Multiagent Collaborative Inference Optimization for Large-Scale DNNs in IoT Edge Systems
- 16 March 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (11) , 24938-24953
Abstract
Deploying large deep neural networks (DNNs) on resource-constrained Internet of Things (IoT) devices is often limited by high inference latency and energy consumption. This article studies collaborative inference between user devices and edge servers (ESs), where a deep neural network (DNN) is partitioned and executed across both sides under shared wireless resources. We jointly optimize the partition point across layers, uplink channel allocation and transmission power control, and formulate the coupled decisions as a Markov decision process (MDP). Under centralized training with decentralized execution (CTDE), we develop a multiagent proximal policy optimization (MAPPO) framework with a multihead critic and profiling-aware state design to stabilize learning under large hybrid action spaces. To validate practicality, we implement a containerized experimental platform that emulates resource-limited IoT devices and GPU-enabled ESs, enabling repeatable measurements of end-to-end latency and energy. Experiments with representative DNNs show that the proposed method consistently improves the latency–energy tradeoff over baseline algorithms, achieving lower end-to-end latency and comparable or lower energy consumption across diverse model structures and computation patterns.Keywords
Funding Information
- National Natural Science Foundation of China (61202076)
- Beijing Municipal Natural Science Foundation (4262021)
- Fundamental Research Funds for the Central Universities (312000546325001)
This publication has 38 references indexed in Scilit:
- An energy-focused model for batteryless IoT: Vortex wireless power transfer and fog computing in 6 G networksInternet of Things, 2025
- A comprehensive and systematic literature review on intrusion detection systems in the internet of medical things: current status, challenges, and opportunitiesArtificial Intelligence Review, 2025
- Multi-agent deep reinforcement learning-based partial offloading and resource allocation in vehicular edge computing networksComputer Communications, 2025
- A novel offloading strategy for multi-user optimization in blockchain-enabled Mobile Edge Computing networks for improved Internet of Things performanceComputers and Electrical Engineering, 2024
- An Intrusion Detection System on The Internet of Things Using Deep Learning and Multi-objective Enhanced Gorilla Troops OptimizerJournal of Bionic Engineering, 2024
- An advanced deep reinforcement learning algorithm for three-layer D2D-edge-cloud computing architecture for efficient task offloading in the Internet of ThingsSustainable Computing: Informatics and Systems, 2024
- CRESPR: Modular sparsification of DNNs to improve pruning performance and model interpretabilityNeural Networks, 2023
- An O-MAPPO scheme for joint computation offloading and resources allocation in UAV assisted MEC systemsComputer Communications, 2023
- JMDC: A joint model and data compression system for deep neural networks collaborative computing in edge-cloud networksJournal of Parallel and Distributed Computing, 2022
- AMC: AutoML for Model Compression and Acceleration on Mobile Devices2018