Farzad Tashtarian to give the initial talk of his habilitation at University of Klagenfurt

How to Optimize Dynamic Adaptive Video Streaming? Challenges and Solutions

[slide]

Abstract: Empowered by today’s rich tools for media generation and collaborative production and convenient network access to the Internet, video streaming has become very popular. Dynamic adaptive video streaming is a technique used to deliver video content to users over the Internet, where the quality of the video adapts in real time based on the network conditions and the capabilities of the user’s device. HTTP Adaptive Streaming (HAS) has become the de-facto standard to provide a smooth and uninterrupted viewing experience, especially when network conditions frequently change. Improving the QoE of users concerning various applications‘ requirements presents several challenges, such as network variability, limited resources, and device heterogeneity. For example, the available network bandwidth can vary over time, leading to frequent changes in the video quality. In addition, different users have different preferences and viewing habits, which can further complicate live streaming optimization. Researchers and engineers have developed various approaches to optimize dynamic adaptive streaming, such as QoE-driven adaptation, machine learning-based approaches, and multi-objective optimization, to address these challenges. In this talk, we will give an introduction to the topic of video streaming and point out the significant challenges in the field. We will present a layered architecture for video streaming and then discuss a selection of approaches from our research addressing these challenges. For instance, we will present approaches to improve the  QoE of clients in User-generated content applications in centralized and distributed fashions. Moreover, we will present a novel architecture for low-latency live streaming that is agnostic to the protocol and codecs that can work equally with existing HAS-based approaches.

,

Paper accepted: C3-Edge – An Automated Mininet-Compatible SDN Testbed On Raspberry Pis and Nvidia Jetsons

36th IEEE/IFIP Network Operations and Management Symposium (NOMS 2023) Miami, USA
Authors: Josef Hammer, Dragi Kimovski, Narges Mehran, Radu Prodan, and Hermann Hellwagner (Alpen-Adria-Universität Klagenfurt, Austria)
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.
,

Poster-Paper accepted: Unique Prefix vs. Unique Mask for Minimizing SDN Flows with Transparent Edge Access

23rd International Symposium on Cluster, Cloud and Internet Computing (CCGrid 2023) Bangalore, India
Authors: Josef Hammer and Hermann Hellwagner (Alpen-Adria-Universität Klagenfurt, Austria)
Abstract: Multi-access Edge Computing (MEC) is a central piece of 5G telecommunication systems and is essential to satisfy the challenging low-latency demands of future applications. MEC provides a cloud computing platform at the edge of the radio access network that developers can utilize for their 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. In this work, 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 %.
,

Paper accepted: Scalable Transparent Access to 5G Edge Services

7th IEEE International Conference on Fog and Edge Computing (ICFEC 2023) held in conjunction with CCGrid 2023 Bangalore, India
Authors: Josef 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.
Read more
Hadi
,

Patent approval for “Fast multi-rate encoding for adaptive HTTP streaming”

Title: Fast multi-rate encoding for adaptive HTTP streaming

Authors: Hadi Amirpour (Alpen-Adria-Universität Klagenfurt, Austria), Ekrem Çetynkaya (Alpen-Adria-Universität Klagenfurt, Austria), and Christian Timmerer (Alpen-Adria-Universität Klagenfurt, Austria)

Abstract: According to embodiments of the disclosure, information of higher and lower quality encoded video segments is used to limit Rate-Distortion Optimization (RDO) for each Coding Unit Tree (CTU). A method first encodes the highest bit-rate segment and consequently uses it to encode the lowest bit-rate video segment. Block structure and selected reference frame of both highest and lowest bit-rate video segments are used to predict and shorten RDO process for each CTU in middle bit-rates. The method delays just one frame using parallel processing. This approach provides time-complexity reduction compared to the reference software for middle bit-rates while degradation is negligible. Read more

23 February. Radu Prodan presented the Graph-Massivizer project at the “Get-to-know” introductory and welcome day, part of Data Spaces Support Centre activities.

Radu Prodan presented the Graph-Massivizer project at the “Get-to-know” introductory and welcome day, part of Data Spaces Support Centre activities on 23 February.

HE Data-DSSC-23022023-Agenda

Radu Prodan presented the Graph-Massivizer project at the CERCIRAS COST action in Gdansk, Poland

Radu Prodan presented the Graph-Massivizer project at the CERCIRAS COST action on 7th February in Gdansk, Poland

,

EduDay 2023 a great success

On February 8, 2023, EduDay – organised by the educational lab and students of the HAK 1 Klagenfurt – took place for the first time. Several hundred students were guided through the laboratories and got their first insight into research. CD laboratory ATHENA participated as well and presented background and results from the world of video streaming to the interested participants.

Find more info here.

 

 

 

Kick-off meeting Graph-Massivizer

The kick-off meeting of the EU Horizon project – Graph-Massivizer (Massive Graph Processing of Extreme Data for a Sustainable Economy, Society, and Environment) took place from January 30th – February 2nd, 2023, at Klagenfurt University.
The Graph-Massivizer team comprising twelve international industrial and academic partners from Austria, Italy, Ireland, Slovenia, Norway, Netherlands, and Germany, pledged support to research and develop a high-performance, scalable, and sustainable platform for information processing and reasoning based on the massive graph representation of extreme data. Moreover, various aspects of the Graph-Massivizer toolkit, including five open-source software tools and FAIR graph datasets, were discussed in this meeting.

SIGMM Records Column: Green Video Streaming: Challenges and Opportunities

SIGMM Records Column

Samira Afzal (Alpen-Adria-Universität (AAU) Klagenfurt, Austria), Radu Prodan (Alpen-Adria-Universität (AAU) Klagenfurt, Austria), Christian Timmerer (Alpen-Adria-Universität (AAU) Klagenfurt and Bitmovin Inc., Austria)

Introduction:

Regarding the Intergovernmental Panel on Climate Change (IPCC) report in 2021 and Sustainable Development Goal (SDG) 13 “climate action”, urgent action is needed against climate change and global greenhouse gas (GHG) emissions in the next few years [1]. This urgency also applies to the energy consumption of digital technologies. Internet data traffic is responsible for more than half of digital technology’s global impact, which is 55% of energy consumption annually. The Shift Project forecast [2] shows an increase of 25% in data traffic associated with 9% more energy consumption per year, reaching 8% of all GHG emissions in 2025.

Video flows represented 80% of global data flows in 2018, and this video data volume is increasing by 80% annually [2].  This exponential increase in the use of streaming video is due to (i) improvements in Internet connections and service offerings [3], (ii) the rapid development of video entertainment (e.g., video games and cloud gaming services), (iii) the deployment of Ultra High-Definition (UHD, 4K, 8K), Virtual Reality (VR), and Augmented Reality (AR), and (iv) an increasing number of video surveillance and IoT applications [4]. Interestingly, video processing and streaming generate 306 million tons of CO2, which is 20% of digital technology’s total GHG emissions and nearly 1% of worldwide GHG emissions [2].

While research has shown that the carbon footprint of video streaming has been decreasing in recent years [5], there is still a high need to invest in research and development of efficient next-generation computing and communication technologies for video processing technologies. This carbon footprint reduction is due to technology efficiency trends in cloud computing (e.g., renewable power), emerging modern mobile networks (e.g., growth in Internet speed), and end-user devices (e.g., users prefer less energy-intensive mobile and tablet devices over larger PCs and laptops). However, since the demand for video streaming is growing dramatically, it raises the risk of increased energy consumption.

Investigating energy efficiency during video streaming is essential to developing sustainable video technologies. The processes from video encoding to decoding and displaying the video on the end user’s screen require electricity, which results in CO2 emissions. Consequently, the key question becomes: “How can we improve energy efficiency for video streaming systems while maintaining an acceptable Quality of Experience (QoE)?”.