All tutorials will take place on Monday, November 6, 2017.
Tutorial #1:Fast Packet Processing Towards Scalable and Agile VNFs
Presenters: Sujata Tibrewala, Muthurajan Jayakumar, Sundar Vedantham, Harry van Haaren, Shohreh Ahvar (Intel)
Time (full day): 9:30 – 11:00, 11:30 – 13:00, 14:00 – 15:30, 16:00 – 18:00
Room: Großes Forum
Abstract:
With ever increasing network demands, and cost wars carriers are hard pressed to deploy optimized , scalable and agile VNFs. With 5G in the horizon , the demand for every changing yet faster networks is only going to increase. What does all this mean when we get down to bits and bytes of packet processing. How does a general purpose processor cope with the ever increasing packet processing work load and what software tools are available to aid this.”
Each session has link to the slides/videos. These sessions will be updated before the conference with the latest info, releases etc as available
Sessions:
- Need for High Performance Data Plane: session on how packet processing operations, header look ups, sanity checks, quality of service get translated onto CPU cycles and the performance considerations while implementing VNFs. (Speaker: Sujata Tibrewala)
- Cache Consistency – Requirements and its Packet Processing Performance Implications: Session on how where the data is stored in your VNF effects the performance under the hood and what CPU architecture advances optimize them for faster packet processing and agile VNFs (Speaker: Muthurajan Jayakumar)
- Using VPP and SRIO-V with Clear Containers: Session on demonstrating the use of VPP with DPDK and SRIO-v based networks to connect Intel Clear Containers (Speaker: Manohar Castelino and Shohreh Ahvar)
- Improving Performance of your Network Application Using Load Aware Libeventdev: Session on how an event scheduler improves core utilization and better handles dynamic traffic mixes by scheduling packets to cores according to their load with DPDK. (Speakers: Sundar Vedantham and Harry van Haaren)
CV of Presenters:
Sujata Tibrewala: is a Networking Community Manager and Developer Evangelist at Intel and is a published author and presenter at multiple IEEE conferences. She has a bachelors in Mathematics from IIT KGP and Masters from IISC in EE Bangalore. She started her career writing Layer2/Layer 3 code for Agere network processors. Subsequently she has worked on 802.1x security technologies at CISCO and also implemented Openflow 1.3 on CISCO switches. She also has worked with Virtualization using VMware stack, and works today on Intel assist open source technologies for SDN/NFV, and drives adoption of these technologies among developers.
Mjay (Muthurajan Jayakumar): has worked with the DPDK team since 2009. He joined Intel in 1991 and has been in various roles and divisions: 64- bit CPU front side bus architect, 64 bit HAL developer, among others, before he joined the DPDK team. M Jay holds 21 US patents, both individually and jointly, all issued while working at Intel. M Jay was awarded the Intel Achievement Award in 2016, Intel’s highest honor based on innovation and results.
Sundar Vedantham: is a Senior Technical Manager working in the Data Center Group in Allentown, PA. His research interests include network traffic and congestion management, high-speed networking, and theoretical computer models, areas in which he holds patents and has published papers, book chapter & articles. He received his Ph.D. in Computer Science in 1997 from Louisiana State University. He enjoys writing articles in English and Tamil to help improve public understanding of technical details behind the fields he has worked on and to attract young students to get into STEM fields.
Harry van Haaren is a Network Software Engineer based in Shannon, Ireland. Primarily working on DPDK, he has been involved with the design of the eventdev API since it was publicly available. He gained hands-on experience and practical learnings of achieving high-performance event scheduling in software during the implementation of the software eventdev PMD. He received a B.S degree in Music, Media, and Performance technology from the University of Limerick, and has a background in design and implementation of real-time audio software on Linux.
Shohreh Ahvar is currently a Ph.D candidate at the Institut Mines-Telecom, Telecom SudParis in co-accreditation with the Pierre and Marie Curie University (Paris 6) on the topic of cloud based content delivery networks. She is also a collaborating researcher at Concordia University, Montreal, Canada working on Ericsson funded project. Her research interests are Network Function Virtualization, Content Delivery Networks, Cloud computing and Wireless Sensor Networks.
Tutorial #2: Intent-based Network Programmability
Presenters: Franco Callegati, Walter Cerroni, Chiara Contoli (University of Bologna, Italy); Flavio Esposito (Saint Louis University, USA)
Time (half day): 14:00 – 15:30, 16:00 – 18:00
Room: Kleines Forum
Abstract:
The tutorial will introduce and explain the “intent-based” network programmability concept. Recently, network programmability received a lot of attention from both academia and industry, and the first ready-to-market solutions are now emerging. The concept of network programmability stems from the increasingly dominant role that software aspects are taking in modern communication infrastructures, fostered by the unprecedented combination of several technological paradigms that evolved significantly in recent years, such as virtualization, Cloud Computing, Software Defined Networking, Network Operating System, Network Function Virtualization, etc. Similarly to what happened in the computing field, one of the most relevant key enablers to efficient network programmability will be the adoption of proper abstraction models. Abstractions will allow network operators and service providers to “think out of the box” and focus on high-level resource management and service description issues, instead of taking care of technology-specific and vendor-dependent details for network service deployment.
The first goal of this tutorial is to provide an introduction to the enabling technologies, with particular emphasis on their role and interplay in determining current network programmable solutions. Once these concepts are clarified, the focus is moved to the service composition issue. The role of the orchestration will be discussed together with the interactions used to pilot them. To date such interactions have been defined by means of very specific programming interfaces, making network programmability a technically challenging task, especially in case of multi-vendor deployments. However, the need for a more user-friendly approach emerged, which allows specifying service description by means of abstractions closer to natural language expressiveness.
A solution to this problem that is currently gaining momentum is the so-called “intent-based” approach, that puts the focus on what we want to achieve instead of how to achieve it. In the second part of the tutorial the intent-based approach will be explained, with particular reference to the ONF vision as a network programming abstraction. Then some case studies will be presented, mapped on the most relevant platforms that implement this functionality, such as ONOS and OpenDaylight. A short hands-on session will be included to help the audience familiarizing with the practical aspects of intent-based network programming. Finally, current research directions and open issues will be discussed.
Tutorial outline:
- introduction to network virtualization and Software Defined Networking (SDN)
- introduction to the Network Function Virtualization (NFV) approach: ETSI NFV architectureand relevant interfaces
- network programmability and service deployment: orchestration and Service Function Chaining (SFC)
- general definition of the “intent-based” approach
- intent-based management vs. policy-based management
- current standardization directions: the ONF approach
- examples of current implementations of intent-based APIs for SDN: ONOS, ODL
- hands-on session with simple use cases
- open research questions
CV of Presenters:
Franco Callegati: is an associate professor of telecommunication networks at the University of Bologna, Italy. His research interests are in the field of teletraffic modeling and performance evaluation of telecommunication networks. He is currently working on performance evaluation and experimental validation of SDN/NFV-based networking solutions. He has been active in EU- funded research projects since FP4, where he led activities and participated in various steering committees.
Walter Cerroni: is an assistant professor of communication networks at the University of Bologna, Italy. His most recent research interests include design, implementation, and performance evaluation of virtual network function chaining in cloud computing platforms (e.g. OpenStack); modeling and design of inter- and intra-data center interconnection networks for cloud computing infrastructures; design of programmable, software-defined hybrid optical network architectures; and performance evaluation of dynamic spectrum allocation techniques in flexible optical networks.
Chiara Contoli: is a Post-doc Researcher at the University of Bologna, Italy, where she obtained her Ph.D. degree in 2017. She was a research scientist at the Network Research Laboratory of the University of California at Los Angeles, USA, where she worked on content delivery networks for automotive applications to complete her Master’s thesis. In 2016 she was visiting the Computer Science Department at Saint Louis University, USA. Her research interests are in programmable networks, SDN, NFV, and more generally in advanced networking architectures.
Flavio Esposito: received the PhD in computer science from the Boston University in 2013, and his Master of Science in telecommunication engineering from the University of Florence, Italy in 2005. He is currently an assistant professor in the Computer Science Department, Saint Louis University, St. Louis, MO. His research interests include architectures and protocols for (virtual) network management; design, implementation and evaluation of algorithms and protocols for service- based architectures, such as Software Defined Networks (SDN) and Delay-Tolerant Networks (DTN).
Tutorial #3: Softwarized Internet of Things with Lightweight Clouds in Practice
Presenters: Tryfon Theodorou, George Violettas, Lefteris Mamatas (University of Macedonia, Greece)
Time (half day): 9:30 – 11:00, 11:30 – 13:00
Room: Kleines Forum
Abstract:
The Internet of Things (IoT) technology is characterized by an explosive growth, changing our world rapidly. IoT systems and devices define a huge area of innovation, allowing people to create their own designs and products, even at home. Cloud Computing is responsible for the main infrastructures for data storage in today’s IoT applications. In high mobility environments, Lightweight Cloud solutions deployed in the edge of the infrastructure network, using Unikernel virtual machines, can achieve ultra-low latency and high bandwidth. Furthermore, the Software-Defined Networks (SDNs) and their successful implementation for infrastructure networks gradually expand to new application areas, such as the Wireless Networks and the Wireless Sensor Networks (WSNs) (i.e., enabling aesthesia in the IoT). The integration of SDN with IoT and lightweight clouds brings a new perspective and ground for innovation and research.
People with no practical experience to the above technologies usually face the following issues: (i) the setup and configuration of IoT devices and WSNs requires knowledge close to the specific hardware, where the available documentation usually refers to experts or it is obsolete; (ii) the learning curve of acquiring applied knowledge in edge computing and lightweight clouds for IoT is steep; and (iii) the solutions integrating SDN with IoT are very few and in many cases under development. The above problems create a barrier for those attempting to study these technologies, especially at their starting point.
This tutorial aims to provide knowledge and hands-on experience in the development of IoT solutions in an SDN or SDN-like controlled environment deployed in the edge of the infrastructure network and using a lightweight cloud paradigm with single-purpose network functions. Participants will realize the benefits and shortcomings of such solutions. They will also have the chance to use and program real IoT devices and setup IoT networks.
Sessions:
- The Internet of Things (IoT) session gives a general overview of the importance of IoT, present IoT solutions, the architecture of typical IoT devices, IoT design considerations and constraints, the interfacing between IoT and infrastructure networks, relevant network stacks and protocols, and the future trends. A general introduction to SDN, focusing on its application in the IoT and providing detailed description of most current Softwarized IoT solutions (including our own proposal, i.e., CORAL), their architectural design principles and implementations, followed by a review discussing the strengths and weaknesses of these approaches. The session includes hands-on activities using real IoT devices accessed through our emulab testbed.
Topics:
- Internet of Things: Trends, Benefits and Applications
- IoT Software and Hardware (Operating Systems, Sensors, Actuators and IoT Devices)
- Hands-on Exercise (no1) in IoT: The participants will connect to our emulab IoT testbed using their laptops and experiment with the Contiki operating system and Zolertia RE-Mote IoT devices
- IPv6 Protocol Stack for IoT and Application Layer Protocols
- Hands-on Exercise (no2) in IoT: Building on top of the previous practical example, the participants will gain experience in implementing and configuring an IoT network and setting up an IPv6 protocol stack (i.e., the 6LowWPAN, RPL and MQTT protocols) using our IoT testbed
- SDN architecture, applications and controllers for Software-Defined Wireless Sensor Networks (SDN-WSN)
- The CORAL SDN approach to IoT
- Hands-on Exercise (no3) in SDN-WSN: The participants will gain practical experience in Software-Defined Wireless Sensor Networks using our own CORAL-SDN protocol, implemented in the context of the Cross-Layer Control of Data Flows (CORAL) – WiSHFUL OC2 Project (Speakers: Tryfon Theodorou, Lefteris Mamatas)
- The Softwarized IoT with Lightweight Clouds session starts with a general introduction to Network Function Virtualization (NFV) using Unikernels and concludes with lightweight cloud solutions for IoT deployed at the network edge. The tutorial participants gain hands-on experience using the Softwarized IoT with Lightweight Clouds framework proposed and implemented by the Softwarized & Wireless Networks research group in the context of the Multi-homing with Ephemeral Clouds on the Move (MEC) – MONROE OC2 project.
Topics:
-
- Unikernel-based single-purpose network functions
- Network Function Virtualization for IoT
- Hands-on Exercise (no4) in Unikernels: The participants will set up and operate example Virtualization Network Functions (VNFs) using Rumprun Unikernels
- Lightweight clouds for low latency computing at the network edge
- Hands-on Exercise (no5) in Softwarized IoT and Lightweight Clouds: The participants will integrate the 2nd, 3rd and 4th hands-on exercises to build a Softwarized IoT solution with Lightweight Clouds using the MEC facilities (i.e., dashboard, controller, unikernels and protocols)
- Advantages, challenges, research trends and open issues in Softwarized IoT with Lightweight Clouds. (Speakers: George Violettas, Lefteris Mamatas)
Equipment used in practical demonstrations and exercises:
Hardware: Zolertia RE-Mote, Mini-PCs
Software: UBUNTU 16.04, Contiki 3.0, Putty and Emulab
Requirements: Attendants participating in the practical exercises should bring their own laptops. An Internet connection will be required
CV of Presenters:
Tryfon Theodorou: is the deputy Head and a senior Lecturer in the Information and Communication Technology Department, Technical Trainers College (TTC) in Riyadh, Saudi Arabia. He is a Ph.D. candidate in the area of Software-Defined Networks and IoT networks at the University of Macedonia, Thessaloniki, Greece. He holds two MSc degrees: one in Artificial Intelligence – Knowledge Based Systems from the University of Edinburgh, Scotland and one in Applied Informatics from the University of Macedonia, Thessaloniki, Greece. He received his BSc. in Information Technology from the Hellenic Open University of Patra, Greece. He has been working in the ICT sector since 1993. Over the years, he successfully managed and developed a variety of applications and software products, either as a researcher or as a software developer. From 1998 he has been involved in the area of Technical Education and Vocational Studies starting as an Information Technology Lecturer and gradually taking positions as Head of Information Technology department, Director of Studies at Technical Vocational Institutes and Colleges in Greece and Saudi Arabia. He is an active researcher with several publications. His academic interests are primarily focused in the areas of wireless sensor networks, software-defined networks, communication security and Internet of Things.
George Violettas: is a Ph.D. candidate in the area of Network Control for Wireless Mobile Devices, at the University of Macedonia, Thessaloniki, Greece. He holds a Master’s Degree in Applied Informatics from the same University. His Postgraduate Thesis investigated the Wi-Fi mobile devices positioning exploiting the wireless signal strength. He has worked for several years as a Project Manager for large-scale Wireless Networks and fire prevention facilities all over Greece. He has published more than ten publications in international journals and conferences and serves as a reviewer for several journals and conferences. His scientific interests are focused in the areas of Mobile Opportunistic Networks, Software-Defined Networks and their Security Aspects. He has been teaching in many Technical Universities and Vocational Institutes all over Greece for more than ten years. He is currently a senior lecturer and head of the TTC-ΙοΤ Laboratory at the Technical Trainers College (TTC) in Riyadh, Saudi Arabia, teaching ICT undergraduate courses and supervising Bachelor theses. He is also the Head of the Embedded System Lab in which there are many applied projects in connection with the local industry. He is also a member of various committees in the College, where he also has designed the curriculum for the network-engineering specialty of the three-year accredited bachelor offered at TTC.
Lefteris Mamatas: is an Assistant Professor in the Department of Applied Informatics, University of Macedonia, Greece. Before that, he was a researcher at University College London, Space Internetworking Center/Democritus University of Thrace, and DoCoMo Eurolabs in Munich. He received his Ph.D. from the Department of Electrical and Computer Engineering, Democritus University of Thrace in Greece. His research interests lie in the areas of software-defined networks, network management, opportunistic networks, and energy efficient communication. He participated in many international research projects, such as Dolfin (FP7), Autonomic Internet (FP7), UniverSELF (FP7), Extending Internet into Space (ESA), Ambient Networks (FP6), and others. He has published more than 40 papers in international journals and conferences. He served as a General or TPC Chair for the WWIC 2016 and 2012 conference, the INFOCOM SWFAN 2016 and 2017 workshops, and the E-DTN 2009 conference. He was a Guest Editor for the Elsevier Ad Hoc Networks Journal. He has a long teaching and thesis advising experience in University of Macedonia, Democritus University of Thrace, and University College London. He implements distance education teaching material for the Hellenic Open University. He teaches undergraduate and graduate courses in the scientific areas of the tutorial (i.e., computer networks, telecommunication systems, Software- Defined Networks, Wireless Sensor Networks and Network Function Virtualization). He is a co-author of a university textbook on lab exercises for computer networks.