Automated configuring of non-iterative co-simulation modeled by synchronous data flow

doctoral thesis

• Title (croatian): Automatizirano oblikovanje neiterativne kosimulacije modelirane sinkronim protokom podataka
• Author: Slaven Glumac
• Mentor: Zdenko Kovačić (mentor)
• Committee member: Stjepan Bogdan (predsjednik povjerenstva)
• Committee member: Željko Ban (član povjerenstva)
• Committee member: Bojan Jerbić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; (Department of Control and Computer Engineering); Zagreb
• Defense date and country: 2022-05-03, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing
• Universal decimal classification (UDC): 004 - Computer science and technology. Computing. Data processing

Abstract

This thesis proposes the use of a synchronous data flow graph (SDFG) to model the computation of a non-iterative co-simulation. An SDFG is a determinate model of computation with a lot of scheduling research available. A method for creating an SDFG from a co-simulation network, initial tokens and simulator step sizes is described. A simulator in the proposed method is a synchronous data flow actor that is used to model the execution of a co-simulation slave. It is shown that such an SDFG has consistent rates and uniformly updates the states of all simulators. To analyze the behavior of numerical errors introduced in the co-simulation, it is assumed that coupled ordinary differential equations can represent the modeled system. This thesis uses the numerical defect analysis to formulate a co-simulation quality criterion. The numerical defect is divided into integration, output and connection defects. Such a defect distribution reflects the division of responsibility between the co-simulation master and the internal solvers of the slaves. This work proposes how connection defects can be calculated and output defects can be estimated. Integration defects are not analyzed as it is assumed that they are controlled by internal solvers of the slaves. The proposed quality criterion for the co-simulation is based on the aggregation of the output and connection defects. The simulator step sizes, the number and values of the initial tokens should be determined in order to configure the execution of a co-simulation network. A method for calculating the number of initial tokens based on the simulator step sizes is proposed. It is shown that an SDFG with such number of initial tokens does not deadlock. Furthermore, a method how to check whether it can run in real-time is shown. The quality criterion enables an optimization approach to find the values of the initial tokens. In the proposed approach, the quality criterion is assessed in a single iteration of the SDFG. The Nelder-Mead algorithm is used to solve the optimization problem of finding initial token values. To complete the automatic configuration of the co-simulation, the simulator step sizes must be determined. This is done by reducing the simulator step sizes until the requested tolerance is met. This thesis proves that connection and output defects can be controlled by reducing simulator step sizes. The automated configuration algorithm presented in the last chapter is the main goal of this thesis. The methods for determining the step sizes of the simulator, the number and the values of the initial tokens are building blocks of this algorithm. The validity and usefulness of the proposed algorithm is justified with theorems and examples presented throughout this thesis.

Abstract (croatian)

Ovaj rad predlaže korištenje grafa sinkronog protoka podataka (SDFG) za modeliranje izračuna neiterativne kosimulacije. SDFG je jedinstveno definiran računski model s dostupnom literaturom u području planiranja izvedbe. Opisana je metoda za generiranje SDFG iz kosimulacijske mreže, početnih žetona i veličina koraka simulatora. Simulator u predloženoj metodi je agent sinkronog protoka podataka koji se koristi za modeliranje izvedbe kosimulacijske jedinice. Pokazalo se da takav SDFG ima konzistentne stope i jednoliko ažurira stanja svih simulatora. Pretpostavlja se da povezane obične diferencijalne jednadžbe mogu predstavljati modelirani sustav zbog analize ponašanja numeričkih pogrešaka unesenih u kosimulaciji. Ovaj rad koristi numeričku analizu defekata za formuliranje kriterija kvalitete kosimulacije. Numerički defekt dijeli se na integracijske, izlazne i spojne defekte. Takva raspodjela defekata odražava podjelu odgovornosti između algoritma upravljanja kosimulacijom i kosimulacijskih jedinica. Ovaj rad sugerira kako se mogu izračunati spojni defekti i procijeniti izlazni defekti. Izlazni defekti se ne analiziraju jer se pretpostavlja da ih kontroliraju algoritmi rješavanja običnih diferencijalnih jednadžbi. Predloženi kriterij kvalitete za kosimulaciju temelji se na spajanju izlaznih i spojnih defekata. Potrebno je odrediti veličinu koraka simulatora, broj i vrijednosti početnih žetona kako bi se oblikovalo izvođenje kosimulacijske mreže. Predložena je metoda za izračunavanje broja početnih žetona na temelju veličina koraka simulatora. Pokazano je da SDFG s takvim brojem početnih žetona ne dolazi u zastoj. Nadalje, prikazana je metoda kako provjeriti može li raditi u stvarnom vremenu. Kriterij kvalitete omogućuje optimizacijski pristup za pronalaženje vrijednosti početnih žetona. U predloženom pristupu, kriterij kvalitete ocjenjuje se u jednoj iteraciji SDFG-a. Nelder-Mead algoritam se koristi za rješavanje problema optimizacije pronalaženja početnih vrijednosti žetona. Da bi se dovršilo automatsko oblikovanje kosimulacije, mora se odrediti veličina koraka simulatora. To se postiže smanjenjem koraka simulatora sve dok se ne ispuni tražena tolerancija. Ovaj rad dokazuje da se spojni i izlazni defekti mogu kontrolirati smanjenjem koraka simulatora. Algoritam automatiziranog oblikovanja predstavljen u posljednjem poglavlju glavni je cilj ovog rada. Metode za određivanje veličine koraka simulatora, broja i vrijednosti početnih tokena osnovni su blokovi ovog algoritma. Valjanost i korisnost predloženog algoritma opravdane su teoremima i primjerima prikazanim u ovom radu.

• Keywords: co-simulation; synchronous data flow; error analysis; coupled ordinary differential equations; defect control; automated configuration; model-based development
• Keywords (croatian): kosimulacija; model sinkronog protoka podataka; analiza pogreške; povezane obične diferencijalne jednadžbe; kontrola defekta; automatizirano oblikovanje; razvoj temeljen na modelu
• Language: english
• URN:NBN: urn:nbn:hr:168:965024
• Promotion: 2022
• Study programme: Title: Computer Science; Study programme type: university; Study level: postgraduate; Academic / professional title: Doktor znanosti (Doktor znanosti)
• Type of resource: Text
• Extent: 131 str. : graf. prikazi ; 30 cm.
• File origin: Born digital
• Access conditions: Open access; Embargo expiration date: 2022-05-04
• Created on: 2022-07-11 08:12:07