Mobile Instant Messaging (MIM) applications such as WhatsApp transformed human communication by enabling global exchange of various message types, such as text, image, video, or voice, at any time. Network providers are facing a substantial user base and network load which is especially high in group chats where each message needs to be distributed to each member. Due to end-to-end encryption, network operators must obtain knowledge about the communication and the resulting load on the network by other means, which makes it necessary to model the network traffic of MIM. In this work, we therefore present an approach to source traffic modeling for MIM. After identifying the building blocks of a Source Traffic Model (STM) for MIM, we address existing gaps through studies on MIM communication networks, contact proximity, media compression and payload size, as well as media file size distribution. Combining existing literature and our work, we present and implement a modular STM approach which can be used for developing STMs for MIM. Using an exemplary STM, we evaluate the daily network traffic per user. With this, we provide a comprehensive description of MIM in the network researching context and enable consideration of MIM in future network design.

Explainable Artificial Intelligence (XAI) is essential for the acceptance of machine learning (ML) models, especially in critical domains like network security. Administrators need interpretable explanations to validate decisions, yet existing XAI methods often suffer from low consensus, where different techniques yield conflicting explanations. A key factor contributing to this issue is the presence of correlated features, which allows multiple equivalent but divergent explanations. While decorrelation techniques, such as Principal Component Analysis (PCA), can mitigate this, they often reduce interpretability by abstracting original features into complex combinations. This work investigates whether feature decorrelation via decomposition techniques can improve consensus among post-hoc XAI methods in the context of ML-based network intrusion detection (ML-NIDS). Using both NIDS and synthetic data, we analyze the effect of decorrelation across different models and preprocessing. We find that decorrelation can significantly improve consensus, but its effectiveness is highly dependent on the underlying model, preprocessing, and dataset characteristics. We also explore sparsityinducing variants of PCA to partially recover interpretability, though results vary depending on the level of sparsity enforced.

Delivering popular short video streaming services like TikTok, Instagram Reels, or YouTube Shorts, poses substantial challenges for service providers and network operators. This is not only due to high download volumes but also due to high-volume pre-loading strategies that cause high bandwidth demand variations. These strategies, designed to reduce initial delays, can additionally lead to bandwidth excess when users swipe quickly through videos and consume only a fraction of downloaded content. This creates inefficiencies and unbalanced network resource utilization, particularly in competitive bandwidth environments. To address these challenges, we investigate the effectiveness of bandwidth capping in this paper, i.e., limiting the throughput of video flows in the network. We conduct measurement studies to analyze the impact of capping on network interactions and Quality of Experience (QoE) of three popular short video services in different scenarios. We find that capping substantially reduces download volume (15% -- 45% median reduction) and bandwidth excess (18% -- 52% mean reduction), while bandwidth utilization fairness improves. Meanwhile, QoE surprisingly remains nearly unaffected in most cases, with only minor statistical differences in a few scenarios.

Video conferencing has become indispensable in both professional and social contexts. From a networking point of view, timely distribution of media to all clients participating in a video conference is required. However, fluctuating network conditions pose a challenge, so that a high Quality of Experience (QoE) might not always be achieved. When assessing how network conditions impact the QoE of video conferencing, previous QoE studies focused on one-to-one settings and suffered from small numbers of participants due to their costly laboratory setups. In this work, we investigate crowdsourcing-based QoE studies for video conferencing in order to obtain a higher number and more globally distributed and diverse participants. For this, we consider multi-party video conferencing and design a web-based study framework which provides a high realism to online study participants by involving themselves in the presented video call. Finally, we conduct a QoE study with our framework to demonstrate the suitability of crowdsourcing for assessing the QoE impact of network-level and application-level degradations of video conferencing applications.

Short-form video (SFV) services, such as TikTok and Instagram Reels, have rapidly gained widespread popularity, accumulating billions of users. However, evaluating Quality of Experience (QoE) for these services poses challenges as they are typically consumed in mobile and interactive settings. In this paper, we introduce a novel QoE evaluation framework for SFV, which allows for a controlled presentation of stimuli and a reliable collection of valid QoE ratings in an unsupervised setting, while maintaining the authenticity of the mobile, interactive SFV experience. We use our framework to conduct two QoE studies on the impact of waiting times, i.e., initial delay and stalling, on the QoE of SFV via crowdsourcing. Our findings reveal that initial delay results in a three times higher probability that users swipe to the next video within the first ten seconds compared to stalling. In contrast, the Mean Opinion Score (MOS) of stalling is up to 0.4 lower than initial delay for the same waiting time conditions. These insights provide valuable guidelines for optimizing SFV content delivery to enhance user satisfaction, but also highlight the need for novel QoE models, which can describe not only perceived QoE but also resulting user engagement and behavior.

Deterministic Wireless Sensor Networks over IEEE 802.15.4 can provide latency-bounded transmission of flows, which is an important enabler for current and future Internet of Things (IoT) use cases. To realise such networks, a viable routing and scheduling solution must be found that can accept all given flows and maintain their latency requirements. The joint routing and scheduling (JRaS) problem promises optimal routing and scheduling decisions-however, at the expense of very high computation times. To overcome this issue, we propose efficient modifications to the separate routing and scheduling problems, such that we can obtain a success rate similar to the optimal JRaS approach. However, our solutions can be found in much less time. We conduct extensive performance evaluations for different problem complexities and found a speedup in the range of 3.03× up to 6.09× compared to JRaS while having almost no statistical difference in success rates.

Modern network monitoring applications often rely on traditional machine learning models conceived for specific analysis tasks, which require extensive feature engineering, retraining for different use cases, and struggle with generalization. This lack of adaptability makes the deployment of AI/ML solutions in network monitoring a daunting task, as each new scenario requires significant reconfiguration, manual tuning, and retraining efforts, undermining the broader adoption of AI/ML for network traffic analysis. Time Series Foundation Models (TSFMs), pre-trained on vast and diverse time-series datasets, offer a promising alternative in the network monitoring realm by enabling zero-shot and few-shot adaptability across different monitoring scenarios. In this work, we explore the potential of TSFMs for network monitoring by evaluating their performance in a challenging analysis task: estimating video streaming Quality of Experience (QoE) from encrypted network traffic. Our study assesses the zero-shot and few-shot capabilities of state-of-the-art TSFMs, the impact of time-series granularity, and the role of common traffic features in performance. Using real-world video streaming QoE datasets, we show that TSFMs achieve competitive results in a zero-shot setting – plug-and-play approach, and that their performance can be easily and cost-effectively improved through few-shot learning techniques, even when applied on NetFlow-like features with coarse granularity. Beyond the specific video streaming QoE monitoring application, our findings demonstrate the viability and broader applicability of TSFMs to network monitoring tasks, opening the door to more scalable and generalizable network management solutions.

The increasing complexity and frequency of cyber attacks require Network Intrusion Detection Systems (NIDS) that can adapt to evolving threats. Artificial intelligence (AI), particularly machine learning (ML), has gained increasing popularity in detecting sophisticated attacks. However, their potential lack of interpretability remains a significant barrier to their widespread adoption in practice, especially in security-sensitive areas. In response, various explainable AI (XAI) methods have been proposed to provide insights into the decision-making process. This paper investigates whether these XAI methods, including SHAP, LIME, Tree Interpreter, Saliency, Integrated Gradients, and DeepLIFT, produce similar explanations when applied to ML-NIDS. By analyzing consensus among these methods across different datasets and ML models, we explore whether an agreement exists that could simplify the practical adoption of XAI in cybersecurity, as similar explanations would eliminate the need for rigorous selection processes. Our findings reveal varying degrees of consensus among the methods, suggesting that while some align closely, others diverge significantly, highlighting the need for careful selection and combination of XAI tools to enhance trustworthiness in real-world applications.

Artificial Intelligence (AI), particularly Machine Learning (ML), has become prominent in network monitoring, yet its practical adoption, such as for anomaly and intrusion detection, remains limited. Standard AI/ML methods often exclude experts, reducing trust and hindering practical implementations. Active Learning (AL) allows to integrate admins and their expert knowledge into the ML loop by leveraging expert-labeled data. Together with self-training and automated decisions, AL can enhance model performance, trust, and the ability to adapt to system changes. In this work, we evaluate uncertainty-based AL in network monitoring, offering a comprehensive parameter study for best practices in real-world AI/ML adoption. To this end, we evaluate stream-based and pool-based AL across four datasets for various monitoring use cases and conduct a parameter study on ten uncertainty measures, thereby identifying scenarios benefiting from self-training. By analyzing the impact of admin competence on model performance, we offer actionable guidelines towards the practical implementation of AL.

The integration of web and video applications as dominant Internet content has underscored the importance of Quality of Experience (QoE) for user satisfaction, retention, and digital service success. While current research has extensively studied QoE for individual stimuli, such as web page loading or video streaming, there exists a significant gap in understanding and quantifying QoE for mixed web browsing and video streaming sessions. This paper addresses the critical need to evaluate session QoE when web and video stimuli are combined within a single web session. Employing a crowdsourcing methodology, we investigate the impact of session length, content type, and individual stimuli QoE on the overall session QoE through a full factorial design with both unimpaired and impaired stimuli. Based on these results, we evaluate the applicability of various models to accurately estimate session QoE from information about individual stimuli, offering insights into optimizing the subjective experience in web sessions.

This paper explores the relationship between loading times and Quality of Experience (QoE) in Mobile Instant Messaging (MIM) applications. Using a web application that mimics MIM interfaces, we conducted a QoE study in which participants engaged with a virtual chat partner. We controlled image loading times during chatting and evaluated their impact on QoE, annoyance, and acceptance ratings. Although the results show no difference in the QoE ratings, they clearly show that longer delays lead to greater annoyance and lower user acceptance. These findings underscore the importance for MIM app providers to minimize loading times in order to increase user satisfaction and retention.

In this paper, we present QoEXplainer, a QoE dashboard for supporting humans in understanding the internals of an explainable, data-driven Quality of Experience model. This tool leverages Large Language Models and the concept of Mediators to convey relevant explanations to the user in an understandable, chatbot-like fashion. For this purpose, our tool QoEXplainer integrates a data-driven video streaming QoE model and techniques from Explainable Artificial Intelligence. The resulting data-driven model explanations are illustrated in the dashboard and users can interact with the chatbot to ask questions about the data and QoE model and control the dashboard to enhance model understanding. With this hybrid demo, we aim to conduct a live study at QoMEX 2024 to evaluate Mediators in the context of (data-driven) QoE modelling with domain experts.

Wide Area Network (WAN) research benefits from the availability of realistic network topologies, e. g., as input to simulations, emulators, or testbeds. With the rise of Machine Learning (ML) and particularly Deep Learning (DL) methods, this demand for topologies, which can be used as training data, is greater than ever. However, public datasets are limited, thus, it is promising to generate synthetic graphs with realistic properties based on real topologies for the augmentation of existing data sets. As the generation of synthetic graphs has been in the focus of researchers of various application fields since several decades, we have a variety of traditional model-dependent and model-independent graph generators at hand, as well as DL-based approaches, such as Generative Adversarial Networks (GANs). In this work, we adapt and evaluate these existing generators for the WAN use case, i. e., for generating synthetic WANs with realistic geographical distances between nodes. We investigate two approaches to improve edge weight assignments: a hierarchical graph synthesis approach, which divides the synthesis into local clusters, as well as sophisticated attributed sampling. Finally, we compare the similarity of synthetic and real WAN topologies and discuss the suitability of the generators for data augmentation in the WAN use case. For this, we utilize theoretical graph metrics, as well as practical, communication network-centric performance metrics, obtained via OMNeT++ simulation.

Network operators require real-time traffic monitoring insights to provide high performance and security to their customers. It has been shown that artificial intelligence and machine learning (ML) can improve the visibility of telemetry systems, especially with encrypted traffic. However, current solutions cannot cope with high traffic rates and volumes in large-scale networks. To realize the ML-driven network intelligence paradigm at terabit scale, we design Marina, a system that spreads monitoring over a highly efficient data plane, which can extract traffic statistics at line rate, and a powerful ML server, which can run monitoring inference using complex ML models. We apply temporal microaggregation into sub-second time slots and extract moment-based statistics. These allow to flexibly obtain accurate ML-based monitoring decisions during the next time slot. To demonstrate the scalability of our design, we implement and evaluate a Marina data plane prototype on a Barefoot Wedge 100BF-65X P4 switch, which can monitor more than 520,000 concurrent flows at full switching capacity of 6.4 Tbps. We validate the analytics capabilities enabled by our Marina implementation for four ML-driven real-time monitoring tasks with a broad set of standard ML models, achieving comparable or better than state-of-the-art results.

With video streaming traffic generally being encrypted end-to-end, there is a lot of interest from network operators to find novel ways to evaluate streaming performance at the application layer. Machine learning (ML) has been extensively used to develop solutions that infer application-level Key Performance Indicators (KPI) and/or Quality of Experience (QoE) from the patterns in encrypted traffic. Having such insights provides the means for more user-centric traffic management and enables the mitigation of QoE degradations, thus potentially preventing customer churn. The ML–based QoE/KPI estimation solutions proposed in literature are typically trained on a limited set of network scenarios and it is often unclear how the obtained models perform if applied in a previously unseen setting (e.g., if the model is applied at the premises of a different network operator). In this paper, we address this gap by cross-evaluating the performance of QoE/KPI estimation models trained on 4 separate datasets generated from streaming 48000 video streaming sessions. The paper evaluates a set of methods for improving the performance of models when applied in a different network. Analyzed methods require no or considerably less application-level ground-truth data collected in the new setting, thus significantly reducing the extensiveness of required data collection.

Reaching close-to-optimal bandwidth utilization in dynamic adaptive streaming over HTTP (DASH) systems can, in theory, be achieved with a small discrete set of bit rate representations. This includes typical bit rate ladders used in state-of-the-art DASH systems. In practice, however, we demonstrate that bandwidth utilization, and consequently the quality of experience (QoE), can be improved by offering a continuous set of bit rate representations, i.e., a continuous bit rate slide (COBIRAS). Moreover, we find that the buffer fill behavior of different standard adaptive bit rate (ABR) algorithms is sub-optimal in terms of bandwidth utilization. To overcome this issue, we leverage COBIRAS’ flexibility to request segments with any arbitrary bit rate and propose a novel ABR algorithm MinOff , which helps maximizing bandwidth utilization by minimizing download off-phases during streaming. To avoid extensive storage requirements with COBIRAS and to demonstrate the feasibility of our approach, we design and implement a proof-of-concept DASH system for video streaming that relies on just-in-time encoding ( JITE ), which reduces storage consumption on the DASH server. Finally, we conduct a performance evaluation on our testbed and compare a state-of-the-art DASH system with few bit rate representations and our JITE DASH system, which can offer a COBIRAS, in terms of bandwidth utilization and video QoE for different ABR algorithms.

Software-based network security solutions using SDN/NFV provide high flexibility and short development cycles, but may impose a bottleneck onto the network due to their lack of ASIC-based hardware packet processing. To overcome this limitation, several frameworks have emerged to enable flexible high speed packet processing in software, e.g., NAPI, XDP, or DPDK, or on programmable data planes in hardware, e.g., P4. Despite aiming for a common goal, the design principles of these technologies diverge, which raises the question of their suitability for critical security-related network functions, such as firewalls. In this work, we implement a stateful firewall, which is capable of tracking TCP state and sequence numbers, for each of the four aforementioned high speed packet processing technologies and make the firewall modules publicly available. We integrate multithreading strategies, where applicable, and discuss the impact of each packet processing technology during the development process. Finally, we evaluate and compare their performance in terms of throughput in two scenarios following the guidelines of RFC3511 in a 100 Gbps testbed.

The notion of experiment precision quantifies the variance of user ratings in a subjective experiment. Although there exist measures that assess subjective experiment precision, to the best of our knowledge, there is no systematic framework in the Multimedia Quality Assessment (MQA) field for comparing subjective experiments in terms of their precision. Therefore, the main idea of this paper is to propose a framework for comparing subjective experiments in the field of MQA based on appropriate experiment precision measures. We present three experiment precision measures and three related experiment precision comparison methods. We analyze the performance of the measures by using data from real-world Quality of Experience (QoE) subjective experiments. We believe our experiment precision assessment framework will help compare different subjective experiment methodologies. For example, it may help decide which methodology results in more precise user ratings. This may potentially inform future standardization activities.

Data-driven QoE modelling using Machine Learning (ML) allows to reduce the modelling bias and to continuously integrate new QoE results into the QoE model, which can improve its generalizability. The downside is that the majority of ML models are black-box models, which prevent to obtain insights about QoE influence factors and their fundamental relationships that are highly relevant for researchers and providers of services and networks. However, recent advances in the field of eX-plainable Artificial Intelligence (XAI) resolve these issues. Thus, XAI allows to benefit from data-driven QoE modelling to obtain generalizable QoE models, and at the same time to understand what QoE factors are relevant and how they affect the QoE score. In this work, we showcase the feasibility of explainable data-driven QoE modelling for video streaming, since video streaming QoE has been well researched, and thus, allows us to validate our results. Finally, we discuss opportunities and challenges of deploying XAI for QoE modelling.

Wide Area Network (WAN) research benefits from the availability of realistic network topologies, e.g., as input to simulations, emulators, or testbeds. With the rise of Machine Learning (ML) and particularly Deep Learning (DL) methods, this demand for topologies, which can be used as training data, is greater than ever. However, public datasets are limited, thus, it is promising to generate synthetic graphs with realistic properties based on real topologies for the augmentation of existing data sets. As the generation of synthetic graphs has been in the focus of researchers of various applications fields since several decades, we have a variety of traditional model-dependent and model-independent graph generators at hand, as well as DL-based approaches, such as Generative Adversarial Networks (GANs). In this work, we adapt and evaluate these existing generators for the WAN use case, i.e., for generating synthetic WANs with realistic geographical distances between nodes. Moreover, we investigate a hierarchical graph synthesis approach, which divides the synthesis into local clusters. Finally, we compare the similarity of synthetic and real WAN topologies and discuss the suitability of the generators for data augmentation in the WAN use case.

We introduce DeepCrypt, a deep-learning based approach to analyze YouTube adaptive video streaming Quality of Experience (QoE) from the Internet Service Provider (ISP) perspective, relying exclusively on the analysis of encrypted network traffic. Using raw features derived on-line from the encrypted stream of bytes, DeepCrypt infers six different video QoE indicators capturing the user-perceived performance of the service, including the initial playback delay, the number and frequency of rebuffering events, the video playback quality and encoding bitrate, and the number of quality changes. DeepCrypt offers deep visibility into the behavior of the end-user, enabling the fingerprinting and detection of different user actions on the video player, such as video pauses and playback scrubbing (forward, backward, out-of-buffer), offering a complete visibility on the video streaming process from in-network traffic measurements. Evaluations over a large and heterogeneous dataset composed of mobile and fixed-line measurements, using the YouTube HTML5 player, the native YouTube mobile app, as well as a generic HTML5 video player built on top of open source libraries, and considering measurements collected at different ISPs, confirm the out-performance of DeepCrypt over previously used shallow-learning models, and its generalization to different video players and network setups.

With increasing digitization and the emergence of the Internet of Things, more and more devices communicate with each other, resulting in a drastic growth of communication networks. Consequently, managing these networks, too, becomes harder and harder. Thus, Software-defined Networking (SDN) is employed, simplifying the management and configuration of networks by introducing a central controlling entity, which makes the network programmable via software and ultimately more flexible. As the SDN controller may impose scalability and elasticity issues, distributed controller architectures are utilized to combat this potential performance bottleneck. However, these distributed architectures introduce the need for constant synchronization to keep a centralized network view, and controller instances need to be placed in appropriate locations. As a result, thoroughly designing SDN-enabled networks with respect to a multitude of performance metrics, e. g., latency and induced traffic, is a challenging task. To assist in this process, we train a performance prediction model based on properties which are available during the network planning phase. We utilize a simulation-based approach for data collection to cover a large parameter space, simulating a variety of networks and controller placements for two opposing SDN architectures. On basis of this dataset, we apply Machine Learning (ML) to solve the performance prediction as a regression problem.

This work presents a novel concept for learning embeddings from encrypted network traffic. In contrast to existing approaches, we evaluate the feasibility of hierarchical embeddings by iteratively aggregating packet embeddings to flow embeddings, and flow embeddings to trace embeddings. The hierarchical embedding concept was designed to especially consider complex dependencies of Internet traffic on different time scales. We describe this novel embedding concept for the domain of network traffic in full detail, and evaluate its performance for the downstream task of website fingerprinting, i.e., identifying websites from encrypted traffic, which is relevant for network management, e.g., as a prerequisite for QoE monitoring or for intrusion detection. Our evaluation reveals that embeddings are a promising solution for website fingerprinting as our model correctly labels up to 99.8% of traces from 500 target websites.

Streaming has become the dominant source of media consumption, which not only applies to the widely researched field of video streaming, but also to music streaming. Here, previous studies so far have only researched the impact of streaming aspects, such as stalling events or initial loading times, on the QoE of music streaming. However, when using a music streaming application, users are already facing waiting times along the click path before they can start the actual streaming. These waiting times are caused by browsing delays, e.g., during searching for songs or scrolling through playlists, and can potentially deteriorate the QoE of the music streaming application. In this work, we conduct an online QoE study to quantify the impact of these browsing delays with the support of an emulated mobile music streaming web app. We found that browsing delays have no impact on the music streaming QoE, which shows that users are able to clearly distinguish between the two main functionalities of such apps, namely, browsing and streaming. However, browsing delays significantly reduce the QoE of the entire music streaming application, to a similar extent as if QoE degradations happen during the actual streaming. This shows that both browsing and streaming are equally important and have to be considered when designing music streaming annlications.

Providing sophisticated web Quality of Experience (QoE) has become paramount for web service providers and network operators alike. Due to advances in web technologies (HTML5, responsive design, etc.), traditional web QoE models focusing mainly on loading times have to be refined and improved. In this work, we relate Google's Core Web Vitals, a set of metrics for improving user experience, to the loading time aspects of web QoE. To this end, we first perform objective measurements in the web using Google's Lighthouse. To close the gap between metrics and experience, we complement these objective measurements with subjective assessment by performing multiple crowdsourcing QoE studies. In these studies, we use CWeQS, a customized framework to emulate the entire web page loading process, and ask users for their experience while controlling the Core Web Vitals. Our results suggest that the Core Web Vitals have less predictive value for web QoE than expected and that page loading times remain the main influence factor in this context.

Continuously monitoring the network activity to proactively recognise possible problems and prevent users QoE degradation is a major concern for network operators, for both mobile radio and home networks. Considering video streaming applications, which generate the majority of overall Internet traffic, monitoring the chunk requests from the video client to the video server is of particular interest, as they not only indicate that a download burst is imminent, but their type (e.g., request of an audio or video chunk) and frequency also allow to estimate which and how much data will be downloaded to the client. In this work, we propose a machine-learning based video streaming traffic monitoring architecture able to i) predict when next uplink request will be issued by the video client and ii) classify the type of next uplink request. We evaluate the system performance on a dataset of more than 900 HTTP adaptive streaming sessions and 15,000 request-response exchanges, where both the predictor of the next request arrival and the request type classifier are fed with lightweight features extracted from encrypted traffic in an online fashion, both in the uplink and downlink directions of the traffic. Results show that i) the system is able to classify the type of a HAS uplink requests with an accuracy greater than 95 % and ii) pipe-lining request type classification and prediction of next request arrival time improves the final prediction performance.

Web browsing has become the most important application of the Internet for the end user. When it comes to mobile devices, web services are mainly accessed through apps. This paper tackles the problem of Web Quality of Experience (QoE) in mobile devices, with a specific focus on apps QoE monitoring and analysis, using in-network (encrypted) traffic measurements. Measuring apps QoE is complex, not only from an instrumentation point of view, but also from the heterogeneity of user interactions which might realize substantially different user experience. To this end, we conduct a feasibility study on four specific and popular Android apps and their corresponding web services. Our test automation framework emulates and measures different user interactions commonly executed during an app session, including the app startup, clicking, scrolling, and searching. The resulting traffic is characterized on different dimensions, and machine learning models are trained to identify web services, apps, and user interactions, and to infer their QoE. The proposed models can correctly identify the specific web service and app in 86% of the cases and accurately estimate the associated QoE with small errors. Our preliminary study represents a first step towards an in-network, web QoE monitoring solution for mobile-device apps.

Today's communication networks process an increasing amount of traffic, while simultaneously providing services to a larger and more diverse quantity of devices. This enhances the complexity of the network and imposes a larger attack space, impacting network management and security efforts. Deployed hardware middle-boxes, like firewalls and Intrusion Detection Systems (IDSs) often lack the flexibility to adapt to this dynamic environment, which Network Function Virtualization (NFV) addresses by implementing these services in software. Yet, this may impose a bottleneck, due to the absence of hardware acceleration. To mitigate this drawback, the functionality can be offloaded to programmable hardware, using P4. In this work we implement an IDS, capable of operating in core and backbone networks up to 100Gbps. This is achieved by using the hardware acceleration of P4-enabled Intel©Tofino™ switches for high performance metadata extraction, in order to train an ML-based detection engine. The system is evaluated regarding its throughput and obtainable aggregation levels as well as its accuracy for detecting a variety of network attacks.

Crowdsourcing offers a faster, cheaper, and more scalable approach than the traditional laboratory quality assessment tests. However, participants perform the test in their own working environment, using their own hardware and without direct supervision of a test moderator, leading to different types of biases on the ratings. In this paper, we compare several reliability metrics that are commonly applied to the subjective ratings in terms of their sensitivity to identify typical issues of crowdsourced media quality tests. Following the subject bias theory, we simulate the ratings of different user groups with different bias and various magnitudes of uncertainty, while also considering the presence of unreliable raters. We apply traditional reliability metrics on the ratings and compare their sensitivity in identifying the severity of the raters' biases and uncertainties. Our results show that the average Spearman's rank correlation coefficient between raters can serve as a strong indicator for issues with the crowdsourcing study. This means that scoring too low for this metric should encourage researchers to revisit their study design in order to eventually improve the reliability of results from crowdsourcing-based quality studies.

HTTP Adaptive Streaming has become the de facto choice for multimedia delivery. However, the quality of adaptive video streaming may fluctuate strongly during a session due to throughput fluctuations. So, it is important to evaluate the quality of a streaming session over time. In this article, we propose a model to estimate the cumulative quality for HTTP Adaptive Streaming. In the model, a sliding window of video segments is employed as the basic building block. Through statistical analysis using a subjective dataset, we identify four important components of the cumulative quality model, namely the minimum window quality, the last window quality, the maximum window quality, and the average window quality. Experiment results show that the proposed model achieves high prediction performance and outperforms related quality models. In addition, another advantage of the proposed model is its simplicity and effectiveness for deployment in real-time estimation. Our subjective dataset as well as the source code of the proposed model have been made publicly available at https://sites.google.com/site/huyenthithanhtran1191/cqmdatabase .

Education Service Providers (ESPs) have a paramount role in the digitization of education, providing reliable devices for students and teachers and high quality Internet access at schools. In this paper, a large-scale, passive, in-device Quality of Experience (QoE) monitoring system is presented, which was deployed into a nationwide network of education-purpose devices. Four months' worth of continuous measurements were conducted by an ESP, covering more than 800 education centers and about 4000 devices, used both in schools and at home. When analyzing the QoE of web sessions in school networks, we identify a fundamental issue with the compatibility of web browsing and video QoE models, which inhibits the successful application of QoE-aware network management for multiple services.

Web browsing is one of the key applications of the Internet, if not the most important one. We address the problem of Web Quality-of-Experience (QoE) monitoring from the ISP perspective, relying on in-network, passive measurements. As a proxy to Web QoE, we focus on the analysis of the well-known SpeedIndex (SI) metric. Given the lack of application-level-data visibility introduced by the wide adoption of end-to-end encryption, we resort to machine-learning models to infer the SI and the QoE level of individual web-page loading sessions, using as input only packet- and flow-level data. In this paper, we study the impact of different end-user device types (e.g., smartphone, desktop, tablet) on the performance of such models. Empirical evaluations on a large, multi-device, heterogeneous corpus of Web-QoE measurements for the most popular websites demonstrate that the proposed solution can infer the SI as well as estimate QoE ranges with high accuracy, using either packet-level or flow-level measurements. In addition, we show that the device type adds a strong bias to the feasibility of these Web-QoE models, putting into question the applicability of previously conceived approaches on single-device measurements. To improve the state of the art, we conceive cross-device generalizable models operating at both packet and flow levels, offering a feasible solution for Web-QoE monitoring in operational, multi-device networks. To the best of our knowledge, this is the first study tackling the analysis of Web QoE from encrypted network traffic in multi-device scenarios.

Large-scale events pose severe challenges to live video streaming service providers, who need to cope with high, peaking viewer numbers and the resulting fluctuating resource demands, keeping high levels of Quality of Experience (QoE) to avoid end-user frustration and churn. In this paper, we analyze a unique dataset consisting of more than a million 2018 FIFA World Cup mobile live streaming sessions, collected at a large national public broadcaster. Different from previous work, we analyze QoE and user engagement as well as their interaction, in dependency to specific soccer match events, which have the potential to trigger flash crowds during a match. Flash crowds are a particular challenge to video service providers, since they cause sudden load peaks and consequently, the likelihood of quality problems. We further exploit the data to model viewer engagement over the course of a soccer match, and show that client counts follow very similar patterns of change across all matches. We believe that the analysis as well as the resulting models are valuable sources of insight for service providers, equipping them with tools for customer-centric resource and capacity management.

In recent years, an increasing number of Internet-based applications have been released that use virtual reality for education, training, gaming, and various forms of entertainment. When transmitting an omnidirectional 360° video over the Inter-net, it consumes considerably more data compared to traditional video streaming. To overcome the high network requirements and still reach a high Quality of Experience, HTTP adaptive streaming technology is considered for 360° video streaming. In contrast to traditional streaming, the adaptation logic considers not only the current network conditions, but also the viewport of the user, i.e., which part of the 360° sphere the user is currently focusing on. However, as the viewport of the user might change anytime, the adaptation logic is required to accurately predict the viewport in the next seconds of the playback to allow for an efficient and smooth streaming with a high visual quality.In this paper, we present novel linear programs that determine the optimal visual quality, which is reachable in a given network scenario using different approaches for viewport prediction. Our results are an important contribution for designing adaptation logics for 360° video streaming, which allow for efficient data transmission in the network while reaching a high QoE in VR applications.

In most companies, enterprise applications, such as office products or databases, are heavily used by employees during work hours. Impairments and performance issues not only slow down business processes, but might also increase the frustration of the workforce. While Quality of Experience (QoE) has been widely studied for personal multimedia applications, such as video streaming, its application to the business usage domain is still in its infancy. Due to several reasons, e.g., the high complexity of IT infrastructure, classical QoE studies can hardly be transferred to business applications. These studies are often independent from the context of usage and actively poll ratings from their participants. This work contrasts the commonly used “pull” method for collecting user ratings with a self-motivated “push” approach. This approach is inspired by complaint systems, in which users can directly report problems with a technical system as soon as they notice them. Therefore, performance assessments of a business application from employees of a cooperating company are collected with both rating systems during a time span of 1.5 years. Besides the analysis of the interaction of users with the “push” system, differences between the two methods are discussed. Further, QoE models for the monitored business application are derived based on the self-motivated “push” ratings.

Modern photogrammetric methods as well as laser measurement systems make it easy to collect large 3D point clouds that sample objects or environments. As the recorded point clouds can be used to render computer-generated images and models, they are of particular interest in the domains of geographical and architectural engineering, as well as for computer graphics (e.g., games or virtual reality). However, point clouds have a huge storage demand, thus, point clouds shall be reduced by removing some of the points. This will inevitably also reduce the Quality of Experience (QoE) of media, which is rendered from the reduced point clouds. In this work, the impact of two different reduction methods on the QoE of rendered images is investigated from two point of views, i.e., based on ratings from both naive crowdworkers as well as point cloud experts.

When conducting video QoE studies participants are usually asked to rate the QoE of prepared test videos. However, participants are given no choice to select content, which they like or in which they are interested. This may cause annoyance or frustration when conducting the QoE study, which eventually might affect the QoE results of the study. The consequent question is whether the content liking has a direct impact on the submitted ratings by the participants and whether the freedom of choosing the video content in QoE studies results in better ratings. To investigate this research question, CroQoE, an existing framework for crowdsourced video testing, is extended and used in a pilot field study. In this work, the results of a QoE study with individual and dynamic content selection are compared to a QoE study with pre-selected contents. Moreover, this work includes a comparison to a previous QoE study for validation. As the previous study was conducted on desktop PCs, the CroQoE study further allows to identify differences in the stalling perception between studies on desktop PCs and mobile devices.

Video streaming is the killer application of the Internet today. In this article, we address the problem of real-time, passive Quality-of-Experience (QoE) monitoring of HTTP Adaptive Video Streaming (HAS), from the Internet-Service-Provider (ISP) perspective - i.e., relying exclusively on in-network traffic measurements. Given the wide adoption of end-to-end encryption, we resort to machine-learning (ML) models to estimate multiple key video-QoE indicators (KQIs) from the analysis of the encrypted traffic. We present ViCrypt, an ML-driven monitoring solution able to infer the most important KQIs for HTTP Adaptive Streaming (HAS), namely stalling, initial delay, video resolution, and average video bitrate. ViCrypt performs estimations in real-time, during the playback of an ongoing video-streaming session, with a fine-grained temporal resolution of just one second. For this, it relies on lightweight, stream-like features continuously extracted from the encrypted stream of packets. Empirical evaluations on a large and heterogeneous corpus of YouTube measurements show that ViCrypt can infer the targeted KQIs with high accuracy, enabling large-scale passive video-QoE monitoring and proactive QoE-aware traffic management. Different from the state of the art, and besides real-time operation, ViCrypt is not bound to coarse-grained KQI-classes, providing better and sharper insights than other solutions. Finally, ViCrypt does not require chunk-detection approaches for feature extraction, significantly reducing the complexity of the monitoring approach, and potentially improving on generalization to different HAS protocols used by other video-streaming services such as Netflix and Amazon.

Due to biased assumptions on the underlying ordinal rating scale in subjective Quality of Experience (QoE) studies, Mean Opinion Score (MOS)-based evaluations provide results, which are hard to interpret and can be little meaningful. This paper proposes to consider the full QoE distribution for evaluating and reporting QoE results instead of only using MOS values. The QoE distribution can be represented in a concise way by using the parameters of a multinomial distribution without losing any information about the underlying QoE ratings, and even keeps backward compatibility with previous, biased MOS-based results. Considering QoE results as a realization of a multinomial distribution allows to rely on a well-established theoretical background, which enables meaningful evaluations also for ordinal rating scales. Exemplary evaluations are described in this work, which demonstrate these fundamental advantages of considering QoE distributions over MOS-based evaluations.

Over the last years, QUIC (Quick UDP Internet Connections) has become the default protocol for networked communication of Google services, heralded as improved successor of the prevailing Transport Control Protocol (TCP). While the deployment of QUIC is increasing, QUIC is also planned to be the foundation of HTTP/3, the next generation of the HTTP protocols, which drive almost all applications on the Web. Given these developments, this paper aims to raise the awareness of the QoE research community to the increasing presence of QUIC, which likely brings implications for QoE monitoring and management of networked multimedia applications, as well as for the overall QoE research agenda. In particular, a major promise during the introduction of QUIC has been the improvement of the QoE of web-based applications (like browsing and video) by overcoming certain limitations and inefficiencies of TCP. In order to validate this claim, a measurement study was conducted to test whether the promised QoE benefits of QUIC are indeed noticeable for end users of streaming and browsing services. Surprisingly, no evidence for any QoE improvement of QUIC over TCP could be found. This way this paper aims to demonstrate how QoE research can and should successfully address relevant current and future developments on the Internet.

Whether it is for network engineering or business intelligence insight purposes, it is crucial for an Internet Service Provider (ISP) to infer the Quality of Experience (QoE) perceived by the end user during a video streaming session. Specifically, it is important to detect video stalls as soon as they occur, to rapidly take counter-measures such as re-allocating resources more fairly among users. Video stalls fall into two different classes: (i) those caused by poor network conditions and (ii) those caused directly by the user when scrubbing or dragging the video playback forwards or backwards. However, only the former type of stalls degrade the QoE perceived by the end user. Therefore, in this paper we propose a technique to detect and classify stall events by observing the packets associated to a streaming session. We solve a least squares problem to minimize the distance between the estimated chunk's bitrate and the potential bitrate sequence that a plausible playback buffer dynamics would produce. This amounts to finding the maximally likely state sequence for a properly defined Hidden Markov Model. We propose two polynomial dynamic programming algorithms, one of which running in online fashion, computing the exact solution in the ideal case of complete and exact measurement set. We claim that our method is also applicable in an encrypted scenario, since it is robust with respect to the estimation error of a number of parameters, as we show via simulations.

This paper presents a novel adaptation logic for HTTP adaptive streaming (HAS), which achieves not only a high quality of experience (QoE) but also high QoE fairness among independent and heterogeneous clients. The algorithm forces video clients to adapt the requested quality level based on the current network conditions and their individual bit rate requirements, such that the overall quality levels selected by all currently active streaming clients are fairly distributed, i.e., they do not diverge too much. The design of the algorithm is inspired by the well-known transmission control protocol (TCP) congestion control, and drives heterogeneous clients to independently converge on similar quality levels without the need for communicating with each other and/or with a centralized controller in the network. By defining quality levels with equal visual quality, and preparing video representations accordingly, the quality level fairness is extended to QoE fairness. In this paper, the design of the TCP-inspired adaptation logic (TCPAL) is described and a simulative performance evaluation is conducted to compare the QoE and QoE fairness of the proposed algorithm with other HAS adaptation logics. TCPAL is evaluated both in scenarios with stable and fluctuating streaming capacity, and the impact of its parameters is explored. The results suggest that TCPAL performs on par with other HAS adaptation logics in terms of QoE and QoE fairness for low link capacities, but significantly improves the QoE fairness for increased link capacity. Moreover, the fairness achieved by TCPAL does not degrade in situations with fluctuating streaming capacity.

The number of smartphones connected to wireless networks and the volume of wireless network traffic generated by such devices have dramatically increased in the last few years, making it more challenging to tackle wireless network monitoring applications. The high-dimensionality of network data provided by current smartphone devices opens the door to the massive application of machine learning approaches to improve different wireless networking applications. In this paper we study the specific problem of Quality of Experience (QoE) prediction for popular smartphone apps, using machine learning models and in-smartphone measurements. We evaluate and compare different models for the analysis of smartphone generated data, including single models as well as machine learning ensembles such as bagging, boosting and stacking. Results suggest that, while decision-tree based models are the most accurate single models to predict QoE, ensemble learning models, and in particular stacking ones, are capable to significantly increase accuracy prediction and overall classification performance.

P.1203 is a recent standardized model for assessing the Quality of Experience (QoE) of HTTP Adaptive Video Streaming (HAS). However, its complex definition does not allow for a straightforward identification of the underlying assumptions. To overcome this issue, this work investigates the impact of the well-known QoE factors of HAS, namely, initial delay, stalling, and adaptation, on the output QoE score of the model. Therefore, parameter studies are conducted using a reference implementation of P.1203, and the model response to variations of the input QoE factors are compared to results of previous QoE studies in order to get a deeper understanding of the standardized model and its inherent weighting of the QoE factors of HAS.

Although Quality of Experience (QoE) of Internet services can be affected by context influence factors, their actual impact is not widely investigated yet. In the context of online video services, web portals often display advertisement banners or clips to monetize their service. However, these advertisements can distract or annoy the users, which might degrade the QoE of the actual video service. In this work, two crowdsourcing studies were conducted to investigate the impact of advertisement banners and clips on video QoE. Therefore, both theoretical opinions on in-service advertisements and subjective quality ratings are evaluated. The findings confirm that advertisements are negatively perceived by users during service consumption, but a generally negative impact on video QoE cannot be supported, as the interplay of advertisement and the QoE of video services is rather complex.

This demo introduces a wrapper used for automated measurements of mobile video streaming in the Android YouTube app. The difference to traditional measurement techniques is that the measurement is done with the native YouTube app as it is provided in the Google Play Store. In addition to bandwidth or packet loss detection, the QoE of the video stream can be measured and quantified. For this, the amount of quality changes, the current playtime, the buffer level, and statistics like video and audio format are captured. Thus, detailed relationships between network parameters and streaming behavior based on many factors can be detected within the native app available in the Play Store.

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.

Internet Service Providers need a thorough understanding of a service to maximize the Quality of Experience (QoE) of their customers by network management. Instead of quantifying the user satisfaction with long and cost-intensive subjective user studies, the QoE can often be estimated with the help of dedicated measurements of application and network parameters. We designed a QoE measurement tool for the popular audio streaming service Spotify that runs inside a Docker software container. The container is able to run headlessly as active measurement probe and emulates a user who is streaming audio files via Spotify. While streaming, network and application parameters are collected that have a high correlation to the user's QoE. The results of the measurements are used to characterize audio streaming in Spotify on application and network layer, and to evaluate important QoE factors.

One of the benefits when network operators adopt the Software Defined Networking (SDN) paradigm is the ability to monitor the traffic in the network without an additional network management system. Usually, SDN controllers utilize OpenFlow statistics messages in order to regularly gather information about all flows in the network. However, using the same polling interval for all flows does not take into account the heterogeneity of real world traffic and thus results in an imbalance between monitoring accuracy and control plane overhead. In particular, frequent querying results in a high resource consumption at the controller. This work proposes a Selective Flow Monitoring (SFM) mechanism that allows administrators to classify flows according to their individual requirements in terms of monitoring frequency, e.g., less frequent polling of elephant flows and frequent polling of QoS sensitive VoIP connections. We compare the performance of the SFM mechanism with the default monitoring scheme in a testbed featuring the Open Network Operating System (ONOS) controller. In this context, the CPU utilization of the controller is used as performance indicator. After identifying relevant influence factors like the number of flows and switches in the network, we investigate the viability of the approaches in different scenarios. Finally, we provide guidelines regarding their choice.

Offloading mobile Internet data via WiFi has emerged as an omnipresent trend. WiFi networks are already widely deployed by many private and public institutions (e.g., libraries, cafes, restaurants) but also by commercial services to provide alternative Internet access for their customers and to mitigate the load on mobile networks. Moreover, smart cities start to install WiFi infrastructure for current and future civic services, e.g., based on sensor networks or the Internet of Things. A simple model for the distribution of WiFi hotspots in an urban environment is presented. The hotspot locations are modeled with a uniform distribution of the angle and an exponential distribution of the distance, which is truncated to the city limits. We compare the characteristics of this model in detail to the real distributions. Moreover, we show the applicability and the limitations of this model, and the results suggest that the model can be used in scenarios, which do not require an accurate spatial collocation of the hotspots, such as offloading potential, coverage, or signal strength.

To cope with the increasing demands of mobile devices and the limited capacity of cellular networks, mobile connections are offloaded to WiFi. The access capacity is further increased by aggregating backhaul bandwidth of WiFi access links. To analyze the performance of aggregated access links we develop a model for two and more cooperating systems sharing capacities using an offloading scheme. The state probabilities of the different cooperating systems in the analytic model are determined by a fixed point iterative procedure. By investigating an inner and outer composite system we are able to analyze the system in imbalanced load conditions where the system reaches its full potential utilizing spare bandwidth. To evaluate the robustness of the system against users that try to exploit the system, the bandwidth received by prioritized users is quantified.

The fast growth of video streaming offers a potential market for video providers, which can significantly increase their revenues. In order to provide users a good experience, HTTP adaptive video streaming has been introduced to adapt the video quality to the network conditions. Nevertheless, it is still difficult for the network operators to assess the actual video quality on the device of the users and therefore they may not react to improve the service on the network. In this work, we propose a Virtual Network Function (VNF) to monitor the Quality of Experience (QoE) for online video service in the network. To conduct the study, on the one hand, we design a VNF monitoring to measure the video quality and estimate the QoE at the client machine. On the other hand, we place the function in two locations nearby and far away from the user to analyze the impact of geographical placement of the VNF on its performance. Our findings show that with respect to function placement, the VNF has high accuracy in estimating the QoE if it is deployed at the edge network close to the user. However, the VNF does not perform well when it operates far away from the users, e.g., at data centers. These insights help network vendors to more closely monitor the quality of the videos streamed to their customers.

In this demonstration we will show the prospects of dynamic cloud service placement. A cloud service is implemented that manages real-time video streaming and real-time control commands for a remote controlled drone. The requirements for this cloud service are groundbreaking because the image transfer and the control commands should be transmitted in real time that the drone can be controlled smoothly by a user. The goal is to improve user QoE for streaming services and real-time control by cloud service migrations, respecting the concept of dynamic Edge Computing by means of moving computing and monitoring applications on demand close to the user and the end device.

Edge cloud computing is a trending paradigm, which extends cloud computing by additionally utilizing computing resources at the network edge, e.g., at mobile base stations. Especially personalized services can be instantiated or migrated close to end users, which improves the latency and supports user mobility. However, the placement of the service chains is crucial for the performance of the services and the energy consumption of the edge cloud platform, and appropriate algorithms have to be designed. To support the simulative performance evaluation of such algorithms, EdgeNetworkCloudSim was developed. It is an extension of NetworkCloudSim, and allows to simulate and evaluate the orchestration and consolidation of service chains in an edge network cloud.

Monitoring the Quality of Experience (QoE) undergone by cellular network customers has become paramount for cellular ISPs, who need to ensure high quality levels to limit customer churn due to quality dissatisfaction. This paper tackles the problem of QoE monitoring, assessment and prediction in cellular networks, relying on end-user device (i.e., smart-phone) QoS passive traffic measurements and QoE crowdsourced feedback. We conceive different QoE assessment models based on supervised machine learning techniques, which are capable to predict the QoE experienced by the end user of popular smartphone apps (e.g., YouTube and Facebook), using as input the passive in-device measurements. Using a rich QoE dataset derived from field trials in operational cellular networks, we benchmark the performance of multiple machine learning based predictors, and construct a decision-tree based model which is capable to predict the per-user overall experience and service acceptability with a success rate of 91% and 98% respectively To the best of our knowledge, this is the first paper using end-user, in-device passive measurements and machine learning models to predict the QoE of smartphone users in operational cellular networks.

YoMoApp (YouTube Monitoring App) is an Android app to monitor mobile YouTube video streaming on both application- and network-layer. Additionally, it allows to collect subjective Quality of Experience (QoE) feedback of end users. During the development of the app, the stable versions of YoMoApp were already available in the Google Play Store, and the app was downloaded, installed, and used on many devices to monitor streaming sessions. As the app was not advertised in special campaigns or used for dedicated QoE studies, the monitored streaming sessions of this period compose the data set of a large unsupervised field study. The collected data set is evaluated to characterize current mobile YouTube streaming on both application and network layers. Furthermore, the problems and methodology to obtain QoE results from such unsupervised field study are discussed together with the actual QoE results. Correlations between QoE factors are investigated, and the QoE of clusters of similar streaming sessions is analyzed.

Quality of Experience (QoE) of Internet services is affected by human, system, and context influence factors. While most QoE studies so far are focused on system factors only, this work will assess the impact of context factors of video streaming on QoE. As video streaming is mostly consumed from web pages, such as video portals, the investigated test conditions are applied to the web page, which embeds the video player. Therefore, the study of context factors is implicitly conducted within a crowdsourced QoE study. The test conditions considered different page load times, poster image qualities, and displayed advertisements on the web page, which are typical context factors when consuming a video streaming service. The results of the study show that the modification of the context factors on the streaming web page leaves the users' QoE rating unperturbed, which suggests that the investigated context factors have a negligible impact on video streaming QoE, or that the rating task of the subjective QoE study superimposed the context factors.

Software defined networking (SDN) has emerged as a promising networking paradigm overcoming various drawbacks of current communication networks.The control and data plane of switching devices is decoupled and control functions are centralized at the network controller. In SDN, each new flow introduces additional signaling traffic between the switch and the controller. Based on this traffic, rules are created in the flow table of the switch, which specify the forwarding behavior. To avoid table overflows, unused entries are removed after a predefined time-out period. Given a specific traffic mix, the choice of this time-out period affects the tradeoff between signaling rate and table occupancy. As a result, network operators have to adjust this parameter to enable a smooth and efficient network operation. Due to the complexity of this problem caused by the various traffic flows in a network, a suitable abstraction is necessary in order to derive valid parameter values in time. The contribution of this paper is threefold. First, we formulate a simple analytical model that allows optimizing the network performance with respect to the table occupancy and the signaling rate. Second, we validate the model by means of simulation. Third, we illustrate the impact of the time-out period on the signaling traffic and the flow table occupancy for different data-plane traffic mixes and characteristics. This includes scenarios with single application instances, as well as multiple application instances of different application types in an SDN-enabled network.

Software Defined Networking (SDN) is a major paradigm in the field of current communication networks. SDN is used as the basis of many new networks although few performance models are available in the literature, and the majority of performance evaluations are based primarily on practical measurements. To fill this gap, we develop an analytical model to assess SDN control plane traffic as well as the occupancy of the flow table of an SDN switch. The contribution of this work is the formulation of the model for the performance-decisive parameters control-plane traffic and flow table occupancy and the application of the model for different data plane traffic characteristics. In the end, there is a discussion about the setting of time-out values for storing flow entries in the switch flow table depending on the traffic characteristics in the data plane. The trade-off between the signaling traffic in the control plane and the occupancy of the flow table is discussed to minimize both.

Free-to-play models, streaming of games and eSports are reasons for online gaming to grow in popularity recently. On the forefront are multiplayer online battle arenas, which gain high popularity by introducing a competitive format that is easy to access and requires cooperation and team play. These games highly rely on fast reaction of the players, which makes latency the key performance indicator of such applications. To obtain low latency, this paper proposes moving game servers close to players towards the edge of the network. The performance of such mechanism highly depends on the geographic distribution of players. By analyzing match histories and statistics, we develop models for the arrival process and location of game requests. This allows us to evaluate the performance of edge server resource migration policies in an event based simulation. Our results show that a high number of edge servers is preferable compared to few larger edge servers to reduce the latency of players. This supports approaches that allow deploying virtual server instances in the back-haul.

Adaptive crowdsourcing is a new approach to crowdsourced Quality of Experience (QoE) studies, which aims to improve the certainty of resulting QoE models by adaptively distributing a fixed budget of user ratings to the test conditions. The main idea of the adaptation is to dynamically allocate the next rating to a condition, for which the submitted ratings so far show a low certainty. This paper investigates the effects of statistical adaptation on the distribution of ratings and the goodness of the resulting QoE models. Thereby, it gives methodological advice how to select test conditions for future crowdsourced QoE studies.

Today's packet-switched networks are subject to bandwidth fluctuations that cause degradation of the user experience of multimedia services. In order to cope with this problem, HTTP adaptive streaming (HAS) has been proposed in recent years as a video delivery solution for the future Internet and being adopted by an increasing number of streaming services, such as Netflix and Youtube. HAS enables service providers to improve users' quality of experience (QoE) and network resource utilization by adapting the quality of the video stream to the current network conditions. However, the resulting time-varying video quality caused by adaptation introduces a new type of impairment and thus novel QoE research challenges. Despite various recent attempts to investigate these challenges, many fundamental questions regarding HAS perceptual performance are still open. In this paper, the QoE impact of different technical adaptation parameters, including chunk length, switching amplitude, switching frequency, and temporal recency, are investigated. In addition, the influence of content on perceptual quality of these parameters is analyzed. To this end, a large number of adaptation scenarios have been subjectively evaluated in four laboratory experiments and one crowdsourcing study. A statistical analysis of the combined data set reveals results that partly contradict widely held assumptions and provide novel insights in perceptual quality of adapted video sequences, e.g., interaction effects between quality switching direction (up/down) and switching strategy (smooth/abrupt). The large variety of experimental configurations across different studies ensures the consistency and external validity of the presented results that can be utilized for enhancing the perceptual performance of adaptive streaming services.

A quarter of the world population will be using smartphones to access the Internet in the near future. In this context, understanding the quality of experience (QoE) of popular apps in such devices becomes paramount to cellular network operators, who need to offer high-quality levels to reduce the risks of customers churning for quality dissatisfaction. In this paper, we address the problem of QoE provisioning in smartphones from a double perspective, combining the results obtained from subjective laboratory tests with end-device passive measurements and QoE crowd-sourced feedback obtained in operational cellular networks. The study addresses the impact of both access bandwidth and latency on the QoE of five different services and mobile apps: YouTube, Facebook, Web browsing through Chrome, Google Maps, and WhatsApp. We evaluate the influence of both constant and dynamically changing network access conditions, tackling in particular the case of fluctuating downlink bandwidth, which is typical in cellular networks. As a main contribution, we show that the results obtained in the laboratory are highly applicable in the live scenario, as mappings track the QoE provided by users in real networks. We additionally provide hints and bandwidth thresholds for good QoE levels on such apps, as well as discussion on end-device passive measurements and analysis. The results presented in this paper provide a sound basis to better understand the QoE requirements of popular mobile apps, as well as for monitoring the underlying provisioning network. To the best of our knowledge, this is the first paper providing such a comprehensive analysis of QoE in mobile devices, combining network measurements with users QoE feedback in laboratory tests, and operational networks.

A quarter of the world population will be using smartphones to access the Internet in the near future. In this context, understanding the Quality of Experience (QoE) of popular apps in such devices becomes paramount to cellular network operators, who need to offer high quality levels to reduce the risks of customers churning for quality dissatisfaction. In this paper we address the problem of QoE provisioning in smartphones from a double perspective, combining the results obtained from subjective lab tests with end-device passive measurements and QoE crowd-sourced feedback obtained in operational cellular networks. The study addresses the impact of the downlink bandwidth on the QoE of three popular smartphone apps: YouTube, Facebook and Google Maps. As a main contribution, we show that the results obtained in the lab are highly applicable in the live scenario, as mappings track the QoE provided by users in real networks. We additionally provide hints and bandwidth thresholds for good QoE levels on such apps, as well as discussion on end-device passive measurements and analysis. The results presented in this paper provide a sound basis to better understand the QoE requirements of popular mobile apps, as well as for monitoring the underlying provisioning network. To the best of our knowledge, this is the first paper providing such a comprehensive analysis of QoE in mobile devices, combining network measurements with users QoE feedback in lab tests and operational networks.

HTTP Adaptive Streaming (HAS) adapts the video quality to the current network condition by switching between different quality layers. As HAS was shown to perform better than classical video streaming, it is becoming increasingly popular. Recent research showed that quality switch amplitude and time on layer have an impact on the Quality of Experience (QoE) of HAS. However, those studies focused only on adaptation between two layers so far. This work extends these findings by taking adaptation between three layers into account. Thereby, especially the impact of an intermediate layer on user perceived quality is investigated. Crowdsourcing experiments were conducted in order to collect subjective ratings for adaptation between three layers. The results indicate that the quality of each layer and the time on each layer are important QoE parameters. This encourages the usage of temporal pooling approaches for QoE prediction and QoE-aware traffic management. Therefore, mean pooling of per-frame metrics will be applied and its performance will be validated with the subjective crowdsourcing results.

YouTube is the most popular service in the Internet and is increasingly consumed on mobile devices. With emerging adaptive video streaming technology, the question arises whether it should be also employed in the mobile context, which shows different characteristics in terms of display sizes and reliability of Internet connection. This paper compares YouTube QoE on mobile devices for both classical and adaptive video streaming based on a subjective lab experiment, in which different network conditions were emulated. Our results show that adaptive video streaming provides almost excellent results for the poorest network conditions. Thereby, it clearly outperforms classical video streaming, and thus, should be considered to achieve higher QoE in future mobile streaming applications.

Mobile users' Quality-of-Experience (QoE) is degrading as network usage increases while Internet Service Providers (ISP) face increased inter-domain traffic. This paper presents a network traffic management mechanism, named RBHORST, addressing these inefficiencies. RB-HORST exploits home routers by using them as caches and forming an overlay network between them to transfer content. To shift traffic from peak hours, RB-HORST employs predictions based on social network properties and based on similarity in the overlay network. To further improve user QoE, home routers allow trusted mobile devices to offload their mobile connection to the local WiFi. Simulation results show that an overlay is imperative for the success of the proposed caching mechanism. Especially ISPs with a large number of customers can benefit if only every thousandth user shares its router, reducing inter-domain traffic by half and superseding an ISP operated cache. The presented implementation proves that the concept is technically feasible and can be deployed and run on constrained devices.

The performance of YouTube in cellular networks is crucial to network operators, who try to find a trade-off between cost-efficient handling of the huge traffic amounts and high perceived end-user Quality of Experience (QoE). In this paper we present YoMoApp (YouTube Performance Monitoring Application), an Android application which passively monitors key performance indicators (KPIs) of YouTube adaptive video streaming on end-user smartphones. The monitored KPIs (i.e., player state/events, re-buffering, and video quality levels) can be used to analyze the QoE of mobile YouTube video sessions. YoMoApp is a valuable tool to assess the performance of cellular networks with respect to YouTube traffic, as well as to develop optimizations and QoE models for mobile HTTP adaptive streaming. We try YoMoApp through real subjective QoE lab tests showing that the tool is accurate to capture the experience of end-users watching YouTube on smartphones.

Since its introduction a few years ago, the concept of `Crowdsourcing' has been heralded as highly attractive alternative approach towards evaluating the Quality of Experience (QoE) of networked multimedia services. The main reason is that, in comparison to traditional laboratory-based subjective quality testing, crowd-based QoE assessment over the Internet promises to be not only much more cost-effective (no lab facilities required, less cost per subject) but also much faster in terms of shorter campaign setup and turnaround times. However, the reliability of remote test subjects and consequently, the trustworthiness of study results is still an issue that prevents the widespread adoption of crowd-based QoE testing. Various ideas for improving user rating reliability and test efficiency have been proposed, with the majority of them relying on a posteriori analysis of results. However, such methods introduce a major lag that significantly affects efficiency of campaign execution. In this paper we address these shortcomings by introducing in momento methods for crowdsourced video QoE assessment which yield improvements of results reliability by factor two and campaign execution efficiency by factor ten. The proposed in momento methods are applicable to existing crowd-based QoE testing approaches and suitable for a variety of service scenarios.

Today's Internet services are increasingly accessed from mobile devices, thus being responsible for growing load in mobile networks. At the same time, more and more WiFi routers are deployed such that a dense coverage of WiFi is available. Results from different related works suggest that there is a high potential of reducing load on the mobile networks by offloading data to WiFi networks, thereby improving mobile users' quality of experience (QoE) with Internet services. Additionally, the storage of the router could be used for content caching and delivery close to the end user, which is more energy efficient compared to classical content servers, and saves costs for network operators by reducing traffic between autonomous systems. Going one step beyond, we foresee that merging these approaches and augmenting them with social information from online social networks (OSNs) will result both in even less costs for network operators and increased QoE of end users. Therefore, we propose home router sharing based on trust (HORST) - a socially-aware traffic management solution which targets three popular use cases: data offloading to WiFi, content caching/prefetching, and content delivery.

This paper addresses the challenge of assessing and modeling Quality of Experience (QoE) for online video services that are based on TCP-streaming. We present a dedicated QoE model for You Tube that takes into account the key influence factors (such as stalling events caused by network bottlenecks) that shape quality perception of this service. As second contribution, we propose a generic subjective QoE assessment methodology for multimedia applications (like online video) that is based on crowd sourcing - a highly cost-efficient, fast and flexible way of conducting user experiments. We demonstrate how our approach successfully leverages the inherent strengths of crowd sourcing while addressing critical aspects such as the reliability of the experimental data obtained. Our results suggest that, crowd sourcing is a highly effective QoE assessment method not only for online video, but also for a wide range of other current and future Internet applications.