Christian Koch

Optimizing Mobile Prefetching by Leveraging Usage Patterns and Social Information

Real-time entertainment constitutes the majority of traffic in todays mobile networks. The data volume is expected to increase in the near future, whereas the mobile bandwidth capacity is likely to increase significantly slower. Especially peak hour traffic often leads to overloaded mobile networks and poor user experience. This increases costs for the mobile operator, which has to adapt to the peak demand by capacity over provisioning. The new approach proposed in this paper aims to leverage the users context and video meta-information to unleash the potential of video prefetching. Based on observed user interactions with social networks, the videos a user consumes from social neighbours can be predicted. Moreover, the users daily routine even enables a prediction of the time when videos are consumed as well as the network capabilities available at that point. First results show that partial prefetching based on content categories provides a potential for efficiently offloading mobile networks. Additionally, the user experience can be improved as freezing playbacks of videos can be decreased. Initial results show a high potential for category-based prefeching.

The potential of social-aware multimedia prefetching on mobile devices

The access to Online Social Networks (OSN) and to media shared over these platforms account for around 20% of todays mobile Internet traffic. For mobile device users, the access to media content and specifically videos is still challenging and costly. Mobile contracts usually have a data cap and connection qualities can vary greatly, depending on the cellular network coverage. Prefetching mechanisms that fetch content items beforehand, in times when the mobile device is connected to a WiFi network, have a high potential to address these problems. Yet, such a mechanism can only be effective if relevant content can be predicted with a high accuracy. Therefore, in this paper, an analysis of content properties and their potential for prediction are presented. An initial user study with 14 Facebook users running an app on their mobile device was conducted. The results show that video consumption is very diverse across the users. This work discusses the evaluation setup, the data analysis, and their potential to define an effective prefetching algorithm.

ID2T: A DIY dataset creation toolkit for Intrusion Detection Systems

Intrusion Detection Systems (IDSs) are an important defense tool against the sophisticated and ever-growing network attacks. These systems need to be evaluated against high quality datasets for correctly assessing their usefulness and comparing their performance. We present an Intrusion Detection Dataset Toolkit (ID2T) for the creation of labeled datasets containing user defined synthetic attacks. The architecture of the toolkit is provided for examination and the example of an injected attack, in real network traffic, is visualized and analyzed. We further discuss the ability of the toolkit of creating realistic synthetic attacks of high quality and low bias.

Proactive Caching of Music Videos based on Audio Features, Mood, and Genre

The preferred channel for listening to music is shifting towards the Internet and especially to mobile networks. Here, the overall traffic is predicted to grow by 45% annually till 2021. However, the resulting increase in network traffic challenges mobile operators. As a result, methods are researched to decrease costly transit traffic and the traffic load inside operator networks using in-network and client-side caching. Additionally to traditional reactive caching, recent works show that proactive caching increases cache efficiency. Thus, in this work, a mobile network using proactive caching is assumed. As music represents the most popular content category on YouTube, this work focuses on studying the potential of proactively caching content of this particular category using a YouTube trace containing over 4 million music video user sessions. The contribution of this work is threefold: First, music content-specific user behavior is derived and audio features of the content are analyzed. Second, using these audio features, genre and mood classifiers are compared in order to guide the design of new proactive caching policies. Third, a novel trace-based evaluation methodology for music-specific proactive in-network caching is proposed and used to evaluate novel proactive caching policies to serve either an aggregate of users or individual clients.

CPSys: A System for Mobile Video Prefetching

Online media services are reshaping the way video content is watched. People with similar interests tend to request same content. This provides enormous potential to predict which content users are interested in. Besides, mobile devices are commonly used to watch videos which popularity is largely driven by its social success. In this paper, we design CPSys a Central Predictor System to prefetch relevant videos for each user. To fine tune our prefetching system, we rely on a large dataset collected from a large mobile carrier in Europe. The rationale of our prefetching strategy is first to form a graph and build implicit or explicit ties between similar users. On top of this graph, we propose the Most Popular and Most Recent (MPMR) policy to predict relevant videos for each user. We show that CPSys can achieve high performance with respect to the correct prediction ratio and by significantly reducing the traffic overhead. We further show that CPSys outperforms other prefetching schemes that have been presented and studied in the state of the art. At the end, we provide a proof-of-concept implementation of our prefetching system.

Media download optimization through prefetching and resource allocation in mobile networks

Mobile network operators are expected to face significant traffic increase in the upcoming years. One alternative method is to intelligently move transmissions to times of network underutilization, either on 3G/4G or by offloading to WiFi. Video content, predicted by Cisco to constitute 69% of mobile traffic, offers the greatest potential for offloading. To this end, the demonstrated app strives to relieve the mobile network in a two ways. First, long-term prefetching of promising videos based on posts from the users Online Social Network feed is performed. The knowledge about which video is likely being requested in the near future offers the opportunity to schedule the transmission according to its probability of being watched. Second, the approach is complemented with short-term prefetching, which is used whenever a content could not be downloaded by long-term prefetching. In this case, resources are optimized so as to maximize the communication efficiency while preserving the quality of service. The demonstrated app considers the smartphones observed cellular network history to optimize the mobile throughput. A customized video player implements both the long-term and short-term prefetching. It reduces both the load on mobile networks, decreases playback pausing events and hereby achieves a high QoE. Thus, the player addresses both the operators and the users needs.

Category-aware hierarchical caching for video-on-demand content on youtube

Content delivery networks (CDNs) carry more than half of the video content in todays Internet. By placing content in caches close to the users, CDNs help increasing the Quality of Experience, e.g., by decreasing the delay until a video playback starts. Existing works on CDN cache performance focus mostly on distinct caching metrics, such as hit rate, given an abstract workload model. Moreover, the nature of the geographical distribution and connection of caches is often oversimplified. In this work, we investigate the performance of cache hierarchies while taking into account the presence of a mixed content workload comprising multiple categories, e.g., news, comedy, and music. We consider the performance of existing caching strategies in terms of cache hit rate and deterioration costs in terms of write operations. Further, we contribute a design and an evaluation of a content category-aware caching strategy, which has the benefit of being sensitive to changing category-specific content popularity. We evaluate our caching strategy, denoted as ACDC (Adaptive Content-Aware Designed Cache), using multiple caching hierarchy models, different cache sizes, and a real world trace covering one week of YouTube requests observed in a large European mobile ISP network. We demonstrate that ACDC increases the cache hit rate for certain hierarchies up to 18.39% and decreases transmission latency up to 12%. Additionally, a decrease in disk write operations up to 55% is observed.

Collaborations on YouTube: From Unsupervised Detection to the Impact on Video and Channel Popularity

YouTube is the most popular platform for streaming of user-generated videos. Nowadays, professional YouTubers are organized in so-called multichannel networks (MCNs). These networks offer services such as brand deals, equipment, and strategic advice in exchange for a share of the YouTubers’ revenues. A dominant strategy to gain more subscribers and, hence, revenue is collaborating with other YouTubers. Yet, collaborations on YouTube have not been studied in a detailed quantitative manner. To close this gap, first, we collect a YouTube dataset covering video statistics over 3 months for 7,942 channels. Second, we design a framework for collaboration detection given a previously unknown number of persons featured in YouTube videos. We denote this framework, for the detection and analysis of collaborations in YouTube videos using a Deep Neural Network (DNN)-based approach, as CATANA. Third, we analyze about 2.4 years of video content and use CATANA to answer research questions guiding YouTubers and MCNs for efficient collaboration strategies. Thereby, we focus on (1) collaboration frequency and partner selectivity, (2) the influence of MCNs on channel collaborations, (3) collaborating channel types, and (4) the impact of collaborations on video and channel popularity. Our results show that collaborations are in many cases significantly beneficial regarding viewers and newly attracted subscribers for both collaborating channels, often showing more than 100% popularity growth compared with noncollaboration videos.

VoDCast: Efficient SDN-based multicast for video on demand

Video constitutes the majority of traffic in ISP networks. The demand for more and higher quality videos is growing rapidly while network capacities are limited. Today, OTT video is mostly delivered over CDNs. For ISP-internal video such as IPTV channels, IP multicast provides an efficient delivery method. However, this does not scale for OTT videos due to their large number and their Zipf-distributed popularity. SDN-based multicast enables ISPs to deliver content based on efficient network-level multicast. However, so far this concept has not been applied for OTT Video-on-Demand (VoD) scenarios. To this end, this papers contribution is threefold. First, a novel network-based multicast approach for OTT VoD delivery is presented, named VoDCast. Second, trace-based network simulations are designed and conducted. Third, the achievable bandwidth reduction and practicability of VoDCast is shown based on a two-week YouTube trace of a nation-wide mobile provider. VoDCast is able to decrease traffic volume and variance, while keeping network provider costs in terms of state overhead and state change low.