Accuracy-Aware MLLM Task Offloading and Resource Allocation in UAV-Assisted Satellite Edge Computing
Sábháilte in:
| Foilsithe in: | Drones vol. 9, no. 7 (2025), p. 500-525 |
|---|---|
| Príomhchruthaitheoir: | |
| Rannpháirtithe: | , , , |
| Foilsithe / Cruthaithe: |
MDPI AG
|
| Ábhair: | |
| Rochtain ar líne: | Citation/Abstract Full Text + Graphics Full Text - PDF |
| Clibeanna: |
Níl clibeanna ann, Bí ar an gcéad duine le clib a chur leis an taifead seo!
|
MARC
| LEADER | 00000nab a2200000uu 4500 | ||
|---|---|---|---|
| 001 | 3233140495 | ||
| 003 | UK-CbPIL | ||
| 022 | |a 2504-446X | ||
| 024 | 7 | |a 10.3390/drones9070500 |2 doi | |
| 035 | |a 3233140495 | ||
| 045 | 2 | |b d20250101 |b d20251231 | |
| 100 | 1 | |a Yan Huabing | |
| 245 | 1 | |a Accuracy-Aware MLLM Task Offloading and Resource Allocation in UAV-Assisted Satellite Edge Computing | |
| 260 | |b MDPI AG |c 2025 | ||
| 513 | |a Journal Article | ||
| 520 | 3 | |a 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. | |
| 653 | |a Internet of Things | ||
| 653 | |a Adaptability | ||
| 653 | |a Bandwidths | ||
| 653 | |a Optimization techniques | ||
| 653 | |a Real time | ||
| 653 | |a Edge computing | ||
| 653 | |a Resource allocation | ||
| 653 | |a Mobile computing | ||
| 653 | |a Adaptation | ||
| 653 | |a Remote monitoring | ||
| 653 | |a Unmanned aerial vehicles | ||
| 653 | |a Machine learning | ||
| 653 | |a Low earth orbit satellites | ||
| 653 | |a Energy consumption | ||
| 653 | |a Low earth orbits | ||
| 653 | |a Nonlinear programming | ||
| 653 | |a Distributed processing | ||
| 653 | |a Efficiency | ||
| 653 | |a Scheduling | ||
| 653 | |a Dynamic programming | ||
| 653 | |a Large language models | ||
| 653 | |a Artificial intelligence | ||
| 653 | |a Cloud computing | ||
| 653 | |a Decision making | ||
| 653 | |a Optimization | ||
| 653 | |a Network latency | ||
| 653 | |a Computation offloading | ||
| 653 | |a Variables | ||
| 653 | |a Algorithms | ||
| 653 | |a Mixed integer | ||
| 700 | 1 | |a Huang Hualong | |
| 700 | 1 | |a Zhao Zijia | |
| 700 | 1 | |a Wang, Zhi | |
| 700 | 1 | |a Zhao Zitian | |
| 773 | 0 | |t Drones |g vol. 9, no. 7 (2025), p. 500-525 | |
| 786 | 0 | |d ProQuest |t Advanced Technologies & Aerospace Database | |
| 856 | 4 | 1 | |3 Citation/Abstract |u https://www.proquest.com/docview/3233140495/abstract/embedded/6A8EOT78XXH2IG52?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text + Graphics |u https://www.proquest.com/docview/3233140495/fulltextwithgraphics/embedded/6A8EOT78XXH2IG52?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text - PDF |u https://www.proquest.com/docview/3233140495/fulltextPDF/embedded/6A8EOT78XXH2IG52?source=fedsrch |