IEEE Workshop Data Science for Networking (DS4N)

Previously Big Data and Machine Learning in Telecom (BMLIT)

Dec 14, 2017, Boston, MA, USA

In conjunction with the 2017 IEEE International Conference on Big Data (Big Data 2017)

Schedule

Time	Title	Presenter/Author
8:45-8:50	Opening remarks	Dr.Jin Yang
8:50-9:35	Keynote Talk I: Human Behavior is Low Dimensional	Prof. Mark Crovella
9:35-10:20	Keynote Talk II: Leveraging “Big” Data Analytics for Network Performance Monitoring & Trouble-Shooting	Prof. Zhi-Li Zhang
10:20-10:45	Paper I: Automatic Detection of DNS Manipulations	Martino Trevisan
Coffee Break (10:45 – 11:05)
11:05-11:50	Keynote Talk III: AI/ML in Network Operations Automation – Challenges & Opportunities	Dr. Zihui Ge
11:50-12:15	Paper II: Mining and Modeling Web Trajectories from Passive Traces	Luca Vassio
12:15-12:40	Paper III: Application Specific Traffic Control using Network Virtualization Node in Large-Scale Disasters	Tsumugi Tairaku
12:40-12:45	Closing Remarks	Dr.Jin Yang

Overview

In recently years, data science technologies, such as big data, AI and machine learning, have attracted increasing attention in various networking domains, from network applications to network infrastructure, from telecom networks to enterprise networks, from service providers to equipment manufactures. This trend is enabled by advances and applications of big data technologies in communication networks, and increasing bodies of networked data have become available to be analyzed and mined. Therefore, there is an urgent demand of tools and products of exploiting this data to provide more intelligence in network operations and management. We see largely three bodies of networked data to be explored:

Telecom data. Operation logs of network elements, telecom data, especially data from cellular networks provide a wide variety of subscriber activity logs ranging from social activities such as calls and messaging, mobile payments, to multimedia streaming and gaming, with or without geographical information. The massive amount of telecom data offers network operators a unique opportunity to gain a more comprehensive picture of the network operation as well as their customers.
Enterprise network data. Data from machines connected to an enterprise network can be exploited to improve security, IT ops, and business analysis for the enterprise.
IoT data. The advances in IoT technologies have opened up new playgrounds for data science. Many new data science applications are proposed and deployed to optimize and improve the performance of such networks and the applications on top.

The workshop aims to bringing together researchers, data scientists, data analysts, and engineers in the area of networking to exchange their ideas, experience, and results in all aspects of mining networking data and injecting intelligence into networks and networking equipment.

This workshop is a half-day event in which there will be three keynote talks and four regular talks. You can see the detailed program here.

Topics

Topics of interest include data science practices in areas of but not limited to:

Network monitoring, anomaly detection and localization, and root cause analysis
Anomaly detection and root cause analysis in time series of network data
Learning based network resource management and provisioning
IoT network design and optimization
SDN design and optimization
Cloud provisioning, management and troubling shooting
Customer profiling and behavior analysis, and retention
Deep learning applications in network operation and optimization
Big data system management in networks or networking applications
Graph computing for communication networks
Mobile application behaviors and recommendation
Business and operational transformation through big data and learning
Application of AI in network planning, optimization, and protocol design
AI-assisted power and energy management in network
Application of reinforcement learning in network management and control
Data-driven network architecture design
Network economics through machine learning
Cost and benefit tradeoff of running machine learning based networking applications
Security for machine learning applications in networking domain
Machine learning applications in edge computing

Paper submission instructions

Please submit a full-length paper (up to 6 pages IEEE 2-column format) through the online submission system here .

Papers should be formatted to IEEE Computer Society Proceedings Manuscript Formatting Guidelines. Use the templates shown below.

8.5" x 11" Word template downloadable from here.
8.5" x 11" Word template (PDF) downloadable from here.
LaTeX formatting macros downloadable from here.

Important Dates

~~October 1~~ October 27, 2017: Due date for full workshop papers submission
November 10, 2017: Notification of paper acceptance to authors
November 20, 2017: Camera-ready of accepted papers
December 11-14 (TBD), 2017: Workshop

Review procedure

All submitted paper will be reviewed by 3 program committee members.

Workshop Organizers

Workshop Chairs

Hui Zang, Huawei Technologies, USA, hui.zang@huawei.com
Kai Yang, Tongji University, China, kaiyang@tongji.edu.cn
Jin Yang, Huawei Technologies, USA, jin.yang@huawei.com

Technical Program Committee

Soshant Bali, Facebook, USA
Vijay Erramilli, Symantec, USA
Zihui Ge, AT&T Research, USA
Xin Liu, University of California, Davis, USA
Yong Liu, New York University, USA
Xiaoli Ma, Georgia Institute of Technology, USA
Ye Ouyang, Verizon Wireless, USA
Dan Pei, Tsinghua University, China
Gyan Ranjan, Symantec, USA
Ashwin Sridharan, AT&T Research, USA
Qingsong Wen, Alibaba Group, USA
Hui Zhang, NEC Laboratories America, USA
Ying Zhang, Facebook, USA
Yanjia Sun, ADP, USA
Jun Wang, East China Normal University, China
Le Zheng, Columbia University, USA

Keynote talks

Human Behavior is Low Dimensional

Dr.Mark Crovella, Professor and Chair of the Department of Computer Science, Boston University, USA

Abstract: The talk is mainly about analysis of data from computer networks. Every person is unique and complex. But can we predict anything about how large groups of people will behave? In the 1960s the science fiction writer Isaac Asimov imagined a field called “Psychohistory” that could mathematically describe the actions of large groups. I will argue that in a certain way, aspects of that vision are in wide use today. To illustrate, I will describe examples from my own work in which the “low dimensionality” of aggregate human behavior gives us leverage on a range of problems, from predicting network traffic to detecting anomalous or malicious behavior in social networks.

Mark Crovella is Professor and Chair of the Department of Computer Science at Boston University, where he has been since 1994. From 2012 to 2014 he served as Chief Scientist of Guavus, Inc. During 2003-2004 he was a Visiting Associate Professor at the Laboratoire d'Infomatique de Paris VI (LIP6). He received a B.S. from Cornell University in 1982, and an M.S. from the State University of New York at Buffalo. He received his Ph.D. in Computer Science from the University of Rochester in 1994. From 1984 to 1994 he worked at Calspan Corporation in Buffalo NY, eventually as a Senior Computer Scientist.
His research interests span both computer networking and network science. Much of his work has been on improving the understanding, design, and performance of parallel and networked computer systems, mainly through the application of data mining, statistics, and performance evaluation. In the networking arena, he has worked on characterizing the Internet and the World Wide Web. He has explored the presence and implications of self-similarity and heavy-tailed distributions in network traffic and Web workloads. He has also investigated the implications of Web workloads for the design of scalable and cost-effective Web servers. In addition he has made numerous contributions to Internet measurement and modeling; and he has examined the impact of network properties on the design of protocols and the construction of statistical models. In the network science arena, he has focused on the analysis of social, biological, and data networks. As of 2017, Google Scholar reports over 25,000 citations to his work. He has given numerous invited talks and tutorials, and is a founder of and consultant to companies involved in Internet technologies.
Professor Crovella is co-author of Internet Measurement: Infrastructure, Traffic, and Applications (Wiley Press, 2006) and is the author of over two hundred papers on networking and computer systems. He holds ten patents deriving from his research. Between 2007 and 2009 he was Chair of ACM SIGCOMM. He is a past editor for Computer Communication Review, IEEE-ACM Transactions on Networking, Computer Networks and IEEE Transactions on Computers. He was the Program Chair for the 2003 ACM SIGCOMM Internet Measurement Conference and for IFIP Networking 2010, and the General Chair of the 2005 Passive and Active Measurement Workshop. His paper (with Azer Bestavros) “Self-Similarity in World Wide Web Traffic: Evidence and Possible Causes” received the 2010 ACM SIGMETRICS Test of Time Award, and his paper (with Gonca Gursun, Natali Ruchansky, and Evimaria Terzi) “Routing State Distance: A Path-Based Metric for Network Analysis” won a 2013 IETF/IRTF Applied Networking Research Prize. Professor Crovella is a Fellow of the ACM and the IEEE.

Leveraging “Big” Data Analytics for Network Performance Monitoring & Trouble-Shooting

Dr.Zhi-Li Zhang, McKnight Distinguished University Professor, Qwest Chair Professor of Computer Science at the University of Minnesota, USA

Abstract: As we become increasingly reliant on a variety of large-scale Internet services for our daily activities, providing as good a quality-of-experience (QoE) as possible to users become imperative. For example, even a small increase in response time hurts user experience and impacts the monetization ability of service providers. It is thus extremely important for service providers to understand the key factors that impact performance and to quickly detect and diagnose any performance degradation. However, this is an extremely challenging task, as cloud computing and large-scale Internet services such as search engine and online video streaming services have necessitated a complex architecture of centralized data centers and distributed edge servers dispersed across a web of interconnected access and backbone networks to provide speedy response times to users. There are a gamut of diverse, interacting factors that can influence and affect users' QoE, spanning servers in data centers, CDN edge servers, various networks on the paths, client machines and user agents (e.g., web browser) and user behavior.
Clearly, it is important to collect various sources of data from system configurations, performance metrics and dynamic network usage and leverage "big" data analytics to tackle this challenge. In this talk, we argue that it is important to develop a systematic framework to guide this process in order to cope with the vast complexity of network performance monitoring and trouble-shooting, where domain knowledge plays a crucial role. In particular, we will describe a framework based on statistical inference and machine learning techniques to first identity and quantify the major categories of factors that have major influences on system performance. We will use two real-world case studies to illustrate the utility of this framework: i) understanding the complexity of 3G UMTS cellular network performance; and ii) dissecting the search response time variations of a large web search engine as well as a comparative study of the impact of architectural design choices on the performance of two large web search engine services.

Zhi-Li Zhang received the B.S. degree in computer science from Nanjing University, China and his M.S. and Ph.D. degrees in computer science from the University of Massachusetts. He joined the faculty of the Department of Computer Science and Engineering at the University of Minnesota in 1997, where he is currently the Qwest Chair Professor in Telecommunications and Distinguished McKnight University Professor. He currently also serves as the Associate Director for Research at the Digital Technology Center, University of Minnesota.
Prof. Zhang's research interests lie broadly in computer communication and networks, Internet technology, multimedia and emerging applications. His past research was centered on the analysis, design and development of scalable Internet QoS solutions to support performance-demanding multimedia applications. His current research thrusts focus primarily on i) building highly scalable, resilient and secure Internet infrastructure and mechanisms to enhance Internet service availability, reliability, mobility, manageability and security; and on ii) developing next-generation, service-oriented, manageable and economically viable Internet architectures to provide better support for creation, deployment, operations and and management of value-added Internet services and underlying networks.
Prof. Zhang has served on the Editorial Boards of IEEE/ACM Transactions on Networking, Computer Network -- an International Journal, Chinese Academy of Science's Journal of Computer Science and Technology, Springer's Journal of Computational Social Sciences. He was Technical Program Co-chair of IEEE INFOCOM 2006, ACM SIGMETRICS,17, ACM/USENIX Internet Measurement Conference (ACM/USENIX IMC'08), IEEE ICNP'13, and has served on the Technical Program Committees of variou conferences and workshops including ACM SIGCOMM, ACM SIGMETRICS, ACM/USENIX IMC, IEEE INFOCOM, IEEE ICNP and CoNext. He received the National Science Foundation CAREER Award in 1997. He has also been awarded the prestigious McKnight Land-Grant Professorship and George Taylor Distinguished Research Award at the University of Minnesota, and the Miller Visiting Professorship at Miller Institute for Basic Sciences, University of California, Berkeley. Prof. Zhang is co-recipient of an ACM SIGMETRICS best paper award, an IEEE International Conference on Network Protocols (ICNP) best paper award, an IEEE INFOCOM best paper award, a RAID best paper award, a SIMPLEX workshop and an APNET workshop paper award. He is a member of IEEE and ACM, and a Fellow of IEEE.

AI/ML in Network Operations Automation – challenges and opportunities

Dr.Zihui Ge, director of Operations Analytics Research department, AT&T Research, USA

Abstract: There is a recent boom on Artificial Intelligence (AI) and Machine Learning (ML) driven by significant advances in Deep Learning technologies and applications. It has become a common belief that in the years to come artificial intelligence can replace human intelligence in performing many types of tasks, including some highly complicated ones such as communication network management. On the other hand, technology advances in software defined networking (SDN) and network function virtualization (NFV) are transforming how networked services are managed and operated, driving toward a highly efficient, even a “zero-touch”, network operation model. In this talk, I will discuss how ML/AI fit in the vision of “zero-touch” network operations, particularly on control loop automation, a mechanism that facilitates fault management, performance management, service and resource optimization functions in network operations. I will focus on the challenges and opportunities both in enabling smooth operation adoption of ML/AI capabilities and in creating ML/AI based solutions for operational problems.

Zihui Ge is the director of Operations Analytics Research department in AT&T Labs – Research in Bedminster, NJ. Zihui received his Ph.D. degree in computer science from the University of Massachusetts at Amherst, his Master’s degree in computer science from Boston University, and his Bachelor’s degree in computer science from Tsinghua University. Zihui has published more than 60 research papers in the broad area of computer networking, including best paper awards in ACM CoNEXT 2011 and IEEE ICNP 2017. He won the AT&T science and technology medal in 2012 for technical innovation and leadership in creating platforms for service quality management and network management in IP and mobility networks. His research interests include network and service quality management, network operations automation, and network design and optimization.