3761854
doi
10.5281/zenodo.3761854
oai:zenodo.org:3761854
user-eu
Emmanouil Christakis
Visual Computing Lab (VCL), Information Technologies Institute (ITI), Centre for Research and Technology - Hellas (CERTH), Thessaloniki, Greece
Konstantinos Konstantoudakis
Visual Computing Lab (VCL), Information Technologies Institute (ITI), Centre for Research and Technology - Hellas (CERTH), Thessaloniki, Greece
Petros Drakoulis
Visual Computing Lab (VCL), Information Technologies Institute (ITI), Centre for Research and Technology - Hellas (CERTH), Thessaloniki, Greece
Stamatia Rizou
Singular Logic S.A., Athens, Greece
Avi Weit
IBM Research, Haifa, Israel
Alexandros Doumanoglou
Visual Computing Lab (VCL), Information Technologies Institute (ITI), Centre for Research and Technology - Hellas (CERTH), Thessaloniki, Greece
Nikolaos Zioulis
Visual Computing Lab (VCL), Information Technologies Institute (ITI), Centre for Research and Technology - Hellas (CERTH), Thessaloniki, Greece
Dimitrios Zarpalas
Visual Computing Lab (VCL), Information Technologies Institute (ITI), Centre for Research and Technology - Hellas (CERTH), Thessaloniki, Greece
Optimizing QoE and Cost in a 3D Immersive Media Platform: A Reinforcement Learning Approach
Panagiotis Athanasoulis
Singular Logic S.A., Athens, Greece
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/legalcode
immersive media
cognitive network optimizer
reinforcement learning
5g
5g media
<p>Recent advances in media-related technologies, including capturing and processing, have facilitated novel forms of 3D media content, increasing the degree of user immersion. In order to ensure these technologies can readily support the rising demand for more captivating entertainment, both the production and delivery mechanisms should be transformed to support the application of media or network-related optimizations and refinements on-the-fly. Network peculiarities deriving from geographic and other factors make it difficult for a greedy or a supervised machine learning algorithm to successfully foresee the need for reconfiguration of the content production or delivery procedures. For these reasons, Reinforcement Learning (RL) approaches have lately gained popularity as partial information on the environment is enough for an algorithm to begin its training and converge to an optimal policy. The contribution of this work is a Cognitive Network Optimizer (CNO) in the form of an RL agent, designed to perform corrective actions on both the production and consumption ends of an immersive 3D media platform, depending on a collection of real-time monitoring parameters, including infrastructure, application-level and quality of experience (QoE) metrics. Our work demonstrates CNO approaches with different foci, i.e., a greedy maximization of the users’ QoE, a QoE-focused RL approach and a combined QoE-and-Cost RL approach.</p>
Zenodo
2020-04-22
info:eu-repo/semantics/conferencePaper
3761853
user-eu
1
award_title=Programmable edge-to-cloud virtualization fabric for the 5G Media industry; award_number=761699; award_identifiers_scheme=url; award_identifiers_identifier=https://cordis.europa.eu/projects/761699; funder_id=00k4n6c32; funder_name=European Commission;
1587673220.479258
781740
md5:33f3abda084213aa9f77d028833c215c
https://zenodo.org/records/3761854/files/Optimizing QoE and Cost in a 3D Immersive Media Platform - A Reinforcement Learning Approach - camera ready.pdf
public
10.5281/zenodo.3761853
isVersionOf
doi