mlsanityData to 7 Oct 2026

Dynamic Pricing for On-Demand DNN Inference in the Edge-AI Market

arXiv 2503.04521 ↗First posted 6 Mar 2025cs.AI cs.CE cs.DCcited by 0

On the map: Efficient LLM inference and serving → Early exit and edge inference

Abstract (arXiv)

The convergence of edge computing and Artificial Intelligence (AI) gives rise to Edge-AI, which enables the deployment of real-time AI applications at the network edge. A key research challenge in Edge-AI is edge inference acceleration, which aims to realize low-latency high-accuracy Deep Neural Network (DNN) inference by offloading partitioned inference tasks from end devices to edge servers. However, existing research has yet to adopt a practical Edge-AI market perspective, which would explore the personalized inference needs of AI users (e.g., inference accuracy, latency, and task complexity), the revenue incentives for AI service providers that offer edge inference services, and multi-stakeholder governance within a market-oriented context. To bridge this gap, we propose an Auction-based Edge Inference Pricing Mechanism (AERIA) for revenue maximization to tackle the multi-dimensional optimization problem of DNN model partition, edge inference pricing, and resource allocation. We develop a multi-exit device-edge synergistic inference scheme for on-demand DNN inference acceleration, and theoretically analyze the auction dynamics amongst the AI service providers, AI users and edge infrastructure provider. Owing to the strategic mechanism design via randomized consensus estimate and cost sharing techniques, the Edge-AI market attains several desirable properties. These include competitiveness in revenue maximization, incentive compatibility, and envy-freeness, which are crucial to maintain the effectiveness, truthfulness, and fairness in auction outcomes. Extensive simulations based on four representative DNN inference workloads demonstrate that AERIA significantly outperforms several state-of-the-art approaches in revenue maximization. This validates the efficacy of AERIA for on-demand DNN inference in the Edge-AI market.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Early exit and edge inference, one of 12 directions in Efficient LLM inference and serving. Builds on 13 of its 56 references that are in the map. First posted on arXiv 6 Mar 2025.

Builds on

13 of 56 references.

References · 13

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  4. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  5. 2017BranchyNet: Fast Inference via Early Exiting from Deep Neural Networkscited by 591
  6. 2016Multi30K: Multilingual English-German Image Descriptionscited by 250
  7. 2019Edge AI: On-Demand Accelerating Deep Neural Network Inference via Edge Computingcited by 150
  8. 2017Distributed Deep Neural Networks over the Cloud, the Edge and End Devicescited by 119
  9. 2020CoEdge: Cooperative DNN Inference with Adaptive Workload Partitioning over Heterogeneous Edge Devicescited by 65
  10. 2022Task-Oriented Sensing, Computation, and Communication Integration for Multi-Device Edge AIcited by 31
  11. 2020Joint Multi-User DNN Partitioning and Computational Resource Allocation for Collaborative Edge Intelligencecited by 12
  12. 2022Task-Oriented Over-the-Air Computation for Multi-Device Edge AIcited by 12
1 more
  1. 2023Task Placement and Resource Allocation for Edge Machine Learning: A GNN-based Multi-Agent Reinforcement Learning Paradigmcited by 7

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2022Graph Reinforcement Learning-based CNN Inference Offloading in Dynamic Edge Computing
  2. 2023Adaptive DNN Surgery for Selfish Inference Acceleration with On-demand Edge Resource
  3. 2026A Comparative Study of CNN Optimization Methods for Edge AI: Exploring the Role of Early Exits
  4. 2022Resource-Constrained Edge AI with Early Exit Prediction
  5. 2025Rethinking Inference Placement for Deep Learning across Edge and Cloud Platforms: A Multi-Objective Optimization Perspective and Future Directions
  6. 2025DistrEE: Distributed Early Exit of Deep Neural Network Inference on Edge Devices
  7. 2022Distributed Deep Learning Inference Acceleration using Seamless Collaboration in Edge Computing
  8. 2026DyMoE: Dynamic Expert Orchestration with Mixed-Precision Quantization for Efficient MoE Inference on Edge