.png){kind=icon}
返回
MobiSplit: Mobility-Aware Inference Partitioning and Offloading for Efficient Edge Intelligence
.png){kind=icon}
PRE
AI
DOI：10.1109/TMC.2025.3620438.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Edge intelligence enhances the computational capabilities of resource-limited devices by offloading inference tasks to edge servers. Traditional methods either execute the entire model on the device, resulting in slow inference, or fully offload it to the server, incurring communication delays and privacy risks due to raw data transmission. Model partitioning addresses these challenges by splitting the model for execution on both the device and edge server, transmitting only intermediate inference results. However, current model partitioning methods lack consideration of device mobility, resulting in reduced inference efficiency and task interruptions. To address these limitations, we introduce MobiSplit, a novel mobility-aware framework that dynamically partitions inference models between resource-constrained devices and edge servers. MobiSplit adapts to real-time device mobility, fluctuating network conditions, and computational constraints to minimize inference latency and energy consumption while ensuring robust task execution. Additionally, we propose a distributed auction-based algorithm that empowers edge devices to autonomously determine optimal partitioning and offloading strategies in a scalable and adaptive manner. Extensive simulations demonstrate that MobiSplit enhances inference efficiency, achieving a 60% latency reduction and a 20% energy consumption decrease compared to the best-performing baseline across diverse edge scenarios.
Keyword:
Edge intelligence
inference offloading
distributed auction
mobility-aware computing
energy efficiency
期刊
IF:
9.2
论文数:
5.9K
被引数:
1.8W
机构
引用论文
Yuan, X.; Li, N.; Wei, K.; Xu, W.; Chen, Q.; Chen, H.; Guo, S. Mobility and Cost Aware Inference Accelerating Algorithm for Edge Intelligence. IEEE Trans. Mob. Comput. 2024, 24, 1530–1549. [Google Scholar] [CrossRef]Yuan, X.; Li, N.; Wei, K.; Xu, W.; Chen, Q.; Chen, H.; Guo, S. 移动性和成本感知的推理加速算法用于边缘智能。IEEE Trans. Mob. Comput. 2024, 24, 1530–1549. [Google Scholar] [CrossRef].png)
IF0
PREAI
分享收藏Channel Allocation to GAA Users Using Double Deep Recurrent Q-Learning Based on Double Auction MethodIEEE ACCESS
OAAI
IEEE ACCESSIF3.6
OAAI分享收藏Cloud-Edge-End Collaborative Task Offloading in Vehicular Edge Networks: A Multilayer Deep Reinforcement Learning Approach车载边缘网络中的云-边端协同任务卸载: 一种多层深度强化学习方法
PREAI
分享收藏MAT-IGA: A Deadline and Priority-Aware Task Offloading Method in Resource-Constrained Vehicular NetworksIEEE ACCESSOAAI
IEEE ACCESSIF3.6
OAAI分享收藏
查看更多内容