Conformal Lyapunov Optimization: Optimal Resource Allocation under Deterministic Reliability Constraints
This paper introduces conformal Lyapunov optimization (CLO), a novel resource allocation framework for networked systems that optimizes average long-term objectives, while satisfying deterministic long-term reliability constraints. Unlike traditional Lyapunov optimization (LO), which addresses resource allocation tasks under average long-term constraints, CLO provides formal worst-case deterministic reliability guarantees. This is achieved by integrating the standard LO optimization framework with online conformal risk control (O-CRC), an adaptive update mechanism controlling long-term risks. The effectiveness of CLO is verified via experiments for hierarchal edge inference targeting image segmentation tasks in a networked computing architecture. Specifically, simulation results confirm that CLO can control reliability constraints, measured via the false negative rate of all the segmentation decisions made in the network, while at the same time minimizing the weighted sum of energy consumption and imprecision, with the latter accounting for the rate of false positives.
Code (0)
등록된 구현이 없습니다.
Tasks
Image SegmentationSemantic SegmentationSimilar Papers 제목 키워드 기반
Energy Efficient Edge Computing: When Lyapunov Meets Distributed Reinforcement Learning
In this work, we study the problem of energy-efficient computation offloading enabled by edge computing. In the considered scenario, multiple users simultaneously compete for limited radio and edge computing resources to…
CPUEdge-computingMulti-agent Reinforcement Learningreinforcement-learning+4DNN Partitioning, Task Offloading, and Resource Allocation in Dynamic Vehicular Networks: A Lyapunov-Guided Diffusion-Based Reinforcement Learning Approach
The rapid advancement of Artificial Intelligence (AI) has introduced Deep Neural Network (DNN)-based tasks to the ecosystem of vehicular networks. These tasks are often computation-intensive, requiring substantial comput…
Deep Reinforcement LearningEdge-computingData-Driven Online Resource Allocation for User Experience Improvement in Mobile Edge Clouds
As the cloud is pushed to the edge of the network, resource allocation for user experience improvement in mobile edge clouds (MEC) is increasingly important and faces multiple challenges. This paper studies quality of ex…
Online Client Scheduling and Resource Allocation for Efficient Federated Edge Learning
Federated learning (FL) enables edge devices to collaboratively train a machine learning model without sharing their raw data. Due to its privacy-protecting benefits, FL has been deployed in many real-world applications.…
Federated LearningSchedulingStochastic OptimizationA Reinforcement Learning Formulation of the Lyapunov Optimization: Application to Edge Computing Systems with Queue Stability
In this paper, a deep reinforcement learning (DRL)-based approach to the Lyapunov optimization is considered to minimize the time-average penalty while maintaining queue stability. A proper construction of state and acti…
Deep Reinforcement LearningEdge-computingreinforcement-learningReinforcement Learning+1