Dependability and Performance with Discrete Event Simulation

The course gives a basic introduction to measurement, discrete event simulation, and analytic modelling for performance and dependability assessment.

Basics: Dependability, performance and QoS measures; resources and utilization, failure and repair, system models, analytic modeling, discrete and continuous distributions, basics on stochastic processes, Poisson process, discrete-state - continuous-time Markov models and analysis.

Simulation: process-oriented simulation, generation of random variables, problem analysis and model design, DEMOS/SIMULA primitives, output analysis.

Performance: Erlang and Engset blocking models, M/M/1 and Erlang queuing models, Jackson networks.

Dependability: reliability, availability and system time in simple redundant systems determined by Markov models, block schemes, fault-trees, structure functions, path and cut sets.

Measurements: observation strategies, point and interval estimation, design of experiments.

A. Knowledge:

1. To gain a basic understanding of the importance of non-functional requirements for service and system design.
2. To gain a basic understanding of the principles of dependability and performance evaluation and design of information and communication systems (ICT).
3. To gain a basic understanding of modeling, analysis and measurements for evaluation and dimensioning.
4. To gain a basic understanding of probability theory, statistics, and stochastic processes in modeling ICT system's behavior.
5. To gain a basic understanding of Markov modeling and solution of such models.
6. To gain a basic understanding of process-oriented modeling and simulations.
7. To gain a basic understanding of simulation and measurement methods.

B. Skills:

1. To be able to specify the performance and dependability requirements.
2. To be able to describe the system properties by using a Markov Model.
3. To be able to determine the system properties symbolically and numerically from a Markov model.
4. To be able to describe a simulation model, implementing a simulator and conduct a simulation experiment.
5. To be able to derive system properties from the measurements, analytically and from simulation results.

The learning outcomes of this course are related to the assessment of large-scale, distributed ICT systems that are the backbone of digital infrastructures critical to society. The trustworthiness in that the systems and its services are provided in a robust and efficient manner, is directly related to the UN Sustainability Development Goals (SDG) 9 (Industry, Innovation and Infrastructure) - "Build resilient infrastructure, promote inclusive and sustainable industrialization and foster innovation".

Lectures and lab assignments in analytic evaluation techniques and in simulation. Optional self-tests and exercises.