio Contribution to Meeting Vehicular Communication Needs of Autonomous Vehicles 245Francine KRIEF, Hasnaâ ANISS, Marion BERBINEAU and Killian LE PAGE10.1. Introduction 24510.2. Autonomous vehicles 24610.2.1. Automation levels 24610.2.2. The main components 24710.3. Connected vehicle 25110.3.1. Road safety applications 25110.3.2. Entertainment applications 25210.4. Communication architectures 25310.4.1. ITS-G5 25610.4.2. LTE-V2X 25710.4.3. Hybrid communication 25810.5. Contribution of CR to vehicular networks 25810.5.1. Cognitive radio 25910.5.2. CR-VANET 26010.6. SERENA project: self-adaptive selection of radio access technologies using CR 26410.6.1. Presentation and positioning 26510.6.2. General architecture being considered 26610.6.3. The main stakes 26910.7. Conclusion 27010.8. References 270List of Authors 275Index 277