D 3 NN: Adaptive Partitioning and Cross-Tier Resource Orchestration for Cloud–Edge Collaborative Inference
IEEE Transactions on Computers · 2026-09 · 75 (9) · 3055-3069
DOI: 10.1109/tc.2026.3699819 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Computers, 2026-09. Verfasst von Yong Zhao und 5 weiteren Autor:innen. Die Arbeit nennt 45 Literaturangaben. Gefördert von: Science Foundation for Youths of the Natural Science Foundation of Sichuan Province, China Postdoctoral Science Foundation, National Natural Science Foundation of China.
Abstract (Originalsprache)
Deep Neural Networks (DNNs) have become foundational to intelligent systems, yet deploying them efficiently under strict latency, resource, and privacy constraints remains challenging. While cloud-only inference suffers from transmission latency and privacy risks, and edge-only execution is limited by hardware capacity, cloud–edge collaborative inference offers a practical middle ground by combining the cloud’s compute strength with the edge’s proximity to data sources for low-latency, scalable, and privacy-aware inference. However, realizing this potential requires adaptive DNN partitioning that responds to dynamic workloads and network conditions, as well as fine-grained cross-tier resource orchestration to avoid bottlenecks and ensure system stability. To this end, we propose DDPG-DRPA-driven Deep Neural Network(D3NN), a novel and efficient framework for partitioned DNN deployment across cloud and edge resources. We formulate the pipeline partitioning of DNNs as a Markov Decision Process (MDP). A value function is trained using the Deep Deterministic Policy Gradient (DDPG) algorithm, and a Dynamic Resource Partitioning Agent (DRPA) allocates suitable cloud or edge resources to each DNN layer according to specific task types. As a result, D3NN adapts dynamically to both environmental conditions and task requirements. Under maximum task arrival rate scenarios, our approach reduces inference latency by 13.7% compared to pure cloud-based inference and by 33.5% compared to pure edge-based inference, demonstrating its practical effectiveness in resource-constrained cloud–edge systems.
Förderung
- Science Foundation for Youths of the Natural Science Foundation of Sichuan Province
- China Postdoctoral Science Foundation
- National Natural Science Foundation of China
- Fundamental Research Funds for the Central Universities
Zitieren
APA
Zhao, Y., Mo, Z., He, Q., Niu, Z., Cao, J., & Hawbani, A. (2026). D 3 NN: Adaptive Partitioning and Cross-Tier Resource Orchestration for Cloud–Edge Collaborative Inference. IEEE Transactions on Computers, 75(9), 3055-3069. https://doi.org/10.1109/tc.2026.3699819
Vancouver
Zhao Y, Mo Z, He Q, Niu Z, Cao J, Hawbani A. D 3 NN: Adaptive Partitioning and Cross-Tier Resource Orchestration for Cloud–Edge Collaborative Inference. IEEE Transactions on Computers. 2026;75(9):3055-3069. doi:10.1109/tc.2026.3699819
BibTeX
@article{Zhao2026,
author = {Zhao, Yong and Mo, Zhenjia and He, Qiang and Niu, Zifeng and Cao, Jiannong and Hawbani, Ammar},
title = {D 3 NN: Adaptive Partitioning and Cross-Tier Resource Orchestration for Cloud–Edge Collaborative Inference},
journal = {IEEE Transactions on Computers},
year = {2026},
volume = {75},
number = {9},
pages = {3055--3069},
doi = {10.1109/tc.2026.3699819}
}
EUVIMED