Refine
Has Fulltext
- yes (20)
Year of publication
- 2022 (20) (remove)
Document Type
- Working Paper (20) (remove)
Keywords
- Datennetz (14)
- P4 (2)
- SDN (2)
- 5G-ATSSS (1)
- 5GC (1)
- Arbeitsmarktforschung (1)
- Arbeitsmarktintegration (1)
- Aufführung (1)
- Autorotation (1)
- Balloon (1)
Institute
Sonstige beteiligte Institutionen
Tactile Internet aims at allowing perceived real-time interactions between humans and machines. This requires satisfying a stringent latency requirement of haptic data streams whose data rates vary drastically as the results of perceptual codecs. This introduces a complex problem for the underlying network infrastructure to fulfill the pre-defined level of Quality of Service (QoS). However, novel networking hardware with data plane programming capability allows processing packets differently and opens up a new opportunity. For example, a dynamic and network-aware resource management strategy can help satisfy the QoS requirements of different priority flows without wasting precious bandwidth. This paper introduces virtual queues for service differentiation between different types of traffic streams, leveraging protocol independent switch architecture (PISA). We propose coordinating the management of all the queues and dynamically adapting their sizes to minimize packet loss and delay due to network congestion and ensure QoS compliance.
Today’s advanced Internet-of-Things applications raise technical challenges on cloud, edge, and fog computing. The design of an efficient, virtualized, context-aware, self-configuring orchestration system of a fog computing system constitutes a major development effort within this very innovative area of research. In this paper we describe the architecture and relevant implementation aspects of a cloudless resource monitoring system interworking with an SDN/NFV infrastructure. It realizes the basic monitoring component of the fundamental MAPE-K principles employed in autonomic computing. Here we present the hierarchical layering and functionality within the underlying fog nodes to generate a working prototype of an intelligent, self-managed orchestrator for advanced IoT applications and services. The latter system has the capability to monitor automatically various performance aspects of the resource allocation among multiple hosts of a fog computing system interconnected by SDN.
Future mobile communication networks, such as 5G and beyond, can benefit from Virtualized Network Functions (VNFs) when deployed on cloud infrastructures to achieve elasticity and scalability. However, new challenges arise as to managing states of Network Functions (NFs). Especially control plane VNFs, which are mainly found in cellular core networks like the 5G Core (5GC), received little attention since the shift towards virtualizing NFs. Most existing solutions for these core networks are often complex, intrusive, and are seldom compliant with the standard. With the emergence of 5G campus networks, UEs will be mainly machine-type devices. These devices communicate more deterministically, bringing new opportunities for elaborated state management. This work presents an emulation environment to perform rigorous measurements on state access patterns. The emulation comes with a fully parameterized Markov model for the UE to examine a wide variety of different devices. These measurements can then be used as a solid base for designing an efficient, simple, and standard conform state management solution that brings us further towards stateless core networks.
This document presents a networking latency measurement setup that focuses on affordability and universal applicability, and can provide sub-microsecond accuracy. It explains the prerequisites, hardware choices, and considerations to respect during measurement. In addition, it discusses the necessity for exhaustive latency measurements when dealing with high availability and low latency requirements. Preliminary results show that the accuracy is within ±0.02 μs when used with the Intel I350-T2 network adapter.
In scientific research, the independent reproduction of experiments is the source of trust. Detailed documentation is required to enable experiment reproduction. Reproducibility awards were created to honor the increased documentation effort. In this work, we propose a novel approach toward reproducible research—a structured experimental workflow that allows the creation of reproducible experiments without requiring additional efforts of the researcher. Moreover, we present our own testbed and toolchain, namely, plain orchestrating service (pos), which enables the creation of such experimental workflows. The experiment is documented by our proposed, fully scripted experiment structure. In addition, pos provides scripts enabling the automation of the bundling and release of all experimental artifacts. We provide an interactive environment where pos experiments can be executed and reproduced, available at https://gallenmu.github.io/single-server-experiment.
Time-to-Live (TTL) caches decouple the occupancy of objects in cache through object-specific validity timers. Stateof- the art techniques provide exact methods for the calculation of object-specific hit probabilities given entire cache hierarchies with random inter-cache network delays. The system hit probability is a provider-centric metric as it relates to the origin offload, i.e., the decrease in the number of requests that are served by the content origin server. In this paper we consider a user-centric metric, i.e., the response time, which is shown to be structurally different from the system hit probability. Equipped with the state-of-theart exact modeling technique using Markov-arrival processes we derive expressions for the expected object response time and pave a way for its optimization under network delays.
This paper gives an overview of our recent activities in the field of satellite communication networks, including an introduction to geostationary satellite systems and Low Earth Orbit megaconstellations. To mitigate the high latencies of geostationary satellite networks, TCP-splitting Performance Enhancing Proxies are deployed. However, these cannot be applied in the case of encrypted transport headers as it is the case for VPNs or QUIC. We summarize performance evaluation results from multiple measurement campaigns. In a recently concluded project, multipath communication was used to combine the advantages of very heterogeneous communication paths: low data rate, low latency (e.g., DSL light) and high data rate, high latency (e.g., geostationary satellite).
Die Bedeutung der sozialen Bewegung Fridays for Future (FFF) ist auch nach der Covid-19-Pandemie hoch, was sich daran zeigt, dass am 23.09.2022 weltweit zahlreiche Demonstrierende beim globalen Klimastreik für Klimagerechtigkeit auf die Straße gingen. Aus dem großen Zuspruch für die Bewegung ergibt sich zum einen die Frage, was die Klimabewegung unter Gerechtigkeit versteht und zum anderen die Frage, wie sie diese politisch umsetzen möchte. Für die Untersuchung wird ein Ländervergleich zwischen den FFF-Gruppen Deutschland, Österreich, Italien und Ungarn vorgenommen. Die Autor:innen des Forschungsbeitrags führten mithilfe von Interviews mit Aktivist:innen, Analysen der Websites und des relevantesten Social Media-Kanals Fallanalysen durch. Die Forschungsarbeit kommt dabei zum Ergebnis, dass die Gerechtigkeitsvorstellungen der Gruppen nahezu übereinstimmen. Hinsichtlich der Umsetzungsperspektiven ergeben sich viele Gemeinsamkeiten bei der Netzwerkbildung und dem Agenda Setting der nationalen FFF-Gruppen. Während die konkreten Forderungen der Aktivist:innen an verschiedene Akteur:innen divergieren, ist allen vier untersuchten FFF-Gruppen gemein, dass die Politik der zentrale Adressat der Forderungen ist.
Um zu beweisen, daß Senecas Tragödien nicht aufführbar seien, hat Kugelmeier auf ihre zahlreichen Unstimmigkeiten und Widersprüche hingewiesen. Zum Beispiel begehe Phaedra Selbstmord über dem Leichnam des Hippolytus, als dieser noch gar nicht vorhanden ist. Für Kugelmeier werden diese Unstimmigkeiten allerdings, wenn der Text nur vorgelesen wird, infolge der „inneren Vergegenwärtigung“ nicht ernsthaft wahrgenommen. Die vorliegende Arbeit möchte genau das Gegenteil zeigen: Berücksichtigung dessen, was auf einer Bühne dargestellt werden kann und eindringliches Studium von Senecas Texten erweisen, daß die Tragödien aufführbar sind und nach Absicht Senecas auch für Aufführungen konzipiert wurden. In einer wohldurchdachten Aufführung verschwinden die von Kugelmeier behaupteten Schwierigkeiten.
Utilizing multiple access technologies such as 5G, 4G, and Wi-Fi within a coherent framework is currently standardized by 3GPP within 5G ATSSS. Indeed, distributing packets over multiple networks can lead to increased robustness, resiliency and capacity. A key part of such a framework is the multi-access proxy, which transparently distributes packets over multiple paths. As the proxy needs to serve thousands of customers, scalability and performance are crucial for operator deployments. In this paper, we leverage recent advancements in data plane programming, implement a multi-access proxy based on the MP-DCCP tunneling approach in P4 and hardware accelerate it by deploying the pipeline on a smartNIC. This is challenging due to the complex scheduling and congestion control operations involved. We present our pipeline and data structures design for congestion control and packet scheduling state management. Initial measurements in our testbed show that packet latency is in the range of 25 μs demonstrating the feasibility of our approach.