Network Calculus and Optimization
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.
Communication in energy information networks
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.
Time Management and Real-Time Capabilities of Parallel and Distributed Simulation for the Virtual Development and Validation of Automated Driving Functions
(Third Party Funds Single)
Distributed simulations are often used to improve performance or to couple different simulators. This coupling is very important for the simulation of autonomous driving functions, because reusable simulation components can be created for the closer and wider environment of the vehicle, for the ego and other vehicles, for sensor technology, for procedures in the control units, for vehicle dynamics and for similar aspects and can be executed together in a simulation. Furthermore, such a distributed simulation provides a starting point for coupling with real software or hardware components (SIL or HIL). Time management in the distributed simulation must ensure causality: if there are deviations in the assignment of simulation time to real-time in the components, causality violations can occur. One example is cooperative safety functions, where actions take place in a very fast sequence. Reasons for causality violations can be, for example, non-synchronized clocks or delays in message delivery. Another task of the time management is to ensure the reproducibility of the simulation results. Jitter in the execution time of individual components or during message transmission results in a non-determinism in the execution sequence, which can lead to a different simulation result.
NC for TSN: Network Calculus for Time-Sensitive Networking
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.
NG-TCMS: Engineering of next-generation Train Control and Management Systems
(Third Party Funds Single)
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.
MBPLE4Mobility: MBPLE4Mobility - Continuous model-based product line development for control systems in vehicle technology
(Third Party Funds Single)
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.
QUICSAT: New protocols for faster Internet via satellite
(Third Party Funds Single)
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.
5G-AUTOSAT_KI: Simulation KI-unterstützter automobiler Szenarien und Protokoll-Optimierung
(Third Party Funds Group – Sub project)
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.