Oct 2026· IEEE Transactions on Mobile Computing· Vol 25, pp. 16158-16174· 0 citations· 50 references
Abstract
Offloading DNN workload to an edge network for parallel and distributed computing is a promising solution to hosting computation-intensive DNN services. The challenge is how to partition DNN models and to reduce the communication to realize a high-performance multi-edge DNN computing. In this paper, we first propose a novel two-stage bayesian optimization based approach to DNN model partitioning, which can decouple a DNN model into components at appropriate granularity while at the same time incur less communication cost between them. The proposed approach is physical infrastructure agnostic and can achieve a decomposition ratio of 3.2× to 35.0× on popular DNN models while respecting their execution parallelism. Moreover, we consider online DNN model deployment scenarios, with the aim to maximize the rate of requests supported by the network. We formulate a mixed integer linear programming (MILP) problem for the task and establish its NP-hardness. To tackle it efficiently, we decompose the problem into two sub-problems, and propose a binary search method to the upper-level one and a backtracking based algorithm to the lower-level one. We evaluate our mechanisms through both simulation and experiments, and results show they are effective as compared to baselines.
Generative Artificial Intelligence (GAI) has been attracting a massive and rapidly expanding user base worldwide in recent years, resulting in enormous demand for inference requests that cannot be handled efficiently by centralized cloud-based architectures. Edge computing presents a promising approach to mitigate thes...
C. T. Nguyen, D. Hoang, D. Nguyen et al.· IEEE Transactions on Network...· 0 citations
These findings demonstrate that DI-MNA provides an effective balance between solution quality, scalability, and computational efficiency for resource allocation in large-scale IoT networks.
Distributed optimization, learning, and inference across data centers are typical applications in the era of intelligent computing networks. These types of applications have high dependencies and are sensitive to delay. Offloading delay-sensitive dependency tasks to distributed elastic optical data center networks (EOD...
Xu Zhang, Xue Zhou, Chuan Feng et al.· Journal of Optical Communica...· 0 citations
An AI-driven VNF allocation framework for 6G-NTN environments built on an O-RAN-based distributed architecture and orchestrated on top of Kubernetes is introduced, demonstrating that AI-driven orchestration can systematically uncover non-obvious resource configurations that purely analytical or static approaches consis...
Francisco Muro, Eduardo Baena, T. de Cola et al.· IEEE Transactions on Network...· 0 citations
A product-form queueing-network (PFQN) model with an approximation to capture the computation and communication dynamics of tree-structured task execution in a multi-tier MEC system is developed and results show that the proposed PFQN approximation provides accurate delay estimates.
Amirparsa Bahrami, Farid Ashtiani· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduNov 20, 2026
Senior Research Scientist Jim Glass discusses how his MIT-IBM Computing Research Lab collaboration connects perception and language, and addresses the shortcoming of current models.