Joint DNN Partitioning and Task Offloading Based on Attention Mechanism-Aided Reinforcement Learning
Year: 2025
Type: article
Abstract: The rapid advancement of artificial intelligence applications has resulted in the deployment of a growing number of deep neural networks (DNNs) on mobile devices. Given the limited computational capabilities and small battery capacity of these devices, supporting efficient DNN inference presents a significant challenge. This paper considers the joint design of DNN model partitioning and offloading under high-concurrent tasks scenarios. The primary objective is to accelerate DNN task inference and reduce computational delay. Firstly, we propose an innovative adaptive inference framework that partitions DNN models into interdependent sub-tasks through a hierarchical partitioning method. Secondly, we develop a delay prediction model based on a Random Forest (RF) regression algorithm to estimate the computational delay of each sub-task on different devices. Finally, we designed a high-performance DNN partitioning and task offloading method based on an attention mechanism-aided Soft Actor-Critic (AMSAC) algorithm. The bandwidth allocation for each user is determined by the attention mechanism based on the characteristics of the DNN tasks, and the Soft Actor-Critic algorithm is used for adaptive layer-level partitioning and offloading of the DNN model, reducing collaborative inference delay. Extensive experiments demonstrate that our proposed AMSAC algorithm effectively reduces DNN task inference latency cost and improves service quality.
Authors: Mengyuan Zhang, Juan Fang, Ziyi Teng, Yaqi Liu, Shen Wu
Institution: Beijing University of Technology
Language: English
Topic: IoT and Edge/Fog Computing
Subfield: Computer Networks and Communications
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Estimated APC paid: $2,645
Award: G3474172640
OpenAlex ID: W4409561031