LLM-Ehnanced Holonic Architecture for Ad-Hoc Scalable SoS

TL;DR

This paper presents a layered holonic architecture for system of systems that integrates large language models to enhance adaptability, interoperability, and reconfigurability, demonstrated through a smart city transportation case study.

Contribution

It introduces a novel layered holonic architecture with LLM-enabled specialised holons to improve SoS adaptability and interoperability in complex environments.

Findings

Enhanced data exchange among heterogeneous systems.

Improved decision-making with LLM-powered holons.

Demonstrated scalability in a smart city case study.

Abstract

As modern system of systems (SoS) become increasingly adaptive and human centred, traditional architectures often struggle to support interoperability, reconfigurability, and effective human system interaction. This paper addresses these challenges by advancing the state of the art holonic architecture for SoS, offering two main contributions to support these adaptive needs. First, we propose a layered architecture for holons, which includes reasoning, communication, and capabilities layers. This design facilitates seamless interoperability among heterogeneous constituent systems by improving data exchange and integration. Second, inspired by principles of intelligent manufacturing, we introduce specialised holons namely, supervisor, planner, task, and resource holons aimed at enhancing the adaptability and reconfigurability of SoS. These specialised holons utilise large language models within their reasoning layers to support decision making and ensure real time adaptability. We demonstrate our approach through a 3D mobility case study focused on smart city transportation, showcasing its potential for managing complex, multimodal SoS environments. Additionally, we propose evaluation methods to assess the architecture efficiency and scalability,laying the groundwork for future empirical validations through simulations and real world implementations.