Multimedia Communication

Prof. Hermann Hellwagner is a keynote speaker at IEEE MIPR, 30th August – 1st September 2023.

Title: Advances in Edge-Based and In-Network Media Processing for Adaptive Video Streaming

Talk Abstract: Media traffic (mainly, video) on the Internet is constantly growing; networked multimedia applications consume a predominant share of the available Internet bandwidth. A major technical breakthrough and enabler in multimedia systems research was the HTTP Adaptive Streaming (HAS) technique. While this technique is widely used and works well in industrial networked multimedia services today, challenges exist for future multimedia systems, dealing with the trade-offs between (i) the ever-increasing content complexity, (ii) various requirements with respect to time (most importantly, low latency), and (iii) quality of experience (QoE). This situation sets the stage for our research work in the ATHENA Christian Doppler (CD) Laboratory (Adaptive Streaming over HTTP and Emerging Networked Multimedia Services; https://athena.itec.aau.at/), jointly funded by public sources and industry.

In this talk, I’ll explore one facet of the ATHENA research, namely how and with which benefits edge-based and in-network media processing can cope with adverse network conditions and/or improve media quality/perception. Content Delivery Networks (CDNs) are the classical example of supporting content distribution on today’s Internet. In recent years, though, techniques like Multi-access Edge Computing (MEC), Software Defined Networking (SDN), Network Function Virtualization (NFV), Peer Assistance (PA) for CDNs, and Machine Learning (ML) have emerged that can additionally be leveraged to support adaptive video streaming services. In the talk, I’ll present several approaches of edge-based and in-network media processing in support of adaptive streaming, in four groups:

  1. Edge Computing (EC) support, for instance transcoding, content prefetching, and adaptive bitrate algorithms at the edge.
  2. Virtualized Network Function (VNF) support for live video streaming.
  3. Hybrid P2P, Edge and CDN support including content caching, transcoding, and super-resolution at various layers of the system.
  4. Machine Learning (ML) techniques facilitating various (end-to-end) properties of an adaptive streaming system.

21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 2024), APRIL 16–18, 2024, SANTA CLARA, CA, USA

Authors: Farzad Tashtarian (Alpen-Adria Universität Klagenfurt),  Abdelhak Bentaleb (Concordia University), Hadi Amirpour (Alpen-Adria Universität Klagenfurt)Sergey Gorinsky (IMDEA Networks Institute),  Junchen Jiang (University of Chicago), Hermann Hellwagner (Alpen-Adria-Universität Klagenfurt)Christian Timmerer (Alpen-Adria Universität Klagenfurt)

Live streaming of segmented videos over the Hypertext Transfer Protocol (HTTP) is increasingly popular and serves heterogeneous clients by offering each segment in multiple representations. A bitrate ladder expresses this choice as an ordered list of bitrate-resolution pairs. Whereas existing solutions for HTTP-based live streaming use a static bitrate ladder, the fixed ladders struggle to appropriately accommodate the dynamics in the video content and network-conditioned client capabilities. This paper proposes ARTEMIS as a practical scalable alternative that dynamically configures the bitrate ladder depending on the content complexity, network conditions, and clients’ statistics. ARTEMIS seamlessly integrates with the end-to-end streaming pipeline and operates transparently to video encoders and clients. We develop a cloud-based implementation of ARTEMIS and conduct extensive real-world and trace-driven experiments. The experimental comparison vs. existing prominent bitrate ladders demonstrates that live streaming with ARTEMIS outperforms all baselines, reduces encoding computation by 25%, end-to-end latency by 18%, and increases quality of experience (QoE) by 11%.

Sebastian Uitz and Hannes Dermutz had an amazing time showcasing their highly anticipated game, A Webbing Journey, at the Level Up event at Messe Salzburg on July 1 and 2, 2023. The event was a vibrant gathering of game developers and enthusiasts, providing the perfect platform to connect with fellow game devs and experience many fantastic games.

At our booth, attendees had the opportunity to immerse themselves in the enchanting world of “A Webbing Journey” on the PC, Steam Deck, and Nintendo Switch. Players of all ages were captivated by the game’s endearing storyline and unique gameplay mechanics, embarking on a spider’s extraordinary adventure. The valuable feedback from the event-goers will be crucial in further refining and enhancing the game for its upcoming release.

In addition to the exhilarating gameplay experience, we had the privilege of sitting down for an insightful interview with the FM4 radio channel. It was an incredible opportunity to discuss the inspiration behind “A Webbing Journey” and delve into the game’s captivating features. We’re grateful for the chance to share our journey with a broader audience and promote the excitement surrounding our game.

Call for Papers

Network-assisted video streaming has become a substantial part of modern multimedia applications, enabling users to access high-quality video content over different networks, including the Internet and wireless networks. Efficiently delivering video content over networks poses numerous challenges, such as limited bandwidth, varying network conditions, heterogeneous end devices, and diverse user preferences. Network-assisted video streaming approaches leverage modern networking technologies, such as Software-Defined Networking (SDN), Network Function Virtualization (NFV), and edge computing, to not only improve the users’ Quality of Experience (QoE) but also enhance network utilization. Read more

Title: Designing A Sustainable Serverless Graph Processing Tool on the Computing Continuum

Authors: Reza Farahani, Sashko Ristov, and Radu Prodan

29th International European Conference on Parallel and Distributed Computing, , LIMASSOL, CYPRUS, 28 August–1 September 2023

Abstract: Graph processing has become increasingly popular and essential for solving complex problems in various domains, like social networks. However, processing graphs at a massive scale poses critical challenges, such as inefficient resource and energy utilization. To bridge such challenges, the Graph-Massivizer project, funded by the Horizon Europe research and innovation program, conducts research and develops a high-performance, scalable, and sustainable platform for information processing and reasoning based on the massive graph (MG) representation of extreme data. This paper presents an initial architectural design for the Choreographer, one of the five Graph-Massivizer tools. We explain Choreographer’s components and their collaboration with other Graph-Massivizer tools. We demonstrate how Choreographer can adopt the emerging serverless computing paradigm to process Basic Graph Operations (BGOs) as serverless functions across the computing continuum efficiently. Moreover, we present an early vision of our federated Function-as-a-Service (FaaS) testbed, which will be used to conduct experiments and assess Choreographer performance.

Josef Hammer presented the poster Unique Prefix vs. Unique Mask for Minimizing SDN Flows with Transparent Edge Access” at the 23rd IEEE/ACM International Symposium on Cluster, Cloud and Internet Computing (CCGrid 2023) and the paper “Scalable Transparent Access to 5G Edge Services” at the 7th IEEE International Conference on Fog and Edge Computing (ICFEC 2023), both in Bangalore, India.
AuthorsJosef Hammer and Hermann Hellwagner – Alpen-Adria-Universität Klagenfurt
Abstract: The challenging demands for the next generation of the Internet of Things have led to a massive increase in edge computing and network virtualization technologies. One significant technology is Multi-access Edge Computing (MEC), a central piece of 5G telecommunication systems. MEC provides a cloud computing platform at the edge of the radio access network and is particularly essential to satisfy the challenging low-latency demands of future applications. Our previous publications argue that edge computing should be transparent to clients. We introduced an efficient solution to implement such a transparent approach, leveraging Software-Defined Networking (SDN) and virtual IP+port addresses for registered edge services. Building on our already efficient approach, in this work, we propose significant improvements to scale our transparent solution to large-scale real-world access networks. First, by improving the modularity of our SDN controller design, we enable various options to distribute both the SDN controller’s load and the switches’ flows. Second, we introduce the Unique Mask, a solution superior to the Unique Prefix presented in our previous work that considerably reduces the number of required flows in the switches. Our evaluations show that both algorithms perform very well, with the Unique Mask capable of reducing the number of flows by up to 98 %.
 
For more information about the research, visit the website: https://edge.itec.aau.at/.
  • CP-Steering: CDN- and Protocol-Aware Content Steering Solution for HTTP Adaptive Video Streaming
    Reza Farahani (University of Klagenfurt, Austria), Abdelhak Bentaleb (Concordia University, Canada), Mohammad Shojafar (University of Surrey, UK), Hermann Hellwagner (University of Klagenfurt, Austria)
    https://dl.acm.org/doi/10.1145/3588444.3591044
  • Context-Aware HTTP Adaptive Video Streaming Utilizing QUIC’s Stream Priority
    Sindhu Chellappa (University of New Hampshire), Reza Farahani (University of Klagenfurt, Austria), Radim Bartos (University of New Hampshire, USA), Hermann Hellwagner (University of Klagenfurt, Austria)
    https://dl.acm.org/doi/10.1145/3588444.3591038
  • Which CDN to Download From? A Client and Server Strategies
    Abdelhak Bentaleb (Concordia University, Canada), Reza Farahani (University of Klagenfurt, Austria), Farzad Tashtarian (University of Klagenfurt, Austria), Hermann Hellwagner (University of Klagenfurt, Austria), Roger Zimmermann (National University of Singapore, Singapore)
    https://dl.acm.org/doi/10.1145/3588444.3591030

Titles: Modern Network-Assisted Delivery of Adaptive Video Streaming Services and Towards Sustainable Servessless Processing of Massive Graphs on Computing Continuum

Link: https://springschool.iaik.tugraz.at/

Josef Hammer presented the paper “C3-Edge – An Automated Mininet-Compatible SDN Testbed On Raspberry Pis and Nvidia Jetsons” at the 36th IEEE/IFIP Network Operations and Management Symposium (NOMS 2023) in Miami, Florida, USA.

Authors: Josef Hammer, Dragi Kimovski, Narges Mehran, Radu Prodan, and Hermann Hellwagner – Alpen-Adria-Universität Klagenfurt

Abstract: The challenging demands for the next generation of the Internet of Things have led to a massive increase in edge computing and network virtualization technologies. While there is vast potential for research in these areas, managing complex adaptive infrastructure is difficult, and experiments with real hardware are tedious to set up. Furthermore, proposed solutions often require expensive hardware or labor-intensive procedures to replicate and build on these ideas. With our C3-Edge testbed, we address these challenges and propose a novel approach for automated edge testbed setup with a low-cost software-defined network and adaptive infrastructure configuration. We validated the efficiency of our approach on a real-world computing continuum infrastructure. The evaluation results confirm that our flexible approach is suitable for all but the most bandwidth-intensive applications.

Josef Hammer presented our work at NOMS 2023

For more information about the research, visit the website: https://edge.itec.aau.at/.

Josef Hammer received the 2nd Place Outstanding Poster Award at the IPDPS PhD Forum 2023 for his poster titled “Distributed On-Demand Deployment for Transparent Access to 5G Edge Computing Services.” The event took place in St. Petersburg, Florida, USA, and was attended by Josef Hammer and Radu Prodan.

The recognition was part of the 37th IEEE International Parallel & Distributed Processing Symposium (IPDPS 2023). For more information about the research and its contributors, visit the website: https://edge.itec.aau.at/.