Salvato in:
Dettagli Bibliografici
Autori principali: Yang, Zhiying, Liu, Fang, Zhang, Wei, Lou, Xin, Low, Malcolm Yoke Hean, Gan, Boon Ping
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2512.06351
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911306097885184
author Yang, Zhiying
Liu, Fang
Zhang, Wei
Lou, Xin
Low, Malcolm Yoke Hean
Gan, Boon Ping
author_facet Yang, Zhiying
Liu, Fang
Zhang, Wei
Lou, Xin
Low, Malcolm Yoke Hean
Gan, Boon Ping
contents This paper presents \textsc{Luca}, a \underline{l}arge language model (LLM)-\underline{u}pgraded graph reinforcement learning framework for \underline{c}arbon-\underline{a}ware flexible job shop scheduling. \textsc{Luca} addresses the challenges of dynamic and sustainable scheduling in smart manufacturing systems by integrating a graph neural network and an LLM, guided by a carefully designed in-house prompting strategy, to produce a fused embedding that captures both structural characteristics and contextual semantics of the latest scheduling state. This expressive embedding is then processed by a deep reinforcement learning policy network, which generates real-time scheduling decisions optimized for both makespan and carbon emission objectives. To support sustainability goals, \textsc{Luca} incorporates a dual-objective reward function that encourages both energy efficiency and scheduling timeliness. Experimental results on both synthetic and public datasets demonstrate that \textsc{Luca} consistently outperforms comparison algorithms. For instance, on the synthetic dataset, it achieves an average of 4.1\% and up to 12.2\% lower makespan compared to the best-performing comparison algorithm while maintaining the same emission level. On public datasets, additional gains are observed for both makespan and emission. These results demonstrate that \textsc{Luca} is effective and practical for carbon-aware scheduling in smart manufacturing.
format Preprint
id arxiv_https___arxiv_org_abs_2512_06351
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LLM-Upgraded Graph Reinforcement Learning for Carbon-Aware Job Scheduling in Smart Manufacturing
Yang, Zhiying
Liu, Fang
Zhang, Wei
Lou, Xin
Low, Malcolm Yoke Hean
Gan, Boon Ping
Machine Learning
Computation and Language
This paper presents \textsc{Luca}, a \underline{l}arge language model (LLM)-\underline{u}pgraded graph reinforcement learning framework for \underline{c}arbon-\underline{a}ware flexible job shop scheduling. \textsc{Luca} addresses the challenges of dynamic and sustainable scheduling in smart manufacturing systems by integrating a graph neural network and an LLM, guided by a carefully designed in-house prompting strategy, to produce a fused embedding that captures both structural characteristics and contextual semantics of the latest scheduling state. This expressive embedding is then processed by a deep reinforcement learning policy network, which generates real-time scheduling decisions optimized for both makespan and carbon emission objectives. To support sustainability goals, \textsc{Luca} incorporates a dual-objective reward function that encourages both energy efficiency and scheduling timeliness. Experimental results on both synthetic and public datasets demonstrate that \textsc{Luca} consistently outperforms comparison algorithms. For instance, on the synthetic dataset, it achieves an average of 4.1\% and up to 12.2\% lower makespan compared to the best-performing comparison algorithm while maintaining the same emission level. On public datasets, additional gains are observed for both makespan and emission. These results demonstrate that \textsc{Luca} is effective and practical for carbon-aware scheduling in smart manufacturing.
title LLM-Upgraded Graph Reinforcement Learning for Carbon-Aware Job Scheduling in Smart Manufacturing
topic Machine Learning
Computation and Language
url https://arxiv.org/abs/2512.06351