LearnQoS: A Learning Approach for Optimizing QoS Over Multimedia-Based SDNs

Al-Jawad, Ahmed; Shah, Purav; Gemikonakli, Orhan; Trestian, Ramona

doi:10.1109/bmsb.2018.8436781

Cited by 21 publications

(18 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Low QoE (i.e., QoE 33%) corresponded to PSNR < 25, SSIM ≤ 0.88 and ID ≥ 0.66. These boundaries conform to the values for PSNR and SSIM in previous studies [12,13,17,18,34].…”

Section: Mechanism Determining Video Qualitysupporting

confidence: 88%

Section: Implementation Of Fis2supporting

confidence: 81%

“…They mapped the inputs to FIS2 to its output and indicated QoE in form of degrees of memberships belonging to high, medium and low. The rules conformed to the previous related studies [13,17,21,34,35]. FIS3 combined the QoS and QoE values determined from FIS1 and FIS2 to indicate the overall quality of the received video.…”

Section: Implementation Of Fis2mentioning

confidence: 83%

See 2 more Smart Citations

Evaluation of Wirelessly Transmitted Video Quality Using a Modular Fuzzy Logic System

Salama¹,

Saatchi²

2019

Technologies

View full text Add to dashboard Cite

Video transmission over wireless computer networks is increasingly popular as new applications emerge and wireless networks become more widespread and reliable. An ability to quantify the quality of a video transmitted using a wireless computer network is important for determining network performance and its improvement. The process requires analysing the images making up the video from the point of view of noise and associated distortion as well as traffic parameters represented by packet delay, jitter and loss. In this study a modular fuzzy logic based system was developed to quantify the quality of video transmission over a wireless computer network. Peak signal to noise ratio, structural similarity index and image difference were used to represent the user's quality of experience (QoE) while packet delay, jitter and percentage packet loss ratio were used to represent traffic related quality of service (QoS). An overall measure of the video quality was obtained by combining QoE and QoS values. Systematic sampling was used to reduce the number of images processed and a novel scheme was devised whereby the images were partitioned to more sensitively localize distortions. To further validate the developed system, a subjective test involving 25 participants graded the quality of the received video. The image partitioning significantly improved the video quality evaluation. The subjective test results correlated with the developed fuzzy logic approach. The video quality assessment developed in this study was compared against a method that uses spatial efficient entropic differencing and consistent results were observed. The study indicated that the developed fuzzy logic approaches could accurately determine the quality of a wirelessly transmitted video.

show abstract

“…Low QoE (i.e., QoE 33%) corresponded to PSNR < 25, SSIM ≤ 0.88 and ID ≥ 0.66. These boundaries conform to the values for PSNR and SSIM in previous studies [12,13,17,18,34].…”

Section: Mechanism Determining Video Qualitysupporting

confidence: 88%

Section: Implementation Of Fis2supporting

confidence: 81%

See 1 more Smart Citation

Evaluation of Wirelessly Transmitted Video Quality Using a Modular Fuzzy Logic System

Salama¹,

Saatchi²

2019

Technologies

View full text Add to dashboard Cite

show abstract

“…The user specifies an abstract task description, which is converted into network requirements, resulting in corresponding network resources being reserved using the SDN controller. An approach named LearnQoS is proposed in [13] for QoS provisioning in multimedia video services. SDN is integrated with machine learning and policy-based network management for compliance with QoS requirements.…”

Section: Controller and Clientmentioning

confidence: 99%

“…Similarly, path P 2 has smaller length than path P 1 , but is longer than path P 3 . Similar network topologies and link parameters have been used in [9], [11], and [13].…”

Section: B Core-qosmentioning

confidence: 99%

Beyond 5G: Hybrid End-to-End Quality of Service Provisioning in Heterogeneous IoT Networks

et al. 2020

View full text Add to dashboard Cite

A significant increase is expected in video and multimedia traffic in Beyond 5G networks. The inclusion of a huge number of IoT nodes in Beyond 5G networks further complicates the design of such networks. These futuristic networks are expected to deal with this increased traffic and number of nodes while ensuring that network delays do not exceed a certain threshold. In such networks, Quality of Service (QoS) provisioning has become vital, not only to guarantee certain key performance indicators but also to improve user experience. This paper proposes a hybrid approach for end-to-end QoS provisioning, involving both clients and controllers to address these challenges. Each client tries to satisfy its own access QoS requirements by choosing optimal access device(s) and makes decisions based on locally available view. Controllers are then responsible for finding optimal paths in the core network to satisfy client core QoS requirements. Experimental results show that the proposed approach provides better QoS guarantees than several other access device selection and routing schemes.

show abstract

Solutions for Improving Rich Media Streaming Quality in Heterogeneous Network Environments

Trestian

Muntean

2022

Wiley Encyclopedia of Electrical and Electronics Engineering

View full text Add to dashboard Cite

Growing amounts of data are exchanged globally, especially with the latest increase in the number and types of smart devices, from smartphones to smart TVs, which enable both generation and consumption of rich media content. In a global context, in which the internet traffic is expected to exceed several zettabytes per year and the video traffic is estimated to exceed 82% of the total data traffic by 2022, respectively, there is a significant pressure on the underlying network infrastructure to support high quality of these rich media services. The improved wired and guided network infrastructure and emerging 5G networks, and evolving LTE and Wi‐Fi networks, are providing increasing bandwidth support and improved Quality of Service for these applications. However, the pressure the rich media content, including omnidirectional, 4K, 3D, HD video, and VR/AR applications, place on these networks is also increasing with a high rate, mostly due to the number and range of services as well as the increasing number of users. As a consequence, the increased latency and loss affects the users' Quality of Experience when consuming these rich media services. However, a simple increase in system capacity will not be enough, and alternative solutions are required to fix the provisioning of QoE for rich media streaming applications. This article describes such solutions, including adaptive multimedia and multisensorial media delivery schemes, which were proposed to improve the overall user‐perceived quality, energy efficiency, and/or network utilization.

show abstract

LearnQoS: A Learning Approach for Optimizing QoS Over Multimedia-Based SDNs

Cited by 21 publications

References 12 publications

Evaluation of Wirelessly Transmitted Video Quality Using a Modular Fuzzy Logic System

Evaluation of Wirelessly Transmitted Video Quality Using a Modular Fuzzy Logic System

Beyond 5G: Hybrid End-to-End Quality of Service Provisioning in Heterogeneous IoT Networks

Solutions for Improving Rich Media Streaming Quality in Heterogeneous Network Environments

Contact Info

Product

Resources

About