AMP4EC: Adaptive Model Partitioning Framework for Efficient Deep Learning Inference in Edge Computing Environments
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908300897943552 |
|---|---|
| author | Zhang, Guilin Guo, Wulan Tan, Ziqi Jiang, Hailong |
| author_facet | Zhang, Guilin Guo, Wulan Tan, Ziqi Jiang, Hailong |
| contents | Edge computing facilitates deep learning in resource-constrained environments, but challenges such as resource heterogeneity and dynamic constraints persist. This paper introduces AMP4EC, an Adaptive Model Partitioning framework designed to optimize deep learning inference in edge environments through real-time resource monitoring, dynamic model partitioning, and adaptive task scheduling. AMP4EC features a resource-aware model partitioner that splits deep learning models based on device capabilities, a task scheduler that ensures efficient load balancing using a weighted scoring mechanism, and a Docker-based deployment environment for validation. Experimental results show up to a 78% reduction in latency and a 414% improvement in throughput compared to baseline methods. The framework achieves consistent performance with low scheduling overhead across varying resource profiles, demonstrating adaptability in high-resource (1 CPU, 1GB RAM) and low-resource (0.4 CPU, 512MB RAM) scenarios. These results highlight AMP4EC's scalability, efficiency, and robustness for real-world edge deployments, addressing the critical need for efficient distributed inference in dynamic, resource-constrained environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_00407 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AMP4EC: Adaptive Model Partitioning Framework for Efficient Deep Learning Inference in Edge Computing Environments Zhang, Guilin Guo, Wulan Tan, Ziqi Jiang, Hailong Distributed, Parallel, and Cluster Computing I.2.11; I.2.6; C.2.4 Edge computing facilitates deep learning in resource-constrained environments, but challenges such as resource heterogeneity and dynamic constraints persist. This paper introduces AMP4EC, an Adaptive Model Partitioning framework designed to optimize deep learning inference in edge environments through real-time resource monitoring, dynamic model partitioning, and adaptive task scheduling. AMP4EC features a resource-aware model partitioner that splits deep learning models based on device capabilities, a task scheduler that ensures efficient load balancing using a weighted scoring mechanism, and a Docker-based deployment environment for validation. Experimental results show up to a 78% reduction in latency and a 414% improvement in throughput compared to baseline methods. The framework achieves consistent performance with low scheduling overhead across varying resource profiles, demonstrating adaptability in high-resource (1 CPU, 1GB RAM) and low-resource (0.4 CPU, 512MB RAM) scenarios. These results highlight AMP4EC's scalability, efficiency, and robustness for real-world edge deployments, addressing the critical need for efficient distributed inference in dynamic, resource-constrained environments. |
| title | AMP4EC: Adaptive Model Partitioning Framework for Efficient Deep Learning Inference in Edge Computing Environments |
| topic | Distributed, Parallel, and Cluster Computing I.2.11; I.2.6; C.2.4 |
| url | https://arxiv.org/abs/2504.00407 |