Moving Edge for On-Demand Edge Computing: An Uncertainty-aware Approach

2025-03-31

AI Summary

To address the challenge of dynamically responding to hotspot regions in edge computing, this paper proposes URANUS—a unified framework integrating Bayesian deep learning with distributionally robust optimization. URANUS jointly models three sources of uncertainty—data, model, and underlying distribution—to enable robust demand forecasting and online scheduling of mobile computing units (e.g., vehicle-mounted modular data centers) in a synergistic manner. Compared to state-of-the-art reinforcement learning and deterministic approaches, URANUS improves decision robustness in simulations: expected revenue increases by 12.7%, service satisfaction rate rises by 9.3%, while scheduling costs and SLA violation risk decrease. Notably, this work is the first to embed distributionally robust approximation into uncertainty-aware edge scheduling, establishing a verifiable and scalable theoretical and practical paradigm for dynamic edge resource orchestration. (149 words)

Technology Category

• Planning, Routing, and Scheduling: Scheduling under Uncertainty
• Reasoning under Uncertainty: Stochastic Optimization
• Machine Learning: Learning on the Edge & Model Compression

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

We study an edge demand response problem where, based on historical edge workload demands, an edge provider needs to dispatch moving computing units, e.g. truck-carried modular data centers, in response to emerging hotspots within service area. The goal of edge provider is to maximize the expected revenue brought by serving congested users with satisfactory performance, while minimizing the costs of moving units and the potential service-level agreement violation penalty for interrupted services. The challenge is to make robust predictions for future demands, as well as optimized moving unit dispatching decisions. We propose a learning-based, uncertain-aware moving unit scheduling framework, URANUS, to address this problem. Our framework novelly combines Bayesian deep learning and distributionally robust approximation to make predictions that are robust to data, model and distributional uncertainties in deep learning-based prediction models. Based on the robust prediction outputs, we further propose an efficient planning algorithm to optimize moving unit scheduling in an online manner. Simulation experiments show that URANUS can significantly improve robustness in decision making, and achieve superior performance compared to state-of-the-art reinforcement learning, uncertainty-agnostic learning-based methods, and other baselines.

Problem

• Dispatch mobile computing units to handle edge workload hotspots efficiently
• Maximize revenue while minimizing costs and SLA violation penalties
• Robust demand prediction and optimized unit scheduling under uncertainties

Innovation

• Bayesian deep learning for robust predictions
• Distributionally robust approximation for uncertainties
• Online planning algorithm for unit scheduling