Journal article · 2026 · Open access

An adaptive deep reinforcement learning framework enhanced by broad reinforcement learning–based state transition for efficient task offloading and resource allocation at the network edge

Wei Zhou, Yongbing Ji

Journal of Engineering and Applied Science, 73(1) · Published 27 March 2026 · DOI 10.1186/s44147-026-00982-z

Open PDFView at the publisherCite this paper

In brief

“An adaptive deep reinforcement learning framework enhanced by broad reinforcement learning–based state transition for efficient task offloading and resource allocation at the network edge” is a 2026 journal article by Wei Zhou and Yongbing Ji, published in Journal of Engineering and Applied Science. OpenAlex counts 1 citations as of 19 November 2026. It is open access under a CC BY licence: the full text is free to read at Journal of Engineering and Applied Science.

Citations
1
Most cited in
2026 (1)
Field-weighted impact
1.68
References
31
Authors
2

Abstract

Mobile Edge Computing (MEC) empowers resource-constrained devices to offload computationally intensive tasks to nearby edge servers, reducing latency and energy consumption. Existing deep reinforcement learning approaches have improved offloading and resource allocation decisions; however, their performance often depends on heuristic or manually tuned hyperparameters, which limit adaptability in non-stationary environments. To address this issue, we propose a Broad Reinforcement Learning–enhanced State-Driven Task Offloading Algorithm (BRL-STOA), which integrates fitness landscape analysis–based state representation, Broad Learning System (BLS)–assisted Q-value approximation, and Gaussian Mixture Model (GMM)–based data augmentation to allow efficient and adaptive decision-making. Unlike conventional deep reinforcement learning approaches that incur high computational overhead, the proposed framework employs a lightweight BLS structure to accelerate convergence while maintaining decision accuracy. Simulation results demonstrate that BRL-STOA achieves up to 21.2% reduction in execution cost, 38.8% lower energy consumption, and 9.1% improvement in system throughput compared with state-of-the-art meta-heuristic algorithms. Moreover, the proposed method increases the accumulated reward by approximately 8–14% across different state-space sizes and converges faster while maintaining improved stability.

Cite this paper

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

APA 7

Zhou, W., & Ji, Y. (2026). An adaptive deep reinforcement learning framework enhanced by broad reinforcement learning–based state transition for efficient task offloading and resource allocation at the network edge. Journal of Engineering and Applied Science, 73(1). https://doi.org/10.1186/s44147-026-00982-z

MLA 9

Zhou, Wei, and Yongbing Ji. “An adaptive deep reinforcement learning framework enhanced by broad reinforcement learning–based state transition for efficient task offloading and resource allocation at the network edge.” Journal of Engineering and Applied Science, vol. 73, no. 1, 2026. https://doi.org/10.1186/s44147-026-00982-z.

Chicago

Zhou, Wei and Yongbing Ji. 2026. “An adaptive deep reinforcement learning framework enhanced by broad reinforcement learning–based state transition for efficient task offloading and resource allocation at the network edge.” Journal of Engineering and Applied Science 73 (1). https://doi.org/10.1186/s44147-026-00982-z.

Harvard

Zhou, W. and Ji, Y. (2026) ‘An adaptive deep reinforcement learning framework enhanced by broad reinforcement learning–based state transition for efficient task offloading and resource allocation at the network edge’, Journal of Engineering and Applied Science, 73(1). doi:10.1186/s44147-026-00982-z.

IEEE

W. Zhou and Y. Ji, “An adaptive deep reinforcement learning framework enhanced by broad reinforcement learning–based state transition for efficient task offloading and resource allocation at the network edge,” Journal of Engineering and Applied Science, vol. 73, no. 1, 2026, doi: 10.1186/s44147-026-00982-z.

BibTeX

@article{zhou2026adaptive,
  title     = {{An adaptive deep reinforcement learning framework enhanced by broad reinforcement learning–based state transition for efficient task offloading and resource allocation at the network edge}},
  author    = {Zhou, Wei and Ji, Yongbing},
  journal   = {Journal of Engineering and Applied Science},
  year      = {2026},
  volume    = {73},
  number    = {1},
  doi       = {10.1186/s44147-026-00982-z},
  url       = {https://doi.org/10.1186/s44147-026-00982-z}
}

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

  • mobile edge computing
  • task offloading
  • resource allocation
  • deep reinforcement learning
  • broad learning system
  • state representation
  • fitness landscape analysis
  • energy consumption

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?

Zhou, W., & Ji, Y. (2026). An adaptive deep reinforcement learning framework enhanced by broad reinforcement learning–based state transition for efficient task offloading and resource allocation at the network edge. Journal of Engineering and Applied Science, 73(1). https://doi.org/10.1186/s44147-026-00982-z

How many times has this paper been cited?

1 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 Journal of Engineering and Applied Science: sign in and open the PDF from this page.

Who wrote this paper?

Wei Zhou, Yongbing Ji.

What is the DOI of this paper?

10.1186/s44147-026-00982-z, permanently at https://doi.org/10.1186/s44147-026-00982-z. 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.