DNI - Descartes Network Infrastructures Modeling
DNI is a family of meta-models designed for modeling the performance of communication networks. DNI is tightly related to DML and the main modeling domain are data center networks. A user can model network topology, switches, routers, servers, virtual machines, deployment of software, network protocols, routes, flow-based configuration and other relevant network parts. DNI can be used to model any type of network as it was designed to be as generic as possible.
The DNI Meta-model has been designed to support describing the most relevant performance influencing factors that occur in practice while abstracting fine-granular low level protocol details. Instances of the DNI Meta-model (DNI models) are automatically transformed to predictive stochastic models (e.g., product-form queueing networks or stochastic simulation models) by means of model-to-model transformations.
The DNI consists of the following elements:
- DNI and miniDNI meta-models – written in Emfatic and Ecore
- Scripts for generating DNI model instances – written in EOL
- Set of model-to-model transformations between the meta-models and to selected predictive simulation models (solvers) – written in ETL
- Default tree editor for specifying the DNI and miniDNI models manually
- HUTN (Human Usable Textual Notation) text editor for DNI
- Traffic model extraction library TrafficMSD@Github (full tooling for DNI extraction: coming soon)
- Download meta-models, transformations, and examples: DNI Git repository
- Manual that explains the meta-models and transformations
If you have any questions, please contact Piotr Rygielski.
Model-Based Network Analysis and Optimization. S. Herrnleben; (2018, Februar).
Flexible Modeling of Data Center Networks for Capacity Management. P. Rygielski; (2017, März).
Performance Analysis of SDN Switches with Hardware and Software Flow Tables. P. Rygielski; M. Seliuchenko; S. Kounev; M. Klymash; in Proceedings of the 10th EAI International Conference on Performance Evaluation Methodologies and Tools (ValueTools 2016) (2016).
Modeling and Prediction of Software-Defined Networks Performance using Queueing Petri Nets. P. Rygielski; M. Seliuchenko; S. Kounev; in Proceedings of the Ninth International Conference on Simulation Tools and Techniques (SIMUTools 2016) (2016). 66–75.
Automated Extraction of Network Traffic Models Suitable for Performance Simulation. P. Rygielski; V. Simko; F. Sittner; D. Aschenbrenner; S. Kounev; K. Schilling; in Proceedings of the 7th ACM/SPEC International Conference on Performance Engineering (ICPE 2016) (2016). 27–35.
Flexible Performance Prediction of Data Center Networks using Automatically Generated Simulation Models. P. Rygielski; S. Kounev; P. Tran-Gia; in Proceedings of the Eighth International Conference on Simulation Tools and Techniques (SIMUTools 2015) (2015). 119–128.
Descartes Network Infrastructures (DNI) Manual: Meta-models, Transformations, Examples P. Rygielski; S. Kounev; (2014).
Data Center Network Throughput Analysis using Queueing Petri Nets. P. Rygielski; S. Kounev; in 34th IEEE International Conference on Distributed Computing Systems Workshops (ICDCS 2014 Workshops). 4th International Workshop on Data Center Performance, (DCPerf 2014) (2014). 100–105.
Model-Based Throughput Prediction in Data Center Networks. P. Rygielski; S. Kounev; S. Zschaler; in Proceedings of the 2nd IEEE International Workshop on Measurements and Networking (M\&N 2013) (2013). 167–172.
A Meta-Model for Performance Modeling of Dynamic Virtualized Network Infrastructures. P. Rygielski; S. Zschaler; S. Kounev; in Proceedings of the 4th ACM/SPEC International Conference on Performance Engineering (ICPE 2013) (2013). 327–330.