Discrete Event Modeling and Simulation-Driven Engineering for the ATLAS Data Acquisition Network

Abstract

R obust engineering methodologies offering product lifecycle control have proved to be a cornerstone in modern software development projects. Simultaneously, various modeling and simulation (M&S) techniques have become increasingly adopted in complex system design, particularly in scenarios in which it's difficult to predict system behavior as changes are introduced.The DEVS (Discrete Event Systems Specification) framework is the most general formalism for modeling discrete event systems 1-3 and has been adopted in several disciplines for complex software and hardware system design and analysis. 4,5 In addition to providing an unambiguous mathematical formalism to define model behavior and structure, DEVS provides a clear framework for system analysis, experimental frame definition, model-to-simulator verification, and model-to-system validation.We present a DEVS-based methodology for M&S-driven engineering projects that integrates software development best practices tailored to a large-scale networked data acquisition system in a physics experiment (specifically, the ATLAS particle detector 6 at CERN 7 ). This project poses M&S challenges from several viewpoints, including system complexity, tight delivery times, the quality and flexibility of the developed models and tools, interdisciplinary communication of results to collaborators (mostly scientists), and big data-scale analysis.

Modeling and Validating Time, Buffering, and Utilization of a Large-Scale, Real-Time Data Acquisition System

“…Simulations of the ATLAS network can be found at [12] and [7], where packet drops, network latency, TCP retransmissions, and TCP incast pathology are analyzed.…”

“…Ongoing work [7] also using the ATLAS data acquisition system as a case study aims at providing a scalable and complete simulation framework based on a combination of discrete and continuous models. At this stage however the discrete component dominates, limiting the performance and therefore the capability to effectively study a large spectrum of system-level operating conditions.…”

TopoGen: A network topology generation architecture with application to automating simulations of software defined networks

“…In this context, modeling and simulation-driven network engineering (Bonaventura et al 2016) stands as a promising strategy: system verification with dynamic simulations can mitigate the risks of deploying functional SDN controllers that may cause poor quality of performance. Among the services implemented by SDN controllers, topology discovery keeps the topology information updated.…”

“…We adopt the DEVS formalism and the PowerDEVS tool in our case study as they currently support the TDAQ network engineering team of the ATLAS experiment at CERN (Bonaventura et al 2016, introduced below. Yet, the TopoGen architecture could be directly applied to produce network topologies for any other DEVS-based toolkits (Van Tendeloo and Vangheluwe 2017) that accepts a file-based structured specification of models (e.g.…”

“…In this section we describe TopoGen as applied in a real world scenario. The case study builds upon a modeling and simulation-driven engineering process (Bonaventura et al 2016) developed for the ATLAS TDAQ network at CERN (Pozo Astigarraga et al 2015). We show how TopoGen can assist the design phase for the network to be implemented 2019-2020 in the ATLAS FELIX project (Anderson et al 2015).…”