Real-Time AI Service Economy: A Framework for Agentic Computing Across the Continuum
Lauri Lov\'en, Alaa Saleh, Reza Farahani, Ilir Murturi, Miguel Bordallo L\'opez, Praveen Kumar Donta, Schahram Dustdar

TL;DR
This paper analyzes how the structure of AI service dependency graphs affects the stability and efficiency of decentralized resource allocation in real-time AI service ecosystems, proposing a hybrid management architecture to improve scalability.
Contribution
It introduces a hybrid architecture for managing complex dependency graphs in decentralized AI markets, demonstrating improved stability and efficiency through extensive experiments.
Findings
Hierarchical graphs enable stable prices and efficient allocations.
Hybrid architecture reduces price volatility by up to 75%.
Decentralized market matches centralized optimal allocations under truthful bidding.
Abstract
Real-time AI services increasingly operate across the device-edge-cloud continuum, where autonomous AI agents generate latency-sensitive workloads, orchestrate multi-stage processing pipelines, and compete for shared resources under policy and governance constraints. This article shows that the structure of service-dependency graphs, modelled as DAGs whose nodes represent compute stages and whose edges encode execution ordering, is a primary determinant of whether decentralised, price-based resource allocation can work reliably at scale. When dependency graphs are hierarchical (tree or series-parallel), prices converge to stable equilibria, optimal allocations can be computed efficiently, and under appropriate mechanism design (with quasilinear utilities and discrete slice items), agents have no incentive to misreport their valuations within each decision epoch. When dependencies are…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsIoT and Edge/Fog Computing · Distributed and Parallel Computing Systems · Blockchain Technology Applications and Security
