Quality Of Experience Research Articles

Stable QoE-Aware Multi-SFCs Cooperative Routing Mechanism Based on Deep Reinforcement Learning

The explosive development of the Internet of Things (IOT) has stimulated the sudden and dynamic demand pattern of potential Service Function Chain (SFC) traffic. The virtual network built based on the requirements of Multiple SFCs (Multi-SFCs), sharing the resource, should provide better Quality of Experience (QoE) for Multi-SFCs according to the real-time network status. However, simultaneous Multi-SFCs in the routing process compete for the VNF resources of the same node and preempt the same link. The instability of QoE caused by node invalidation and link faults is highlighted. Therefore, to provide a more efficient and stable service to Multi-SFCs, quantitative QoE utility and stability models and cooperative Multi-SFCs path allocation are needed. Considering the limited resources, this paper designs a stable QoE-aware Multi-SFCs Cooperative Routing Mechanism (CRM) based on Deep Reinforcement Learning (DRL). Firstly, we model the problem of Multi-SFCs cooperative routing aiming at optimizing diverse QoEs of utility, stability and delay, and formulate it as a multi-objective optimization problem. Moreover, the QoE stable queueing model based on node and link availability is formulated by Lyapunov drift, which can potentially mitigate the QoE fluctuations. Then we associate triple Dueling Deep Q-Networks (DDQNs) and propose a cooperative computing multi-task DRL to obtain the optimal path allocation policy. Experiments are conducted to verify the effectiveness and the results show that our method outperforms its peers on QoE, delay, throughput and stability.

Joint Optimization of QoE and Fairness for Adaptive Video Streaming in Heterogeneous Mobile Environments

The rapid growth of mobile video traffic and user demand poses a more stringent requirement for efficient bandwidth allocation in mobile networks where multiple users may share a bottleneck link. This provides content providers an opportunity to jointly optimize multiple users’ experiences but users often suffer short connection durations and frequent handoffs because of their high mobility. In this paper, we propose an end-to-end scheme, VSiM, for supporting mobile video streaming applications in heterogeneous wireless networks. The key idea is allocating bottleneck bandwidth among multiple users based on their mobility profiles and Quality of Experience (QoE)-related knowledge to achieve max-min QoE fairness. Besides, the QoE of buffer-sensitive clients is further improved by the novel server push strategy based on HTTP/3 protocol without affecting the existing bandwidth allocation approach or sacrificing other clients’ view quality. VSiM is lightweight and easy to deploy in the real world without touching the underlying network infrastructure. We evaluated VSiM experimentally in both simulations and a lab testbed on top of the HTTP/3 protocol. We find that the clients’ QoE fairness of VSiM achieves more than 40% improvement compared with state-of-the-art solutions, i.e., the viewing quality of clients in VSiM can be improved from 720p to 1080p in resolution. Meanwhile, VSiM provides about 20% improvement of average QoE.

TrafAda: Cost-Aware Traffic Adaptation for Maximizing Bitrates in Live Streaming

The business growth of live streaming causes expensive bandwidth costs from the Content Delivery Network service. It necessitates traffic adaptation, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">i.e.</i> , adapting video bitrates for cost-efficient bandwidth utilization, especially under the 95 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <i>th</i> </sup> percentile pricing. However, our data-driven investigations indicate the existing methods are hard to achieve bitrate-cost balance in a long month-level billing cycle due to dynamic traffic patterns. We propose <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">TrafAda</i> , a learning-based cost-aware traffic adaptation method consisting of i) an ultra-long-term bandwidth demand forecasting model to learn complex bandwidth usage patterns, and ii) an imitation learning-based bitrate decision mechanism to optimize the ultra-long-term objective. We have implemented and deployed <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">TrafAda</i> on a large-scale live streaming system in China serving over one billion viewers from 388 cities. The results show that <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">TrafAda</i> improves peak-hour bitrate, quality of experience (QoE), and watching time by 34.75%, 44.56%, and 10.68%, respectively, without extra bandwidth cost, which can be converted to a considerable value for a commercial system.

Intelligent RAN Automation for 5G and Beyond

5G is becoming more agile and inevitably more complicated for supporting various deployment scenarios and diversified applications. Artificial Intelligence (AI) is becoming one of the most essential driving forces for 5G evolution to handle the complexity and further improve the network spectrum efficiency, energy efficiency and user experience. In this article, we share the latest standardization progress of the industry on AI in 5G. Evolving directions for the intelligent radio access networks (RAN) are analyzed and further enhancements on both AI for RAN and RAN for AI are proposed based on a hierarchical and distributed intelligent RAN architecture. Case studies are presented along with field trial results. An innovative AI-empowered RAN and service-aware cross layer optimization framework is illustrated for the quality of experience (QoE) optimization of cloud virtual reality (VR) with converged communication and computing services provided by RAN. The extension of the solution to support the AI/ML services is also discussed to shed some light on how to evolve network for AI towards the 6G vision.

Protocol of a 12-week eHealth programme designed to reduce concerns about falling in community-living older people: Own Your Balance randomised controlled trial

IntroductionConcerns about falling (CaF) are common in older people and have been associated with avoidance of activities of daily life. Exercise designed to prevent falls can reduce CaF, but the...

Networking of Internet of UAVs: Challenges and Intelligent Approaches

Internet of unmanned aerial vehicle (I-UAV) networks promise to accomplish sensing and communication tasks quickly, robustly, safely, and cost-efficiently via effective situation awareness and cooperation among UAVs. To achieve the promising benefits, the crucial IUAV networking issue should be tackled. This article argues that I-UAV networking can be classified into two categories: quality-of-service (QoS) driven networking and quality-of-experience (QoE) driven networking. Each category of networking poses emerging challenges that have severe effects on the safe and efficient accomplishment of I-UAV missions. This article elaborately analyzes these challenges and expounds on the corresponding intelligent approaches to tackle the I-UAV networking issue. Besides, considering the uplifting effect of extending the scalability of I-UAV networks through cooperating with high altitude platforms (HAPs), this article gives an overview of the integrated I-UAV and HAP network and presents the corresponding networking challenges and intelligent approaches.

EMS: Erasure-Coded Multi-Source Streaming for UHD Videos Within Cloud Native 5G Networks

Ultra-High-Definition (UHD) videos have been getting increasing attention. However, existing video streaming solutions fail to deliver them due to the extremely high bandwidth requirement. The emerging cloud native 5G networks have opened up the possibility of enhancing UHD video quality by leveraging in-network video streaming. Unfortunately, the restricted storage and bandwidth of in-network servers could become the main bottleneck. To this end, we present <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math>${\sf EMS}$</tex-math></inline-formula> , a novel UHD video streaming framework, by integrating <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">E</u> rasure-coded storage with <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">M</u> ulti-source <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">S</u> treaming. We respectively introduce a deadline-aware and a latency-sensitive metric to indicate the service quality of video servers and advocate a federated learning paradigm for the adaptive service quality update, including a reinforcement learning based multi-server selection (i.e., user local training) and a global service quality aggregation. To facilitate user local training without sacrificing streaming Quality-of-Experience (QoE), we cast the multi-server selection associated with the restriction on the average number of selected servers per video chunk into two kinds of Multi-Armed Bandit (MAB) models in terms of the proposed service quality metrics. We design lightweight Upper Confidence Bound (UCB) based algorithms with a theoretical performance guarantee. We implement a prototype of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math>${\sf EMS}$</tex-math></inline-formula> , and extensive experiments confirm the superiority of the proposed algorithms.

Green Edge Intelligence Scheme for Mobile Keyboard Emoji Prediction

Emoji prediction has been widely adopted in most mobile keyboards to improve the quality of user experience. Considering the resource constraints of smartphones, it is promising to deploy well-trained prediction models on edge servers, with which smartphones can carry out emoji prediction in an online fashion. However, a key issue in such a scenario lies in how the smartphone should select a subset of models to achieve high-accuracy and real-time emoji prediction with energy efficiency ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">a.k.a.</i> the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">model selection</i> problem). Moreover, part of the system dynamics such as the prediction accuracy and the inference latency of each model are usually unknown <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">a priori</i> in practice, further complicating the problem. In this paper, with an effective integration of history-aware online learning and online control, we propose the first green edge intelligence scheme to solve the model selection problem for mobile keyboard emoji prediction. Our theoretical analysis and simulation results verify the effectiveness of our proposed scheme in achieving a sub-linear round-averaged regret bound and energy efficiency with a high prediction accuracy and a low latency.

Towards better video services: An EEG-based interpretable model for functional quality of experience evaluation

Since emerging video services can provide emotional and social value to users, the setting of their functional parameters directly affects human cognitive and affective states, further influencing video services’ quality of experience (QoE), which we call functional QoE (fQoE). FQoE is highly dependent on human subjective perceptions and the reasons for its generation are important for service providers to optimize video services. However, existing fQoE research methods are unable to perform quantitative assessment and lack interpretability. Electroencephalogram (EEG) signals have the advantage of being difficult to disguise, and contain rich brain activity information, gaining more attention from researchers nowadays. Based on EEG, we propose an interpretable model to evaluate fQoE, and the model is tested on a self-built dataset for bullet chatting video (BCV) service. Our model can effectively fuse single electrode and multi-electrode features from EEG, and introduces Graph-based Brain-area Perception Network (GBPN) for extracting fQoE sensitive brain areas, achieving satisfactory results. We find brain areas associated with fQoE caused by different functional parameters of BCV. To sum up, our fQoE model enables quantitative assessment with neurophysiological interpretability of fQoE, providing a scientific basis for the optimization and development of video services.

QoE-aware budgeted edge data caching online: A primal–dual approach

Data caching has garnered significant attention in the field of edge computing due to the low-latency services offered by nearby edge servers. To efficiently utilize the data cache budget and ensure minimal data transmission latency, selecting appropriate edge servers for data caching is crucial. While the users’ Quality of Experience (QoE) plays a vital role in the service providers’ benefits, it has not been adequately considered in dynamic edge computing environments. This is primarily due to the non-linear correlation between QoE and Quality-of-Service (QoS), making cost-effective edge data caching challenging within the service provider’s limited budget. In this paper, we formally define the QoE-aware budgeted online edge data caching (QoE-BOEDC) problem, aiming to maximize the average user QoE while adhering to the service provider’s budget in a dynamic edge computing environment. Here, we formulate a formal optimization model for QoE-BOEDC, which can be proven to be NP-complete. Subsequently, we propose an online algorithm, PDOQ (Primal–Dual Optimization for QoE), based on the primal–dual technique, and theoretically establish its comparative ratio. Additionally, we conduct both small-scale and large-scale experimental tests, and the experimental results demonstrate that PDOQ significantly outperforms other representative algorithms.

Controlling Media Player with Hands: A Transformer Approach and a Quality of Experience Assessment

In this article, we propose a Hand Gesture Recognition (HGR) system based on a novel deep transformer (DT) neural network for media player control. The extracted hand skeleton features are processed by separate transformers for each finger in isolation to better identify the finger characteristics to drive the following classification. The achieved HGR accuracy (0.853) outperforms state-of-the-art HGR approaches when tested on the popular NVIDIA dataset. Moreover, we conducted a subjective assessment involving 30 people to evaluate the Quality of Experience (QoE) provided by the proposed DT-HGR for controlling a media player application compared with two traditional input devices, i.e., mouse and keyboard. The assessment participants were asked to evaluate objective (accuracy) and subjective (physical fatigue, usability, pragmatic quality, and hedonic quality) measurements. We found that (i) the accuracy of DT-HGR is very high (91.67%), only slightly lower than that of traditional alternative interaction modalities; and that (ii) the perceived quality for DT-HGR in terms of satisfaction, comfort, and interactivity is very high, with an average Mean Opinion Score (MOS) value as high as 4.4, whereas the alternative approaches did not reach 3.8, which encourages a more pervasive adoption of the natural gesture interaction.

QoE Estimation of WebRTC-based Audio-visual Conversations from Facial and Speech Features

The utilization of user’s facial- and speech-related features for the estimation of the Quality of Experience (QoE) of multimedia services is still underinvestigated despite its potential. Currently, only the use of either facial or speech features individually has been proposed, and relevant limited experiments have been performed. To advance in this respect, in this study, we focused on WebRTC-based videoconferencing, where it is often possible to capture both the facial expressions and vocal speech characteristics of the users. First, we performed thorough statistical analysis to identify the most significant facial- and speech-related features for QoE estimation, which we extracted from the participants’ audio-video data collected during a subjective assessment. Second, we trained individual QoE estimation machine learning-based models on the separated facial and speech datasets. Finally, we employed data fusion techniques to combine the facial and speech datasets into a single dataset to enhance the QoE estimation performance due to the integrated knowledge provided by the fusion of facial and speech features. The obtained results demonstrate that the data fusion technique based on the Improved Centered Kernel Alignment (ICKA) allows for reaching a mean QoE estimation accuracy of 0.93, whereas the values of 0.78 and 0.86 are reached when using only facial or speech features, respectively.

COCKTAIL: Video streaming QoE optimization with chunk replacement and guided learning

Adaptive bitrate (ABR) algorithms aim to provide the best user quality of experience (QoE) under fluctuating operating environments. Prior ABR protocols address the QoE maximization problem with a plethora of approximate optimization techniques including model predictive control (MPC), Lyapunov optimization, and deep reinforcement learning (DRL). Even though these algorithms provide adequate performances, they focus only on bitrate selections, precluding the chunk replacement option. We proclaim that chunk replacement can enhance the QoE if duplicated downloading is carefully administered. Moreover, we point out that bitrate selection and chunk replacement should be closely coupled into the optimization problem to fully realize the potential of chunk replacement. We first formulate a novel optimization problem with an expanded decision space that encompasses chunk replacement as well as bitrate selection. We then propose COCKTAIL, a DRL-based ABR algorithm that discovers efficient solutions to the new optimization problem by using several learning techniques. Experiments on real-world network traces show that COCKTAIL outperforms state-of-the-art baselines with improvements up to 16.1% in average QoE.

QoE-Based Performance Comparison of AVC, HEVC, and VP9 on Mobile Devices with Additional Influencing Factors

While current video quality assessment research predominantly revolves around resolutions of 4 K and beyond, targeted at ultra high-definition (UHD) displays, effective video quality for mobile video streaming remains primarily within the range of 480 p to 1080 p. In this study, we conducted a comparative analysis of the quality of experience (QoE) for widely implemented video codecs on mobile devices, specifically Advanced Video Coding (AVC), its successor High-Efficiency Video Coding (HEVC), and Google’s VP9. Our choice of 720 p video sequences from a newly developed database, all with identical bitrates, aimed to maintain a manageable subjective assessment duration, capped at 35–40 min. To mimic real-time network conditions, we generated stimuli by streaming original video clips over a controlled emulated setup, subjecting them to eight different packet-loss scenarios. We evaluated the quality and structural similarity of the distorted video clips using objective metrics, including the Video Quality Metric (VQM), Peak Signal-to-Noise Ratio (PSNR), Video Multi-Method Assessment Fusion (VMAF), and Multi-Scale Structural Similarity Index (MS-SSIM). Subsequently, we collected subjective ratings through a custom mobile application developed for Android devices. Our findings revealed that VMAF accurately represented the degradation in video quality compared to other metrics. Moreover, in most cases, HEVC exhibited an advantage over both AVC and VP9 under low packet-loss scenarios. However, it is noteworthy that in our test cases, AVC outperformed HEVC and VP9 in scenarios with high packet loss, based on both subjective and objective assessments. Our observations further indicate that user preferences for the presented content contributed to video quality ratings, emphasizing the importance of additional factors that influence the perceived video quality of end users.

Applying Software Engineering Based on Peer to Peer ‎‎Communication

The JavaScript programming language was selected to create software creation that facilitates the creation of a video connection between users because it enables the creation of cross-platform apps relatively quickly. For example, “Web Real-Time Communication (WebRTC)” standards do not specify exactly how two browsers initiate and manage communication with one another. The reason for this is that WebRTC does not specify the signaling technique or protocol. This paper's main goal is to design and construct a WebRTC simultaneous video conference between peers utilizing Google Chrome and the Socket.io signaling technology. A Local Area Network was used in this experiment (LAN). Furthermore, an assessment was conducted on the quality of experience (QoE), the Socket.io signaling method, and resources, including bandwidth consumption. This paper describes the simultaneous execution of peer-to-peer video calls with user identification (user-id).

DashReStreamer: Framework for Creation of Impaired Video Clips under Realistic Network Conditions

The continuous rise of multimedia entertainment has led to an increased demand for delivering outstanding user experience of multimedia content. However, modelling user-perceived Quality of Experience (QoE) is a challenging task, resulting in efforts for better understanding and measurement of user-perceived QoE. To evaluate user QoE, subjective quality assessment, where people watch and grade videos, and objective quality assessment in which videos are graded using one or many objective metrics are conducted. While there is a plethora of video databases available for subjective and objective video quality assessment, these videos are artificially infused with various temporal and spatial impairments. Videos being assessed are artificially distorted with startup delay, bitrate changes, and stalls due to rebuffering events. To conduct a more credible quality assessment, a reproduction of original user experiences while watching different types of streams on different types and quality of networks is needed. To aid current efforts in bridging the gap between the mapping of objective video QoE metrics to user experience, we developed DashReStreamer, an open-source framework for re-creating adaptively streamed video in real networks. The framework takes inputs in the form of video logs captured by the client in a non-regulated setting, along with an.mpd file or a YouTube URL. The ultimate result is a video sequence that encompasses all the data extracted from the video log. DashReStreamer also calculates popular video quality metrics like PSNR, SSIM, MS-SSIM and VMAF. Finally, DashReStreamer allows creating impaired video sequences from the popular streaming platform, YouTube. As a demonstration of framework usage we created a database of 332 realistic video clips, based on video logs collected from real mobile and wireless networks. Every video clip is supplemented with bandwidth trace and video logs used in its creation and also with objective metrics calculation reports. In addition to dataset, we performed subjective evaluation of video content, assessing its effect on overall user QoE. We believe that this dataset and framework will allow the research community to better understand the impacts of video QoE dynamics.

5G's Integration with Edge Computing

This study addresses the transformative integration of 5G networks with Edge Computing and Mobile Edge Computing (MEC) and explores the collaborative standards established by industry associations such as ETSI and 3GPP. The article explores the multiple possibilities of this integration, encompassing consumer and operator services, and meeting the demands of new technologies such as augmented reality, virtual reality and the Internet of Things. The strategic coexistence of distributed MEC is explored, while the security and privacy challenges of MEC are explored, emphasizing layered security and blockchain technologies. The study highlights the role of 5G and MEC in reshaping the communications landscape, providing affordable and efficient computing at the network edge, and improving network performance and quality of experience (QoE). As the 5G and MEC ecosystem evolves, the paper predicts a transformative impact on connectivity, speed, reliability and responsiveness across industries, and emphasizes the continued importance of research and development in shaping the future of communications and computing.

Leveraging Deep Q-Learning to maximize consumer quality of experience in smart grid

The smart grid system has addressed the problems of traditional power grid by not only meeting energy demand in real-time but also limiting its wastage. The two key objectives of a smart grid system are to ensure a higher Quality of Experience (QoE) for consumers and to reduce consumer costs using dynamically varying pricing concepts. However, these two objective parameters oppose each other as maximizing the consumer QoE requires the availability of sufficient electric power at any given time, which in turn increases power purchase cost. In this paper, we introduce an efficient power management system architecture of a smart grid and develop an Optimal Energy Allocation and Prediction system based on Deep Q-Leaning, namely OEAP-DQL, that brings a trade-off between the two. The developed OEAP-DQL system is a multi-objective linear programming (MOLP) problem that predicts consumer electricity demand by exploiting four different weighted and regressive moving average forecasting methods in the action space to accurately capture dynamically varying customer demand behaviors. Furthermore, iterative exploitation of multiple learning methods decreases forecasting error and intelligent stored power management helps the OEAP-DQL smart grid operator (SGO) to enhance its profit. The results of our simulation experiments show that the OEAP-DQL system outperforms the state-of-the-art works in terms of QoE and cost.

Bayesian K-means clustering based quality of experience aware multimedia video streaming

&lt;span&gt;Media streaming is an essential approach for delivering multimedia information from the source distributor to the end-user through the Internet. Along with the development of more number of users and the spread of mobile devices, the availability and diversity of multimedia applications has also increased. Multimedia users primarily prioritize quality of experience (QoE), as they seek to access multimedia content with high availability and enjoy smooth video streaming in the shortest possible time. The impact of video delivery plays a significant role in QoE, which is efficiently made by delivering the content through a specialized content delivery network architecture. In this research, a Bayesian K-means clustering algorithm is proposed for the identification of QoE in multimedia video streaming. In this multimedia video streaming, the Amazon Prime video dataset is utilized for determining the performance of the proposed model. The proposed method is developed from the ‘Patching Up’ the video quality problem (PatchVQ) model, the from patches to pictures (PaQ-2-PiQ) model is utilized for the spatial feature extraction, and 3D ResNet-18 is utilized for temporal feature extraction. The proposed Bayesian K-means achieved a QoE reward function of 5,237.42 and 5841.36 as well as a fairness reward function of 5,841.36 and 8,732.08 at the speed of 1,500 kB/s and 2,000 kB/s respectively.&lt;/span&gt;

MADRL-Based Joint Edge Caching and Bitrate Selection for Multicategory 360° Video Streaming

360-degree video streaming has gained increasing attraction in the current popular VR, AR, and MR applications, which can provide users with an immersive experience. In tile-based 360-degree video streaming, edge caching and bitrate selection strategies are jointly designed to improve users’ Quality of Experience (QoE), which incorporates video quality and rebuffer. However, the existing QoE-driven approaches use a unified QoE function to guide the decisions of edge caching and bitrate selection, which neglect the impact of video quality and rebuffer on different categories of 360-degree videos, thus failing to provide high average QoE for users. In this paper, we propose a MADRL-based joint edge caching and bitrate selection strategy for multicategory 360-degree video streaming to improve users’ average QoE. The key idea is to employ different edge caching and bitrate selection strategies for different video categories to enable fine-grained performance optimization. Based on multicategory 360-degree video streaming, we first model a joint edge caching and bitrate selection problem as a multi-agent cooperative Markov decision process with the goal of maximizing users’ average QoE. Next, an FoV-aware multi-agent soft actor-critic (FA-MASAC) algorithm is designed to help agents collaboratively learn optimal edge caching and bitrate selection decisions in a distributed way, in which each video category is treated as an agent. Finally, experimental results on real-world datasets show that our proposed strategy can greatly benefit users’ average QoE compared to existing strategies.