QoE Metrics Research Articles

Optimized Visual Internet of Things in Video Processing for Video Streaming

The global expansion of the Visual Internet of Things (VIoT) has enabled various new applications during the last decade through the interconnection of a wide range of devices and sensors.Frame freezing and buffering are the major artefacts in broad area of multimedia networking applications occurring due to significant packet loss and network congestion. Numerous studies have been carried out in order to understand the impact of packet loss on QoE for a wide range of applications. This paper improves the video streaming quality by using the proposed framework Lossy Video Transmission (LVT) for simulating the effect of network congestion on the performance of encrypted static images sent over wireless sensor networks.The simulations are intended for analysing video quality and determining packet drop resilience during video conversations.The assessment of emerging trends in quality measurement, including picture preference, visual attention, and audio visual quality is checked. To appropriately quantify the video quality loss caused by the encoding system, various encoders compress video sequences at various data rates.Simulation results for different QoE metrics with respect to user developed videos have been demonstrated which outperforms the existing metrics.

Demystifying Content-Blockers: Measuring Their Impact on Performance and Quality of Experience

With the evolution of the online advertisement and tracking ecosystem, content-blockers have become the reference tool for improving the security, privacy and browsing experience when surfing the Internet. It is also commonly believed that using content-blockers to stop unsolicited content decreases the time needed for loading websites. In this work, we perform a large-scale study on the actual improvements of using content-blockers in terms of performance and quality of experience. For measuring it, we analyze the page size and loading times of the 100K most popular websites, as well as the most relevant QoE metrics, such as the Speed Index, Time to Interactive or the Cumulative Layout Shift, for the subset of the top 10K of them. Our experiments show that using content-blockers results in small improvements in terms of performance. However, contrary to popular belief, this has a negligible impact in terms of loading time and quality of experience. Moreover, in the case of small and lightweight websites, the overhead introduced by content-blockers can even result in decreased performance. Finally, we evaluate the improvement in terms of QoE based on the Mean Opinion Score (MOS) and find that two of the three studied content-blockers present an overall decrease between 3% and 5% instead of the expected improvement.

Telecom Operator’s Approach to QoE

Telecommunication networks are ever more frequently relying on artificial intelligence and machine learning techniques to detect specific use patterns or potential errors and to take automated decisions when these are encountered. This concept requires that methods be employed to measure the level of quality of a given telecommunication service, i.e. to verify quality of service (QoS) metrics. In a broader context, methods assessing the entire user experience (quality of experience – QoE) are required as well. In this article, various approaches to assessing QoS, QoE and the related metrics are presented, with a view to implement these at an FTTH network operator in Poland. Since this article presents the architecture of the system used to analyze QoE performance based on a number of QoS metrics collected by the operator, we also provide a comprehensive introduction to the QoS and QoE metrics used herein.

Energy efficient multipath routing protocol for MANET for enhancing QoS and QoE in multimedia applications

In mobile ad hoc network (MANET) the devices are interconnected by wireless manner that are able to ubiquitously retrieve contents such as video and audio streams, still images, and scalar sensor data from the environment. MANET provides low power in hazardous environment where replacement of fault evaluation in the MANET is impossible. Hence, development of an energy efficient network is essential in MANET, where the cost of network depends on the energy consumption of each mobile node. Overutilization of energy by a mobile node cannot contribute to the utility or the network as a whole. Hence to optimize the utilization of energy at each node, we propose an energy efficient multipath routing protocol for MANET for enhancing QoS and QoE metrics (EMRP-QQ), which can eventually minimize the data loss and hence there liability of the mobile nodes and the overall network. In our proposed approach an energy efficient clustering is performed using particle swarm optimization (PSO), where all the nodes are clustered without any residual nodes left in the system. Using the appropriate selection of CH and SCH the overall networks overhead utilization is reduced and hence the QoS of the network is enhanced. The result obtained through NS-2 simulation shows that the proposed algorithm performs better than FQ-MP-OLSR approach in terms of reduced energy consumption of each node without affecting QoS and QoE metrics.

Strategizing secured image storing and efficient image retrieval through a new cloud framework

Nowadays, a major problem in faster page loading through optimizing websites is the absence of having images in their intended sizes. Accordingly, while loading a webpage, most of the time overhead pertains to image-related tasks such as image loading and resizing, which can be optimized substantially through the pre-availability of smaller-size images. Therefore, in this study, we propose a strategy to enable faster and efficient image retrieval from a cloud via the necessary pre-processing of images beyond conventional online processing. We also extend the abilities of cloud file sharing from the conventional “only storing images” to pre-processing along with security reinforcing. Here, we perform the first task of resizing images to several dimensions for covering diversified remote user devices available nowadays. Then, we perform encoding and encryption of images using the P-Fibonacci transform of Discrete Cosine Coefficients (PFCC) algorithm. Afterward, we resize images using the Bicubic interpolation method to both JPEG and Progressive-JPEG (PJPEG) formats by adding a new middleware named iBuck for faster and smooth retrieval. We leverage necessary algorithms and image types after careful evaluation of their performances in our intended framework. Our evaluation covers both objective and subjective evaluations including QoE metrics such as MSE, SSIM, etc. Furthermore, we conduct detailed experimentation over real setups to evaluate the performance of our implemented middleware in a cloud file sharing environment with both custom and standard data sets. Our evaluation reveals substantial performance improvement using our proposed framework compared to that using conventional alternatives.

Deployable Models for Approximating Web QoE Metrics From Encrypted Traffic

Being on endpoints, Content Providers can easily evaluate end users' Web browsing quality of experience (Web QoE) by accessing in-browser computed application-level metrics. Because of end-to-end traffic encryption, it is becoming considerably harder for Internet Service Providers (ISPs) to evaluate the Web QoE of their customers, which is important for management purposes. In this paper, we propose data-driven machine learning techniques and exact flow-level algorithmic methods to infer well-known application-level Web performance metrics (such as SpeedIndex and Page Load Time) from raw encrypted streams of network traffic. We prove the efficiency of our approach taking as input a unique dataset of more than 200,000 experiments, targeting a large set of popular pages (Alexa top-500), from probes from several ISPs networks, with different browsers (Chrome, Firefox) and viewport combinations. Results show that our data-driven models are not only accurate for several Web performance metrics, but also feature the ability to generalize to previously unseen conditions. Furthermore, we discuss how our extremely lightweight flow-level method has a provable accuracy on a specific metric, and is thus of particular appeal from a deployment viewpoint.

VidCloud

As video-streaming services have expanded and improved, cloud-based video has evolved into a necessary feature of any successful business for reaching internal and external audiences. In this article, video streaming over distributed storage is considered where the video segments are encoded using an erasure code for better reliability. We consider a representative system architecture for a realistic (typical) content delivery network (CDN). Given multiple parallel streams/link between each server and the edge router, we need to determine, for each client request, the subset of servers to stream the video, as well as one of the parallel streams from each chosen server. To have this scheduling, this article proposes a two-stage probabilistic scheduling. The selection of video quality is also chosen with a certain probability distribution that is optimized in our algorithm. With these parameters, the playback time of video segments is determined by characterizing the download time of each coded chunk for each video segment. Using the playback times, a bound on the moment generating function of the stall duration is used to bound the mean stall duration. Based on this, we formulate an optimization problem to jointly optimize the convex combination of mean stall duration and average video quality for all requests, where the two-stage probabilistic scheduling, video quality selection, bandwidth split among parallel streams, and auxiliary bound parameters can be chosen. This non-convex problem is solved using an efficient iterative algorithm. Based on the offline version of our proposed algorithm, an online policy is developed where servers selection, quality, bandwidth split, and parallel streams are selected in an online manner. Experimental results show significant improvement in QoE metrics for cloud-based video as compared to the considered baselines.

How User Engagement Metrics Ameliorate the Web QoE?

User engagement in general is an interpretation of an individual’s reaction to an offer (a service, a product, an application). We can determine a person’s degree of commitment directly by interacting with him or by observing his behavior. To measure the user engagement some actions can be interpreted such as clicks on links, comments and download of documents. In an other hand, we can measure the user satisfaction towards a web page using web QoE metrics such as Time to First Byte (TTFB), onLoad (Load Time) and Above the Fold (ATF). These metrics are commenly used to predict web QoE using Machine Learning (ML) algorithms. By comparing the two groups of metrics (user engagement and web QoE) we conclude that user engagaement metrics are closer to user desires, that’s why in our work we focus on user engagement to predict user’s satisfaction by predicting the Mean Opinion Score (MOS). Existing works dont use user engagement metrics in datasets to predict MOS, that’s why in this paper, we propose to focus on user engagement to predict our MOS. To do so, we use the help of an existing dataset whose parameters are web QoE metrics. At first, we select metrics that have a direct relation with user enagement. Then, we refine their coefficients to obtain the best combination that gives a MOS very close to the real one (expressed directly by users). After that, we add a new column to the existing dataset that containes the new obtained engagement parameter. Finally, we apply different ML algorithms on our new dataset to predict the MOS and we conclude that decision tree is the best in our case.

An Intelligent SDN Framework Based on QoE Predictions for Load Balancing in C-RAN

The rapid growth of the Internet and technological advances are forcing mobile operators to increasingly invest in network infrastructures. C-RAN and SDN are regarded as enabling technologies that can overcome the limitations faced by operators, by reducing costs, increasing scalability, and paving the way for the next generation of 5G cellular networks. In this paper, an architectural solution based on SDN and computational intelligence is proposed for C-RAN, which can adjust BBU-RRH mapping through network load balancing rules by predicting subjective and objective QoE metrics for UHD video streaming. The simulation results achieved gains between 59% and 129%, in scenarios without activating a new BBU and scenarios that involve activating a new BBU, respectively.

Route Availability with QoE and QoS Metrics for Data Analysis of Video Stream Over a Mobile Ad Hoc Networks

Using ad hoc information amid of adaptable terminals, mobile ad hoc networks (MANETs) are absolute of any kind of communication infrastructure even though the communication quality might be degrade, since the mobile nodes roam in the service area and therefore the route paths have been disconnected frequently and re-established later. This has been considered as a major problem for quality metric and this proposes non uniformity in route path. To overcome this unstable state this paper introduces a new metric called route availability (RA). This paper proposes a new abstraction of RA as a metric for route non uniformity in a MANET and verifies how efficiently it represents the quality of service of a mobile network or the quality of experience of audio and video streaming. This concept is experimented with environment support and congenital ambience that emulates a MANET able of audio and video streaming. An additional parameter is developed for measuring route availability of two routing techniques are ad hoc on-demand distance vector routing and destination sequenced distance vector. This RA has been observed with metrics of quality of service like packet loss ratio, throughput. Finally the availability of the route is estimated by quality assessment test. The quality of audio and video streaming is increased with experimental results.

Janus: A Multi-TCP Framework for Application-Aware Optimization in Mobile Networks

As the dominant protocol on the Internet, TCP has attracted significant attention and has been implemented in various ways, each of which optimizes for a single objective such as high throughput or low delay. However, in today's mobile networks that carry traffic from diverse types of flows, this approach may lead to misconfiguration of TCP congestion control algorithms and further degrade performance for many applications. In this paper, we propose Janus, a new transport-layer framework that automatically selects among existing congestion control variants to optimize traffic in accordance with application demands. Janus is easy to deploy because it reuses existing, well-tested congestion control implementations, and does not require any in-network or client-side changes. To explore the potential for this approach, we implement Janus in the Linux kernel and extensively evaluate its performance with both emulated and real Internet traffic. We show Janus outperforms alternative protocols by offering fast convergence times in response to changing network conditions, achieving 5-10X lower delay with comparable or higher throughput. Our approach also significantly improves user-perceived performance according to QoE metrics, with up to 5X fewer interruptions for video streaming applications and 2X faster page loading for web-browsing applications.

Quality of Experience Inference for Video Services in Home WiFi Networks

Customer experience is becoming of utmost importance for operators in home network management. Hence, a notion of the customers' QoE is vital, but has mostly been neglected in favor of QoS. In this article, we aim to close a significant gap between QoS and QoE in home networks by proposing a framework for inferring QoE from remotely collected network QoS metrics. We focus on video services (e.g., YouTube application) as the main contributor and generator of indoor network traffic. A case study is performed where an experimentally obtained dataset comprising network and application QoS parameters is obtained under varying conditions (i.e., poor coverage, network overload, contention, and interference). Predictive modeling is then used to build a predictor for multiple QoE classes given the network QoS metrics remotely accessible from access points based on industry adopted standards (i.e., TR-181). This enables operators to infer specific QoE metrics using remotely collected passive network measurement with no knowledge of application-specific parameters. We show that the proposed framework achieves accuracy in the range of 85 to 95 percent depending on the QoE class, hence demonstrating the effectiveness and potential of our approach.

Benefits of mobile end user network switching and multihoming

Mobile users have not been able to exploit spatio-temporal differences between individual mobile networks operators for a variety of reasons. End user network switching and multihoming are two promising mechanisms that could allow such exploitation. However these mechanisms have not been thoroughly explored at a general system level with QoE metrics. Therefore, in this work we analyze these mechanisms in a variety of diverse scenarios through a system level model based on an agent based modeling framework.In terms of results, we find that in all scenarios end user network switching provides significant benefits in terms of both throughput and mean opinion score as the number of available networks increases. However, contrastingly, end user multihoming in most scenarios does not provide significant benefits over network switching given the same number of available networks. The major reason is inefficient radio resource allocation resulting from individual networks not taking the multihoming nature of end users into account. Though, in low user density situations this inefficiency is not a problem and multihoming does provide increased throughput though not increased mean opinion scores. Finally, scenarios that vary the fraction of users adopting multihoming suggests that both early and late adopters will have similar gains over users not adopting multihoming. Thus the adoption dynamics of multihoming appear favorable. Overall, the results support the applicability of end user network switching for improving mobile user experience and the applicability of end user multihoming in more limited situations.

Unikernels Everywhere

Video streaming dominates the Internet's overall traffic mix, with reports stating that it will constitute 90% of all consumer traffic by 2019. Most of this video is delivered by Content Delivery Networks (CDNs), and, while they optimize QoE metrics such as buffering ratio and start-up time, no single CDN provides optimal performance. In this paper we make the case for elastic CDNs, the ability to build virtual CDNs on-the-fly on top of shared, third-party infrastructure at a scale. To bring this idea closer to reality we begin by large-scale simulations to quantify the effects that elastic CDNs would have if deployed, and build and evaluate MiniCache, a specialized, minimalistic virtualized content cache that runs on the Xen hypervisor. MiniCache is able to serve content at rates of up to 32 Gb/s and handle up to 600K reqs/sec on a single CPU core, as well as boot in about 90 milliseconds on x86 and around 370 milliseconds on ARM32.

QoE beyond the MOS: an in-depth look at QoE via better metrics and their relation to MOS

This technical report formally defines the QoE metrics which are introduced and discussed in the article "QoE Beyond the MOS: An In-Depth Look at QoE via Better Metrics and their Relation to MOS" by Tobias Ho{\ss}feld, Poul E. Heegaard, Martin Varela, Sebastian M\"oller, accepted for publication in the Springer journal "Quality and User Experience". Matlab scripts for computing the QoE metrics for given data sets are available in GitHub.

Location-based social video sharing over next generation cellular networks

The popularity of video sharing over social networks is straining service providers to maintain high quality of service. With the introduction of live video streaming over social networks, video sharing is truly becoming social and real time. However, existing video distribution architecture, split across content providers and mobile network operators, cannot leverage crossprovider information. We argue that MNOs can explore the knowledge of users' location to route video traffic intelligently. This can enable better quality of experience for live social video sharing. We show different scenarios in existing cellular networks, where user experience can suffer due to current video distribution mechanism. We propose that use of the location information of the receiver with respect to the sender can be exploited by next generation cellular networks for improving video streaming quality. Our simulation experiments validate that on all QoE metrics there is opportunity for significant improvement in live video streaming by using relative locations of the receivers and senders.

Adaptive Streaming: A subjective catalog to assess the performance of objective QoE metrics

Scalable streaming has emerged as a feasible solution to resolve users' heterogeneity problems. SVC is the technology that has served as the definitive impulse for the growth of streaming adaptive systems. Systems seek to improve layer switching efficiency from the network point of view but, with increasing importance, without jeopardizing user perceived video quality, i.e., QoE. We have performed extensive subjective experiments to corroborate the preference towards adaptive systems when compared to traditional non-adaptive systems. The resulting subjective scores are correlated with most relevant Full Reference (FR) objective metrics. We obtain an exponential relationship between human decisions and the same decisions expressed as a difference of objective metrics. A strong correlation with subjective scores validates objective metrics to be used as aid in the adaptive decision taking algorithms to improve overall systems performance. Results show that, among the evaluated objective metrics, PSNR is the metric that provide worse results in terms of reproducing the human decisions.

A quality of experience handover architecture for heterogeneous mobile wireless multimedia networks

The convergence of emerging real-time multimedia services, the increasing coverage of high-speed wireless networks, and the evergrowing popularity of mobile devices are leading to an era of user-centric multimedia wireless services. In this scenario, heterogeneous wireless communications will coexist and ensure that the end user is always best connected. However, the quality of experience supported for highquality applications in multi-operator environments remains a significant challenge and is crucial for the success of wireless multimedia systems. This article proposes a quality of experience handover architecture for heterogeneous mobile wireless multimedia networks. The architecture extends the media independent handover/ IEEE 802.21 proposal with QoE-aware seamless mobility, video quality estimator, dynamic class of service mapping, and a set of content adaptation schemes. The proposed architecture always provides the best connection and considers the QoE needs of mobile clients and available wireless resources in IEEE 802.11e and IEEE 802.16e service classes. Simulation experiments were performed to show the impact and benefits of the proposed solution from the user's perception, by using both objective and subjective QoE metrics.

Quality of Experience Evaluation for Networked Video Services

Rapid development of network technologies has led to a proliferation of networked video applications, making efficient and effective assessment of the related Quality of (user) Experience (QoE) an acute need. In literature, there has been a non-uniform view of Quality of Service (QoS) and therefore the concept of QoE is introduced to avoid the confusion. The difference between QoS and QoE is first clarified in this paper. Then QoE metrics in the current standardized framework for Internet Protocol (IP) based streaming applications in 3G networks, i.e., 3GPP PSS, are introduced. Moreover, objective QoE evaluation for networked video is addressed in respect to perceived video quality, which can be categorized into the parametric-planning model, parametric packet-layer model, parametric bit-stream-layer model, media-layer model, and hybrid model. The related characteristics, state-of-the-art, standardization process and key patents are respectively reviewed.