Optimal Convergence and Edge Efficiency Cloud Prediction for Multi-domain Lightweight Models

Chen Wang

doi:10.54254/2755-2721/2025.LD26179

Applied and Computational EngineeringOpen access

Optimal Convergence and Edge Efficiency Cloud Prediction for Multi-domain Lightweight Models

Research Article

Open Access

Optimal Convergence and Edge Efficiency Cloud Prediction for Multi-domain Lightweight Models

Chen Wang ^1*

¹ School of Electrical and Electronic Engineering, Hubei University of Technology, Hubei, China

^*Corresponding author: 2310211129@hbut.edu.cn

Published on 20 August 2025

ACE Vol.179

ISSN (Print): 2755-273X

ISSN (Online): 2755-2721

ISBN (Print): 978-1-80590-184-6

ISBN (Online): 978-1-80590-129-7

Download Cover

Abstract

To address the growing demand for efficient natural language processing capabilities on resource-constrained edge devices, lightweight transformer architectures like Nano-GPT have emerged as essential solutions. However, their operational efficiency is profoundly influenced by the domain characteristics of their training data. This comprehensive investigation employs Nano-GPT progressively trained on three distinct datasets—Twitter conversations, scientific publications, and Shakespearean literature—identifying optimal validation loss at 20,000 training iterations while demonstrating peak text generation performance. Given significant variations in convergence patterns across domains and practical constraints in edge deployment scenarios, we standardized the evaluation framework at 5,000 iterations for consistent preliminary assessment. Through meticulously designed cloud-based experiments under rigorously controlled conditions—where data domain served as the sole independent variable—we quantitatively measured domain-specific impacts on three critical deployment metrics: inference latency, memory footprint, and energy consumption per operation. Our empirical findings conclusively demonstrate that data domain characteristics fundamentally determine compact models' real-world deployment efficiency, establishing a critical correlation between linguistic properties and computational resource requirements. These insights provide actionable guidance for selecting domain-appropriate models and optimizing architecture configurations in edge intelligence applications, particularly for IoT devices with stringent power and computational constraints.

Keywords:

Nano-GPT, Edge Deployment Capability Pre-assessment, Cloud Platform, Multi-domain Datasets, Optimal Validation Loss.

View PDF

References

[1]. Elhosary E, Moselhi O. (2025) Evaluating Natural Language Processing Algorithms for Improved Hazard and Operability Analysis. Geodata and AI, 4, 100026.

[2]. Zixuan Xiao, Jun. (2025) LLM agent framework for intelligent change analysis in urban environment using remote sensing imagery.Automation in Construction, 177, 106341.

[3]. Maharani A D, Utaminingrum F, Husnina N N D, et al. (2025) A review: Lightweight architecture model in deep learning approach for lung disease identification. Computers in biology and medicine, 194, 110425.

[4]. Fuming, Xu, Jian, Runjiang, Nanjian, et al. (2024) DT-SCNN: dual-threshold spiking convolutional neural network with fewer operations and memory access for edge applications. Frontiers in Computational Neuroscience, 18, 1418115.

[5]. Li Jieyu, Chen Zhi, Chen Lu, Zhu Zichen, Li Hanqi, et al. (2023) DIR: A Large-Scale Dialogue Rewrite Dataset for Cross-Domain Conversational Text-to-SQL. Applied Sciences, 13(4): 2262-2262.

[6]. Bouchiha D, Bouziane A, Doumi N, et al. (2025) Hierarchical Text Classification: Fine-tuned GPT-2 vs BERT-BiLSTM. Applied Computer Systems, 30(1): 40-46.

[7]. Dhillon A S, Torresin A. Advancing Vehicle Diagnostic: Exploring the Application of Large Language Models in the Automotive Industry. Chalmers University of Technology, Gothenburg, Sweden 2024.

References

[1]. Elhosary E, Moselhi O. (2025) Evaluating Natural Language Processing Algorithms for Improved Hazard and Operability Analysis. Geodata and AI, 4, 100026.

[2]. Zixuan Xiao, Jun. (2025) LLM agent framework for intelligent change analysis in urban environment using remote sensing imagery.Automation in Construction, 177, 106341.

[5]. Li Jieyu, Chen Zhi, Chen Lu, Zhu Zichen, Li Hanqi, et al. (2023) DIR: A Large-Scale Dialogue Rewrite Dataset for Cross-Domain Conversational Text-to-SQL. Applied Sciences, 13(4): 2262-2262.

[6]. Bouchiha D, Bouziane A, Doumi N, et al. (2025) Hierarchical Text Classification: Fine-tuned GPT-2 vs BERT-BiLSTM. Applied Computer Systems, 30(1): 40-46.

[7]. Dhillon A S, Torresin A. Advancing Vehicle Diagnostic: Exploring the Application of Large Language Models in the Automotive Industry. Chalmers University of Technology, Gothenburg, Sweden 2024.

Cite this article

Wang,C. (2025). Optimal Convergence and Edge Efficiency Cloud Prediction for Multi-domain Lightweight Models. Applied and Computational Engineering,179,30-36.

Data availability

The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.

About volume

Volume title: Proceedings of CONF-MLA 2025 Symposium: Intelligent Systems and Automation: AI Models, IoT, and Robotic Algorithms

ISBN: 978-1-80590-184-6(Print) / 978-1-80590-129-7(Online)

Editor: Hisham AbouGrad

Conference website: https://www.confmla.org/london.html

Conference date: 17 November 2025

Series: Applied and Computational Engineering

Volume number: Vol.179

ISSN: 2755-2721(Print) / 2755-273X(Online)

© 2024 by the author(s). Licensee EWA Publishing, Oxford, UK. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license. Authors who publish this series agree to the following terms:

1. Authors retain copyright and grant the series right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this series.

2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the series's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this series.

3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See Open access policy for details).