Refine
Has Fulltext
- yes (9)
Is part of the Bibliography
- yes (9)
Document Type
- Doctoral Thesis (7)
- Bachelor Thesis (1)
- Master Thesis (1)
Language
- English (9)
Keywords
- Leistungsbewertung (5)
- Quality of Experience (4)
- Simulation (4)
- LoRaWAN (2)
- Streaming <Kommunikationstechnik> (2)
- Video Streaming (2)
- Autonomer Roboter (1)
- Bestärkendes Lernen (1)
- Crowdsourcing (1)
- DASH (1)
Institute
Reliable, deterministic real-time communication is fundamental to most industrial systems today. In many other domains Ethernet has become the most common platform for communication networks, but has been unsuitable to satisfy the requirements of industrial networks for a long time. This has changed with the introduction of Time-Sensitive-Networking (TSN), a set of standards utilizing Ethernet to implement deterministic real-time networks. This makes Ethernet a viable alternative to the expensive fieldbus systems commonly used in industrial environments. However, TSN is not a silver bullet. Industrial networks are a complex and highly dynamic environment and the configuration of TSN, especially with respect to latency, is a challenging but crucial task.
Various approaches have been pursued for the configuration of TSN in dynamic industrial environments. Optimization techniques like Linear Programming (LP) are able to determine an optimal configuration for a given network, but the time consumption exponentially increases with the complexity of the environment. Machine Learning (ML) has become widely popular in the last years and is able to approximate a near-optimal TSN configuration for networks of different complexity. Yet, ML models are usually trained in a supervised manner which requires large amounts of data that have to be generated for the specific environment. Therefore, supervised methods are not scalable and do not adapt to changing dynamics of the network environment.
To address these issues, this work proposes a Deep Reinforcement Learning (DRL) approach to the configuration of TSN in industrial networks. DRL combines two different disciplines, Deep Learning (DL) and Reinforcement Learning (RL), and has gained considerable traction in the last years due to breakthroughs in various domains. RL is supposed to autonomously learn a challenging task like the configuration of TSN without requiring any training data. The addition of DL allows to apply well-studied RL methods to a complex environment such as dynamic industrial networks.
There are two major contributions made in this work. In the first step, an interactive environment is proposed which allows for the simulation and configuration of industrial networks using basic TSN mechanisms. The environment provides an interface that allows to apply various DRL methods to the problem of TSN configuration. The second contribution of this work is an in-depth study on the application of two fundamentally different DRL methods to the proposed environment. Both methods are evaluated on networks of different complexity and the results are compared to the ground truth and to the results of two supervised ML approaches. Ultimately, this work investigates if DRL can adapt to changing dynamics of the environment in a more scalable manner than supervised methods.
Streaming of videos has become the major traffic generator in today's Internet and the video traffic share is still increasing. According to Cisco's annual Visual Networking Index report, in 2012, 60% of the global Internet IP traffic was generated by video streaming services. Furthermore, the study predicts further increase to 73% by 2017. At the same time, advances in the fields of mobile communications and embedded devices lead to a widespread adoption of Internet video enabled mobile and wireless devices (e.g. Smartphones). The report predicts that by 2017, the traffic originating from mobile and wireless devices will exceed the traffic from wired devices and states that mobile video traffic was the source of roughly half of the mobile IP traffic at the end of 2012.
With the increasing importance of Internet video streaming in today's world, video content provider find themselves in a highly competitive market where user expectations are high and customer loyalty depends strongly on the user's satisfaction with the provided service. In particular paying customers expect their viewing experience to be the same across all their viewing devices and independently of their currently utilized Internet access technology. However, providing video streaming services is costly in terms of storage space, required bandwidth and generated traffic. Therefore, content providers face a trade-off between the user perceived Quality of Experience (QoE) and the costs for providing the service.
Today, a variety of transport and application protocols exist for providing video streaming services, but the one utilized depends on the scenario in mind. Video streaming services can be divided up in three categories: Video conferencing, IPTV and Video-on-Demand services. IPTV and video-conferencing have severe real-time constraints and thus utilize mostly datagram-based protocols like the RTP/UDP protocol for the video transmission. Video-on-Demand services in contrast can profit from pre-encoded content, buffers at the end user's device, and mostly utilize TCP-based protocols in combination with progressive streaming for the media delivery.
In recent years, the HTTP protocol on top of the TCP protocol gained widespread popularity as a cost-efficient way to distribute pre-encoded video content to customers via progressive streaming. This is due to the fact that HTTP-based video streaming profits from a well-established infrastructure which was originally implemented to efficiently satisfy the increasing demand for web browsing and file downloads. Large Content Delivery Networks (CDN) are the key components of that distribution infrastructure. CDNs prevent expensive long-haul data traffic and delays by distributing HTTP content to world-wide locations close to the customers. As of 2012, already 53% of the global video traffic in the Internet originates from Content Delivery Networks and that percentage is expected to increase to 65% by the year 2017. Furthermore, HTTP media streaming profits from existing HTTP caching infrastructure, ease of NAT and proxy traversal and firewall friendliness.
Video delivery through heterogeneous wired and wireless communications networks is prone to distortions due to insufficient network resources. This is especially true in wireless scenarios, where user mobility and insufficient signal strength can result in a very poor transport service performance (e.g. high packet loss, delays and low and varying bandwidth). A poor performance of the transport in turn may degrade the Quality of Experience as perceived by the user, either due to buffer underruns (i.e. playback interruptions) for TCP-based delivery or image distortions for datagram-based real-time video delivery.
In order to overcome QoE degradations due to insufficient network resources, content provider have to consider adaptive video streaming. One possibility to implement this for HTTP/TCP streaming is by partitioning the content into small segments, encode the segments into different quality levels and provide access to the segments and the quality level details (e.g. resolution, average bitrate). During the streaming session, a client-centric adaptation algorithm can use the supplied details to adapt the playback to the current environment. However, a lack of a common HTTP adaptive streaming standard led to multiple proprietary solutions developed by major Internet companies like Microsoft (Smooth Streaming), Apple (HTTP Live Streaming) and Adobe (HTTP Dynamic Streaming) loosely based on the aforementioned principle. In 2012, the ISO/IEC published the Dynamic Adaptive Streaming over HTTP (MPEG-DASH) standard. As of today, DASH is becoming widely accepted with major companies announcing their support or having already implemented the standard into their products. MPEG-DASH is typically used with single layer codecs like H.264/AVC, but recent publications show that scalable video coding can use the existing HTTP infrastructure more efficiently. Furthermore, the layered approach of scalable video coding extends the adaptation options for the client, since already downloaded segments can be enhanced at a later time.
The influence of distortions on the perceived QoE for non-adaptive video streaming are well reviewed and published. For HTTP streaming, the QoE of the user is influenced by the initial delay (i.e. the time the client pre-buffers video data) and the length and frequency of playback interruptions due to a depleted video playback buffer. Studies highlight that even low stalling times and frequencies have a negative impact on the QoE of the user and should therefore be avoided. The first contribution of this thesis is the identification of QoE influence factors of adaptive video streaming by the means of crowd-sourcing and a laboratory study.
MPEG-DASH does not specify how to adapt the playback to the available bandwidth and therefore the design of a download/adaptation algorithm is left to the developer of the client logic. The second contribution of this thesis is the design of a novel user-centric adaption logic for DASH with SVC. Other download algorithms for segmented HTTP streaming with single layer and scalable video coding have been published lately. However, there is little information about the behavior of these algorithms regarding the identified QoE-influence factors. The third contribution is a user-centric performance evaluation of three existing adaptation algorithms and a comparison to the proposed algorithm. In the performance evaluation we also evaluate the fairness of the algorithms. In one fairness scenario, two clients deploy the same adaptation algorithm and share one Internet connection. For a fair adaptation algorithm, we expect the behavior of the two clients to be identical. In a second fairness scenario, one client shares the Internet connection with a large HTTP file download and we expect an even bandwidth distribution between the video streaming and the file download. The forth contribution of this thesis is an evaluation of the behavior of the algorithms in a two-client and HTTP cross traffic scenario.
The remainder of this thesis is structured as follows. Chapter II gives a brief introduction to video coding with H.264, the HTTP adaptive streaming standard MPEG-DASH, the investigated adaptation algorithms and metrics of Quality of Experience (QoE) for video streaming. Chapter III presents the methodology and results of the subjective studies conducted in the course of this thesis to identify the QoE influence factors of adaptive video streaming. In Chapter IV, we introduce the proposed adaptation algorithm and the methodology of the performance evaluation. Chapter V highlights the results of the performance evaluation and compares the investigated adaptation algorithms. Section VI summarizes the main findings and gives an outlook towards QoE-centric management of DASH with SVC.
This dissertation focuses on the performance evaluation of all components of Software Defined Networking (SDN) networks and covers whole their architecture. First, the isolation between virtual networks sharing the same physical resources is investigated with SDN switches of several vendors. Then, influence factors on the isolation are identified and evaluated. Second, the impact of control mechanisms on the performance of the data plane is examined through the flow rule installation time of SDN switches with different controllers. It is shown that both hardware-specific and controller instance have a specific influence on the installation time. Finally, several traffic flow monitoring methods of an SDN controller are investigated and a new monitoring approach is developed and evaluated. It is confirmed that the proposed method allows monitoring of particular flows as well as consumes fewer resources than the standard approach. Based on findings in this thesis, on the one hand, controller developers can refer to the work related to the control plane, such as flow monitoring or flow rule installation, to improve the performance of their applications. On the other hand, network administrators can apply the presented methods to select a suitable combination of controller and switches in their SDN networks, based on their performance requirements
Nowadays, employees have to work with applications, technical services, and systems every day for hours. Hence, performance degradation of such systems might be perceived negatively by the employees, increase frustration, and might also have a negative effect on their productivity. The assessment of the application's performance in order to provide a smooth operation of the application is part of the application management. Within this process it is not sufficient to assess the system performance solely on technical performance parameters, e.g., response or loading times. These values have to be set into relation to the perceived performance quality on the user's side - the quality of experience (QoE).
This dissertation focuses on the monitoring and estimation of the QoE of enterprise applications. As building models to estimate the QoE requires quality ratings from the users as ground truth, one part of this work addresses methods to collect such ratings. Besides the evaluation of approaches to improve the quality of results of tasks and studies completed on crowdsourcing platforms, a general concept for monitoring and estimating QoE in enterprise environments is presented. Here, relevant design dimension of subjective studies are identified and their impact of the QoE is evaluated and discussed. By considering the findings, a methodology for collecting quality ratings from employees during their regular work is developed. The method is realized by implementing a tool to conduct short surveys and deployed in a cooperating company.
As a foundation for learning QoE estimation models, this work investigates the relationship between user-provided ratings and technical performance parameters. This analysis is based on a data set collected in a user study in a cooperating company during a time span of 1.5 years. Finally, two QoE estimation models are introduced and their performance is evaluated.
In the past two decades, there has been a trend to move from traditional television to Internet-based video services. With video streaming becoming one of the most popular applications in the Internet and the current state of the art in media consumption, quality expectations of consumers are increasing. Low quality videos are no longer considered acceptable in contrast to some years ago due to the increased sizes and resolution of devices. If the high expectations of the users are not met and a video is delivered in poor quality, they often abandon the service. Therefore, Internet Service Providers (ISPs) and video service providers are facing the challenge of providing seamless multimedia delivery in high quality. Currently, during peak hours, video streaming causes almost 58\% of the downstream traffic on the Internet. With higher mobile bandwidth, mobile video streaming has also become commonplace. According to the 2019 Cisco Visual Networking Index, in 2022 79% of mobile traffic will be video traffic and, according to Ericsson, by 2025 video is forecasted to make up 76% of total Internet traffic. Ericsson further predicts that in 2024 over 1.4 billion devices will be subscribed to 5G, which will offer a downlink data rate of 100 Mbit/s in dense urban environments.
One of the most important goals of ISPs and video service providers is for their users to have a high Quality of Experience (QoE). The QoE describes the degree of delight or annoyance a user experiences when using a service or application. In video streaming the QoE depends on how seamless a video is played and whether there are stalling events or quality degradations. These characteristics of a transmitted video are described as the application layer Quality of Service (QoS). In general, the QoS is defined as "the totality of characteristics of a telecommunications service that bear on its ability to satisfy stated and implied needs of the user of the service" by the ITU. The network layer QoS describes the performance of the network and is decisive for the application layer QoS.
In Internet video, typically a buffer is used to store downloaded video segments to compensate for network fluctuations. If the buffer runs empty, stalling occurs. If the available bandwidth decreases temporarily, the video can still be played out from the buffer without interruption. There are different policies and parameters that determine how large the buffer is, at what buffer level to start the video, and at what buffer level to resume playout after stalling. These have to be finely tuned to achieve the highest QoE for the user. If the bandwidth decreases for a longer time period, a limited buffer will deplete and stalling can not be avoided. An important research question is how to configure the buffer optimally for different users and situations. In this work, we tackle this question using analytic models and measurement studies. With HTTP Adaptive Streaming (HAS), the video players have the capability to adapt the video bit rate at the client side according to the available network capacity. This way the depletion of the video buffer and thus stalling can be avoided. In HAS, the quality in which the video is played and the number of quality switches also has an impact on the QoE. Thus, an important problem is the adaptation of video streaming so that these parameters are optimized. In a shared WiFi multiple video users share a single bottleneck link and compete for bandwidth. In such a scenario, it is important that resources are allocated to users in a way that all can have a similar QoE. In this work, we therefore investigate the possible fairness gain when moving from network fairness towards application-layer QoS fairness. In mobile scenarios, the energy and data consumption of the user device are limited resources and they must be managed besides the QoE. Therefore, it is also necessary, to investigate solutions, that conserve these resources in mobile devices. But how can resources be conserved without sacrificing application layer QoS? As an example for such a solution, this work presents a new probabilistic adaptation algorithm that uses abandonment statistics for ts decision making, aiming at minimizing the resource consumption while maintaining high QoS.
With current protocol developments such as 5G, bandwidths are increasing, latencies are decreasing and networks are becoming more stable, leading to higher QoS. This allows for new real time data intensive applications such as cloud gaming, virtual reality and augmented reality applications to become feasible on mobile devices which pose completely new research questions. The high energy consumption of such applications still remains an issue as the energy capacity of devices is currently not increasing as quickly as the available data rates. In this work we compare the optimal performance of different strategies for adaptive 360-degree video streaming.
In this doctoral thesis we cover the performance evaluation of next generation data plane architectures, comprised of complex software as well as programmable hardware components that allow fine granular configuration. In the scope of the thesis we propose mechanisms to monitor the performance of singular components and model key performance indicators of software based packet processing solutions. We present novel approaches towards network abstraction that allow the integration of heterogeneous data plane technologies into a singular network while maintaining total transparency between control and data plane. Finally, we investigate a full, complex system consisting of multiple software-based solutions and perform a detailed performance analysis. We employ simulative approaches to investigate overload control mechanisms that allow efficient operation under adversary conditions. The contributions of this work build the foundation for future research in the areas of network softwarization and network function virtualization.
Development, Simulation and Evaluation of Mobile Wireless Networks in Industrial Applications
(2023)
Manyindustrialautomationsolutionsusewirelesscommunicationandrelyontheavail-
ability and quality of the wireless channel. At the same time the wireless medium is
highly congested and guaranteeing the availability of wireless channels is becoming
increasingly difficult. In this work we show, that ad-hoc networking solutions can be
used to provide new communication channels and improve the performance of mobile
automation systems. These ad-hoc networking solutions describe different communi-
cation strategies, but avoid relying on network infrastructure by utilizing the Peer-to-
Peer (P2P) channel between communicating entities.
This work is a step towards the effective implementation of low-range communication
technologies(e.g. VisibleLightCommunication(VLC), radarcommunication, mmWave
communication) to the industrial application. Implementing infrastructure networks
with these technologies is unrealistic, since the low communication range would neces-
sitate a high number of Access Points (APs) to yield full coverage. However, ad-hoc
networks do not require any network infrastructure. In this work different ad-hoc net-
working solutions for the industrial use case are presented and tools and models for
their examination are proposed.
The main use case investigated in this work are Automated Guided Vehicles (AGVs)
for industrial applications. These mobile devices drive throughout the factory trans-
porting crates, goods or tools or assisting workers. In most implementations they must
exchange data with a Central Control Unit (CCU) and between one another. Predicting
if a certain communication technology is suitable for an application is very challenging
since the applications and the resulting requirements are very heterogeneous.
The proposed models and simulation tools enable the simulation of the complex inter-
action of mobile robotic clients and a wireless communication network. The goal is to
predict the characteristics of a networked AGV fleet.
Theproposedtoolswereusedtoimplement, testandexaminedifferentad-hocnetwork-
ing solutions for industrial applications using AGVs. These communication solutions
handle time-critical and delay-tolerant communication. Additionally a control method
for the AGVs is proposed, which optimizes the communication and in turn increases the
transport performance of the AGV fleet. Therefore, this work provides not only tools
for the further research of industrial ad-hoc system, but also first implementations of
ad-hoc systems which address many of the most pressing issues in industrial applica-
tions.
The ongoing and evolving usage of networks presents two critical challenges for current and future networks that require attention: (1) the task of effectively managing the vast and continually increasing data traffic and (2) the need to address the substantial number of end devices resulting from the rapid adoption of the Internet of Things. Besides these challenges, there is a mandatory need for energy consumption reduction, a more efficient resource usage, and streamlined processes without losing service quality. We comprehensively address these efforts, tackling the monitoring and quality assessment of streaming applications, a leading contributor to the total Internet traffic, as well as conducting an exhaustive analysis of the network performance within a Long Range Wide Area Network (LoRaWAN), one of the rapidly emerging LPWAN solutions.
The ongoing and evolving usage of networks presents two critical challenges for current and future networks that require attention: (1) the task of effectively managing the vast and continually increasing data traffic and (2) the need to address the substantial number of end devices resulting from the rapid adoption of the Internet of Things. Besides these challenges, there is a mandatory need for energy consumption reduction, a more efficient resource usage, and streamlined processes without losing service quality. We comprehensively address these efforts, tackling the monitoring and quality assessment of streaming applications, a leading contributor to the total Internet traffic, as well as conducting an exhaustive analysis of the network performance within a Long Range Wide Area Network (LoRaWAN), one of the rapidly emerging LPWAN solutions.