Time-Triggered Traffic Planning for Data Networks with Conflict Graphs

Abstract

Traffic planning is the key enabler of time-triggered real-time communication in distributed systems, and it is known to be notoriously hard. Current approaches predominantly tackle the problem in the domain of the traffic planning problem, e.g., by formulating constraints on the transmission schedules for individual data streams, or the links used by the data streams. This results in a high degree of coupling of the configuration of an individual data stream and the global (network-wide) traffic configuration with detrimental effects on the scalability and runtime of the planning phase.In contrast, we present a configuration-conflict graph based approach, which solves the original traffic planning problem by searching an independent vertex set in the conflict graph. We show how to derive the configuration-conflict graph, and discuss the conceptual advantages of this approach. To show the practical advantages of the conflict-graph based traffic planning approach we additionally present a proof-of-concept implementation and evaluate it against a reference ILP-based implementation. In our evaluations, our proof-of-concept implementation of the conflictgraph based approach outperforms the reference ILP and is more memory efficient, making it a promising alternative to current constraint-based traffic planning approaches.

Дослідження Завантаження Інформаційної Мережі В Умовах Дистанційної Освіти І Дистанційного Моніторингу

“…Therefore, realtime communication in distributed systems is difficult. Poor planning can lead to a high degree of concatenation between the configuration of an individual data stream and the configuration of global (network-wide) traffic [3]. Therefore, forecasting network traffic is an important task [4].…”

Reconfiguration algorithms for high precision communications in time sensitive networks: Time-aware shaper configuration with IEEE 802.1Qcc

“…Vlk et al [87] have proposed a simple hardware enhancement of a switch along with a relaxed scheduling constraint that increases schedulability and throughput of the time-triggered traf ic but maintains the deterministic nature and timeliness guarantees in a TSN network. Several related scheduling re inements that are orthogonal to the recon iguration studied in this article have been examined in [26,40,43,53,74,93]. We note for completeness that multicast for TSN has been studied in [80,92], while our focus is on unicast traf ic.…”

Dynamic QoS-Aware Traffic Planning for Time-Triggered Flows in the Real-time Data Plane

“…Existing work on static planning can be roughly sorted in two categories: 1) approaches that rely at the core on generic constraint programming frameworks at such as Integer Linear Programming (ILP) [13,14,15,7,16] or Satisfiability Modulo Theories (SMT) [17,18,19,20,8] and 2) approaches that use custom heuristics [3,9,21], or a combination of both [12]. Static planning approaches require adaptions to be used for dynamic traffic planning.…”

“…• We present a novel heuristic for the underlying optimization problem which we have to solve to obtain a new traffic plan. In particular, we use a conflict-graph based modeling [12] for the traffic planning. The conflict-graph based modeling is well-suited for dynamic traffic planning because the conflict graph embeds a large portion of the knowledge about the solution space from the previous traffic plan, and thus reduces the effort required to compute the new traffic plan.…”