Exact Worst-Case Delay in FIFO-Multiplexing Feed-Forward Networks

Bouillard, Anne; Stea, Giovanni

doi:10.1109/tnet.2014.2332071

Cited by 27 publications

(15 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, it can be further optimized by finding the best number of variables for the graph neural network as well as its bottleneck. Learning from a dataset including feed-forward networks, more complex curve shapes than the simple affine ones [24], or from/for FIFO-multiplexing networks [40] or entirely non-FIFO [41] is already possible, too.…”

Section: Discussionmentioning

confidence: 99%

DeepTMA: Predicting Effective Contention Models for Network Calculus using Graph Neural Networks

Geyer

Bondorf

2019

IEEE INFOCOM 2019 - IEEE Conference on Computer Communications

View full text Add to dashboard Cite

Network calculus computes end-to-end delay bounds for individual data flows in networks of aggregate schedulers. It searches for the best model bounding resource contention between these flows at each scheduler. Analyzing networks, this leads to complex dependency structures and finding the tightest delay bounds becomes a resource intensive task. The exhaustive search for the best combination of contention models is known as Tandem Matching Analysis (TMA). The challenge TMA overcomes is that a contention model in one location of the network can have huge impact on one in another location. These locations can, however, be many analysis steps apart from each other. TMA can derive delay bounds with high degree of tightness but needs several hours of computations to do so. We avoid the effort of exhaustive search altogether by predicting the best contention models for each location in the network. For effective predictions, our main contribution in this paper is a novel framework combining graph-based deep learning and Network Calculus (NC) models. The framework learns from NC, predicts best NC models and feeds them back to NC. Deriving a first heuristic from this framework, called DeepTMA, we achieve provably valid bounds that are very competitive with TMA. We observe a maximum relative error below 6 %, while execution times remain nearly constant and outperform TMA in moderately sized networks by several orders of magnitude.

show abstract

Section: Discussionmentioning

confidence: 99%

DeepTMA: Predicting Effective Contention Models for Network Calculus using Graph Neural Networks

Geyer

Bondorf

2019

IEEE INFOCOM 2019 - IEEE Conference on Computer Communications

View full text Add to dashboard Cite

show abstract

“…The linear programming approach developed in [12,13] consists in writing the network calculus constraints as linear constraints. If the arrival curves are piecewise linear concave and the service curves piece-wise linear convex, then the exact worst-case bounds can be computed by a MILP (Mixed-integer linear program).…”

Section: Linear Programmingmentioning

confidence: 99%

“…From the first paper on network calculus, phenomena such as the pay burst only once and the pay multiplexing only once have been exhibited, and each time they led to improvements of the performance bounds. More recently, algorithms based on linear programming have been proposed in [12,13] to compute tight bounds in FIFO networks, but the complexity of these algorithms is too high to be used in most of the networks.…”

Section: Introductionmentioning

confidence: 99%

Trade-off between accuracy and tractability of network calculus in FIFO networks

Bouillard¹

2020

Preprint

Self Cite

View full text Add to dashboard Cite

Computing accurate deterministic performance bounds is a strong need for communication technologies having strong requirements on latency and reliability. Beyond new scheduling protocols such as TSN, the FIFO policy remains at work within each class of communication.In this paper, we focus on computing deterministic performance bounds in FIFO networks in the network calculus framework. We propose a new algorithm based on linear programming that presents a trade-off between accuracy and tractability. This algorithm is first presented for tree networks. In a second time, we generalize our approach and present a linear program for computing performance bounds for arbitrary topologies, including cyclic dependencies. Finally, we provide numerical results, both of toy examples and real topologies, to assess the interest of our approach.

show abstract

“…Complex Smart Grid infrastructures and diverse traffic flows require a detailed study of cross traffic impact as they may lead to non-feed forward behavior [53], which continues to be an issue of NC analysis [22,54]. In addition, the influence of HTB scheduling has to be considered in NC evaluations.…”

Section: Queue Rate and Cross Traffic Extensions To Network Calculusmentioning

confidence: 99%

Enabling hard service guarantees in Software-Defined Smart Grid infrastructures

2018

View full text Add to dashboard Cite

Information and Communication Technology (ICT) infrastructures play a key role in the evolution from traditional power systems to Smart Grids. Increasingly fluctuating power flows, sparked by the transition towards sustainable energy generation, become a major issue for power grid stability. To deal with this challenge, future Smart Grids require precise monitoring and control, which in turn demand for reliable, real-time capable and cost-efficient communications.For this purpose, we propose applying Software-Defined Networking (SDN) to handle the manifold requirements of Smart Grid communications. To achieve reliability, our approach encompasses fast recovery after failures in the communication network and dynamic service-aware network (re-)configuration. Network Calculus (NC) logic is embedded into our SDN controller for meeting latency requirements imposed by the standard IEC 61850 of the International Electrotechnical Commission (IEC). Thus, routing provides delay-optimal paths under consideration of existing cross traffic. Also, continuous latency bound compliance is ensured by combining NC delay supervision with means of flexible reconfiguration. For evaluation we consider the well-known Nordic 32 test system, on which we map a corresponding communication network in both experiment and emulation. The described functionalities are validated, employing $ c 2018. This manuscript version is made available under the CC-BY-NC-ND 4.0 license http://creativecommons.org/licenses/by-nc-nd/4.0/. The formal version of this publication is realistic IEC 61850 transmissions and distributed control traffic. Our results show that hard service guarantees can be ensured with the help of the proposed SDN solution. On this basis, we derive extremely time critical services, which must not be subjected to flexible reconfiguration. Service Guarantees, Software-Defined Networking, Network Calculus.culus, for enabling respectively verifying hard service guarantee compliance.Afterwards, results of related work are described and compared to this article. Smart Grid Communication Use CasesSmart Grid communication requirements can be roughly divided into distribution and transmission grid use cases, as detailed below. While these power system levels exhibit widely diverging demands, SDN offers an integrated approach for associated communications. Managing the Distribution Power GridCommunication-dependent applications in the distribution power grid comprise Automated Meter Reading (AMR), DSM, monitoring and control of Distributed Energy Resources (DER), as well as coordination of EV charging. AMR is considered a fundamental function of smart distribution grids, providing measurement data as the basis for more advanced applications, such as novelty detection power meters [11]. For this concept machine learning is deployed on distributed energy measurement data to optimize the energy consumption times of end users. Also, anomalies can be detected, revealing energy consumption that deviates from common patterns (e.g. non-technical losses)....

show abstract

Exact Worst-Case Delay in FIFO-Multiplexing Feed-Forward Networks

Cited by 27 publications

References 28 publications

DeepTMA: Predicting Effective Contention Models for Network Calculus using Graph Neural Networks

DeepTMA: Predicting Effective Contention Models for Network Calculus using Graph Neural Networks

Trade-off between accuracy and tractability of network calculus in FIFO networks

Enabling hard service guarantees in Software-Defined Smart Grid infrastructures

Contact Info

Product

Resources

About