DESIGN OF COMMUNICATION NETWORKS AND SYSTEMS

Academic Year 2023/2024 - Teacher: SALVATORE RIOLO

Expected Learning Outcomes

The objective of the course is to develop skills in terms of the design of communication networks and systems, including structured cabling. In addition to traditional communication systems, the course aims to provide students with skills needed for optimizing fifth and sixth generation networks, including a fundamental understanding of Software Defined Network (SDN) / Network Function Virtualization (NFV) paradigms, 5G RAN slicing, and the application of simple reinforcement learning based techniques for network and service management. 

Knowledge and understanding

By exploiting the knowledge acquired, the student will be able to identify the main problems and solutions for the design of a communication network or system.

Applying knowledge and understanding

 At the end of the course, students will be provided with a) skills in terms of designing a Local Area Network (LAN) b) knowledge of the legislation related to electronic communications and ICT services c) skills needed for optimizing fifth and sixth generation networks.

Making judgements

Starting from technical specifications, the student will be able to design communication networks and systems by making proper design choices autonomously. Numerical exercises, computer simulations, and the development of design projects will refine judgment skills.

Communication skills

The student will improve the technical language and will be able to interact with colleagues of a teamwork to discuss the proper solutions to a specific design problem. To this aim, during the laboratory lessons, students will be grouped in small teams. 

Learning skills

Students can broaden their knowledge through the study of recommended textbooks or scientific papers published in specialized journals.

Course Structure

49 hours theory + 30 hours laboratory.

Should teaching be carried out in mixed mode or remotely, it may be necessary to introduce changes with respect to previous statements, in line with the programme planned and outlined in the syllabus.

Required Prerequisites

Random variables and probability theory.  Main aspects related to digital modulations, source, and channel coding. Knowledge of packet-switched and circuit-switched techniques. Basic knowledge of the object oriented programming paradigm.

Attendance of Lessons

Attendance is not mandatory, but strongly recommended.

Detailed Course Content

Propagation through guided transmission media. Electrical media and optical media. 

Structured cabling design. Structured cabling. Standard TIA/EIA 568A, ISO/IEC 11801 e CEI EN 50173. Construction Products Regulation (CPR). Power over Ethernet (PoE). Italian legislation. Article 135-bis. Reference Guidelines. Optical cabling design.

Simulation theory. Recalls on Markov chains. Introduction to simulation. Simulation of queueing systems. Analysis and representation of results. Applications to communication networks. 

Network softwarization, virtualization, and RAN slicing. Introduction to network softwarization and resource virtualization. Definition of RAN slicing. Centralized, distributed, and virtualized RAN. Splitting RAN options. Network slice selection.

Reinforcement learning for network and services management. Introduction and application of reinforcement learning techniques for network and service management.

Laboratory. Design of a structured cabling. Implementation of queueing systems.Application of reinforcement learning-based solutions for network and service management.

Textbook Information

[1] Digital learning materials provided by the teacher.

[2] I. Afolabi, T. Taleb, K. Samdanis, A. Ksentini and H. Flinck, "Network Slicing and Softwarization: A Survey on Principles, Enabling Technologies, and Solutions," in IEEE Communications Surveys & Tutorials, vol. 20, no. 3, pp. 2429-2453, thirdquarter 2018.

[3] R. S. Sutton and A. G. Barto. Reinforcement Learning: An Introduction. Cambridge, MA, USA.

[4] N. C. Luong et al., "Applications of Deep Reinforcement Learning in Communications and Networking: A Survey," in IEEE Communications Surveys & Tutorials, vol. 21, no. 4, pp. 3133-3174, Fourthquarter 2019.

Course Planning

 SubjectsText References
1Propagation through guided transmission media[1]
2Structured cabling design[1]
3Simulation theory[1]
4RAN slicing[1], [2]
5Reinforcement learning techniques for network and Service management[1], [3], [4]

Learning Assessment

Learning Assessment Procedures

Practice exams and an oral exam.

Examples of frequently asked questions and / or exercises

Definition and estimate of the confidence interval for evaluating the accuracy of the results.

Main Differences between C-RAN, D-RAN, and V-RAN. 

Definition of Markov Decision Process (MDP).

VERSIONE IN ITALIANO