LLM-Based Community Surveys for Operational Decision Making in Interconnected Utility Infrastructures

2025-07-17

AI Summary

In post-disaster restoration of interdependent infrastructure systems, a critical gap exists between technical interdependencies and community preferences, leading to suboptimal recovery outcomes. Method: This paper proposes a socio-technical co-optimization framework: (1) modeling cross-system and system–community functional dependencies via a Heterogeneous Functional Graph (HFG); (2) leveraging large language models (LLMs) to generate diverse, realistic personas representing affected individuals and their repair priority preferences; and (3) integrating these preference data with technical constraints using machine learning–based ranking algorithms to produce globally optimal restoration sequences. Contribution/Results: To our knowledge, this is the first study embedding LLMs as proxy survey instruments within a resilience decision-making framework, enabling computationally tractable integration of community needs and engineering logic. Experimental results demonstrate that the method significantly enhances both social acceptability and overall system resilience under resource constraints.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Humans and AI: Planning and Decision Support for Human-Machine Teams

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Social Networks and Social Media: Socio-technical web-based systems

Abstract

We represent interdependent infrastructure systems and communities alike with a hetero-functional graph (HFG) that encodes the dependencies between functionalities. This graph naturally imposes a partial order of functionalities that can inform the sequence of repair decisions to be made during a disaster across affected communities. However, using such technical criteria alone provides limited guidance at the point where the functionalities directly impact the communities, since these can be repaired in any order without violating the system constraints. To address this gap and improve resilience, we integrate community preferences to refine this partial order from the HFG into a total order. Our strategy involves getting the communities' opinions on their preferred sequence for repair crews to address infrastructure issues, considering potential constraints on resources. Due to the delay and cost associated with real-world survey data, we utilize a Large Language Model (LLM) as a proxy survey tool. We use the LLM to craft distinct personas representing individuals, each with varied disaster experiences. We construct diverse disaster scenarios, and each simulated persona provides input on prioritizing infrastructure repair needs across various communities. Finally, we apply learning algorithms to generate a global order based on the aggregated responses from these LLM-generated personas.

Problem

• Modeling interdependent infrastructure systems with hetero-functional graphs
• Incorporating community preferences to refine repair sequence decisions
• Using LLM-generated personas to simulate diverse disaster scenarios

Innovation

• HFG encodes dependencies for repair sequences
• LLM proxies community surveys via personas
• Learning algorithms aggregate responses for global order