Contact Version Chinese

Embedded and Networked Systems Group

• Home
• Members
• Research
  • Network Measurement
  • Wireless and Protocols
  • Embedded and Mobile Computing
• Seminar
• Publications
• Courses
  • Computer Networks
  • Advanced Computer Networks

Advanced Computer Networks

The past few years have seen a remarkable growth in the global network infrastructure. The Internet has grown from a research curiosity to something we all take for granted, and is becoming as essential as the ubiquitous telephone and utility networks. It has been able to withstand rapid growth fairly well and its core protocols have been robust enough to accommodate applications that were unforeseen by the original Internet designers, such as the World Wide Web.

How does this global network infrastructure work and what are the design principles on which it is based? In what ways are these design principles compromised in practice? How do we make it work better in today's world? How do we ensure that it will work well in the future in the face of rapidly growing scale and heterogeneity? And how should Internet applications be written, so they can obtain the best possible performance both for themselves and for others using the infrastructure? These are some issues that we will grapple with in this course. The course will focus on the design, implementation, analysis, and evaluation of large-scale networked systems.

Topics include introduction, the network layer, the transport layer, wirelss networking, network security, cloud computing and data centers, mobile Internet, Internet of Things and wireless sensor networks, low power wireless, network measurement. Instructor: Dr. Wei Dong; Time: 13:15-16:40, every Wednesday, Summer semester, 2013; Location: Rm 413, Caoguangbiao Main Building.

Textbook

• James F. Kurose, and Keith W. Ross, Computer Networking: A Top-Down Approach, 6th Edition, Higher Education Press.
• Andrew S. Tanenbaum, and David J. Wetherall, Computer Networks, 5th Edition, China Machine Press, 2011.

Notifications

Notice: All students should write a final term report (2-4 pages) and send it to my email address (dongw AT zju.edu.cn) before 31 July, 2013. Otherwise you cannot pass this course!

Lecture Notes

• Lec 1: Course introduction [slides]
• Lec 2: Introduction to Computer Networks [slides]
  • [HotNets'12] Software-Defined Internet Architecture [paper]
  • [SIGCOMM'06] Observing the Evolution of Internet AS Topology [paper]
  • [SIGCOMM'06] Systematic Topology Analysis and Generation Using Degree Correlations [paper]
  • [INFOCOM'13] 2.5K-Graphs: from Sampling to Generation [paper]
  • [SIGCOMM'11] The Evolution of Layered Protocol Stacks Leads to an Hourglass-Shaped Architecture [paper]
  • [SIGCOMM'07] A Light-Weight Distributed Scheme for Detecting IP Prefix Hijacks in Real-Time [paper]
• Lec 3: The Internet (Transport layer) [slides]
  • [SIGCOMM'09] Safe and Effective Fine-grained TCP Retransmissions for Datacenter Communication [paper]
  • [SIGCOMM'10] Data Center TCP (DCTCP) [paper]
• Lec 4: The Internet (Networking layer) [slides]
  • [SIGCOMM'07] Achieving convergence-free routing using failure-carrying packets [paper]
  • [SIGCOMM'08] XL: An Efficient Networking Routing Algorithm [paper]
  • [SIGCOMM'08] Stable and flexible iBGP [paper]
• Lec 5: Wireless [slides]
  • [SIGCOMM'05] Idle Sense: An Optimal Access Method for High Throughput and Fairness in Rate Diverse Wireless LANs [paper]
  • [SIGCOMM'08] In defense of wireless carrier sense [paper]
  • [SIGCOMM'11] DOF: A Local Wireless Information Plane [paper]
  • [SIGCOMM'08] Zigzag decoding: combating hidden terminals in wireless networks [paper]
  • [MobiCom'10] The k-factor: Inferring Protocol Performance Using Inter-Link Reception Correlation [paper]
• Lec 6: Security [slides]
  • [SIGCOMM'11] They can hear your heart: Non-Invasive Security for Implantable Medical Devices [paper]
• Lec 7: Cloud Computing and Data Centers [slides]
  • [SIGCOMM'08] Dcell: a scalable and fault-tolerant network structure for data centers [paper]
  • [SIGCOMM'11] Better Never than Late: Meeting Deadlines in Datacenter Networks (D3) [paper]
  • [SIGCOMM'12] Deadline-Aware Datacenter TCP (D2TCP) [paper]
  • [SIGCOMM'12] Finishing Flows Quickly with Preemptive Scheduling (PDQ) [paper]
  • [NSDI'12] Less is More: Trading a little Bandwidth for Ultra-Low Latency in the Data Center (HULL) [paper]
• Lec 8: The Mobile Internet [slides]
  • [MobiCom'12] Locating in Fingerprint Space: Wireless Indoor Localization with Little Human Intervention [paper]
  • [OSDI'12] AppInsight: Mobile App Performance Monitoring in the Wild [paper]
  • [NSDI'13] eDoctor: Automatically Diagnosing Abnormal Battery Drain Issues on Smartphones [paper]
  • [INFOCOM'13] D2Taint: Differentiated and Dynamic Information Flow Tracking on Smartphones for Numerous Data Sources [paper]
• Lec 9: Internet of Things [slides]
  • [Book] Introduction to IoT (in Chinese), Yunhao Liu
• Lec 10: Wireless Sensor Networks [slides]
  • [Book] Wireless Sensor Networks (in Chinese), limin Sun
  • [COMNET'02] Wireless sensor networks: A survey [paper]
  • [COMST'10] Providing OS Support for Wireless Sensor Networks: Challenges and Approaches [paper]
• Lec 11: Low power wireless networking [slides]
  • [SenSys'03] A unifying link abstraction for wireless sensor networks [paper]
  • [OSDI'06] A Modular Network Layer for Sensornets [paper]
  • [SenSys'10] Collection Tree Protocol [paper]
  • [IPSN'11] Efficient Network Flooding and Time Synchronization with Glossy [paper]
• Lec 12: Measurement in sensor networks [slides]
  • [INFOCOM'13] Measurement and Analysis on the Packet Delivery Performance in A Large Scale Sensor Network [paper]
• Lec 13: Introduction to data mining and its application in computer networks
  • [Book] Data mining: Concepts and techniques, Jiawei Han
  • [Book] Data mining: Practical machine learning tools and techniques, 3rd Edition, Ian H. Witten
  • [MobiCom'12] Radio-jokey: Mining Program Execution to Optimize Celluar Radio Usage [paper]
  • [SIGCOMM'08] Network Discovery from Passive Measurements [paper]
  • [SIGCOMM'09] Towards Automated Performance Diagnosis in a Large IPTV Network [paper]
• Lec 14: Introduction to graph theory and its application in computer networks
  • [Book] Computers and intractability: A guide to the theory of NP-completeness
  • [INFOCOM'12] CitySee: Urban CO2 Monitoring with Sensors [paper]
  • [TMC'11] Sweep Coverage with Mobile Sensors [paper]
• Lec 15: *Introduction to optimization theory and its application in computer networks
• Lec 16: *Introduction to probability and information theory and their application in computer networks

Projects

• A reliable data transport protocol in multi-hop wireless networks. Wireless networks are often unreliable due to various reasons such as mobility of nodes and interference. A number of techniques can be applied to different network layers to enhance the reliability of a wireless network. Examples include packet-level error correction coding, link-level packet retransmissions, and network-level reliable routing. A select set of existing (and possibly new) techniques will be integrated to provide reliable data transport in this project. The protocol will be tested under different interference and mobility scenarios for performance evaluation.
• A robust multimedia streaming protocol. In this project, several techniques (such as packet scheduling and forward error correction coding) discussed in the class will be implemented to support robust audio/video streaming. A ''network controller'' will be implemented to simulate various network dynamics such as random delays and packet loss. Streaming clients and servers will connect the controller node and hence their communications experience the simulated network dynamics.
• A interference-aware routing protocol for sensor networks. Sensor networks have limited radio bandwidth due to tight resource budget. Therefore, interference is an important issue as it further reduces the effective throughput of a sensor network. Interference is usually dealt with at the link (MAC) layer of wireless networks. In this project, a routing layer will be implemented to choose routing paths that do not significantly interfere with each other. The routing layer will leverage on the interference information obtained from the link layer when finding routing paths.