A Bayesian approach to calibrate system dynamics models using Hamiltonian Monte Carlo

Modern Risk Quantification in Complex Projects

10.1093/oso/9780198844334.001.0001 ◽

2020 ◽

Author(s):

Yuri G. Raydugin

Keyword(s):

Monte Carlo ◽

System Dynamics ◽

Project Risk ◽

Risk Quantification ◽

Complex Projects ◽

Non Linear ◽

Business Cases ◽

Project Structure ◽

Dynamics Models ◽

Cost Risk

There are multiple complaints that existing project risk quantification methods—both parametric and Monte Carlo—fail to produce accurate project duration and cost-risk contingencies in a majority of cases. It is shown that major components of project risk exposure—non-linear risk interactions—pertaining to complex projects are not taken into account. It is argued that a project system consists of two interacting subsystems: a project structure subsystem (PSS) and a project delivery subsystem (PDS). Any misalignments or imbalances between these two subsystems (PSS–PDS mismatches) are associated with the non-linear risk interactions. Principles of risk quantification are developed to take into account three types of non-linear risk interactions in complex projects: internal risk amplifications due to existing ‘chronic’ project system issues, knock-on interactions, and risk compounding. Modified bowtie diagrams for the three types of risk interactions are developed to identify and address interacting risks. A framework to visualize dynamic risk patterns in affinities of interacting risks is proposed. Required mathematical expressions and templates to factor relevant risk interactions to Monte Carlo models are developed. Business cases are discussed to demonstrate the power of the newly-developed non-linear Monte Carlo methodology (non-linear integrated schedule and cost risk analysis (N-SCRA)). A project system dynamics methodology based on rework cycles is adopted as a supporting risk quantification tool. Comparison of results yielded by the non-linear Monte Carlo and system dynamics models demonstrates a good alignment of the two methodologies. All developed Monte Carlo and system dynamics models are available on the book’s companion website.

Download Full-text

A Brief Introduction to System Dynamics (SD)

Modern Risk Quantification in Complex Projects ◽

10.1093/oso/9780198844334.003.0007 ◽

2020 ◽

pp. 121-130

Author(s):

Yuri G. Raydugin

Keyword(s):

Monte Carlo ◽

Differential Equations ◽

System Dynamics ◽

Analytical Solutions ◽

Feedback Loops ◽

System Dynamic ◽

Dynamics Models

This chapter introduces all main concepts of system dynamics (levels/stocks, flows/rates, variables, feedback loops, etc.). It represents a ‘crash course’ on system dynamics. It is used for development of project system dynamics models in Chapter 7 that mirror project Zemblanity Monte Carlo modelling undertaken in Chapter 5. System dynamic concepts are introduced using a so-called bathtub (BT) model. Five versions of the BT model are introduced through corresponding differential equations. All considered differential equations have analytical solutions. All five workable BT system dynamics models are available on the book’s companion website.

Download Full-text