.png){kind=icon}
.png){kind=icon}
Return
Adaptive Task Offloading for Edge Computing in Internet of Energy via Retrieval-Augmented Generation
.png){kind=icon}
PRE
AI
X
X
N
H
T
Y
DOI：10.1109/mnet.2026.3665502.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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.
Keywords:
Quality of service
Knowledge based systems
Real-time systems
Decision making
Servers
Semantics
Cognition
Robustness
Edge computing
Energy Internet
Augmented reality
Information retrieval
Journal
IF:
6.3
Papers:
2.6K
Citations:
1.1W
Organization
Cited Papers