Harnessing Large Language Models for Intelligent Resource Allocation in the Internet of Everything

2026-07-29

AI Summary

This work addresses the challenge of dynamic resource scheduling in the Internet of Everything (IoE), where massive heterogeneous tasks demand efficient and adaptive allocation strategies. To this end, we propose a task-oriented intelligent scheduling approach grounded in large language models (LLMs). By integrating task semantics, network states, and operational constraints, we formulate a multidimensional scheduling decision model and devise a task-aware prompt generation mechanism. Furthermore, an external real-time feedback module is incorporated to validate feasibility and iteratively refine scheduling decisions. To the best of our knowledge, this is the first study to leverage LLMs for IoE resource scheduling, achieving significantly faster convergence, reduced processing latency and energy consumption, while enhancing both system resource utilization and task responsiveness without compromising robustness.

Abstract

The rapid development of the Internet of Everything (IoE) is accelerating the adoption of intelligent applications. However, the massive number of connected devices generates diverse and heterogeneous tasks, which pose increasing challenges for dynamic resource scheduling in IoE environments. Using their superior semantic understanding and reasoning capabilities, Large Artificial Intelligence Models (LAIMs) demonstrate significant potential to handle complex scheduling scenarios and improve resource utilization efficiency. This paper investigates a task-oriented LAIM-driven resource scheduling mechanism, which constructs a multidimensional scheduling decision model by integrating task semantics, network states, and constraint conditions. Furthermore, a task-oriented prompt generation method is designed to establish a deep association between task requirements and network state. In the proposed resource allocation scheme, an external evaluation and feedback module is incorporated to conduct real-time feasibility verification and performance evaluation of scheduling strategies, thus enhancing the robustness and adaptability of scheduling. Simulation results demonstrate that the proposed Large Language Model (LLM)-driven network architecture and resource allocation scheme achieve significant improvements in convergence speed, processing latency, and energy consumption, effectively enhancing IoE task responsiveness and resource utilization.

Problem

• Internet of Everything
• resource allocation
• dynamic scheduling
• heterogeneous tasks
• intelligent applications

Innovation

• Large Language Models
• Resource Allocation
• Internet of Everything
• Task-Oriented Prompting
• Real-time Feedback