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

TL;DR

This paper proposes a novel approach using Large Language Models to simulate community surveys, integrating community preferences into infrastructure repair sequencing for improved resilience in interconnected utility systems.

Contribution

It introduces a method to use LLMs as proxy survey tools to incorporate community preferences into repair decision-making for complex infrastructure systems.

Findings

LLMs can effectively simulate diverse community opinions.

Community preferences can be integrated into repair sequencing.

Enhanced decision-making improves infrastructure resilience.

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.