EUVIMEDEUVIMED entdecken
Crossref

MobiSplit: Mobility-Aware Inference Partitioning and Offloading for Efficient Edge Intelligence

Peng Wang, Wen Sun, Yi Yang, Dusit Niyato, Dapeng Oliver Wu

IEEE Transactions on Mobile Computing · 2026-03 · 25 (3) · 3969-3984

DOI: 10.1109/tmc.2025.3620438 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2026-03. Verfasst von Peng Wang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 36 Literaturangaben. Gefördert von: Hong Kong Research Grants Council, Innovation and Technology Commission, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Förderung

  • Hong Kong Research Grants Council
  • Innovation and Technology Commission
  • National Natural Science Foundation of China

Zitieren

APA

Wang, P., Sun, W., Yang, Y., Niyato, D., & Wu, D. O. (2026). MobiSplit: Mobility-Aware Inference Partitioning and Offloading for Efficient Edge Intelligence. IEEE Transactions on Mobile Computing, 25(3), 3969-3984. https://doi.org/10.1109/tmc.2025.3620438

Vancouver

Wang P, Sun W, Yang Y, Niyato D, Wu DO. MobiSplit: Mobility-Aware Inference Partitioning and Offloading for Efficient Edge Intelligence. IEEE Transactions on Mobile Computing. 2026;25(3):3969-3984. doi:10.1109/tmc.2025.3620438

BibTeX
@article{Wang2026,
  author = {Wang, Peng and Sun, Wen and Yang, Yi and Niyato, Dusit and Wu, Dapeng Oliver},
  title = {MobiSplit: Mobility-Aware Inference Partitioning and Offloading for Efficient Edge Intelligence},
  journal = {IEEE Transactions on Mobile Computing},
  year = {2026},
  volume = {25},
  number = {3},
  pages = {3969--3984},
  doi = {10.1109/tmc.2025.3620438}
}
Kostenlos starten →