Journal article · 2025 · Open access

Two-Timescale Model Caching and Resource Allocation for Edge-Enabled AI-Generated Content Services

Zhang Liu, Hongyang Du, Xiangwang Hou, Lianfen Huang, Seyyedali Hosseinalipour, Dusit Tao Niyato, Khaled B. Letaief

IEEE Transactions on Mobile Computing, 25(4), 4822–4838 · Published 31 October 2025 · DOI 10.1109/tmc.2025.3627263

Open PDFView at the publisherCite this paper

In brief

“Two-Timescale Model Caching and Resource Allocation for Edge-Enabled AI-Generated Content Services” is a 2025 journal article by Zhang Liu and 6 co-authors, published in IEEE Transactions on Mobile Computing. OpenAlex counts 22 citations as of 19 November 2026, which puts it in the top 4% of works published in 2025 by citations. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
22
Most cited in
2026 (17)
Field-weighted impact
5.67
References
42
Authors
7

Abstract

Generative AI (GenAI) has emerged as a transformative technology, enabling customized and personalized AI-generated content (AIGC) services. In this paper, we address challenges of edge-enabled AIGC service provisioning, which remain underexplored in the literature. These services require executing GenAI models with billions of parameters, posing significant obstacles to resource-limited wireless edge. We subsequently introduce the formulation of joint model caching and resource allocation for AIGC services to balance a trade-off between AIGC quality and latency metrics. We obtain mathematical relationships of these metrics with the computational resources required by GenAI models via experimentation. Afterward, we decompose the formulation into a model caching subproblem on a long-timescale and a resource allocation subproblem on a short-timescale. Since the variables to be solved are discrete and continuous, respectively, we leverage a double deep Q-network (DDQN) algorithm to solve the former subproblem and propose a diffusion-based deep deterministic policy gradient (D3PG) algorithm to solve the latter. The proposed D3PG algorithm makes an innovative use of diffusion models as the actor network to determine optimal resource allocation decisions. Consequently, we integrate these two learning methods within the overarching two-timescale deep reinforcement learning (T2DRL) algorithm, the performance of which is studied through comparative numerical simulations.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Liu, Z., Du, H., Hou, X., Huang, L., Hosseinalipour, S., Niyato, D. T., & Letaief, K. B. (2025). Two-Timescale Model Caching and Resource Allocation for Edge-Enabled AI-Generated Content Services. IEEE Transactions on Mobile Computing, 25(4), 4822–4838. https://doi.org/10.1109/tmc.2025.3627263

MLA 9

Liu, Zhang, et al. “Two-Timescale Model Caching and Resource Allocation for Edge-Enabled AI-Generated Content Services.” IEEE Transactions on Mobile Computing, vol. 25, no. 4, 2025, pp. 4822–4838. https://doi.org/10.1109/tmc.2025.3627263.

Chicago

Liu, Zhang, Hongyang Du, Xiangwang Hou, Lianfen Huang, Seyyedali Hosseinalipour, Dusit Tao Niyato, and Khaled B. Letaief. 2025. “Two-Timescale Model Caching and Resource Allocation for Edge-Enabled AI-Generated Content Services.” IEEE Transactions on Mobile Computing 25 (4): 4822–4838. https://doi.org/10.1109/tmc.2025.3627263.

Harvard

Liu, Z. et al. (2025) ‘Two-Timescale Model Caching and Resource Allocation for Edge-Enabled AI-Generated Content Services’, IEEE Transactions on Mobile Computing, 25(4), pp. 4822–4838. doi:10.1109/tmc.2025.3627263.

IEEE

Z. Liu et al., “Two-Timescale Model Caching and Resource Allocation for Edge-Enabled AI-Generated Content Services,” IEEE Transactions on Mobile Computing, vol. 25, no. 4, pp. 4822–4838, 2025, doi: 10.1109/tmc.2025.3627263.

BibTeX

@article{liu2025timescale,
  title     = {{Two-Timescale Model Caching and Resource Allocation for Edge-Enabled AI-Generated Content Services}},
  author    = {Liu, Zhang and Du, Hongyang and Hou, Xiangwang and Huang, Lianfen and Hosseinalipour, Seyyedali and Niyato, Dusit Tao and Letaief, Khaled B.},
  journal   = {IEEE Transactions on Mobile Computing},
  year      = {2025},
  volume    = {25},
  number    = {4},
  pages     = {4822--4838},
  doi       = {10.1109/tmc.2025.3627263},
  url       = {https://doi.org/10.1109/tmc.2025.3627263}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing

  • AI-generated content
  • edge computing
  • resource allocation
  • generative AI models
  • double deep Q-network
  • diffusion models
  • deep deterministic policy gradient
  • wireless edge networks

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Liu, Z., Du, H., Hou, X., Huang, L., Hosseinalipour, S., Niyato, D. T., & Letaief, K. B. (2025). Two-Timescale Model Caching and Resource Allocation for Edge-Enabled AI-Generated Content Services. IEEE Transactions on Mobile Computing, 25(4), 4822–4838. https://doi.org/10.1109/tmc.2025.3627263

How many times has this paper been cited?

22 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Zhang Liu, Hongyang Du, Xiangwang Hou, Lianfen Huang, Seyyedali Hosseinalipour, Dusit Tao Niyato, Khaled B. Letaief.

What is the DOI of this paper?

10.1109/tmc.2025.3627263, permanently at https://doi.org/10.1109/tmc.2025.3627263. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.