Conference paper · 2025 · Open access

Energy-efficient DNN Dividing Technique for Latency Optimization in Dynamic Mobile Edge Networks

Eldiyar Zhantileuov, Ali Kadhum Idrees, Suhrut R. Heroorkar, Rolf Schuster

ACM/IEEE Symposium on Edge Computing (SEC), 1–11 · Published 3 December 2025 · DOI 10.1145/3769102.3770626

Open full textCite this paper

In brief

“Energy-efficient DNN Dividing Technique for Latency Optimization in Dynamic Mobile Edge Networks” is a 2025 conference paper by Eldiyar Zhantileuov and 3 co-authors, published in ACM/IEEE Symposium on Edge Computing (SEC). 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 ACM/IEEE Symposium on Edge Computing (SEC).

Citations
0
References
28
Authors
4

Abstract

Mobile devices' processing power and battery life are being strained by the increasing need for real-time computing applications. These tasks can be offloaded to nearby servers with greater processing capability thanks to mobile edge computing. However, choosing the optimal number of tasks to be offloaded to save energy while optimizing the end-to-end latency becomes challenging. This is because we have to make a compromise between minimising energy consumption and optimizing the end-to-end latency. This paper proposes an energy-efficient Deep Neural Network Dividing Technique (EDNNDiT) for latency optimisation in dynamic mobile edge networks. EDNNDiT utilizes external machine-learning models to predict the latency and energy consumption of each DNN layer. These external machine learning models gather real data metrics from the IoT device, edge server, and network components to predict the end-to-end latency and energy consumption for each layer of the DNN model. Next, we use a straightforward heuristic to identify the candidate dividing points of the DNN model that meet the required Quality Service Level (QSL) of the end-to-end latency. Finally, EDNNDiT selects the candidate dividing point with the minimum energy consumption to save power on the IoT device while satisfying the QSL of the end-to-end latency. We conducted real experiments using the NVIDIA JetRacer Robot AI car and Se-QaM platform with both WiFi and 5G that were deployed in our lab under various load conditions on the edge server device. The experimental results for both sequential and non-sequential DNN architectures demonstrate that our EDNNDiT approach reduces energy consumption on the NVIDIA JetRacer while maintaining an acceptable QSL for end-to-end latency. EDNNDiT dynamically adapts to various network conditions and server requirements, showing a powerful and energy-efficient solution for deploying DNNs on limited-resource devices with enhanced overall performance.

Cite this paper

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

APA 7

Zhantileuov, E., Idrees, A. K., Heroorkar, S. R., & Schuster, R. (2025). Energy-efficient DNN Dividing Technique for Latency Optimization in Dynamic Mobile Edge Networks. ACM/IEEE Symposium on Edge Computing (SEC), 1–11. https://doi.org/10.1145/3769102.3770626

MLA 9

Zhantileuov, Eldiyar, et al. “Energy-efficient DNN Dividing Technique for Latency Optimization in Dynamic Mobile Edge Networks.” ACM/IEEE Symposium on Edge Computing (SEC), 2025, pp. 1–11. https://doi.org/10.1145/3769102.3770626.

Chicago

Zhantileuov, Eldiyar, Ali Kadhum Idrees, Suhrut R. Heroorkar, and Rolf Schuster. 2025. “Energy-efficient DNN Dividing Technique for Latency Optimization in Dynamic Mobile Edge Networks.” ACM/IEEE Symposium on Edge Computing (SEC): 1–11. https://doi.org/10.1145/3769102.3770626.

Harvard

Zhantileuov, E. et al. (2025) ‘Energy-efficient DNN Dividing Technique for Latency Optimization in Dynamic Mobile Edge Networks’, ACM/IEEE Symposium on Edge Computing (SEC), pp. 1–11. doi:10.1145/3769102.3770626.

IEEE

E. Zhantileuov, A. K. Idrees, S. R. Heroorkar, and R. Schuster, “Energy-efficient DNN Dividing Technique for Latency Optimization in Dynamic Mobile Edge Networks,” ACM/IEEE Symposium on Edge Computing (SEC), pp. 1–11, 2025, doi: 10.1145/3769102.3770626.

BibTeX

@inproceedings{zhantileuov2025energy,
  title     = {{Energy-efficient DNN Dividing Technique for Latency Optimization in Dynamic Mobile Edge Networks}},
  author    = {Zhantileuov, Eldiyar and Idrees, Ali Kadhum and Heroorkar, Suhrut R. and Schuster, Rolf},
  booktitle = {ACM/IEEE Symposium on Edge Computing (SEC)},
  year      = {2025},
  pages     = {1--11},
  doi       = {10.1145/3769102.3770626},
  url       = {https://doi.org/10.1145/3769102.3770626}
}

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
  • energy efficiency
  • end-to-end delay
  • task offloading
  • latency prediction
  • load forecasting
  • quality of service
  • IoT devices

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?

Zhantileuov, E., Idrees, A. K., Heroorkar, S. R., & Schuster, R. (2025). Energy-efficient DNN Dividing Technique for Latency Optimization in Dynamic Mobile Edge Networks. ACM/IEEE Symposium on Edge Computing (SEC), 1–11. https://doi.org/10.1145/3769102.3770626

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 ACM/IEEE Symposium on Edge Computing (SEC): sign in and open the full text from this page.

Who wrote this paper?

Eldiyar Zhantileuov, Ali Kadhum Idrees, Suhrut R. Heroorkar, Rolf Schuster.

What is the DOI of this paper?

10.1145/3769102.3770626, permanently at https://doi.org/10.1145/3769102.3770626. 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.