Adaptive AI Model Partitioning over 5G Networks

2025/09/02 by Nguyễn Thành Tâm, Nguyen, Tam Thanh, Tuan Van Ngo +11
Computer Science · #Advanced Neural Network Applications #FOS: Computer and information sciences #IoT and Edge/Fog Computing #Networking and Internet Architecture (cs.NI) #Software-Defined Networks and 5G

paper · pdf · doi:10.48550/arxiv.2509.01906

openalex publication_date 2025/09/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Mobile devices increasingly rely on deep neural networks (DNNs) for complex inference tasks, but running entire models locally drains the device battery quickly. Offloading computation entirely to cloud or edge servers reduces processing load at devices but poses privacy risks and can incur high network bandwidth consumption and long delays. Split computing (SC) mitigates these challenges by partitioning DNNs between user equipment (UE) and edge servers. However, 5G wireless channels are time-varying and a fixed splitting scheme can lead to sub-optimal solutions. This paper addresses the limitations of fixed model partitioning in privacy-focused image processing and explores trade-offs in key performance metrics, including end-to-end (E2E) latency, energy consumption, and privacy, by developing an adaptive ML partitioning scheme based on real-time AI-powered throughput estimation. Evaluation in multiple scenarios demonstrates significant performance gains of our scheme.

Citations

• Detecting 5G Narrowband Jammers with CNN, k-nearest Neighbors, and Support Vector Machines
• Jamming Detection in Low-BER Mobile Indoor Scenarios via Deep Learning
• NoPeek: Information leakage reduction to share activations in\n distributed deep learning
• JointDNN: An Efficient Training and Inference Engine for Intelligent\n Mobile Cloud Computing Services
• Very Deep Convolutional Networks for Large-Scale Image Recognition

Related

• Dynamic Split Computing for Efficient Deep Edge Intelligence
• Adaptive Compression-Aware Split Learning and Inference for Enhanced Network Efficiency
• Deploying Large AI Models on Resource-Limited Devices with Split Federated Learning
• Enabling Edge Artificial Intelligence via Goal-oriented Deep Neural Network Splitting
• The Larger the Merrier? Efficient Large AI Model Inference in Wireless Edge Networks