Obálka

Accuracy-Aware MLLM Task Offloading and Resource Allocation in UAV-Assisted Satellite Edge Computing

Uloženo v:
Vydáno v:Drones vol. 9, no. 7 (2025), p. 500-525
Hlavní autor: Yan Huabing
Další autoři: Huang Hualong, Zhao Zijia, Wang, Zhi, Zhao Zitian
Vydáno:
MDPI AG
Témata:
Internet of Things
Adaptability
Bandwidths
Optimization techniques
Real time
Edge computing
Resource allocation
Mobile computing
Adaptation
Remote monitoring
Unmanned aerial vehicles
Machine learning
Low earth orbit satellites
Energy consumption
Low earth orbits
Nonlinear programming
Distributed processing
Efficiency
Scheduling
Dynamic programming
Large language models
Artificial intelligence
Cloud computing
Decision making
Optimization
Network latency
Computation offloading
Variables
Algorithms
Mixed integer
On-line přístup:Citation/Abstract
Full Text + Graphics
Full Text - PDF
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstrakt:This paper presents a novel framework for optimizing multimodal large language model (MLLM) inference through task offloading and resource allocation in UAV-assisted satellite edge computing (SEC) networks. MLLMs leverage transformer architectures to integrate heterogeneous data modalities for IoT applications, particularly real-time monitoring in remote areas. However, cloud computing dependency introduces latency, bandwidth, and privacy challenges, while IoT device limitations require efficient distributed computing solutions. SEC, utilizing low-earth orbit (LEO) satellites and unmanned aerial vehicles (UAVs), extends mobile edge computing to provide ubiquitous computational resources for remote IoTDs. We formulate the joint optimization of MLLM task offloading and resource allocation as a mixed-integer nonlinear programming (MINLP) problem, minimizing latency and energy consumption while optimizing offloading decisions, power allocation, and UAV trajectories. To address the dynamic SEC environment characterized by satellite mobility, we propose an action-decoupled soft actor–critic (AD-SAC) algorithm with discrete–continuous hybrid action spaces. The simulation results demonstrate that our approach significantly outperforms conventional deep reinforcement learning methods in convergence and system cost reduction compared to baseline algorithms.
ISSN:2504-446X
DOI:10.3390/drones9070500
Zdroj:Advanced Technologies & Aerospace Database