CDIO: Cross-Domain Inference Optimization with Resource Preference Prediction for Edge-Cloud Collaboration

2025-02-06

AI Summary

In edge-cloud collaborative video inference, heterogeneous task requirements and dynamic resource conditions lead to significant resource waste and suboptimal inference efficiency. To address this, we propose a cross-domain cooperative scheduling framework tailored for heterogeneous environments. Our approach introduces a novel resource preference type prediction mechanism grounded in spatial complexity and processing demand, and develops a lightweight, constraint-aware scheduling algorithm that jointly models multi-dimensional resources and task features for precise, real-time task-to-edge/cloud server assignment. Extensive experiments on public benchmarks demonstrate that our method reduces computational overhead and bandwidth consumption by 20–40% and cuts energy consumption by over 40%, compared to state-of-the-art approaches, while strictly satisfying both accuracy and end-to-end latency constraints.

Technology Category

• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Machine Learning: Learning on the Edge & Model Compression
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Cloud, edge and content delivery systems for the Web
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Currently, massive video tasks are processed by edge-cloud collaboration. However, the diversity of task requirements and the dynamics of resources pose great challenges to efficient inference, resulting in many wasted resources. In this paper, we present CDIO, a cross-domain inference optimization framework designed for edge-cloud collaboration. For diverse input tasks, CDIO can predict resource preference types by analyzing spatial complexity and processing requirements of the task. Subsequently, a cross-domain collaborative optimization algorithm is employed to guide resource allocation in the edge-cloud system. By ensuring that each task is matched with the ideal servers, the edge-cloud system can achieve higher efficiency inference. The evaluation results on public datasets demonstrate that CDIO can effectively meet the accuracy and delay requirements for task processing. Compared to state-of-the-art edge-cloud solutions, CDIO achieves a computing and bandwidth consumption reduction of 20%-40%. And it can reduce energy consumption by more than 40%.

Problem

• Optimizes resource allocation in edge-cloud systems
• Predicts resource preferences for diverse video tasks
• Reduces computing, bandwidth, and energy consumption

Innovation

• Predicts task resource preferences
• Optimizes edge-cloud resource allocation
• Reduces computing and energy consumption