Journal article · 2026 · Open access

TOMEC-RAS-Net: A Lightweight Deep Reinforcement Learning Framework for Adaptive Task Offloading in Mobile Edge Computing

Durgesh Sharma, Sushil Kumar Sharma

International Journal for Research in Applied Science and Engineering Technology, 14(3), 5270–5278 · Published 31 March 2026 · DOI 10.22214/ijraset.2026.79008

Open PDFCite this paper

In brief

“TOMEC-RAS-Net: A Lightweight Deep Reinforcement Learning Framework for Adaptive Task Offloading in Mobile Edge Computing” is a 2026 journal article by Durgesh Sharma and Sushil Kumar Sharma, published in International Journal for Research in Applied Science and Engineering Technology. OpenAlex counts 0 citations as of 19 November 2026. It is open access: the full text is free to read at International Journal for Research in Applied Science and Engineering Technology.

Citations
0
References
18
Authors
2

Abstract

Mobile Edge Computing (MEC) enables resource-constrained devices to transfer computationally heavy tasks to nearby edge servers, reducing latency and energy consumption while maintaining quality of service. However, unstable network conditions, limited edge resources, and complex decision-making requirements often lead to task backlogs and degraded performance. This paper presents TOMEC-RAS-Net, a lightweight deep reinforcement learning (DRL) framework for real-time adaptive task offloading in dynamic MEC environments. The proposed framework integrates density-based spatial clustering (DBSCAN) for intelligent task grouping, an ensemble RAS-Net actor architecture combining ResNet, AlexNet, and ShuffleNet for robust feature extraction, and a priority-weighted resampling strategy to enhance learning efficiency under varying network conditions. A Markov Decision Process (MDP) formulation jointly optimises binary offloading decisions, CPU frequency allocation, and transmission power under queue stability and average power constraints. Experimental evaluation on an NVIDIA RTX 4090 platform demonstrates that TOMEC-RAS-Net achieves 98.74% accuracy, 98.92% precision, 98.65% sensitivity, 99.01% specificity, and a Matthews Correlation Coefficient (MCC) of 97.46% — outperforming DNN, CNN, ResNet, and LSTM baselines across all metrics. The model maintains low false positive (0.99%) and false negative (1.35%) rates and exhibits stable convergence over five-fold cross-validation, confirming its suitability for real-time MEC task offloading at the network edge.

Cite this paper

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

APA 7

Sharma, D., & Sharma, S. K. (2026). TOMEC-RAS-Net: A Lightweight Deep Reinforcement Learning Framework for Adaptive Task Offloading in Mobile Edge Computing. International Journal for Research in Applied Science and Engineering Technology, 14(3), 5270–5278. https://doi.org/10.22214/ijraset.2026.79008

MLA 9

Sharma, Durgesh, and Sushil Kumar Sharma. “TOMEC-RAS-Net: A Lightweight Deep Reinforcement Learning Framework for Adaptive Task Offloading in Mobile Edge Computing.” International Journal for Research in Applied Science and Engineering Technology, vol. 14, no. 3, 2026, pp. 5270–5278. https://doi.org/10.22214/ijraset.2026.79008.

Chicago

Sharma, Durgesh and Sushil Kumar Sharma. 2026. “TOMEC-RAS-Net: A Lightweight Deep Reinforcement Learning Framework for Adaptive Task Offloading in Mobile Edge Computing.” International Journal for Research in Applied Science and Engineering Technology 14 (3): 5270–5278. https://doi.org/10.22214/ijraset.2026.79008.

Harvard

Sharma, D. and Sharma, S. K. (2026) ‘TOMEC-RAS-Net: A Lightweight Deep Reinforcement Learning Framework for Adaptive Task Offloading in Mobile Edge Computing’, International Journal for Research in Applied Science and Engineering Technology, 14(3), pp. 5270–5278. doi:10.22214/ijraset.2026.79008.

IEEE

D. Sharma and S. K. Sharma, “TOMEC-RAS-Net: A Lightweight Deep Reinforcement Learning Framework for Adaptive Task Offloading in Mobile Edge Computing,” International Journal for Research in Applied Science and Engineering Technology, vol. 14, no. 3, pp. 5270–5278, 2026, doi: 10.22214/ijraset.2026.79008.

BibTeX

@article{sharma2026tomec,
  title     = {{TOMEC-RAS-Net: A Lightweight Deep Reinforcement Learning Framework for Adaptive Task Offloading in Mobile Edge Computing}},
  author    = {Sharma, Durgesh and Sharma, Sushil Kumar},
  journal   = {International Journal for Research in Applied Science and Engineering Technology},
  year      = {2026},
  volume    = {14},
  number    = {3},
  pages     = {5270--5278},
  doi       = {10.22214/ijraset.2026.79008},
  url       = {https://doi.org/10.22214/ijraset.2026.79008}
}

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
  • deep reinforcement learning
  • adaptive offloading
  • DBSCAN
  • task grouping
  • ResNet
  • AlexNet

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?

Sharma, D., & Sharma, S. K. (2026). TOMEC-RAS-Net: A Lightweight Deep Reinforcement Learning Framework for Adaptive Task Offloading in Mobile Edge Computing. International Journal for Research in Applied Science and Engineering Technology, 14(3), 5270–5278. https://doi.org/10.22214/ijraset.2026.79008

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 International Journal for Research in Applied Science and Engineering Technology: sign in and open the PDF from this page.

Who wrote this paper?

Durgesh Sharma, Sushil Kumar Sharma.

What is the DOI of this paper?

10.22214/ijraset.2026.79008, permanently at https://doi.org/10.22214/ijraset.2026.79008. 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.