The paper “The ADAPT Project: Adaptive and Autonomous Data” has been accepted to appear at the conference ACM International Conference on Information Technology for Social Good (GoodIT 2021) as a regular paper.
Authors: Nishant Saurabh, Vladislav Kashanskii, Radu Prodan, Aso Validi, Christina Olaverri-Monreal
Conference info: IEEE LCN
Authors: Jesús Aguilar Armijo (Alpen-Adria-Universität Klagenfurt), Christian Timmerer (Alpen-Adria-Universität Klagenfurt) and Hermann Hellwagner (Alpen-Adria-Universität Klagenfurt)
Abstract: Mobile networks equipped with edge computing nodes enable access to information that can be leveraged to assist client-based adaptive bitrate (ABR) algorithms in making better adaptation decisions to improve both Quality of Experience (QoE) and fairness. For this purpose, we propose a novel on-the-fly edge mechanism, named EADAS (Edge Assisted Adaptation Scheme for HTTP Adaptive Streaming), located at the edge node that assists and improves the ABR decisions on-the-fly. EADAS proposes (i) an edge ABR algorithm to improve QoE and fairness for clients and (ii) a segment prefetching scheme. The results show a QoE increase of 4.6%, 23.5%, and 24.4% and a fairness increase of 11%, 3.4%, and 5.8% when using a buffer-based, a throughput-based, and a hybrid ABR algorithm, respectively, at the client compared with client-based algorithms without EADAS. Moreover, QoE and fairness among clients can be prioritized using parameters of the EADAS algorithm according to service providers’ requirements.
Keywords: Dynamic Adaptive Streaming over HTTP (DASH), Edge Computing, Network-Assisted Video Streaming, Quality of Experience (QoE).
A Special Session on ‘Video Coding for Large Scale HTTP Adaptive Streaming Deployments‘ was organized by Christian Timmerer (Alpen-Adria-Universität Klagenfurt, Austria), Mohammad Ghanbari (University of Essex, UK), and Alex Giladi (Comcast, USA) on July 2 at the 35th Picture Coding Symposium (PCS) 2021. Read more about it here.
With his master thesis about “Animating Characters using Deep Learning based Pose Estimation”, Fabian Schober won the “Dynatrace Outstanding IT-Thesis Award” (DO*IT*TA). The award brings attention to extraordinary theses, motivates creativity, and provides insight into modern technologies.
In his thesis, Fabian Schober focuses on animating 2D (video game) characters using the PoseNet pose estimation model. He delivers a proof of concept on how new machine learning technologies can assist in video game development. Read more at the University press release (German only).
Successful review of the first research phase: Christian Doppler ‘pilot’ laboratory ATHENA to transition to a regular CD laboratory two years after launch. Read more about it at ATHENA website and the press release at AAU website.
Co-chairs:
TF7: Immersive Media Experiences (IMEx)
Immersive media applications are entering our daily lives starting from VR/AR/360° video applications to multi-sensory/multimedia experiences potentially addressing all human senses rather than focusing on hearing and seeing. The overall goal of providing Immersive Media Experiences (IMEx) to end-users is giving them the sensation of being part of the particular media which shall result in a worthwhile, informative user and quality of experience.
The actual objectives of this task force are as follows:
Our project „ADAPT“ started in March 2021, during the most critical phase of the COVID-19 outbreak in Europe. The demand for Personal Protective Equipment (PPE) from each country’s health care system has surpassed national stock amounts by far.
Learn more about it in an interview with Univ.-Prof. DI Dr. Radu Aurel Prodan in University Klagenfurt´s journal „ad astra“ (pdf).
The presentation has been accepted to the main-track of the Austrian-Slovenian HPC Meeting (ASHPC’21). Meeting will be organized in a hybrid format on 31 May – 2 June, 2021 at the Institute of Information Science in Maribor, Slovenia.
Title: Automated Workflows Scheduling via Two-Phase Event-based MILP Heuristic for MRCPSP Problem
Authors: Vladislav Kashansky, Gleb Radchenko, Radu Prodan, Anatoliy Zabrovskiy and Prateek Agrawal
Abstract: In today’s reality massive amounts of data-intensive tasks are managed by utilizing a large number of heterogeneous computing and storage elements interconnected through high-speed communication networks. However, one issue that still requires research effort is to enable effcient workflows scheduling in such complex environments.
As the scale of the system grows and the workloads become more heterogeneous in the inner structure and the arrival patterns, scheduling problem becomes exponentially harder, requiring problem-specifc heuristics. Many techniques evolved to tackle this problem, including, but not limited to Heterogeneous Earliest Finish Time (HEFT), The Dynamic Scaling Consolidation Scheduling (DSCS), Partitioned Balanced Time Scheduling (PBTS), Deadline Constrained Critical Path (DCCP) and Partition Problem-based Dynamic Provisioning Scheduling (PPDPS). In this talk, we will discuss the two-phase heuristic for makespan-optimized assignment of tasks and computing machines on large-scale computing systems, consisting of matching phase with subsequent event-based MILP method for schedule generation. We evaluated the scalability of the heuristic using the Constraint Integer Programing (SCIP) solver with various configurations based on data sets, provided by the MACS framework. Preliminary results show that the model provides near-optimal assignments and schedules for workflows composed of up to 100 tasks with complex task I/O interactions and demonstrates variable sensitivity with respect to the scale of workflows and resource limitation policies imposed.
Keywords: HPC Schedule Generation, MRCPSP Problem, Workflows Scheduling, Two-Phase Heuristic
Acknowledgement: This work has received funding from the EC-funded project H2020 FETHPC ASPIDE (Agreement #801091)
ADAPT started with the online Kickoff meeting, coordinated by Prof. Radu Prodan.
Prof. Radu Prodan is a keynote speaker at Memphis DATA 2021, 25th-26th March 2021.
Talk Abstract: We live in a digital world estimated to host around 4 billion Internet users and 10 billion of mobile connections generating 2.5 billion billion of data every day. Managing and extracting value from this sheer amount of raw data requires deep software analysis tools on massive distributed and parallel computing infrastructures aggregating billions of cores and threads. The talk gives an overview of the research activities at the University of Klagenfurt, Austria, on optimising system software support for extreme-scale data processing applications, with focus on scientific simulations, social media and massively multiplayer online games.