Sequential decision making and simulation-optimization for the design of complex engineering systems
In this dissertation, we create a novel simulation-based design platform to determine the optimal design of engineered systems. We develop resilient, reliable, and flexible design solutions that account for system uncertainties within the optimization algorithm. The purpose of this dissertation is to study simulation-optimization and sequential decision-making strategies for the design of complex engineering systems. Simulation optimization and sequential decision-making frameworks are developed in order to optimize the design of complex engineering systems in four different studies: designing a resilient wind turbine system for risk-averse decision-makers, improving the reliable design of airfield concrete pavement, incorporating flexibility into the design of a hybrid renewable energy system, and finding the optimal policy for the design of engineering systems using reinforcement learning. In chapter 2, a framework is developed to incorporate risk aversion into a firm’s design decisions for a resilient wind turbine system. In chapter 3, a reliability-based design optimization framework is developed for airfield concrete pavement design. Chapter 4 presents a multi-stage simulation-optimization algorithm for the flexible design of a hybrid renewable energy system. In chapter 5, a new framework is developed to find the optimal policy for the design of engineering systems operating under uncertainty.