Adaptive AI Task Partitioning and Safe Offloading in Heterogeneous Edge-Cloud Continuum

[Submitted on 10 May 2026 (v1), last revised 18 Aug 2026 (this version, v2)]

View PDF

Abstract:In recent years, the use of artificial intelligence on resource-constrained IoT devices has grown significantly. However, existing approaches to AI task 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.

Submission history

From: Alfreds Lapkovskis [view email]
[v1] Sun, 10 May 2026 16:09:06 UTC (38 KB)
[v2] Tue, 18 Aug 2026 09:39:07 UTC (38 KB)