Course: Advanced Network Computing

Introduction

This course will introduce recent advances in network computing. Specifically, it contains four sections: SDN/NFV, Edge Computing, IoT, and Network Big Data. In SDN/NFV, we mainly talk about two topics: Consistent update, traffic engineering and VNF embedding. In Edge Computing, we mainly talk about the topics of deployment and task offloading. In Internet-of-Things, we mainly talk about the topics of low-power protocols, long-range IoT and IoT applications/systems. In Network Big Data, we mainly talk about the topics of wireless sensing and various applications based on smartphone big data.

Reference books:

Software Defined Networks: A Comprehensive Approach, 2014
Network Function Virtualization: Ken Gray, Thomas D. Nadeau, 2016
Big Data and The Internet of Things, 2015
Edge Computing: From Hype to Reality, 2019

Requirements (2021)

Final score = 40% x class presentation+ 60% x exam.

Class presentation

The class score comes from the class presentations.

Each student is required to participate in a presentation (15 min) of a research paper selected from the top conferences/journals in network computing.
Each presentation allows up to four presenters.
The fourth presenter will have 10 points fewer than the first three members.
You may also choose to serve as a session chair so that you do not have to present papers. The session chair will share the same score with the highest score of the session papers.

Paper selection

Conference/journal rankings:

Class A: SigComm/INFOCOM/MobiCom/ToN/TMC/TPDS/JSAC/TC/NSDI/
Class B: MobiHoc/MobiSys/SenSys/ICDCS/IPSN/ICNP/IWQoS/other IEEEACM Transactions
Class C: SECON/MASS/DCOSS/Posters from Class-A conferences

If you have no idea after going through the above list, you may select papers from the list.

Time slots

We have in total 32 time slots for presentations. Please send a mail to "anc_course@mobinets.org" and apply for a specific slot. The format of the mail is shown as below.

Title: 时间序列申请 (Time slot application)
Mail: 
论文 (Paper info)：XXXXX, Conference/Journal name, Year
申请序列 (Preferred slots)：14,21,1
演讲成员 (Members)：
刘华强 (Name1)；202101233210
鹿晗 (Name2)； 201901233211
赵本山 (Name3)； 202001233212

If you are applying for a session chair role, please follow the template below.

Title: Session chair application
Mail: 
Session ID: 5, 3, 1
StuInfo: 刘华强，202101233211

Please refer to the following time table before applying for a specific time slot. Green blocks are available slots.

Time\Date	10/11		10/18		10/25		11/01
19:30-20:00	1	2	9	10	23	24	37	38
20:05-20:35	3	4	11	12	25	26	39	40
20:40-21:10	5	6	13	14	27	28	41	42
21:15-21:45	7	8	15	16	29	30	43	44

Time\Date	10/20			10/27
14:30-15:15	17	18	19	31	32	33
15:20-16:05	20	21	22	34	35	36

Presentations:

Section 1 (1-4) (Chair: XXX)
1. 刘婧媛，张鑫 Analyzing User-Level Privacy Attack Against Federated Learning，JSAC'20
2. 王朴真，蒋国庆 Interpreting Deep Learning-Based Networking Systems，SigComm‘20
3. 徐昊，江威峰 Meaningful Availability NSDI'20
4. 周在磊
Section 2 (5-8) (Chair: XXX)

张林元齐，陈嘉俊 When to Hedge in Interactive Services ，NSDI 2021
蒋欣辰 Adaptive Clustering-based Malicious Traffic Classification at the Network Edge, INFOCOM'21
于子青，彭鑫才 Learning-Based Mobile Edge Computing Resource Management to Support Public Blockchain Networks TMC'21
刘祥坤,彭志昊 EagleEye: Wearable Camera-based Person Identification in Crowded Urban Spaces （MobiCom）2021

Section 3 (9-12) (Chair: XXX)

黄宇胜，刘嘉贺 GCN-GAN: A Non-linear Temporal Link Prediction Model for Weighted Dynamic Networks INFOCOM'19
张钦栋，徐盛 Edge Computing Assisted Adaptive Mobile Vedio Streaming，IEEE Transactions on Mobile Computing'21
孙凡，陈柯宇 Distributed Threshold-based Offloading for Large-Scale Mobile Cloud Computing，Infocom 2021
张瀚文,张铭露 Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learning, INFOCOM’19

Section 4 (13-16) (Chair: XXX)

彭翔宇，陈睿 5G Wireless Communications with High Mobility，JSAC'2020
刘佳欣，张宁，邓力玮 Predictability and Prediction of Human Mobility Based on Application-Collected Location Data, TMC, 2021
郑凯文,徐显阳,丛荣 Radio Frequency Fingerprint Identification for LoRa Using Deep Learning, JSAC’ 2021
苑辉辉,曹武豪 EdgeSharing: Edge Assisted Real-time Localization and Object Sharing in Urban Streets, INFOCOM'2021

Section 5 (17-20) (Chair: XXX)

陈一，卢庚源 Learning-Driven Decentralized Machine Learning in Resource-Constrained Wireless Edge Computing, IEEE INFOCOM, 2021

Section 6 (21-24) (Chair: XXX)

Section 7 (25-28) (Chair: XXX)

Section 8 (29-32) (Chair: XXX)

Exam

The exam will contain two types of questions: Concept understanding (7 questions) and problem-solving (2 questions). Don't worry if you do not major in computer networks because all questions will be selected from class tests (answers will be discussed in class).

Bonus system

You have chance to get bonus points before the presentations and the final exam. Here are the ways how you get bonus:

Select papers from top venues.

We encourage all students to select papers from the Class-A conferences and journals.

A Class-A paper gets 4 bonus points for presentation.
A Class-B paper gets 2 bonus points for presentation.

Select earlier time slots

As most of you have no experience of public presentations, I believe pioneers will take more pressure. As a result, the earlier you do the presentation, more bonus you get. Specifically,

time slots 1-6 get 3 bonus points
time slots 9-14 get 2 bonus points
time slots 7,8, 17-22 get 1 bonus points

Raise questions to presenters

To encourage the discussion of the presentation, each raised question will be given a 2 points bonus. Each student can gain 6 bonus (three questions) points at most.

Slides

The slides will be sent to all students in class. Note: the questions and answers will not be shared.