Cooperative Edge Inferences With Online Learning
- 16 September 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (22) , 46611-46625
Abstract
The efficient execution of inferences at the edge is becoming increasingly critical for communication systems that are expected to provide users with fast and accurate mobile data analytics. These inference tasks are inherently latency-sensitive and computationally demanding, whereas edge nodes are limited by energy budgets and heterogeneous resources. This article studies how a set of edge nodes can collaborate in executing demanding streaming inference tasks to optimize their aggregate performance. Such collaborative task exchange schemes enable the sharing of scarce computing resources and machine learning (ML) models (which perform the inferences) and constitute a scalable approach to this intricate problem. We formulate this exchange process as an online convex optimization (OCO) problem and design a dynamic task assignment algorithm, which is proven to have optimality guarantees even when the network and service parameters (resources and task properties) are unknown and vary arbitrarily over time. The algorithm aims to maximize inference accuracy while minimizing overall task latency and energy (including for data transfers) and simultaneously ensures that collaborating nodes do not suffer imbalanced energy costs. Through a series of data-driven experiments, we quantify the cooperation benefits under different weight combinations and validate the convergence and adaptability of the proposed learning algorithm across diverse conditions, including variations of system parameters, as well as heterogeneity across nodes and tasks.Keywords
Funding Information
- National Growth Fund through the Dutch 6G Flagship Project “Future Network Services” and European Commission (101017109 (DAEMON), 101139270 (ORIGAMI), 101192462 (FLECON-6G))
This publication has 54 references indexed in Scilit:
- Cooperative Streaming Inferences in IoT Networks2024
- Energy-Efficient Intelligence Sharing in Intelligence Networking-Empowered Edge Computing: A Deep Reinforcement Learning ApproachIEEE Access, 2024
- A review on edge analytics: Issues, challenges, opportunities, promises, future directions, and applicationsDigital Communications and Networks, 2024
- Novel person detection and suspicious activity recognition using enhanced YOLOv5 and motion feature mapArtificial Intelligence Review, 2024
- Intelligence Inference on IoT Devices2023
- Modeling and Performance Evaluation of Collaborative IoT Cross-Camera Video Analytics2023
- Network for Distributed Intelligence: a Survey and Future PerspectivesIEEE Access, 2023
- A cooperative resource allocation model for IoT applications in mobile edge computingComputer Communications, 2021
- On the Deployability of Augmented Reality Using Embedded Edge Devices2021
- Unequal-Training for Deep Face Recognition With Long-Tailed Noisy Data2019