The course is organized in three main parts: i) technologies for data transport and distribution in smart environments, ii) methodologies for the network design, planning and performance evaluation, and iii) laboratory experience. More in details, the course first provides a general overview of the technologies for data transport and distribution, with a particular attention to smart environments that require the management of large amounts of heterogeneous data. Then, the course focuses on some of the main methodologies used for the design, planning and performance evaluation of data distribution networks. Both analytical modelling (based on queuing theory and random graph theory) and simulation techniques are presented and applied to practical use cases. The lab experience is mainly devoted to simulation techniques (in python) and consists in a practical experience of design or performance evaluation of a smart network.

Knowledge and abilities • Knowledge on smart network architectures • Knowledge on data distribution systems • Knowledge on algorithms and techniques needed to design and manage smart networks while providing a proper level of quality to users • Knowledge of the main methodological tools that can be used to design a networking system or evaluate its performance. • Knowledge of the main elements of a simulator. • Ability to evaluate the performance of a network through simulation • Ability to use basic results of random graph theory to understand some complex networks. • Ability to model traffic sources. • Ability to understand the fundamental behavior of a networking system in terms of its stability, presence of losses, bottlenecks. • Ability to select the proper set of algorithms and technologies to provide a given service with the desired level of quality of service. • Ability in identifying algorithm pros and cons.

Basic knowledge of telecommunications, and computer networks architectures and protocols. Basic knowledge of probability theory. Basic programming skills (python).

Basic concepts on computer networks (9h) • network elements, topologies, switching techniques, multiplexing & multiple access, network congestion • The architecture and protocol stack of the Internet • TCP and UDP Multimedia networking (3h) • RTC/RTCP • HTTP Live Streaming • Adaptive streaming Cloud computing (3h) • Introduction to cloud computing architectures • IaaS, PaaS, SaaS (Infrastructure, Platform, Software as a Service) models Data centers and CDNs (6h) • Data center and content distribution architectures • SDN and virtualization • Virtual machine migration Peer-to-peer systems (9h) • Structured vs unstructured systems • BitTorrent • P2P streaming Basics of Random Graph Theory (12 h) • Basic definitions • Erdos-Renyi random graphs • Random graphs with general distribution of the node degree • Small world effect and clustering coefficient • Watts-Strowgatz random graphs • Preferential attachment graphs Simulation (18 h) • Discrete event simulation • Fitting of empirical distribution • Analysis of simulation outputs • Understanding and identifying transients Fundamental concepts in queuing: (27h) • Markov chains (6h) • Birth-death processes (3h) • Elementary queuing systems (9h) • Queues with vacations (3h) • Erlang-n and hyper-exponential (3h) • M/G/1 queue (3h) Queueing networks (6h) An introduction to traffic measurements (3h) Laboratory (24h) • Performance evaluation of a networking system through simulation

Most lectures are given in a traditional fashion. Group discussions of some of the presented algorithms are also provided to strengthen the knowledge of practical issues faced when implementing some algorithms described during the lectures. Labs will mainly devoted to modelling of smart networks and data distribution systems through simulation techniques.

The teaching material will be provided by the teachers on the web portal.

Modalitΰ di esame: Prova scritta (in aula); Elaborato scritto prodotto in gruppo; Progetto di gruppo;

Exam: Written test; Group essay; Group project;

... The exam is composed of three parts that reflect the three main topics of the course. i) The part on technologies is evaluated through a written examination of 1 h duration. The exam consists on 5 or 6 open questions. This part is evaluated with a score over 30 points. ii) The exam on methodologies is also a written exam, of 1.5h duration, and it includes 2 or 3 problems that require skills on the use of the methodologies for the network performance evaluation and design. This part is evaluated with a score over 30 points. iii) The lab experience will be evaluated through a report and, possibly, a short discussion on the report itself. The report leads to a score between 0 and 3. The final score is obtained by the mean of the first two scores to which the score of the lab report is added. All the three parts must be positively evaluated for passing the exam.

Gli studenti e le studentesse con disabilitΰ o con Disturbi Specifici di Apprendimento (DSA), oltre alla segnalazione tramite procedura informatizzata, sono invitati a comunicare anche direttamente al/la docente titolare dell'insegnamento, con un preavviso non inferiore ad una settimana dall'avvio della sessione d'esame, gli strumenti compensativi concordati con l'Unitΰ Special Needs, al fine di permettere al/la docente la declinazione piω idonea in riferimento alla specifica tipologia di esame.