Tutorial 1 : Towards Cognitive Autonomous Networks

October 12, 2020 – 11:15-12:45

Overview

The ever-increasing complexity of communication networks demands ever better solutions for Network Management (NM) and Network Management Automation (NMA). Over the last decade, teams at Nokia Bell Labs have developed multiple solutions for NMA, the recent solutions focusing on the application of machine learning for Network Management Automation. It is expected that the continued use application of machine learning techniques will evolve the networks to what may be termed Cognitive Autonomous Networks (CAN).

The tutorial aims at motivating and outlining the evolution of communication networks operations and management towards fully cognitive and autonomous networks. It takes the Self-Organizing Network (SON) framework as baseline to set the path to the eventually fully Cognitive Autonomous Networks, which both the academia and the telecommunications industry strive to achieve within the next one to two decades.

The tutorial will address the following:

• the motivation and objectives for pursuing the CAN concept, 
• the state of the art regarding network management automation in mobile networks, 
• the meaning of cognitive automation and proposition for how cognition may be modelled, 
• a summary of available tools for cognitive autonomy in mobile networks, 
• a review of the already developed cognitive solutions and ongoing work and discussion in the industry, 
• a statement of open questions that still need to be addressed to realize fully Cognitive Autonomous Networks.

The tutorial is mainly intended to those undertaking or intending to undertake research work in communication networks – both in wireless networks and otherwise. It is also critical to students who may have to think about how future systems should/will be designed. It also raises question to which members of the academia working on automation system may contribute solutions. However, both leaders and researchers in the communications networks industry will also benefit in getting insight into how networks are likely to evolve and where investments may soon have to be directed. The required background for the tutorial is a general understanding of communication networks, no specialist knowledge is mandatory. However, an appreciation of network management-related literature would be advantageous.

Speakers:

Stephen S. Mwanje is a Senior Research Engineer in the “Network Automation” team at Nokia Bell Labs in Munich, Germany. He is working on the application of machine learning to network management automation and the corresponding system challenges of dealing with non-deterministic multi-agent systems that result from deploying multiple learning agents. He leads the team’s research activities on development and application of Cognition in management of Radio Access Networks. He earned his PhD/Dr.-Ing. degree (with summa cum laude) in the Integrated Communications Research Group at the Ilmenau University of Technology, in Germany. 

His thesis on multi agent coordination of cognitive self-organizing network functions proposed the first approach towards the operation of multiple cognitive functions in cellular networks. He holds a BSc. Electrical Engineering from Makerere University in Kampala, Uganda and MS Electrical Engineering from the University of Rochester in Rochester, NY. He has more than 8 years of background in mobile network operations, where he managed various projects on network planning, deployment, and optimization; microwave radio engineering and spectrum/interference management as well as fiber-optic network planning, deployment and operations. He is (co-) author of numerous articles and papers on automation in mobile network management and co-editor and lead author of the book titled “Towards Cognitive Autonomous Networks – Network Management Automation for 5G and beyond”.

&

Christian Mannweiler is the head of the Core Network Architecture & Security Research department at Nokia Bell Labs in Munich, Germany. His research focuses on network automation for 5G mobile communications systems, architectures for cloudified networks, and integration of cellular and private industrial networks. Prior to working at Bell Labs, he has been a Senior Researcher at the German Research Center for Artificial Intelligence (DFKI GmbH) in Kaiserslautern, Germany. He received his M.Sc. (Dipl.-Ing.) and Ph.D. (Dr.-Ing.) degrees from University of Kaiserslautern (Germany) in 2008 and 2014, respectively. His Ph.D. thesis on “Context-Enabled Optimization of Energy-Autarkic Networks for Carrier-Grade Wireless Backhauling” was among the first works on automation in wireless backhaul networks beyond SON approaches. Christian has worked in several nationally and EU-funded collaborative projects covering the development of cellular and industrial communication systems. He is (co-) author of numerous articles and papers on wireless communication technologies and architectures for future mobile networks and co-editor and -author of the book titled “Towards Cognitive Autonomous Networks – Network Management Automation for 5G and beyond”.

---

Tutorial 2 : Opensource Cloud Testing and Benchmarking Tools and Frameworks

October 13, 2020 – 09:30-12:45

Overview

The Open Platform for NFV (OPNFV) community, under Linux Foundation, spent about four years of collective brainpower in developing testing tools and frameworks. These tools can be run against many different types of cloud deployments as well as test different components of a cloud system. They can also perform different types of testing, such as infrastructure verification, feature validation, stress and resiliency testing, performance benchmarking and characterization. In this tutorial, we propose to educate (both to use and to enhance) the attendees about these tools and automation frameworks, and we explain how these tools can help them in their work – both academic and non-academic.

The outline of the tutorial can be summarized as below. The proposed times are only tentative.

• Introduction
• The cloud domains
• Testing Types
• Testing standards and test methodologies
• Testing challenges and the importance of automation frameworks
• II. Testing
• Functional testing – Openstack and Kubernetes: Demo and Exercise
• Performance testing – Compute Network and Storage: Demo and Exercise
• Monitoring, Reporting, Analysis – Tools
• Discussion, Q&A, and Conclusion

The main takeaways of this tutorial are:

• Testing in Cloud in general and telco-cloud in particular is very important and still has wide ranging open research problems.
• It is important to use test automation frameworks as it can make testing process both easier and reproducible.
• The tools and frameworks developed by projects under OPNFV-umbrella has use-cases beyond Telco-NFV.

Sridhar K. N. Rao received his Ph.D degree in computer science from National University of Singapore, in 2007. He has worked as Post-doctoral fellow at Microsoft Innovation Center, Politecnico Di Torino, Turin, Italy, senior researcher with NEC Technologies, and as a research fellow at Institute for Infocomm Research (I2R) Singapore. Sridhar is currently working as Architect SDN/NFV with Spirent Communications, India.

Sridhar is a Member, Technical Steering Committee, OPNFV and PTL of OPNFV-VSPERF. His research interests are mainly in the domain of next-generation wired and wireless networking, and use of Machine-Learning in Networking.

He has been working on Software-Defined-Networks since its inception in 2009. He has worked on various opensource (ODL, ONOS, RYU, OVS etc) and commercial (NEC) SDN controllers and switching-platforms. He is certified in Next-generation Datacenter Networking, Openstack,

Docker containers, Kubernetes and Machine Learning (MLSS). He has been speaker at various opensource summits and conferences such as OPNFV, OSS, ONS etc. He has contributed to ETSI-NFV TST (TST-009) specifications, winner of Testing award in OPNFV, and his articles on SDN and NFV are published and well-read in www.newstack.io. Sridhar also has a MA degree in education, and is an honorary professor at CIT, Gubbi, a rural engineering college in India. He runs the Center for creativity in Engineering at CIT.