Frequent variations in throughput make mobile networks a challenging environment for video streaming. Current video players deal with those variations by matching video quality to network throughput. However, this adaptation strategy results in frequent changes of video resolution and bitrate, which negatively impacts the users' streaming experience. Alternatively, keeping the video quality constant would improve the experience, but puts additional demand on the network. Downloading high quality content when channel quality is low requires additional resources, because data transfer efficiency is linked to channel quality. In this paper, we present a predictive Channel Quality based Buffering Strategy (CQBS) that lets the video buffer grow when channel quality is good, and relies on this buffer when channel quality decreases. Our strategy is the outcome of a Markov Decision Process. The underlying Markov chain is conditioned on 377 real-world LTE channel quality traces that we have collected using an Android mobile application. With our strategy, mobile network providers can deliver constant quality video streams, using less network resources.

@en

Mobile networks, especially LTE networks, are used more and more for high-bandwidth services like multimedia or video streams. The quality of the data connection plays a major role in the perceived quality of a service. Videos may be presented in a low quality or experience a lot of stalling events, when the connection is too slow to buffer the next frames for playback. So far, no publicly available data set exists that has a larger number of LTE network traces and can be used for deeper analysis. In this data set, we provide 546 traces of 5 minutes each with a sample rate of 100 ms. Thereof 377 traces are pure LTE data. We furthermore provide an Android app to gather further traces as well as R scripts to clean, sort, and analyze the data.

@en

Dynamic Adaptive Streaming over HTTP (DASH) is a technology for delivering video content over the Internet. It provides an effective mechanism, which has been adopted by major content providers. Nevertheless, available DASH player implementations have a number of drawbacks such as performance problems on shared network connections, which lead to video freezes and frequent video quality changes. In this paper, we propose a method to reduce the performance problems that exist in networks with a large number of DASH players. These networks can be found in hotels, apartment complexes, and airports. In experiments with up to 600 simultaneously active players, we are able to reduce the number of DASH players with freezes by 95% (from 345 to 15) compared to throughput-based adaptation and by 75% (from 62 to 15) compared to BOLA using our DASH Assisting Network Element DANE). In addition, we reduced the number of quality switches by 94% compared to throughput-based adaptation, and by 85% compared to BOLA.@en

Videos are an important part of social platforms. With growing data speeds and high resolution cameras on mobile devices and smartphones, mobile instant and live video clip sharing become increasingly popular. However, video uploads are resource consuming which leads to long upload times, especially in environments with poor data connections. In current mobile applications, the user has little to no influence on optimizing the upload of her/his video according to the current (network) context. In this work, we propose a mobile application that shows an accurate upload time estimation and a current network speed indication. The user can select a video quality for uploading and by that possibly reach faster uploads in low bandwidth connection areas. In a user study with 21 users, we show that users perceive the upload speed as higher with given upload estimation and network speed indication when they have less bandwidth available. With this information, participants perceive the application as more reliable and have an increased feeling of control over the upload process. All users liked the proposed video quality customization feature. Compared to a graphical representation of the network speed, the upload time was the more helpful information to customize the upload.

@en

Dynamic Adaptive Streaming over HTTP (DASH) is the premier technology for Internet video streaming. DASH efficiently uses existing HTTP-based delivery infrastructures implementing adaptive streaming. However, DASH traffic is bursty in nature. This causes performance problems when DASH players share a network connection or in networks with heavy background traffic. The result is unstable and lower quality video. In this article, we present the design and implementation of a so-called DASH Assisting Network Element (DANE). Our system provides target bitrate signaling and dynamic traffic control. These two mechanisms realize proper bandwidth sharing among clients. Our system is privacy friendly and fully supports encrypted video streams. Trying to improve the streaming experience for users who share a network connection, our system increases the video bitrate and reduces the number of quality switches. We show this through evaluations in our Wi-Fi testbed.

@en

Dynamic adaptive streaming over HTTP (DASH) is a simple, but effective, technology for video streaming over the Internet. It provides adaptive streaming while being highly scalable at the side of the content providers. However, the mismatch between TCP and the adaptive bursty nature of DASH traffic results in underperformance of DASH streams in busy networks. This paper describes a networking architecture based on the Software Defined Networking (SDN) paradigm. Controllers in the network with a broad overview on the network activity provide two mechanisms for adaptation assistance: explicitly signaling target bitrates to DASH players and dynamic traffic control in the network. We evaluate how each of these mechanisms can contribute to the delivery of a stable and high quality stream. It shows that our architecture improves the quality of experience by doubling the video bitrate and reducing disturbing quality switches. As such, this paper contributes insights on how to implement DASH-aware networking that also enables internet service providers, network administrators, and end-users to configure their networks to their requirements.@en

In this paper, we present a model for evaluating bandwidth sharing policies, that can be applied to networks that handle both video streaming traffic, as well as other traffic. Video streaming is a demanding network application. In crowded networks, resources need to be properly divided in order not to diminish the streaming experience. However, in network deployments with a large number of users, the streaming performance cannot be obtained straightforwardly from a sharing policy. Therefore, we propose a Markov model that is compatible with Dynamic Adaptive Streaming over HTTP (DASH), the major technology for video streaming over the Internet. If DASH is combined with in-network resource management, its performance can be significantly improved. Nevertheless, resource sharing policies need to be configured. This requires evaluation of many different configurations. Real deployments or network simulations demand many system resources and time. In contrast, our model can quickly evaluate many configurations, and for each configuration output the expected video bitrate and number of changes in video bitrate. These two parameters play an important role in the Quality of Experience of the viewer. In this paper, we demonstrate how our model can be used to analyze and optimize resource sharing policies. As such, our model is a useful tool for network administrators and allows them to better provision and configure their networks.@en

HTTP adaptive streaming (HAS) has become the dominant technology for streaming video over the Internet. It gained popularity because of its ability to adapt the video quality to the current network conditions and other appealing properties such as usage of off-the-shelf HTTP servers and easy firewall traversal. However, when multiple HAS players share a bottleneck link for streaming, the individual adaptation techniques in the players have difficulties to maintain a stable bitrate and fairly share the network resources. HAS-assisting network elements can solve these performance problems and allow execution of advanced policies for sharing the available bandwidth. Nonetheless, testing and evaluating new sharing policies is costly and time consuming. This motivated us to formulate a model that allows to differentiate between groups of users depending on the type of user or device, and that can describe the mean bitrate of the video streams and how often this bitrate is expected to change during playout. To show how our model can be used, we demonstrate two applications of our model. Furthermore, we validate the model based results against results obtained using our streaming testbed and proxy server based HAS-assistant. The results show that our model is highly accurate for both the mean bitrate and the number of changes in video bitrate. As such, our model is a useful tool for network administrators and internet service providers for evaluating the performance of sharing policies and for managing and provisioning video delivery networks.@en