A learning-based algorithm for improved bandwidth-awareness of adaptive streaming clients

HTTP adaptive video streaming has become the de facto standard for media data delivery in the Internet. Mobile users are increasingly accessing video streaming services while traveling in fast-moving vehicles (e.g., public transport). The inherent high-speed mobility in these scenarios escalates bandwidth uncertainty and seriously degrades the performance of HTTP adaptive video streaming. This paper proposes a location window based geo-intelligent adaptive streaming algorithm, which adapts to the geo-spatial bandwidth variations experienced by a fast-moving user by adjusting the quality of the next chunk based on the estimated bandwidth at the next X locations of the mobile user. In order to realize geo-intelligence, we introduce a neural network model for accurately creating bandwidth maps that store location-specific bandwidth knowledge. By incorporating both these contributions in conjunction with real-world mobile broadband bandwidth traces from a metropolitan area, we present a systematic study to explore the effects of varying the size of the location window on the user-perceived Quality of Experience (QoE). The evaluation results demonstrate that an optimum location window can be identified, which can almost entirely eliminate playout buffer underruns, thus leading to a smooth and high-quality streaming experience.

The thesis focuses on Quality of Experience (QoE) of HTTP adaptive video streaming (HAS) and traffic management in access networks to improve the QoE of HAS. First, the QoE impact of adaptation parameters and time on layer was investigated with subjective crowdsourcing studies. The results were used to compute a QoE-optimal adaptation strategy for given video and network conditions. This allows video service providers to develop and benchmark improved adaptation logics for HAS. Furthermore, the thesis investigated concepts to monitor video QoE on application and network layer, which can be used by network providers in the QoE-aware traffic management cycle. Moreover, an analytic and simulative performance evaluation of QoE-aware traffic management on a bottleneck link was conducted. Finally, the thesis investigated socially-aware traffic management for HAS via Wi-Fi offloading of mobile HAS flows. A model for the distribution of public Wi-Fi hotspots and a platform for socially-aware traffic management on private home routers was presented. A simulative performance evaluation investigated the impact of Wi-Fi offloading on the QoE and energy consumption of mobile HAS.

The Hypertext Transfer Protocol (HTTP) Adaptive Streaming (HAS) has now become ubiquitous and accounts for a large amount of video delivery over the Internet. But since the Internet is prone to bandwidth variations, HAS's up and down switching between different video bitrates to keep up with bandwidth variations leads to a reduction in Quality of Experience (QoE). In this article, we propose a video bitrate adaptation and prediction mechanism based on Fuzzy logic for HAS players, which takes into consideration the estimate of available network bandwidth as well as the predicted buffer occupancy level in order to proactively and intelligently respond to current conditions. This leads to two contributions: First, it allows HAS players to take appropriate actions, sooner than existing methods, to prevent playback interruptions caused by buffer underrun, reducing the ON-OFF traffic phenomena associated with current approaches and increasing the QoE. Second, it facilitates fair sharing of bandwidth among competing players at the bottleneck link. We present the implementation of our proposed mechanism and provide both empirical/QoE analysis and performance comparison with existing work. Our results show that, compared to existing systems, our system has (1) better fairness among multiple competing players by almost 50% on average and as much as 80% as indicated by Jain's fairness index and (2) better perceived quality of video by almost 8% on average and as much as 17%, according to the estimate the Mean Opinion Score (eMOS) model.

Video streaming applications currently dominate Internet traffic. Particularly, HTTP Adaptive Streaming (HAS) has emerged as the dominant standard for streaming videos over the best-effort Internet, thanks to its capability of matching the video quality to the available network resources. In HAS, the video client is equipped with a heuristic that dynamically decides the most suitable quality to stream the content, based on information such as the perceived network bandwidth or the video player buffer status. The goal of this heuristic is to optimize the quality as perceived by the user, the so-called Quality of Experience (QoE). Despite the many advantages brought by the adaptive streaming principle, optimizing users’ QoE is far from trivial. Current heuristics are still suboptimal when sudden bandwidth drops occur, especially in wireless environments, thus leading to freezes in the video playout, the main factor influencing users’ QoE. This issue is aggravated in case of live events, where the player buffer has to be kept as small as possible in order to reduce the playout delay between the user and the live signal. In light of the above, in recent years, several works have been proposed with the aim of extending the classical purely client-based structure of adaptive video streaming, in order to fully optimize users’ QoE. In this article, a survey is presented of research works on this topic together with a classification based on where the optimization takes place. This classification goes beyond client-based heuristics to investigate the usage of server- and network-assisted architectures and of new application and transport layer protocols. In addition, we outline the major challenges currently arising in the field of multimedia delivery, which are going to be of extreme relevance in future years.

Nowadays, video streaming has become a popular form of multimedia for communication and entertainment. The rapid traffic explosion spurred by the development of emerging video-centric services such as e-science, virtual reality, and video conference has caused network congestion and the degradation in quality of experience (QoE), especially in heterogeneous mobile networks. To cope with that, the development of QoE-efficient video streaming solutions, i.e., HTTP adaptive video streaming, is critical. In this work, we investigate HTTP adaptive video streaming solutions that are capable of improving QoE for heterogeneous mobile networks in which the network conditions including bandwidth are significantly varied. We propose an effective QoE-aware adaptive bitrate video streaming scheme that integrates a bandwidth prediction based on Gated Recurrent Unit (GRU) neural networks with an adaptive bitrate selection strategy to wisely determine the suitable quality level for each video chunk. Thanks to the accurate bandwidth estimation and the adaptation of each video chunk bitrate to the network conditions, QoE metrics have been enhanced. Numerical experiments have been deployed to verify the performance of our proposed solution in comparison with that of the notable conventional methods. The attained simulation results demonstrate that the developed solution is significantly more effective than the conventional methods. The proposed method obtains a performance increment, in terms of QoE, of up to 19.4% compared to the conventional ones.

Lately, HTTP Adaptive Streaming (HAS) has become dominant among different video streaming techniques. However, owing to the unpredictable nature of the wireless radio channel and device mobility, using HAS over mobile wireless networks is still very challenging. In this paper, we propose a novel Quality of Experience (QoE) optimization mechanism for HAS in the context of mobile wireless networks. The proposed mechanism leverages recent advances in HAS specification, which includes new features for QoE measurements and reporting. First, we formulate a discrete optimization problem aiming at maximizing the overall average quality, and minimizing the negative impact of temporal video quality changes for all HAS users simultaneously. Second, in order to take advantage of well-known continuous optimization techniques and to decrease the computational complexity, we convert the formulated problem into a continuous form, and propose a gradient based algorithm to solve the continuous optimization problem. The results of our simulations demonstrate that our system attained better perceived video quality by almost 8% on average, while lowering the freezing period by 20% on average across HAS users when compared to other approaches where HAS users only rely on local adaptation logics.

HTTP Adaptive Streaming(HAS) has become widely deployed in multimedia services for its ability for providing the best Quality of Experience(QoE) for viewers with limited resource, especially in fluctuating wireless networkings. With its client-driven rate adaptation mechanism, HAS is able to adapt to fluctuating network condition and various terminals dynamically. The rate adaptation algorithm is crucial in HAS for its direct impact on the QoE. Most of researches focus on optimizing objective indicators, such as elevating mean bit-rate, lessening playout interruption, and avoiding quality switches, etc. However, the promotion in objective indicators doesn't indicate better experience of end users directly. In this paper, a novel QoE-Optimal Rate Adaptation(QORA) algorithm is proposed to achieve the best QoE. Firstly, a QoE model with iterative form is deduced for on-line evaluation. According to this model, the QORA is able to predict the possible QoE of each bit-rate level in candidate, then greedily choose the one with the highest QoE. The perceptual quality of HAS is optimized by the QORA directly and quantitatively. The simulation result shows that the proposed QORA is able to provide the optimal QoE compared with other rate adaptation schemes, although some of them have better performance in a single objective indicator.

The growing consumer demand for mobile video services is one of the key drivers of the evolution of new wireless multimedia solutions requiring exploration of new ways to optimize future wireless networks for video services towards delivering enhanced quality of experience (QoE). One of these key video enhancing solutions is HTTP adaptive streaming (HAS), which has recently been spreading as a form of Internet video delivery and is expected to be deployed more broadly over the next few years. As a relatively new technology in comparison with traditional push-based adaptive streaming techniques, deployment of HAS presents new challenges and opportunities for content developers, service providers, network operators and device manufacturers. One of these important challenges is developing evaluation methodologies and performance metrics to accurately assess user QoE for HAS services, and effectively utilizing these metrics for service provisioning and optimizing network adaptation. In that vein, this article provides an overview of HAS concepts, and reviews the recently standardized QoE metrics and reporting framework in 3GPP. Furthermore, we present an end-to-end QoE evaluation study on HAS conducted over 3GPP LTE networks and conclude with a discussion of future challenges and opportunities in QoE optimization for HAS services.

HTTP adaptive streaming (HAS) is a state-of-the-art technology for video streaming. Optimal adaptive streaming schemes should be designed to maximize the quality of experience (QoE) in network environments with unstable bandwidths such as wireless networks. QoE is degraded for Advanced Video Coding (AVC)-based HAS due to frequent quality switching and rebuffering in wireless networks. Meanwhile, Scalable Video Coding (SVC)-based HAS can maximize the QoE by flexibly requesting the base layer (BL) and enhancement layer (EL) based on variable network conditions. However, in SVC-based HAS, the required bandwidth is significantly high due to the encoding overhead. In this paper, we propose a layer-assisted video quality adaptation for improving QoE in wireless networks. The proposed scheme employs a video encoding method, composed of multiple BLs and ELs, using both AVC and SVC. The quality of the BL is determined using the buffer occupancy level and measured bandwidth to minimize rebuffering. The quality of the EL is determined using the buffer region and segment quality differences to minimize instability. enhancement dummy (ED) consists of the selected ELs. The layer scheduler decides the segment that is to be requested based on the QoE model according to the BL and ED to maximize the QoE. Experimental results show that the proposed scheme achieves high QoE compared to the existing schemes because the instability is low and no rebuffering occurs.

Most HTTP Adaptive Streaming (HAS) video content delivery solutions today are governed by purely client-based logics. For lack of coordination among clients and awareness of the dynamic Radio Access Network (RAN) conditions, these approaches may lead to suboptimal user experience and underutilization of network resources. Recently, Mobile Edge Computing (MEC) has been studied as a new networking paradigm to play a part in the adaptive video streaming process with lower end-to-end latency and better network awareness. In this paper, we present an edge-assisted adaptive video streaming scheme with deep Q-learning techniques and bandwidth sharing policies, which performs video adaptation according to the real-time radio and network information collected at the network edge. The adaptation scheme is implemented as an edge application hosted on our own deployed MEC server in a real LTE network testbed for experimental evaluation against three popular client-based solutions, namely Buffer-Based Adaptation (BBA), Rate-Based Adaptation (RBA) and adaptation performed by dash.js with its default adaptation logic. To the best of our knowledge, it is one of the few deep Q-learning adaptive video streaming solutions that have been deployed in the MEC framework at network edge in practice. Experiment results show that our proposed scheme outperforms the other three client-based solutions with higher Quality of Experience (QoE) and fairness in the evaluated network environments.

HTTP adaptive streaming (HAS) has emerged as the main technology for video streaming applications. Multiple HAS video clients sharing the same wireless channel may experience different video qualities as well as different play-out buffer levels, as a result of both different video content complexities and different channel conditions. This causes unfairness in the end-user quality of experience. In this paper, we propose a quality-fair adaptive streaming solution with fair buffer (QFAS-FB) to deliver fair video quality and to achieve asymptotically fair play-out buffer levels among HAS clients competing for the same wireless resources in a long-term evolution (LTE) cell. In the QFAS-FB framework, the share of radio resources is optimized according to video content characteristics, play-out buffer levels, and channel conditions. The proposed solution is compared with the other state-of-the-art strategies, and the numerical results show that it significantly improves the quality fairness among heterogeneous HAS users, reduces the video quality variations, and improves the fairness among the user’s play-out buffers.

Multi-bitrate streaming, especially HTTP adaptive streaming (HAS), is becoming popular for video delivery in multimedia network. In this trend, a video is encoded into different versions with different quality levels. Based on the current conditions, a client can adaptively choose the most suitable encoded version. However, the adoption of HAS in managed network (e.g. IPTV) has many challenges because of the purely client-driven approach of current HAS which causes competing behavior, excessive quality oscillations, and thus negatively impacting quality of experience (QoE). Some recent studies have proposed network-based solutions to overcome these problems; however, they just target at constant bitrate (CBR) videos. In this paper, we propose a new method that allows components inside the network to select an adapted version for each HAS client. To the best of our knowledge, this is the first study on the quality optimization when streaming multiple variable bitrate (VBR) videos. The experimental result show that our method can provide in real-time the optimal version for each client with the best possible quality while meeting the constraints of overall bandwidth and delay.

SummaryHypertext Transfer Protocol adaptive streaming switches between different video qualities, adapting to the network conditions, and avoids stalling streamed frames over high‐oscillation client's throughput improving the users' quality of experience (QoE). Quality of experience has become the most important parameter to lead the service providers to know about the end‐user feedback. Implementing Hypertext Transfer Protocol adaptive streaming applications to find out QoE in real‐life scenarios of vast networks becomes more challenging and complex task regarding to cost, agile, time, and decisions. In this paper, a virtualized network testbed to virtualize various machines to support implementing experiments of adaptive video streaming has been developed. Within the test study, the metrics which demonstrate performance of QoE are investigated, respectively, including initial delay (ie, startup delay at the beginning of playback a video), frequency switches (ie, number of times the quality is changed), accumulative video time (ie, number and length of stalls), CPU usage, and battery energy consumption. Furthermore, the relation between effective parameters of QoS on the aforementioned metrics for different segment length is investigated. Experimental results show that the proposed virtualized system is agile, easy to install and use, and costs less than real testbeds. Moreover, the subjective and objective performance studies of QoE evaluation in the system have proven that the segment lengths of 6 to 8 seconds were faired and more efficient than others according to the investigated parameters.

SummaryMost of the video streaming applications running over the Internet send video data over HTTP and provide an architecture for video clients to adapt video quality during streaming. In HTTP adaptive streaming, a raw video is encoded at various qualities, each encoded video file is divided into small segments, and the clients may change the segment quality by sending requests for segments having different qualities over time. MPEG has standardized dynamic adaptive streaming over HTTP (MPEG‐DASH) due to this tendency. In this work, we focus on DASH over software‐defined networks (SDN), and we dynamically reroute DASH flows by considering the current network capacity, available bandwidth of the paths, and bitrate of the segments in order to provide high quality of experience (QoE) and fairness among DASH clients. Simulations performed under various network conditions show that the proposed study provides higher QoE and fairness compared with the max‐flow routing approach.

Web portals, such as the one hosted by news providers, have recently started to provide significant amounts of multimedia content. To deliver this content over the best-effort Internet, HTTP Adaptive Streaming (HAS) is generally used, allowing smoother playback and a better Quality of Experience (QoE). To stimulate user engagement with the provided content, reducing the video's startup time has become more and more important: while the current median video load time is in the order of seconds, research has shown that user waiting times must remain below two seconds to achieve an acceptable QoE. In this work, we present a framework for low-latency delivery of news-related video content, integrating four optimizations either at server-side, client-side, or at the application layer. Most importantly, we propose to identify relevant content through user profiling, using proactive delivery and client-side caching to reduce the video startup time. By means of a large data set from a Belgian news provider, we show that the proposed framework can reduce the startup time from 4.6 s to 1.5 s (-74.6%) in a 3G scenario, at the cost of limited network overhead and additional complexity at server- and client-side.