Journal article · 2026 · Open access

Revenue Maximization in Mobility-Aware Generative AI-enabled Edge Computing Networks

Khanh Quoc Nguyen, Nguyen Duc Hai, Hiep Quang Dao, Nguyen Cong Luong, Xingwang Li, Ngoc Hung Nguyen, Thuan Van Le, Huy T. Nguyen, Dong In Kim

IEEE Internet of Things Journal, 1 · Published 1 January 2026 · DOI 10.1109/jiot.2026.3741553

Open full textCite this paper

In brief

“Revenue Maximization in Mobility-Aware Generative AI-enabled Edge Computing Networks” is a 2026 journal article by Khanh Quoc Nguyen and 8 co-authors, published in IEEE Internet of Things Journal. OpenAlex counts 0 citations as of 19 November 2026. It is open access under a CC BY licence: the full text is free to read at IEEE Internet of Things Journal.

Citations
0
Authors
9

Abstract

In this paper, we investigate a mobility-aware edge-assisted Generative Artificial Intelligence (GAI) framework in which a Service Provider (SP) delivers Latent Diffusion Model (LDM)-based image generation services to mobile users. We formulate a stochastic revenue maximization problem that jointly optimizes user admission, denoising steps, and dynamic unit prices under service-budget, latency, GPU-memory, and perceptual-QoS constraints. We adopt the Perception-based Image Quality Evaluator (PIQUE) as a no-reference QoS metric. To address the non-closed-form QoS and stochastic dynamics induced by user mobility, wireless fading, and task arrivals, we develop GSRM-DiFPO, a Diffusion-driven Fisher-Regularized Policy Optimization algorithm. GSRM-DiFPO combines a diffusion policy with PPO-based advantage optimization and an empirical diagonal-Fisher consolidation loss derived from the auxiliary diffusion denoising likelihood. Unlike Q-guided diffusion RL, it avoids off-policy Q-guidance and directly optimizes the policy using on-policy advantage estimates. Experiments on ImageNet demonstrate that GSRM-DiFPO achieves up to 35% higher revenue than the evaluated baselines while admitting more users and maintaining competitive service latency and perceptual QoS across the considered settings. Its online decision latency remains below 1% of the scheduling sub-slot on the evaluated GPU, at the cost of additional periodic training time and persistent training memory.

Cite this paper

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

APA 7

Nguyen, K. Q., Hai, N. D., Dao, H. Q., Luong, N. C., Li, X., Nguyen, N. H., Van Le, T., Nguyen, H. T., & Kim, D. I. (2026). Revenue Maximization in Mobility-Aware Generative AI-enabled Edge Computing Networks. IEEE Internet of Things Journal, 1. https://doi.org/10.1109/jiot.2026.3741553

MLA 9

Nguyen, Khanh Quoc, et al. “Revenue Maximization in Mobility-Aware Generative AI-enabled Edge Computing Networks.” IEEE Internet of Things Journal, 2026, p. 1. https://doi.org/10.1109/jiot.2026.3741553.

Chicago

Nguyen, Khanh Quoc, Nguyen Duc Hai, Hiep Quang Dao, Nguyen Cong Luong, Xingwang Li, Ngoc Hung Nguyen, Thuan Van Le, Huy T. Nguyen, and Dong In Kim. 2026. “Revenue Maximization in Mobility-Aware Generative AI-enabled Edge Computing Networks.” IEEE Internet of Things Journal: 1. https://doi.org/10.1109/jiot.2026.3741553.

Harvard

Nguyen, K. Q. et al. (2026) ‘Revenue Maximization in Mobility-Aware Generative AI-enabled Edge Computing Networks’, IEEE Internet of Things Journal, p. 1. doi:10.1109/jiot.2026.3741553.

IEEE

K. Q. Nguyen et al., “Revenue Maximization in Mobility-Aware Generative AI-enabled Edge Computing Networks,” IEEE Internet of Things Journal, p. 1, 2026, doi: 10.1109/jiot.2026.3741553.

BibTeX

@article{nguyen2026revenue,
  title     = {{Revenue Maximization in Mobility-Aware Generative AI-enabled Edge Computing Networks}},
  author    = {Nguyen, Khanh Quoc and Hai, Nguyen Duc and Dao, Hiep Quang and Luong, Nguyen Cong and Li, Xingwang and Nguyen, Ngoc Hung and Van Le, Thuan and Nguyen, Huy T. and Kim, Dong In},
  journal   = {IEEE Internet of Things Journal},
  year      = {2026},
  pages     = {1},
  doi       = {10.1109/jiot.2026.3741553},
  url       = {https://doi.org/10.1109/jiot.2026.3741553}
}

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

  • revenue maximization
  • edge computing
  • generative AI
  • latent diffusion models
  • user mobility
  • user admission control
  • dynamic pricing
  • perceptual image quality

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?

Nguyen, K. Q., Hai, N. D., Dao, H. Q., Luong, N. C., Li, X., Nguyen, N. H., Van Le, T., Nguyen, H. T., & Kim, D. I. (2026). Revenue Maximization in Mobility-Aware Generative AI-enabled Edge Computing Networks. IEEE Internet of Things Journal, 1. https://doi.org/10.1109/jiot.2026.3741553

How many times has this paper been cited?

0 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 IEEE Internet of Things Journal: sign in and open the full text from this page.

Who wrote this paper?

Khanh Quoc Nguyen, Nguyen Duc Hai, Hiep Quang Dao, Nguyen Cong Luong, Xingwang Li, Ngoc Hung Nguyen, Thuan Van Le, Huy T. Nguyen, Dong In Kim.

What is the DOI of this paper?

10.1109/jiot.2026.3741553, permanently at https://doi.org/10.1109/jiot.2026.3741553. 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.