Salvato in:
| Autori principali: | , , , , , |
|---|---|
| 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 |