Kai-Steffen Hielscher

The TCP performance over satellite communications has become a well-known problem, following significant experimentation with Internet services over satellite since the '90s. Several tailored TCP optimisations have been introduced (mainly implementing changes at the sender side, but also at the receiver side in some proposals). In parallel, given the challenge of installing tailored TCP versions directly in the end user system, a set of architectural extensions have been introduced culminating in the concept of a Performance Enhancing Proxy (PEP, RFC 3135), whereby a native end-to-end TCP connection is now commonly split into a series of multiple connection (a split TCP concept). This allows a tailored TCP to be deployed on the satellite link (i.e., between the satellite terminals and gateways to be optimised). Though largely used since the early 2000's, PEPs have always been unable to enhance non-TCP protocols or VPN connections traversing the satellite network segment. Application-layer compression and acceleration was also provided in some PEPs.

Since 2000, there has been a continued effort to evolve the protocol stack for Internet web services, with several updates to the protocols for HTTP-based services. A design of HTTP by Google, known as SDPY, was standardised as HTTP/2. This provided significant improvements in download speed of satellite, but at the same time deployed application-layer encryption and compression – making application-layer acceleration dependent on using an authenticated proxy and impossible within a PEP.

A more recent Google proposal (known as gQUIC) sought a transport other than TCP that uses a UDP substrate with transport encryption. This effort evolved in standardisation by the Internet Engineering Task Force (IETF) and was finally published as IETF QUIC (RFC 9000) in 2021. QUIC is specified for use with HTTP/3, a replacement for HTTP2/TCP. The main leap from classical HTTP services over TCP is in that QUIC uses encrypted datagram connections, with congestion control, flow control, NAT-rebinding and migration algorithms directly implemented within the QUIC protocol. Following standardisation, QUIC and HTTP/3 have been implemented and have been rapidly deployed to the Internet.

Hence, the design rationale of QUIC intrinsically prevents using a classical PEP solution for the optimisation of performance over a satellite system.  Whilst the application-layer performance of HTTP/3 resembles or improves on that of HTTP/2, and the transport design has been shown to operate correctly over satellite with respect to initialisation, protocol timers, and other core functions, experiments have shown that performance of QUIC operated end-to-end over paths comprising a satellite network segment can be lower than offered by TCP using a PEP. This has motivated the scientific community and the satellite industry to think of alternative solutions for QUIC congestion control (CC) to accelerate with the QUIC performance degradation, which is still now at the early stages. QUIC has also been suggested for other applications.

The German Aerospace Center (Deutsches Zentrum für Luft- und Raumfahrt), University of Aberdeen, and Friedrich-Alexander-Universität Erlangen-Nürnberg have built a consortium that is committed to thoroughly analyse the existing approaches and options to improve the performance of TCP over satellite network segment and apply the most appropriate concepts to QUIC congestion control mechanisms as well as understanding the implications of deploying the new approaches as a part of a secure end-to-end architecture. As a result, a novel algorithm will be defined and then verified against the relevant technical requirements. Finally, the resulting new QUIC specifications will be validated using real satellite trials in exemplar scenarios.

In transmission systems, a dedicated and high-performance communication infrastructure allows a parallel execution of communication-intensive functions and services. In the course of the expansion of renewable energies at lower voltage levels of the distribution networks and the shift of system responsibility to (operators of) these plants and systems, similar functions and services must also be implemented at the distribution network level in Smart Grids – so-called Smart Grid Services (SGSs).
In this project, we will therefore conduct research on online reconfiguration methods based on a two-step QoS-provisioning approach: At a first level, discrete optimization is used to find an allocation of SGSs to available servers and allocation of flows to paths through the communication network based on a topological view of the compute, storage, and communication facilities. At a second level, Network Calculus is used to ensure analytically that all critical SGSs can meet their QoS requirements. The overall effect of the two-step approach will then be assessed by simulation.
FAU will be mainly considering the networking and QoS aspects in this cooperation, while Oldenburg University will concentrate on the effects on the energy network and the reconfiguration of the Smart Grid Services.

Die Bundesanstalt für den Digitalfunk der Behörden und Organisationen mit Sicherheitsaufgaben (BDBOS) ist die Netzbetreiberin des Bundes. Unter anderem verantwortet sie die Netze des Bundes und entwickelt diese im Zuge der Digitalisierung weiter. Mit der Netzstrategie 2030 verfolgt die BDBOS u.a. das strategische Ziel, einen einheitlichen, zukunftsfähigen, resilienten und leistungsfähigen Informationsverbund der öffentlichen Verwaltung zu schaffen.
In Kooperation mit der BDBOS und auf Basis einer externen Promotion soll dieses strategische Ziel wissenschaftlich untersucht und die daraus resultierenden Ergebnisse evaluiert werden. Das Ergebnis sollte ein resilientes und qualitätsgewährleistendes Modell/Framework sein (resilient QChain of a System – resQoSystem, ausgesprochen: rescue of a system), welches die Leistungsfähigkeit des Informationsverbundes öffentliche Verwaltung in den unterschiedlichsten Lagen sicherstellt und gewährleistet.

The cooperation between Airbus Defense and Space GmbH, Fraunhofer Institute for Integrated Circuits, Friedrich-Alexander-Universität (FAU) Erlangen-Nürnberg and ZF Friedrichshafen AG has the common goal of increasing the connectivity for automotive applications in hybrid satellite-terrestrial 5G networks using artificial intelligence.

The FAU works primarily on concepts for the integration of automotive applications, the creation of a simulation model for the combination of vehicular and satellite communication, the integration of AI algorithms, the performance evaluation and optimization of quality-of-service related protocols, and supporting the implementation of a real-time demonstrator. Results shall be presented at scientific conferences and contribute to the standardization of 5G and future 6G networks.

In the QUICSAT project, the cooperation between the Friedrich-Alexander University (FAU) Erlangen-Nürnberg and ND SatCom GmbH has the common goal of improving Internet protocols and applications for geostationary satellite connections.

The potential of new technologies (AQM, ECN, BBR and especially QUIC) will be examined. The ultimate goal is that Internet via satellite should perform as good as terrestrial Internet connections.

The high latency of geostationary satellites, the current architecture of Internet protocols and the constantly increasing complexity of Internet applications (especially websites) are the reason why the performance of Internet via satellite is sometimes worse than the performance of terrestrial Internet connections, even if the data rates are comparable. Newer Quality of Service (QoS) mechanisms are currently not used in satellite communication. With QUIC there is also the risk that the performance of satellite internet will decrease due to the non-applicability of Performance Enhancing Proxies.

The project makes a contribution to protocol research, standardization and reference implementations.

As part of a large consortium, the Chair of Computer Science 7 is involved in the project with the model-based system design of the vehicle communication systems under inclusion of variant diversity. For this purpose, on the one hand, an optimization for the configuration and resource design of the network architecture for different communication protocols and mechanisms is realized. On the other hand, safety analyses are performed using fault trees and extending them for product lines.

Network calculus is used for the formal verification of the required real-time properties. Therefore, suitable approaches for the scheduling methods applied in the networking technologies (e.g. TAS, priority-based, CBS, etc.) have to be formulated.

Model and code generators will be developed for automated and accelerated generation of the network optimizations. safety and real-time analyses. The results of these analyses are fed back into the modeling of the overall system.

This work evaluates the performance of different applications over different Internet access technologies, with focus on Internet access via satellite.

The following Internet access technologies have been selected:

• Geostationary satellites (Konnect/Eutelsat, skyDSL/Eutelsat, Bigblu/Eutelsat, Novostream/Astra Connect)

• Satellite megaconstellations in low Earth orbit (Starlink)

• Terrestrial systems as reference (o2 DSL, Congstar LTE)

With the developing technologies and methods in the field of real-time communication and the constantly increasing amount of data to be transmitted, the railway industry has jumped on the bandwagon of modernizing its processes.

In the field of railway applications, various manufacturers still provide different and mostly incompatible solutions.  These solutions are specified for a certain constellation of a train, but in most cases they are not able to offer the correct functionality if the constellation of the train changes.  In order to separate safety and time-critical areas from non-critical areas that e.g. offer services for passengers such as wireless LAN, separate networks with their own infrastructure must also be set up. That means more weight and costs for the train and its manufacturers.

In the area of real-time communications, time-sensitive networking (TSN) has proven to be a possible solution to overcome the problems mentioned above.  It provides methods and mechanisms for Ethernet technology that enrich it with aspects of determinism and reliability.

With Time-Sensitive Networks (TSN), the safety and time critical domains can be merged with non-critical areas, so that the safety and time critical domains can still be guaranteed sufficient reliability and determinism and the needs of passengers are satisfied.

The aim of this research project is to test the suitability of TSN in the railway sector.  The primary goal of the project is to analyse whether the requirements of safety and time-critical applications can be met with respect to deterministic network communication and bounded latencies and at the same time to prove that the fulfilment of the requirements of critical applications does not lead to a significant impairment of non-critical applications.

This research project deals with the application of quality of service guarantees in Time-Sensitive Networking, in particular using Network Calculus. Real-time systems are increasingly required in industry, e.g. the automotive, automation or entertainment industries. Classical Ethernet, however, does not guarantee real-time performance, which leads the Time-Sensitive Networking Task Group (IEEE 802.1) to develop standards for real-time data transmission over Ethernet networks. These standards are summarized under the term Time-Sensitive Networking (TSN). Within the scope of this research project, the application of Network Calculus for TSN is now being investigated. Network Calculus (NC) is a system theory for deterministic performance evaluation. It uses mathematical methods to provide performance guarantees for communication systems. NC can help evaluate TSN's real-time properties, meet required latency limits, and provide insight into the optimal configuration of networks. It also enables buffer sizing and can evaluate existing or new scheduling algorithms.

Satellite communication is a way to provide broadband internet access all over the world. However, with geostationary satellites the propagation delay leads to very high delays in the magnitude of several hundred milliseconds. In order to improve the interactivity and responsiveness of communication systems, utilizing a second communication link can be highly beneficial.

The Transparent Multichannel IPv6 (TMC-IPv6) Project aims to combine the advantages of multiple heterogeneous communication links. An illustrative example is the combination of a rural DSL connection with low data rate/low latency and a satellite connection with high data rate but high latency, which results in a user’s internet access with high data rate and low latency providing a better Quality of Experience (QoE).

Satellite-based internet access from different operators is provided by our project partners in order to experience realistic satellite communication environment and test potential solutions. The outdoor unit (parabolic antenna) is mounted on the roof of the Wolfgang-Händler-Hochhaus.

The electrical energy network is in a state of change due to the digitization and integration of decentralized energy sources. Pervasive and interconnected sensors and actuators are creating complex virtual control systems.
Based on an efficient communication network, innovative services and applications can provide an ecological, economical, stable and high-quality energy supply. A particular challenge are the diverse requirements and traffic patterns of applications that may be distributed over large areas and time critical.
The object of this research project is the replacement of proprietary solutions by a programmable communication network with standard components. These enable economical operation and high compatibility, individual requirements are fulfilled by software. The overarching goal is to make optimal use of the infrastructure of the energy and communication networks and to minimize over-provisioning.

As a result of the integration of increasingly elaborate and distributed functionality in modern automobiles the amount of installed electronic and software continuously grows. The associated growth in system complexity makes it inevitable that the test methods used for verification and validation keep pace with this development. Nowadays the test routine in industry usually requires each test case to be crafted manually by a test designer. The test case execution itself and test result evaluation usually are performed in an automated manner. This procedure has many drawbacks, as the crafting of single test cases is apparently awkward and error-prone and it is impractical to calculate test management criteria such as test coverage. Within this project a method is developed that overcomes these drawbacks. Markov chain usage models (MCUM) constitute the central role within this project. MCUMs are employed to describe the possible usage of the System-under-test and to derive test cases from them. On the one hand the integration of MCUMs makes it possible to develop methods to integrate test requirements formally, as to improve traceability. On the other hand they provide the basis to incorporate algorithms or strategies that allow the generation of test cases fitting to various test requirements in the automotive domain. These comprise e.g. different coverage criteria under usage or system oriented aspects. Moreover established methods exist that allow the calculation of dependability measures based on results obtained from test cases automatically generated from MCUMs. Also the test planning can be supported by indicators that are derived during the test process. The project aims for developing a method to describe test requirements formally by building a model. This model allows the derivation of test suites considering various testing aims and constraints. The tools themselves should form a part of the ITF (Integrated Testing Framework) and the process extend the current one described by EXAM and employed within the Volkswagen AG.

Network calculus (NC) is a system theory for deterministic performanceevaluation. It uses mathematical methods to provide performanceguarantees for communication systems. It can be applied in thedesign phase of future systems as well as the analysis of existingsystems. In real-time systems, the timeliness of events plays animportant role. Therefore, the classical performance evaluation based onstochastic methods that result in (stochastic) expectation values, i.e.mean values, has to be extended by mathematical tools producingguaranteed bounds for worst case scenarios. Network calculus allows toobtain upper bounds for end-to-end delays for one nodes or aseries of nodes within a network, upper bounds for the required bufferspace and bounds for the output flow.These analytic performance bounds characterize the worst-case behaviorof traffic flows and allow dimensioning the corresponding systems.

Currently, we study the applicability of NC for multiplexed flows, inparticular when the FIFO property cannot be assumed at the merging ofindividual flows. The aggregation of data flows plays an important rolein modelling the multiplexing scheme. We apply NC for performanceevaluation both of aggregate multiplexing at one node and atconcatenation of aggregated multiple nodes in different scenarios.
We have successfully introduced network calculus methods in thefield of internal automotive communication systems in industrialapplications. Embedded in-car networks need to fulfill hardreal-time constraints. While TDMA-based access schemes in FlexRayguarantee that certain bound can be met, statistical multiplexingin CAN networks only allows to calculate bounds for the highestpriority messages. By applying network calculus, we obtained boundsfor all priority classes without the need to specify a concretescheduling of the messages. Upper bounds for the amount of datathat arrives at each network node are enough to determine hardbounds for the end-to-end delay in CAN networks.

Another field of application is industrial communication.Factory automation often also requires hard real-time boundsfor the end-to-end delay of messages. The use of Ethernet withpriority tagging allows cost-efficient implementation offactory automation systems. But without stringent planningof the network, the required bounds on the end-to-end delaycannot be guaranteed. Network calculus allows to obtain therequired bounds when applied in the planning phase of thenetwork. It also allows to dimension the buffers of nodes,e.g. of industrial Ethernet switches. Nowadays, some ofthe users of industrial Ethernet need to integratenon-real-time products like web cams and remote operationterminals into existing networks. Withoutadditional analysis, the additional traffic caused by devicesthat do not require hard real-time constraints willcause a violation of the bounds for the delay and bufferspace for real-time traffic. By taking into account thisnon-real-time traffic in network calculus and by applyingtraffic shaping for the non-real-time flows allows todimension the network so that all bounds are met.Network calculus is currently integrated into an existingautomated industrial network planning tool.