Servizi per la didattica
PORTALE DELLA DIDATTICA

Network measurement laboratory

01QWPBG

A.A. 2019/20

Course Language

English

Course degree

Master of science-level of the Bologna process in Communications And Computer Networks Engineering - Torino

Course structure
Teaching Hours
Lezioni 15
Esercitazioni in laboratorio 45
Teachers
Teacher Status SSD h.Les h.Ex h.Lab h.Tut Years teaching
Mellia Marco Professore Ordinario ING-INF/03 15 0 25 0 4
Teaching assistant
Espandi

Context
SSD CFU Activities Area context
ING-INF/03 6 B - Caratterizzanti Ingegneria delle telecomunicazioni
2019/20
This is a laboratory and experimental course in the field of Internet traffic measurements. Most of the classes will be given in laboratories, with few introductory lessons for each field. Students will be guided to setup experiments, run active or passive measurement tools in real networks, and apply methodologies learned in previous classes. Students will use both passive traffic analysers, and active traffic generators to characterise and load the network. They will face lab sessions of increasing complexity, maturing a critical approach and scientific methodology toward the understanding of complex systems such as the Internet is. During the class, students will also learn basic machine learning methodologies to support the data analysis, following a data driven approach. In this second group of laboratories students will follow a hands-on approach, where the fundamentals of supervised machine learning for classification problem will be introduced and then applied in the context of Internet measurements.
This is a laboratory and experimental course in the field of Internet traffic measurements. Most of the classes will be given in laboratories, with few introductory lessons for each field. Students will be guided to setup experiments, run active or passive measurement tools in real networks, and apply methodologies learned in previous classes. Students will use both passive traffic analysers, and active traffic generators to characterise and load the network. They will face lab sessions of increasing complexity, maturing a critical approach and scientific methodology toward the understanding of complex systems such as the Internet is. During the class, students will also learn basic machine learning methodologies to support the data analysis, following a data driven approach. In this second group of laboratories students will follow a hands-on approach, where the fundamentals of supervised machine learning for classification problem will be introduced and then applied in the context of Internet measurements.
Students will mature a critical view and acquire the fundamentals of machine learning - applied to network measurements. In particular, students will get 1. the knowledge of the analysis of Internet configurations and misconfigurations, and protocols like IP, TCP, UDP, HTTP, DNS. 2. the knowledge of performance related problems in local and wide area networks via delay and throughput measurements 3. the ability to process real traffic traces and to extract information related to both performance and troubleshooting issues from real traffic. 4. the ability to use understand and use properly machine learning tools to solve some classification problems applied to internet traffic analysis. 5. the ability to use modern tools and programming languages like Python and Jupyter Notebook for quick prototyping of high level machine learning problems. The ability to apply the gained knowledge will be verified by the preparation of lab reports, and its discussion during an oral examination at the end of the course.
Students will mature a critical view and acquire the fundamentals of machine learning - applied to network measurements. In particular, students will get 1. the knowledge of the analysis of Internet configurations and misconfigurations, and protocols like IP, TCP, UDP, HTTP, DNS. 2. the knowledge of performance related problems in local and wide area networks via delay and throughput measurements 3. the ability to process real traffic traces and to extract information related to both performance and troubleshooting issues from real traffic. 4. the ability to use understand and use properly machine learning tools to solve some classification problems applied to internet traffic analysis. 5. the ability to use modern tools and programming languages like Python and Jupyter Notebook for quick prototyping of high level machine learning problems. The ability to apply the gained knowledge will be verified by the preparation of lab reports, and its discussion during an oral examination at the end of the course.
Students must have very good knowledge of the protocols and mechanisms normally used in the Internet. In particular, students must be experts with LAN protocols (Ethernet IEEE 802.3, WiFi IEEE 802.3, CSMA/CD, direct and indirect delivery, LAN interconnections), of network (IP) and transport (TCP/UDP) protocols normally used in the Internet, routing protocols (RIP, OSPF), and application layer protocols (DNS, HTTP, HTTPS, multimedia streaming protocols, etc.). Traffic models will be also used and students must be familiar with basic traffic modeling techniques (Poisson models, Markovian models, hypothesis tests, confidence interval evaluation).
Students must have very good knowledge of the protocols and mechanisms normally used in the Internet. In particular, students must be experts with LAN protocols (Ethernet IEEE 802.3, WiFi IEEE 802.3, CSMA/CD, direct and indirect delivery, LAN interconnections), of network (IP) and transport (TCP/UDP) protocols normally used in the Internet, routing protocols (RIP, OSPF), and application layer protocols (DNS, HTTP, HTTPS, multimedia streaming protocols, etc.). Traffic models will be also used and students must be familiar with basic traffic modeling techniques (Poisson models, Markovian models, hypothesis tests, confidence interval evaluation).
Students will work in the Laboratory using PCs running Linux OS. Using Ethernet switches and WiFi access points, students will have to setup experiments configuring LANs. Each group of students will use 3 PCs. Real traffic traces will be used to allow students to deal with more realistic scenarios. Students will go though the following group of laboratories: • Configuration of hosts in Local Area Networks, IP addresses management, subnetting/supernetting (2 hours) • Traffic monitoring using sniffers in LAN: TCP, UDP and HTTP (6 hours) • Performance measurement for file transfers in wired networks (6 hours) • Performance measurement for file transfers in WiFi setup (6 hours) • Performance measurement for file transfers and impact of delay and packet losses (8 hours) • Analysis of traffic traces collected from real networks and development of post-processing tools to extract information out of the raw data (15 hours) • Usage of statistical methods and data mining techniques to find correlations and solve classification problems (15 hours)
Students will work in the Laboratory using PCs running Linux OS. Using Ethernet switches and WiFi access points, students will have to setup experiments configuring LANs. Each group of students will use 3 PCs. Real traffic traces will be used to allow students to deal with more realistic scenarios. Students will go though the following group of laboratories: • Configuration of hosts in Local Area Networks, IP addresses management, subnetting/supernetting (2 hours) • Traffic monitoring using sniffers in LAN: TCP, UDP and HTTP (6 hours) • Performance measurement for file transfers in wired networks (6 hours) • Performance measurement for file transfers in WiFi setup (6 hours) • Performance measurement for file transfers and impact of delay and packet losses (8 hours) • Analysis of traffic traces collected from real networks and development of post-processing tools to extract information out of the raw data (15 hours) • Usage of statistical methods and data mining techniques to find correlations and solve classification problems (15 hours)
In this course there is large number of laboratory activities on the topics of communication networks. Students perform these laboratory activities at the the LED laboratories of the Electronic and Communication Department. It will also possible to use your own laptop for laboratories. Each laboratory will be introduced in classes, where the fundamentals of technologies and methodologies will be presented.
In this course there is large number of laboratory activities on the topics of communication networks. Students perform these laboratory activities at the the LED laboratories of the Electronic and Communication Department. It will also possible to use your own laptop for laboratories. Each laboratory will be introduced in classes, where the fundamentals of technologies and methodologies will be presented.
The teaching material will be made available by the class teacher on the Didattica web portal. Description of the lab experiments will be provided, and reference documentation will be made available to students. No textbook is available. Students must be familiar with Internet protocol and applications which can be found for example in A. Pattavina: Reti di telecomunicazioni, Mc.Graw-Hill (in Italian) or J.F. Kurose, K.W. Ross: Computer Networking: A Top-Down Approach Featuring the Internet, Pearson (in English)
The teaching material will be made available by the class teacher on the Didattica web portal. Description of the lab experiments will be provided, and reference documentation will be made available to students. No textbook is available. Students must be familiar with Internet protocol and applications which can be found for example in A. Pattavina: Reti di telecomunicazioni, Mc.Graw-Hill (in Italian) or J.F. Kurose, K.W. Ross: Computer Networking: A Top-Down Approach Featuring the Internet, Pearson (in English)
Modalità di esame: prova orale obbligatoria; elaborato scritto individuale; elaborato scritto prodotto in gruppo;
During the laboratories, students are required to work in groups. At the end of the course, each group will have to deliver a written report on the laboratory experiences as indicated by the teacher during the course (group report). In total, the report focuses on 8 topics. The report must be delivered in a single PDF file, to be uploaded to the teaching portal by the end of the exam registration deadline. The report will be corrected to verify the correctness of the reported results, and the completeness in the description of the experiments performed. All students in the group will have the same mark, expressed in thirtieths, up to a maximum of 30/30. The group report mark will be valid for all members of the group, and will be valid for two years. Once corrected, the report can be changed only in case all students agree. Each student will also have to prepare and individual report, that have to be uploaded as a single PDF file on the teaching portal by the deadline for the student registration for the exam. The individual report will be discussed during oral examination. Each student will be asked to discuss the content of the reports (both group and individual) during the oral exam. The oral exam is individual, and students will be asked to answer questions about both the practical and theoretical part of the course. The grade for the oral exam must be sufficient to pass the exam, with minimum 18/30 and maximum 30 cum laude. The final vote will be a weighted average between the evaluations of the group laboratory report (70%) and oral examinations (30%). It is possible to get additional points with specific topics reports, or preparing lessons notes to be reused in subsequent years.
Exam: compulsory oral exam; individual essay; group essay;
During the laboratories, students are required to work in groups. At the end of the course, each group will have to deliver a written report on the laboratory experiences as indicated by the teacher during the course (group report). In total, the report focuses on 8 topics. The report must be delivered in a single PDF file, to be uploaded to the teaching portal by the end of the exam registration deadline. The report will be corrected to verify the correctness of the reported results, and the completeness in the description of the experiments performed. All students in the group will have the same mark, expressed in thirtieths, up to a maximum of 30/30. The group report mark will be valid for all members of the group, and will be valid for two years. Once corrected, the report can be changed only in case all students agree. Each student will also have to prepare and individual report, that have to be uploaded as a single PDF file on the teaching portal by the deadline for the student registration for the exam. The individual report will be discussed during oral examination. Each student will be asked to discuss the content of the reports (both group and individual) during the oral exam. The oral exam is individual, and students will be asked to answer questions about both the practical and theoretical part of the course. The grade for the oral exam must be sufficient to pass the exam, with minimum 18/30 and maximum 30 cum laude. The final vote will be a weighted average between the evaluations of the group laboratory report (70%) and oral examinations (30%). It is possible to get additional points with specific topics reports, or preparing lessons notes to be reused in subsequent years.


© Politecnico di Torino
Corso Duca degli Abruzzi, 24 - 10129 Torino, ITALY
m@il