Quality Of Experience Function Research Articles

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.

Dimensionality reduction of independent influence factors in the objective evaluation of quality of experience

Big Data analytics and Artificial Intelligence (AI) technologies have become the focus of recent research due to the large amount of data. Dimensionality reduction techniques are recognized as an important step in these analyses. The multidimensional nature of Quality of Experience (QoE) is based on a set of Influence Factors (IFs) whose dimensionality is preferable to be higher due to better QoE prediction. As a consequence, dimensionality issues occur in QoE prediction models. This paper gives an overview of the used dimensionality reduction technique in QoE modeling and proposes modification and use of Active Subspaces Method (ASM) for dimensionality reduction. Proposed modified ASM (mASM) uses variance/standard deviation as a measure of function variability. A straightforward benefit of proposed modification is the possibility of its application in cases when discrete or categorical IFs are included. Application of modified ASM is not restricted to QoE modeling only. Obtained results show that QoE function is mostly flat for small variations of input IFs which is an additional motive to propose a modification of the standard version of ASM. This study proposes several metrics that can be used to compare different dimensionality reduction approaches. We prove that the percentage of function variability described by an appropriate linear combination(s) of input IFs is always greater or equal to the percentage that corresponds to the selection of input IF(s) when the reduction degree is the same. Thus, the proposed method and metrics are useful when optimizing the number of IFs for QoE prediction and a better understanding of IFs space in terms of QoE.

Beyond QoE: Diversity Adaptation in Video Streaming at the Edge

Adaptive bitrate (ABR) algorithms are critical techniques for high quality-of-experience (QoE) Internet video delivery. Early ABR algorithms conducting the overall QoE function of fixed parameters are limited by the fact that the QoE of end-users are diverse such that the video bitrate is often chosen in a misleading way. State-of-the-art ABR algorithms like MPC and Pensieve utilize offline modeling techniques and result in performance degradation for online QoE diversity adaptation. To address this issue, we propose Elephanta, an online ABR algorithm for edge users, which incorporates user QoE perception interface and adaptation algorithm with flexible parameters. In order to avoid overhead from updating parameters online, we model video streaming as a renewal system and formulate the specific QoE function into flexible formats by setting constraints on corresponding QoE metrics. To validate parameter settings, we emulate Elephanta under 1500 throughput traces, including FCC broadband, $3G$ HSDPA data set from the Internet, as well as the $4G$ /LTE data set we collect. Evaluation results show that Elephanta achieves QoE improvement of 7% over MPC and 3% over Pensieve under QoE diversity in part because of its superior adaptability to QoE diversity. We implemented Elephanta in dash.js at the client side for subjective experiments. We observed the diverse QoE preferences across users and 19/21 users (strongly) agree that Elephanta is responsive to parameter changes while watching videos.

On accounting for screen resolution in adaptive video streaming: QoE‐driven bandwidth sharing framework

SummaryScreen resolution along with network conditions are main objective factors impacting the user experience, in particular for video streaming applications. User terminals on their side feature more and more advanced characteristics resulting in different network requirements for good visual experience. Previous studies tried to link mean opinion score (MOS) to video bitrate for different screen types (e.g., Common Intermediate Format [CIF], Quarter Common Intermediate Format [QCIF], and High Definition [HD]). We leverage such studies and formulate a Quality of Experience (QoE)‐driven resource allocation problem to pinpoint the optimal bandwidth allocation that maximizes the QoE over all users of a network service provider located behind the same bottleneck link, while accounting for the characteristics of the screens they use for video playout. For our optimization problem, QoE functions are built using curve fitting on datasets capturing the relationship between MOS, screen characteristics, and bandwidth requirements. We propose a simple heuristic based on Lagrangian relaxation and Karush Kuhn Tucker (KKT) conditions to efficiently solve the optimization problem. Our numerical simulations show that the proposed heuristic is able to increase overall QoE up to 20% compared to an allocation with a TCP look‐alike strategy implementing max‐min fairness.

Cooperative Caching for Multiple Bitrate Videos in Small Cell Edges

Caching popular videos at mobile edge servers (MESs) has been confirmed as a promising method to improve mobile users (MUs) perceived quality of experience (QoE) and to alleviate the server load. However, with the multiple bitrate encoding techniques prevalently employed in modern streaming services, caching deployment is challenging for the following three facts: (1) cooperative caching should be explored for MUs located at overlapped coverage areas of MESs; (2) there exists tradeoff consideration for caching either high bitrate videos or high diversity videos; and (3) the relationship between MU perceived QoE and MU received bitrate, known as QoE function, varies in different services. Aiming to maximize the MU perceived QoE, we formulate the multiple bitrate video caching problem, and prove this problem is NP-hard for any given positive and strictly increasing QoE function. We then propose a polynomial complexity algorithm based on a general QoE function, which can achieve an approximate ratio arbitrarily close to 1/2. Specifically, for a linear QoE function, we explore useful property of optimal solutions, based on which more efficient algorithms are proposed. We demonstrate the effectiveness of our solutions via both theoretical analysis and extensive simulations.

Network-Assisted Neural Adaptive Naked-Eye 3D Video Streaming Over Wireless Networks

High quality transmission of Virtual Reality (VR) video depends strictly on bandwidth and delay requirements. It becomes possible with the maturity and commercialization of 5G technology. However, to transmit VR video streaming over wireless communication system, we must cope with the challenge that fluctuation exists in the wireless channel conditions. For example, available channel bandwidth, packet loss rate, and interference level may vary with time due to channel fading and user's mobility. The problem is more prominent when transmitting naked-eye 3D video which generally consists of multiple viewpoints with different resolutions. In order to optimize the quality of experience (QoE) of watching naked-eye VR video over wireless networks, this paper proposes a network-assisted neural adaptive video streaming algorithm (NAVSA). Specifically, we present a modified QoE function to describe the quality of naked-eye 3D streaming quantitatively, which not only considers the quality of naked-eye 3D video itself, but also considers the phenomenon of rebuffering and video fluctuation that occurs during video transmission. Next, with the network-assisted feedback, the physical layer information, the buffer occupancy of the video client, and the size of the next video chunk are collected to train a reinforcement learning model. Based on dynamic adaptive streaming over HTTP (DASH), the model can automatically choose appropriate viewpoints and resolutions corresponding to the current condition of the wireless networks such that the network capacity can be fully explored. To verify the performance of our proposed NAVSA, we simulate 3 naked-eye 3D video application scenarios on the NS3 platform. The results show that the performance of NAVSA is about 5~8% better than some state-of-the-art algorithms in wireless networks.

QoE-Aware Smart Home Energy Management Considering Renewables and Electric Vehicles

To reduce the peak load and electricity bill while preserving the user comfort, a quality of experience (QoE)-aware smart appliance control algorithm for the smart home energy management system (sHEMS) with renewable energy sources (RES) and electric vehicles (EV) was proposed. The proposed algorithm decreases the peak load and electricity bill by deferring starting times of delay-tolerant appliances from peak to off-peak hours, controlling the temperature setting of heating, ventilation, and air conditioning (HVAC), and properly scheduling the discharging and charging periods of an EV. In this paper, the user comfort is evaluated by means of QoE functions. To preserve the user’s QoE, the delay of the starting time of a home appliance and the temperature setting of HVAC are constrained by a QoE threshold. Additionally, to solve the trade-off problem between the peak load/electricity bill reduction and user’s QoE, a fuzzy logic controller for dynamically adjusting the QoE threshold to optimize the user’s QoE was also designed. Simulation results demonstrate that the proposed smart appliance control algorithm with a fuzzy-controlled QoE threshold significantly reduces the peak load and electricity bill while optimally preserving the user’s QoE. Compared with the baseline case, the proposed scheme reduces the electricity bill by 65% under the scenario with RES and EV. Additionally, compared with the method of optimal scheduling of appliances in the literature, the proposed scheme achieves much better peak load reduction performance and user’s QoE.

Quality of Experience-based museum touring: a human in the loop approach

This paper introduces a human in the loop approach toward proposing a physical, personal and interest-aware museum touring in order to maximize visitor’s perceived Quality of Experience (QoE). The most influential parameters on visitors QoE are identified and more importantly quantified via performing an empirical study based on a questionnaire answered by experts in the field of arts and museums. Individual QoE functions with respect to each of the identified parameters are formulated for different museum visitors’ styles, toward capturing visitors’ perceived utility in a formal manner and providing them a customized and personalized experience. A social recommendation and personalization approach is designed toward creating visitors’ profiles, exploiting common characteristics and interests among them and assisting in recommending a set of exhibits to be visited, through a ranking system according to visitor’s interests. A Museum Visitor QoE Routing problem is formulated as an optimization problem considering the various QoE-related characteristics. The latter is solved via a graph-based approach determining both an optimal and a heuristic but less complex solution. Detailed numerical results are provided toward illustrating the applicability of the proposed framework under different scenarios and topologies.

A cost-effective and real-time QoE evaluation method for multimedia streaming services

Traditionally, subjective tests are conducted to obtain the Mean Opinion Score (MOS) or Quality of Experience (QoE) of a video streaming service. However, subjective tests are time-consuming and rather costly. Thus, a cost-effective and real-time QoE evaluation method for video streaming services is presented in this paper. The proposed scheme first adopts subjective tests to find the relationships between the QoE and individual QoS parameters. Next, based on subjective test results, the corresponding QoS---QoE mapping functions for individual QoS metrics are derived using the regression approach. Finally, the integrated QoE function, which is a multi-variate function of multiple QoS metrics, for assessing the overall QoE of video streaming services is proposed. Hence, network/service providers only need to measure related objective QoS parameters while the corresponding MOS/QoE can be easily derived in real time based on the integrated QoE function. Since subjective tests only need to be conducted occasionally for updating the parameters in the QoS---QoE mapping functions, the cost of QoE assessment decreases significantly.

QoE-Aware Scheduling for Sigmoid Optimization in Wireless Networks

This letter proposes a quality-of-experience (QoE)-aware scheduler that maximizes the average number of satisfied users. QoE is different from quality-of-service (QoS) in that QoE is determined by users' subjective satisfaction while QoS is objectively measured. Hence, users' satisfaction needs to be incorporated into the scheduler to better understand QoE maximization. In this regard we propose a simple but effective user participation scheme exploiting one-bit feedback that indicates user's satisfaction upon the end of service. Then, user-centric QoE function is derived, which serves our objective function. Assuming that the QoE function can be successfully modeled by a sigmoid function we solve the non-convex sigmoid optimization. We show that, interestingly, adding non-trivial fairness constraints for starvation prevention can convexify the problem, and we obtain the unique optimal solution. By comparing the case without user participation we show that user participation can substantially improve the total QoE, e.g., nearly 100% improvement of the low 10 percentile users and 40% improvement of the low 50 percentile users.

QoS/QoE Mapping and Adjustment Model in the Cloud-based Multimedia Infrastructure

The quality of service (QoS) requirement and multicast service support from IP networks are two important factors for providing cloud-based multimedia services. However, QoS lacks an important element in characterizing multimedia services, namely, user perception. In this paper, we propose a QoS to quality of experience (QoE) mapping and adjustment model to translate the network QoS parameters into the user's QoE in the cloud-based multimedia infrastructure. The model is composed of three parts: QoE function, practical measurement and statistical analysis, and a simulated streaming video platform. We first discuss how to design the QoE function, and then use the practical measurement and statistical analysis to derive the optimum values of eight QoE parameters in the proposed QoE function. To map the network QoS parameters into the user's QoE, a simulated streaming video platform is used to denote a cloud-based multimedia infrastructure. Each multicast member that has guaranteed bandwidth in the simulated streaming video platform uses the QoE function to calculate its QoE score after watching the streaming video. If the QoE score is less than a derived lower bound value, it means that one of the multicast members has a low QoE. In this situation, the genetic algorithm is enabled to adjust the constructed diffserv-aware multicast tree to respond quickly to the degradation of QoE. The simulation results show that the user's QoE and network QoS are consistent with each other.