Adaptive DNN Partitioning and Offloading in Heterogeneous Edge-Cloud Continuum
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917479384612864 |
|---|---|
| author | Deng, Akuen Akoi Butkus, Eimantas Lapkovskis, Alfreds Donta, Praveen Kumar |
| author_facet | Deng, Akuen Akoi Butkus, Eimantas Lapkovskis, Alfreds Donta, Praveen Kumar |
| contents | In recent years, the use of artificial intelligence on resource-constrained IoT devices has grown significantly. However, existing approaches to DNN partitioning and offloading across the edge-cloud continuum typically rely on static methods that ignore runtime dynamics. Furthermore, they are often evaluated in simulated environments rather than on real hardware. To address this gap, we propose a framework that dynamically splits neural network layers across the heterogeneous continuum. The framework profiles the model at startup, measures network link conditions between nodes, and periodically re-evaluates the partition to adapt to environmental changes. We created a physical testbed comprising a Raspberry Pi edge device, a laptop fog, and a high-performance desktop PC as the cloud. We evaluated the framework over three widely adopted convolutional neural networks: VGG16, AlexNet, and MobileNetV2. Our results show that the framework achieves reductions in energy and end-to-end latency of 27.09--35.82% and 6.34--22.92%, respectively, compared to a static partitioning baseline. These findings confirm the superiority of adaptive to static partitioning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_09623 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Adaptive DNN Partitioning and Offloading in Heterogeneous Edge-Cloud Continuum Deng, Akuen Akoi Butkus, Eimantas Lapkovskis, Alfreds Donta, Praveen Kumar Distributed, Parallel, and Cluster Computing Artificial Intelligence Machine Learning Networking and Internet Architecture Performance In recent years, the use of artificial intelligence on resource-constrained IoT devices has grown significantly. However, existing approaches to DNN partitioning and offloading across the edge-cloud continuum typically rely on static methods that ignore runtime dynamics. Furthermore, they are often evaluated in simulated environments rather than on real hardware. To address this gap, we propose a framework that dynamically splits neural network layers across the heterogeneous continuum. The framework profiles the model at startup, measures network link conditions between nodes, and periodically re-evaluates the partition to adapt to environmental changes. We created a physical testbed comprising a Raspberry Pi edge device, a laptop fog, and a high-performance desktop PC as the cloud. We evaluated the framework over three widely adopted convolutional neural networks: VGG16, AlexNet, and MobileNetV2. Our results show that the framework achieves reductions in energy and end-to-end latency of 27.09--35.82% and 6.34--22.92%, respectively, compared to a static partitioning baseline. These findings confirm the superiority of adaptive to static partitioning. |
| title | Adaptive DNN Partitioning and Offloading in Heterogeneous Edge-Cloud Continuum |
| topic | Distributed, Parallel, and Cluster Computing Artificial Intelligence Machine Learning Networking and Internet Architecture Performance |
| url | https://arxiv.org/abs/2605.09623 |