Towards Self Driven Networks / 10/12 April 2018 / Marriott Paris
Wednesday 11 April 2018 | Conference Day One

  • Registration and welcome coffee from 07.30
  • Start of the Conference 09.00
  • Exhibition open from 08.00 to 20.00
  • Seated Lunch: 12.30
  • End of Conference: 17.30
  • Cocktail Reception: 19.30

 
CHAIRWOMAN
Caroline Gabriel, Co-founder and Research Director, Rethink Technology Research, Senior Contributor,Next Generation Wireless, Analysys Mason,

Caroline has been engaged in technology analysis, research and consulting for 30 years and since 2002, has been focused entirely on mobile and wireless.   As co-founder and research director of Rethink Technology Research, Caroline has developed a significant research base and forecast methodology, based around deep contacts with mobile and converged operators round the world. This addresses critical issues and trends in mobile and wireless infrastructure, and particularly operator deployment intentions for 4G, 5G, small cells, Cloud-RAN and other technologies.   She is also a senior contributor to Analysys Mason’s Next Generation Wireless research programme.   She has led research and consulting projects with a wide range of clients, including mobile infrastructure vendors, large and start-up operators, regulators, trade bodies, government agencies and financial institutions. Her advice and forecasts have helped inform strategic decisions at a wide range of vendors, operators, start-ups and finance houses.   Prior to setting up Rethink, Caroline held various executive positions at VNU Business Publishing BV, then Europe’s largest producer of technology related B2B reports and publications. She was the European content and research director, and was a member of the leadership team for VNU’s online business. She holds an MA from the University of Oxford.

INTRODUCTION SESSION
09.00
Artificial Intelligence for Networking
AI can be effectively used in many networking areas, such as fault isolation, intrusion detection, event correlation, log analysis, capacity planning, and design optimization, just to name a few.

Luyuan Fang,
VP Technology, Expedia

Dr. Luyuan Fang is VP Technology at Expedia, currently focusing on Artificial Intelligence (AI), Machine Learning (ML) for networking.   From 2013 to 2016,Luyuan was Principal Network Engineer at Microsoft Azure, where she led the innovation of Hierarchical SDN architecture for hyper-scale (millions of end-points) Cloud/Data Center (DC) networks; she developed host-based IPv6 Security features in Azure SDN DevOps team; and she prototyped optical fault detection tool using Azure IoT and ML. From 2006 to 2013, Luyuan worked at Cisco as Principal Engineer in SP Routing, DC, SDN, NFV.   From 1998 to 2006, Luyuan was Principal MTS at AT&T Labs, where she played a key architect role in building AT&T’s IP/MPLS Backbone and MPLS/BGP VPN Services. Prior to networking, Dr. Fang also held several research positions in AI, Deep Learning in Australia, Canada, and US, where she built Neural Networks for pattern recognition, applied to speech, hand written character recognition, image compression, and smart network management tools. Her Ph.D. work was “Design of Computational Neuron Networks”.   Luyuan holds several patents and pending patents in computer networking. She has co-authored 14 IETF RFCs for Internet Standards. She is a frequent speaker in prominent Global Networking Conferences in SDN, NFV, and MPLS. She has over 100 publications, including IEEE/ACM articles, conf. papers and industrial speeches.

09.30
Towards Data-Driven Management of the Internet and Cloud in 5G/IoT Era
During the past several years there have been remarkable advancement in academic research for applying data mining techniques for network management. Providing a tutorial survey of those academic research and discussing how those researches will innovate network management tasks such as fault management, configuration, performance management.

Kohei Shiomoto, Professor, Tokyo City University

Kohei Shiomoto is Senior Manager of Communication & Traffic Service Quality Project, NTT Network Technology Laboratories, NTT, Tokyo, Japan.   He joined the Nippon Telegraph and Telephone Corporation (NTT), Tokyo, Japan in April 1989. He has been engaged in R&D of high-speed networking including ATM, IP, (G)MPLS, and IP+Optical networking in NTT labs. From August 1996 to September 1997 he was a visiting scholar at Washington University in St. Louis, MO, USA. From April 2006 to June 2011, he lead the IP Optical Networking Research Group in NTT Network Service Systems Laboratories. He is active in standardization of GMPLS in the IETF. Since July 2011, he has been leading the traffic engineering research group in NTT Service Integration Laboratories. Since July 2012, he has been leading Communication & Traffic Service Quality Project of NTT Network Technology Laboratories, NTT, Tokyo, Japan.   He received the B.E., M.E., and Ph.D degrees in information and computer sciences from Osaka University, Osaka in 1987 1989, and 1998, respectively. He is a Fellow of IEICE, a Senior Member of IEEE, and a member of ACM.

10.00
Coffee Break / Exhibition / Interop Event
10.30
Machine Learning for Networking: Separating Fact from Fiction
Machine Learning is being hyped in almost every imaginable field while at the same time rapid progress is being made in various fields. However, networking is lagging far behind in the development and deployment of Machine Learning techniques. Looking at current events in Machine Learning, and what the challenges, opportunities, and realities are in developing and deploying Machine Learning in the networking space.

David Meyer, Chief Scientist, VP & Fellow, Brocade
11.00
Knowledge-Defined Networking
Exploring the reasons for the lack of AI adoption and demonstrating that the rise of two recent paradigms: Software-Defined Networking (SDN) and Network Analytics (NA), will facilitate the adoption of these techniques in the context of network operation and control. Describing a new paradigm that accommodates and exploits SDN, NA and AI, and providing use cases that illustrate its applicability and benefits. Presenting simple experimental results that support its feasibility. We refer to this new paradigm as Knowledge-Defined Networking (KDN)

Albert Cabelos, Universitat Politècnica de Catalunya

Albert Cabellos received a BSc (2001), MSc (2005) and PhD (2008) degree in Computer Science Engineering from the Technical University of Catalonia (www.upc.edu). In 2004 he was awarded with a full scholarship to carry out PhD studies at the Department of Computer Architecture, Technical University of Catalonia (UPC), Spain.   In september 2005 he became an assistant professor of the Computer Architecture Department and as a researcher in the Broadband Communications Group (http://cba.upc.edu/). In 2010 he joined the NaNoNetworking Center in Catalunya (http://www.n3cat.upc.edu) where he is the Scientific Director. He is an editor of the Elsevier Journal on Nano Computer Network and founder of the ACM NANOCOM conference, the IEEE MONACOM workshop and the N3Summit. He has also founded the LISPmob open-source initiative (http://lispmob.org) along with Cisco. He has been a visiting researcher at Cisco Systems and Agilent Technologies and a visiting professor at the Royal Institute of Technology (KTH) and the Massachusetts Institute of Technology (MIT).   Since 2015 he is the Vice-Dean for International and Institutional Relations at FIB-UPC. He has participated in several national (Cicyt), EU (FP7), USA (NSF) and industrial projects (Samsung and Cisco). He has given more than 10 invited talks (MIT, Cisco, INTEL, MIET, Northeastern Univ. etc.) and co-authored more than 15 journal and 40 conference papers. His main research interests are future architectures for the Internet and nano-scale communications.

AI AND 5G SESSION
11.30
Cognitive 5G Management: It takes a Village
5G is expected to be a revolution and not simply an evolution of current mobile networks. In this regards, 5G management needs to be a built-in management “to avoid the build it first manage it later networks”.

Cognitive network management has been widely accepted as the current orientation for an efficient, agile and automated management operations. Artificial intelligence techniques are the cornerstone of Cognitive network management to develop self-aware, self-configuring, self-optimization, self-healing and self-protecting systems.

Presenting the essence of the H2020 CogNet project in terms of architecture, best practices and key use cases.


Imen Grida Ben Yahia
, Orange Labs

Imen Grida Ben Yahia is currently with Orange Labs, France, as Orange Expert in Future Networks. She is leading a research project, on Autonomic & Cognitive Management for software networks. She received her PhD degree in Telecommunication Networks from Pierre et Marie Curie University in conjunction with Télécom SudParis in 2008.   Her current research interests are autonomic and cognitive management for software and programmable networks that include artificial intelligence for SLA and fault management, knowledge and abstraction for management operations, intent- and policy-based management. As such, she contributed to several European research projects like Servery, FP7 UniverSelf and the H2020 CogNet and authored several scientific conference and journal papers in the field of autonomic and cognitive management. Imen is Chair of the IEEE Technical Committee on Network Intelligence (ongoing). She is currently TPC chair of Netsoft 2018 and also a member of several TPCs and conference organizing committees.

12.00
AI in Handsets and Implications for 4G/5G
Handsets, vehicles and other mobile-connected devices are becoming AI-enabled
  • Will putting more AI capability on the end-points reduce the need for low-latency 5G realtime connections to the cloud?
  • Will future mobile AI applications “learn in the cloud” and “get deployed at the edge”?
  • Does this change the data-traffic assumptions for 5G business models?

Dean Bubley,
Disruptive Analysis
12.30
Seated Lunch


 
SERVICE AUTOMATION & NETWORK MANAGEMENT SESSION
14.00
An Intelligence-Defined Network Architecture
Presenting a centralized and SDN compatible IDN (Intelligence-Defined Network) architecture, aiming to apply Artificial Intelligence technologies, including Machine Learning mechanisms, to networks. It can intelligently learn the network environment and historic data, and dynamically adapt to a changing situation and enhance their own intelligence with by learning from new data. It can learn and complete complicated tasks, such as traffic load balancing associated with link utilities, autonomic network operation & maintenance dynamic flow&path controlling in large-scale network, etc. It can even predict the future network situation for proactive controlling. The IDN architecture can also be integrated with various network infrastructures, such as SDN, NFV&MANO, intelligence router, traditional router, etc.

Sheng Jiang, Principal Engineer of the Network Technology Laboratory,
Huawei Technologies

Dr. Sheng JIANG, Principal Engineer of the Network Technology Laboratory, Huawei Technologies; in charge of standardization works in the Network Technology Laboratory.   He received his Ph.D. degree in Computer Science from University College London 2005. He joined Huawei Technologies 2007, is now mainly working on Intelligence-Defined Network, Autonomic Network research and standardization.   He is active in IETF, IRTF, and ETSI. He is the rapporteur for WI2 (Self-Organizing Control and Management Planes) & WI6 (Intelligence-Defined Network) in ETSI/NGP ISG, and currently chairing IETF ANIMA WG (Autonomic Networking Integrated Model and Approach). He has currently published 24 RFCs, and holding 7 IETF working group drafts.

14.30
AI for Network Automation and Service Design
Proposing to use AI techniques to continuously improve service delivery. The architecture comprises:
  • a high-level, intent-oriented service definition
  • real-time, service-oriented telemetry
  • telemetry correlation and time-series building
  • proactive adjustment of service parameters to meet intent
  • automatic “Service Motion” to maintain SLAs
Bullet 2 requires high-quality telemetry; bullet 3 needs machine learning for prediction and time-series analysis; bullets 4 and 5 need automation to take action in the network.

The whole architecture embodies a closed-loop structure for service life-cycle management.

Kireeti Kompella, Juniper Networks
15.00
Coffee Break / Exhibition / Interop Event
15.30
Network Analytics for Large Scale Internet Security Monitoring
We need the capacity to observe at very large scale what happens in our organization but also on the entire Internet either in a passive or active manner. This prerequisite requires advanced measuring and monitoring techniques supporting then data mining and machine learning algorithms. However, this large scale security analytics has to deal with the large volume of data even if partial, the relative blindness of the observation points with large adoption of encryption, the lack of appropriate existing metrics to compare network data, etc.

Jérôme François, Researcher, INRIA
16.00
Google: Machine Learning and Telemetry Aspects of the Networking Operations
Covering an in-depth review of various aspects of Machine Learning techniques enabling Network Operations. Telemetry data is key to manage networks and its health. Various building blocks like, streaming, publishing, transport, etc., championed by Google, play an important role in manageability of the networks. Subsequently, usage of Machine Learning and AI techniques unlocked whole new insight into network behaviour and enable us to operate networks @scale.

Sam Aldrin,
Network Architect, Google Network Operations

Sam Aldrin works as Network Architect @Google Network Operations. He is involved in architecting and operating of Google DC networks in order to meet the ever growing demands of Network Capacity and Bandwidth. He is also co-chair of Network Virtualization Overlay over Layer 3 Working Group at IETF.  Prior to Google, worked as Principal Engineer at Huawei Technologies and Technical Leader at Cisco Systems, developing various networking technologies. Author of various RFC’s and drafts in the area of Routing Protocols within IETF. Frequent speaker various networking conferences and forums related to SDN, NFV and other networking technologies.


16.30 DEBATE
Machine Learning versus Rule-based Systems

MODERATOR
Caroline Gabriel, Rethink Research

Kireeti Kompella, Juniper Networks

David Meyer, Brocade

Kohei Shiomoto, Senior Manager, NTT

Kohei Shiomoto is Senior Manager of Communication & Traffic Service Quality Project, NTT Network Technology Laboratories, NTT, Tokyo, Japan.   He joined the Nippon Telegraph and Telephone Corporation (NTT), Tokyo, Japan in April 1989. He has been engaged in R&D of high-speed networking including ATM, IP, (G)MPLS, and IP+Optical networking in NTT labs. From August 1996 to September 1997 he was a visiting scholar at Washington University in St. Louis, MO, USA. From April 2006 to June 2011, he lead the IP Optical Networking Research Group in NTT Network Service Systems Laboratories. He is active in standardization of GMPLS in the IETF. Since July 2011, he has been leading the traffic engineering research group in NTT Service Integration Laboratories. Since July 2012, he has been leading Communication & Traffic Service Quality Project of NTT Network Technology Laboratories, NTT, Tokyo, Japan.   He received the B.E., M.E., and Ph.D degrees in information and computer sciences from Osaka University, Osaka in 1987 1989, and 1998, respectively. He is a Fellow of IEICE, a Senior Member of IEEE, and a member of ACM.


Imen Grida Ben Yahia
, Orange Labs

Dean Bubley,
Disruptive Analysis

17.30
End of Conference Day One