The 3rd International Workshop on Network Intelligence (NI 2020): Learning and Optimizing Future Networks

Session NI-Opening

Opening

Conference
2:30 PM — 2:45 PM EDT
Local
Jul 6 Mon, 2:30 PM — 2:45 PM EDT

Opening Session

To Be Determined

2
This talk does not have an abstract.

Session Chair

Laura Galluccio & Giovanni Schembra

Session NI-Session-1

Session 1: Networking Aspects

Conference
2:45 PM — 4:00 PM EDT
Local
Jul 6 Mon, 2:45 PM — 4:00 PM EDT

Towards In-Band Telemetry for Self Driving Wireless Networks

Prabhu Janakaraj; Pinyarash Pinyoanuntapong; Pu Wang; Minwoo Lee (University of North Carolina, Charlotte, USA)

1
This talk does not have an abstract.

End-to-end Delay Prediction Based on Traffic Matrix Sampling

Filip Krasniqi (Politecnico di Milano, Italy); Jocelyne Elias (Paris Descartes Univerisyt & Sorbonne Paris Citè, France); Jeremie Leguay (Huawei technologies, France); Alessandro E. C. Redondi (Politecnico di Milano, Italy)

2
This talk does not have an abstract.

A Novel Methodology for the Automated Detection and Classification of Networking Anomalies

Mohamed Moulay (IMDEA Networks, Spain); Rafael García (IMDEA Networks, Spain); Pablo Rojo (Nokia, Spain); Javier Lazaro (Nokia, Spain); Vincenzo Mancuso (IMDEA Networks, Spain); Antonio Fernández Anta (IMDEA Networks, Spain)

3
This talk does not have an abstract.

WiNetSense: Sensing and Analysis Model for Large-scale Wireless Networks

Nikita Trivedi; Bighnaraj Panigrahi; Hemant Kumar Rath (Tata Consultancy Services, Pvt Ltd., India)

2
This talk does not have an abstract.

Session Chair

Laura Galluccio

Session NI-Keynote

Keynote

Conference
4:30 PM — 5:30 PM EDT
Local
Jul 6 Mon, 4:30 PM — 5:30 PM EDT

Reinforcement Learning for Telecommunication Network: from Opportunistic Spectrum Access to IoTs

Raphaël Féraud (Orange Labs)

4
In reinforcement learning, an agent chooses actions in order to maximize the rewards given by a dynamic environment. As the environment is initially unknown, the agent has to interact with it to gather information. Moreover, only the reward of the chosen actions is revealed. That is why the agent faces the exploration/exploitation dilemma: she has to explore loosely estimated actions in order to build a better estimate, and she would like to maximize her cumulated reward by playing the empirically best actions. The mathematical framework which handles the exploration/exploitation dilemma is called the multi-armed bandit problem. In comparison to the general reinforcement framework, the main difference is that the state of the environment does not depend on the actions chosen previously. This simplification makes it possible to build efficient algorithms that can be proven optimal. Although the multi-armed bandits have been designed for clinical trials, they are used in many fields such as advertising, recommendation, marketing optimization, web site optimization, and since a decade in telecommunication networks. The first use case was the Opportunistic Spectrum Access (OPA), where a Secondary User aims to find a channel free from Primary User. With the development of IoTs networks and 5G networks, new use cases have emerged for instance for configuring Self Organized Network, or for optimizing energy consumption in IoT and sensor networks.

Biography

Raphaël Féraud has obtained is PhD in 1997 at University of Rennes I. During his PhD, he has worked on Neural Networks applied to Face Detection in images and video. Then at France-Télécom R&D, he has worked on different application of Neural Networks for Telecommunication including churn, profiling, fraud detection, resources allocation in ATM networks. As a project leader he has lead several projects on data mining and Big Data at Orange Labs with applications on marketing optimization and Ad targeting. Then as researcher at Orange Labs, he worked on reinforcement learning and in particular on bandit algorithms. His research on contextual bandits, non-stationary bandits and multi-player bandits are applied for optimizing communication in IoT networks.

Session Chair

Imen Grida Ben Yahia, Orange Labs, France

Session NI-Session-2

Session 2: Resource Management Aspects

Conference
5:30 PM — 6:30 PM EDT
Local
Jul 6 Mon, 5:30 PM — 6:30 PM EDT

Large-Scale and Rapid Flow Size Estimation for Improving Flow Scheduling

Su Wang; Shuo Wang; Dong Zhou; Yiran Yang; Wenjie Zhang; Tao Huang; Ru Huo; Yunjie Liu (Beijing University of Posts and Telecommunications, China)

2
This talk does not have an abstract.

Glide and Zap Q-Learning

Xiaofan He (Wuhan University, China); Richeng Jin (North Carolina State University, USA); Huaiyu Dai ((North Carolina State University, USA)

1
This talk does not have an abstract.

When Less is More: Core-Restricted Container Provisioning for Serverless Computing

Gaetano Somma (Università di Napoli, Federico II, Italy); Constantine Ayimba (IMDEA Networks, Spain); Paolo Casari (University of Trento, Italy); Simon Pietro Romano (Università di Napoli, Federico II, Italy); Vincenzo Mancuso (IMDEA Networks, Spain)

3
This talk does not have an abstract.

Removing human players from the loop: AI-assisted assessment of Gaming QoE

German Sviridov (Politecnico di Torino, Italy); Cedric Beliard (Huawei Technologies, France); Andrea Bianco (Politecnico di Torino, Italy); Paolo Giaccone (Politecnico di Torino, Italy); Dario Rossi (Telecom ParisTech, France)

3
This talk does not have an abstract.

Session Chair

Giovanni Schembra

Session NI-Closing

Closing

Conference
6:30 PM — 6:45 PM EDT
Local
Jul 6 Mon, 6:30 PM — 6:45 PM EDT

Closing Remarks

To Be Determined

0
This talk does not have an abstract.

Session Chair

Laura Galluccio & Giovanni Schembra

Made with in Toronto · Privacy Policy · © 2020 Duetone Corp.