Author ORCID Identifier
0009-0009-6923-5557
Document Type
Dissertation
Date of Award
8-31-2024
Degree Name
Doctor of Philosophy in Industrial Engineering - (Ph.D.)
Department
Mechanical and Industrial Engineering
First Advisor
SangWoo Park
Second Advisor
Layek Abdel-Malek
Third Advisor
Sanchoy K. Das
Fourth Advisor
Golgen Bengu
Fifth Advisor
Lian Qi
Abstract
This dissertation explores data-driven decision-making networks, focusing on sustainable planning and operations for large-scale systems such as healthcare supply chains and power systems. One significant application in healthcare is the optimization of vaccine supply chains. An agent-based simulation-optimization modeling framework is developed to enhance the efficiency and sustainability of vaccine distribution. First, an agent-based epidemiological model of COVID-19 is extended to capture disease transmission dynamics and forecast the number of susceptible individuals and infections. Then, a sustainable vaccine supply chain considering the impacts of greenhouse gases is developed and integrated with the simulation model to minimize total costs and environmental impacts. This framework is validated using a real-world COVID-19 scenario in the US, underscoring the importance of advanced modeling techniques in managing complex and dynamic public health challenges, ensuring effective and responsible responses. Another application is in incentive-based demand response programs in the residential sector. The residential sector often struggles with demand response due to a limited understanding of consumer-specific behavior patterns and demand elasticity. This project explores the incorporation of heterogeneous elasticity values in demand response to enhance the economic efficiency of Load Serving Entities. Three distinct models are introduced: aggregate elasticity, appliance-specific elasticity, and customer and appliance-specific elasticity. By assessing the impact of tailored demand response incentives on energy consumption patterns, the model is applied to a test case in New Jersey. The results demonstrate that appliance-specific models and customer-specific elasticities significantly reduce operational costs, benefiting both customers and service providers. The study highlights the critical role of detailed elasticity information in optimizing demand response strategies and suggests future research directions towards leveraging advanced analytics for more effective demand management. Finally, the incentive-based demand response strategy is extended using Reinforcement Learning to optimize residential energy consumption. A Multi-Agent Reinforcement Learning framework is developed, leveraging multiple agents to dynamically adjust appliance usage based on incentive signals. Deep Q-Networks are employed to handle large state spaces. The effectiveness of this approach is demonstrated with real-world data while promoting consumer engagement through adaptive incentive-based strategies.
Recommended Citation
Kargar, Bahareh, "Data driven decision making for sustainable planning and operations of large scale networks" (2024). Dissertations. 1776.
https://digitalcommons.njit.edu/dissertations/1776
