EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multi-Head Attention Reinforcement Learning for Computing Resource Allocation in Flexible Distribution Networks

Hongmin Gao, Tianyang Ni, Li Ding, Chenyu Zhang, Yunlong Jiang, Haixiang Zang, Shufang Xu

Technologies · 09.11.2026 · 14 (11) · 738

DOI: 10.3390/technologies14110738 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Technologies, online erschienen am 09.11.2026. Verfasst von Hongmin Gao und 6 weiteren Autor:innen. Die Arbeit nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Smart Grid-National Science and Technology Major Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In a Flexible Distribution Network (FDN), allocating computing resources to minimize latency and energy while guaranteeing task processability is a significant challenge. Heuristic algorithms and single-agent reinforcement learning suffer from the curse of dimensionality, because FDN nodes are highly heterogeneous and the task scale is massive. Multi-agent reinforcement learning (MARL) is a promising alternative, yet existing methods fail to capture the relationship between local observations and the global state and underuse temporal information, which makes them fragile under bursty task arrivals. We propose Attention QMIX (AQMIX), which embeds a state Q-value attention mechanism into QMIX so that multi-head attention explicitly links the global state with local observations, and adds a self-attention state encoder that extracts temporal features to guide the hypernetwork. On the IEEE 33-bus system, a field-derived 13-node scenario and scale-up scenarios with up to 150 nodes, AQMIX completes 99.5–100% of tasks at an on-time rate of at least 99.3%, and lowers energy per completed task by 14–34% relative to QMIX on the 33-bus system and by 47–87% in the scale-up scenarios.

Förderung

  • Smart Grid-National Science and Technology Major Project

Zitieren

APA

Gao, H., Ni, T., Ding, L., Zhang, C., Jiang, Y., Zang, H., & Xu, S. (2026). Multi-Head Attention Reinforcement Learning for Computing Resource Allocation in Flexible Distribution Networks. Technologies, 14(11), 738. https://doi.org/10.3390/technologies14110738

Vancouver

Gao H, Ni T, Ding L, Zhang C, Jiang Y, Zang H, et al. Multi-Head Attention Reinforcement Learning for Computing Resource Allocation in Flexible Distribution Networks. Technologies. 2026;14(11):738. doi:10.3390/technologies14110738

BibTeX
@article{Gao2026,
  author = {Gao, Hongmin and Ni, Tianyang and Ding, Li and Zhang, Chenyu and Jiang, Yunlong and Zang, Haixiang and Xu, Shufang},
  title = {Multi-Head Attention Reinforcement Learning for Computing Resource Allocation in Flexible Distribution Networks},
  journal = {Technologies},
  year = {2026},
  volume = {14},
  number = {11},
  pages = {738},
  doi = {10.3390/technologies14110738}
}
Kostenlos starten →