Refine
Has Fulltext
- yes (30)
Is part of the Bibliography
- no (30) (remove)
Document Type
- Working Paper (26)
- Conference Proceeding (4)
Language
- English (30) (remove)
Keywords
- Datennetz (10)
- P4 (5)
- SDN (4)
- 5G (2)
- MP-DCCP (2)
- Videospiel (2)
- artificial intelligence (2)
- connected mobility applications (2)
- fog computing (2)
- multipath (2)
- multipath scheduling (2)
- network calculus (2)
- satellite communication (2)
- 5G-ATSSS (1)
- 5GC (1)
- 6G (1)
- ATSSSS (1)
- Add-on-Miss (1)
- Cloud Computing (1)
- Cloud Gaming (1)
- Containerization (1)
- Cost-benefit analysis (1)
- Dijkstra’s algorithm (1)
- FIFO caching strategies (1)
- JCAS (1)
- Kathará (1)
- Kosten-Nutzen-Analyse (1)
- LFU (1)
- LRU (1)
- MTC (1)
- Network Emulator (1)
- Network Experiments (1)
- P4-INT (1)
- Performance Enhancing Proxies (1)
- QUIC (1)
- Quality of Experience (1)
- RRM (1)
- Reproducibility (1)
- SBA (1)
- SDN/NVF (1)
- Sensing-aaS (1)
- TSN (1)
- TTL (1)
- TTL validation of data consistency (1)
- Testbed (1)
- URLLC (1)
- Umfrage (1)
- VNF (1)
- VPN (1)
- Video Game QoS (1)
- Visualized Kathará (1)
- autonomic orchestration (1)
- computer performance evaluation (1)
- container virtualization (1)
- data plane programming (1)
- dataplane programming (1)
- decoding error rate (1)
- delay QoS exponent (1)
- delay bound violation probability (1)
- delay constrained (1)
- disjoint multi-paths (1)
- docker (1)
- dynamic flow migration (1)
- educational games (1)
- effective Bandwidth (1)
- emulation (1)
- federated learning (1)
- games (1)
- hackathons (1)
- haptic data (1)
- hardware-in-the-loop simulation (1)
- hardware-in-the-loop streaming system (1)
- hit ratio analysis and simulation (1)
- hybrid access (1)
- immersive learning technologies (1)
- immersive technologies (1)
- interactive authoring system (1)
- least cost (1)
- locomotion (1)
- measurements (1)
- multimodal learning (1)
- multipath communication (1)
- multipath packet scheduling (1)
- natural language processing · · · (1)
- networking (1)
- non-terrestrial networks (1)
- online survey (1)
- orchestration (1)
- path computation (1)
- performance monitoring (1)
- plain orchestrating service (1)
- pos (1)
- psychomotor training (1)
- reconfiguration (1)
- scalability evaluation (1)
- semantic understanding (1)
- sensor devices (1)
- service-curve estimation (1)
- short block-length (1)
- shortest path routing (1)
- software defined network (1)
- state management (1)
- topology (1)
- transport protocols (1)
- video game QoE (1)
- video game context factors (1)
- virtual queue (1)
- virtual reality (1)
- wheel (1)
Institute
- Institut für Informatik (30) (remove)
Sonstige beteiligte Institutionen
EU-Project number / Contract (GA) number
- 101069547 (1)
This paper discusses the problem of finding multiple shortest disjoint paths in modern communication networks, which is essential for ultra-reliable and time-sensitive applications. Dijkstra’s algorithm has been a popular solution for the shortest path problem, but repetitive use of it to find multiple paths is not scalable. The Multiple Disjoint Path Algorithm (MDPAlg), published in 2021, proposes the use of a single full graph to construct multiple disjoint paths. This paper proposes modifications to the algorithm to include a delay constraint, which is important in time-sensitive applications. Different delay constraint least-cost routing algorithms are compared in a comprehensive manner to evaluate the benefits of the adapted MDPAlg algorithm. Fault tolerance, and thereby reliability, is ensured by generating multiple link-disjoint paths from source to destination.
State Management at line rate is crucial for critical applications in next-generation networks. P4 is a language used in software-defined networking to program the data plane. The data plane can profit in many circumstances when it is allowed to manage its state without any detour over a controller. This work is based on a previous study by investigating the potential and performance of add-on-miss insertions of state by the data plane. The state keeping capabilities of P4 are limited regarding the amount of data and the update frequency. We follow the tentative specification of an upcoming portable-NIC-architecture and implement these changes into the software P4 target T4P4S. We show that insertions are possible with only a slight overhead compared to lookups and evaluate the influence of the rate of insertions on their latency.
Utilizing multiple access networks such as 5G, 4G, and Wi-Fi simultaneously can lead to increased robustness, resiliency, and capacity for mobile users. However, transparently implementing packet distribution over multiple paths within the core of the network faces multiple challenges including scalability to a large number of customers, low latency, and high-capacity packet processing requirements. In this paper, we offload congestion-aware multipath packet scheduling to a smartNIC. However, such hardware acceleration faces multiple challenges due to programming language and platform limitations. We implement different multipath schedulers in P4 with different complexity in order to cope with dynamically changing path capacities. Using testbed measurements, we show that our CMon scheduler, which monitors path congestion in the data plane and dynamically adjusts scheduling weights for the different paths based on path state information, can process more than 3.5 Mpps packets 25 μs latency.
Web caches often use a Time-to-live (TTL) limit to validate data consistency with web servers. We study the impact of TTL constraints on the hit ratio of basic strategies in caches of fixed size. We derive analytical results and confirm their accuracy in comparison to simulations. We propose a score-based caching method with awareness of the current TTL per data for improving the hit ratio close to the upper bound.
This paper presents a novel concept to extend state-of-the-art buffer monitoring with additional measures to estimate service-curves. The online algorithm for service-curve estimation replaces the state-of-the-art timestamp logging, as we expect it to overcome the main disadvantages of generating a huge amount of data and using a lot of CPU resources to store the data to a file during operation. We prove the accuracy of the online-algorithm offline with timestamp data and compare the derived bounds to the measured delay and backlog. We also do a proof-of- concept of the online-algorithm, implement it in LabVIEW and compare its performance to the timestamp logging by CPU load and data-size of the log-file. However, the implementation is still work-in-progress.
This paper presents a prototypical implementation of the In-band Network Telemetry (INT) specification in P4 and demonstrates a use case, where a Tofino Switch is used to measure device and network performance in a lab setting. This work is based on research activities in the area of P4 data plane programming conducted at the network lab of HTW Berlin.
Packets sent over a network can either get lost or reach their destination. Protocols like TCP try to solve this problem by resending the lost packets. However, retransmissions consume a lot of time and are cumbersome for the transmission of critical data. Multipath solutions are quite common to address this reliability issue and are available on almost every layer of the ISO/OSI model. We propose a solution based on a P4 network to duplicate packets in order to send them to their destination via multiple routes. The last network hop ensures that only a single copy of the traffic is further forwarded to its destination by adopting a concept similar to Bloom filters. Besides, if fast delivery is requested we provide a P4 prototype, which randomly forwards the packets over different transmission paths. For reproducibility, we implement our approach in a container-based network emulation system called Kathará.
In network research, reproducibility of experiments is not always easy to achieve. Infrastructures are cumbersome to set up or are not available due to vendor-specific devices. Emulators try to overcome those issues to a given extent and are available in different service models. Unfortunately, the usability of emulators requires time-consuming efforts and a deep understanding of their functionality. At first, we analyze to which extent currently available open-source emulators support network configurations and how user-friendly they are. With these insights, we describe, how an ease-to-use emulator is implemented and may run as a Network Emulator as a Service (NEaaS). Therefore, virtualization plays a major role in order to deploy a NEaaS based on Kathará.
Service orchestration requires enormous attention and is a struggle nowadays. Of course, virtualization provides a base level of abstraction for services to be deployable on a lot of infrastructures. With container virtualization, the trend to migrate applications to a micro-services level in order to be executable in Fog and Edge Computing environments increases manageability and maintenance efforts rapidly. Similarly, network virtualization adds effort to calibrate IP flows for Software-Defined Networks and eventually route it by means of Network Function Virtualization. Nevertheless, there are concepts like MAPE-K to support micro-service distribution in next-generation cloud and network environments. We want to explore, how a service distribution can be improved by adopting machine learning concepts for infrastructure or service changes. Therefore, we show how federated machine learning is integrated into a cloud-to-fog-continuum without burdening single nodes.
In recent years, satellite communication has been expanding its field of application in the world of computer networks. This paper aims to provide an overview of how a typical scenario involving 5G Non-Terrestrial Networks (NTNs) for vehicle to everything (V2X) applications is characterized. In particular, a first implementation of a system that integrates them together will be described. Such a framework will later be used to evaluate the performance of applications such as Vehicle Monitoring (VM), Remote Driving (RD), Voice Over IP (VoIP), and others. Different configuration scenarios such as Low Earth Orbit and Geostationary Orbit will be considered.