Edge AI Inference as a Service via Dynamic Resources From Repeated Auctions
- 26 March 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 24 (9) , 7947-7964
Abstract
To enable edge AI providers to recruit edge devices and use them to deploy AI models and provision inference services, we conduct a comprehensive mathematical and algorithmic study on a novel incentive and optimization mechanism based on repeated auctions. We first model and formulate a time-cumulative social cost optimization problem to capture the challenges of the trade-off between cost and accuracy, the dependency between adjacent auctions, and the need of achieving desired economic properties. Then, to solve this intractable non-linear integer program in an online manner, we design a set of polynomial-time algorithms that work together. Our approach dynamically chooses and switches winning bids under careful control, incorporates online learning to overcome posterior inference accuracy and workload queue dynamics, and leverages randomization to strategically convert fractional decisions of model placement and query dispatch into integers. We also allocate payments to meet the necessary and sufficient conditions for the desired economic properties. Further, we rigorously prove the constant competitive ratio, the sub-linear regret and fit, and the truthfulness and individual rationality for our proposed approach. Finally, through extensive experiments using real devices, AI models, and data traces, we have validated the substantial advantages of our proposed approach compared to the baselines and the state-of-the-art methods.Keywords
Funding Information
- National Natural Science Foundation of China (62441225)
- Jiangsu Collaborative Innovation Center of Novel Software Technology and Industrialization
- National Science Foundation (CNS-2047719, CNS-2225949)
This publication has 39 references indexed in Scilit:
- INTaaS: Provisioning In-band Network Telemetry as a service via online learningComputer Networks, 2024
- Learning to Be Green: Carbon-Aware Online Control for Edge Intelligence with Colocated Learning and Inference2023
- Dynamic Edge-centric Resource Provisioning for Online and Offline Services Co-location2023
- Smart industrial IoT empowered crowd sensing for safety monitoring in coal mineDigital Communications and Networks, 2023
- Enabling Low Latency Edge Intelligence based on Multi-exit DNNs in the Wild2021
- Adaptive DNN Partition in Edge Computing Environments2020
- Deep Learning in Mobile and Wireless Networking: A SurveyIEEE Communications Surveys & Tutorials, 2019
- Application Bandwidth and Flow Rates from 3 Trillion Flows Across 45 Carrier Networks2017
- Rethinking the Inception Architecture for Computer Vision2016
- Dynamic resource provisioning in cloud computing: A randomized auction approach2014