Adaptive Task Offloading for Edge Computing in Internet of Energy via Retrieval-Augmented Generation
IEEE Network · 2026-05 · 40 (3) · 219-228
DOI: 10.1109/mnet.2026.3665502 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Network, 2026-05. Verfasst von Xiongjie Zhou und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref). Gefördert von: State Grid Corporation of China.
Abstract (Originalsprache)
Traditional task offloading in Internet of Energy (loE) edge environments struggles to accommodate heterogeneous user tasks and dynamic system conditions. Although Large Language Models (LLMs) offer potential solutions, their deployment is hindered by the dynamic resource constraints and stringent Quality of Service (QoS) requirements of IoE. Retrieval-augmented generation (RAG) enables LLM to overcome these limitations. In this paper, we propose an RAGempowered adaptive task offloading framework. First, the framework transforms raw loE-collected data into LLM-comprehensible textual inputs. Second, we design an intelligent preference-matching module that guides RAG to retrieve relevant knowledge and cases using key QoS features. Third, we build a composite knowledge vector database with both positive and negative experiences. We introduce a failure severity value to quantify the importance of counterexamples and enhance decision-making robustness. Finally, we design a hybrid knowledge prompt generation module. It utilizes a hierarchical filtering strategy and optimizes the ranking of retrieved knowledge for comprehensive prompts. Experimental results demonstrate that our proposed framework significantly outperforms baselines, increasing cumulative reward by 48.4% while reducing latency and energy consumption by 44.8% and 50.9%, respectively.
Förderung
- State Grid Corporation of China
Zitieren
APA
Zhou, X., Guan, X., Wang, N., Chen, H., Ohtsuki, T., & Zhang, Y. (2026). Adaptive Task Offloading for Edge Computing in Internet of Energy via Retrieval-Augmented Generation. IEEE Network, 40(3), 219-228. https://doi.org/10.1109/mnet.2026.3665502
Vancouver
Zhou X, Guan X, Wang N, Chen H, Ohtsuki T, Zhang Y. Adaptive Task Offloading for Edge Computing in Internet of Energy via Retrieval-Augmented Generation. IEEE Network. 2026;40(3):219-228. doi:10.1109/mnet.2026.3665502
BibTeX
@article{Zhou2026,
author = {Zhou, Xiongjie and Guan, Xin and Wang, Ning and Chen, Hongyang and Ohtsuki, Tomoaki and Zhang, Yan},
title = {Adaptive Task Offloading for Edge Computing in Internet of Energy via Retrieval-Augmented Generation},
journal = {IEEE Network},
year = {2026},
volume = {40},
number = {3},
pages = {219--228},
doi = {10.1109/mnet.2026.3665502}
}
EUVIMED