EdgeRL: Reinforcement Learning-driven Deep Learning Model Inference Optimization at Edge
Balancing mutually diverging performance metrics, such as, processing latency, outcome accuracy, and end device energy consumption is a challenging undertaking for deep learning model inference in ad-hoc edge environments. In this paper, we propose EdgeRL framework that seeks to strike such balance by using an Advantage Actor-Critic (A2C) Reinforcement Learning (RL) approach that can choose optimal run-time DNN inference parameters and aligns the performance metrics based on the application requirements. Using real world deep learning model and a hardware testbed, we evaluate the benefits of EdgeRL framework in terms of end device energy savings, inference accuracy improvement, and end-to-end inference latency reduction.
Code (0)
등록된 구현이 없습니다.
Tasks
Deep LearningInference OptimizationReinforcement Learning (RL)Similar Papers 제목 키워드 기반
Lyapunov-Driven Deep Reinforcement Learning for Edge Inference Empowered by Reconfigurable Intelligent Surfaces
In this paper, we propose a novel algorithm for energy-efficient, low-latency, accurate inference at the wireless edge, in the context of 6G networks endowed with reconfigurable intelligent surfaces (RISs). We consider a…
CPUData CompressionDeep Reinforcement LearningEdge Classification+1RPRO: Ranked Preference Reinforcement Optimization for Enhancing Medical QA and Diagnostic Reasoning
Medical question answering requires advanced reasoning that integrates domain knowledge with logical inference. However, existing large language models (LLMs) often generate reasoning chains that lack factual accuracy an…
Reinforcement LearningQuestion AnsweringData-driven Dynamic Multi-objective Optimal Control: An Aspiration-satisfying Reinforcement Learning Approach
This paper presents an iterative data-driven algorithm for solving dynamic multi-objective (MO) optimal control problems arising in control of nonlinear continuous-time systems. It is first shown that the Hamiltonian fun…
Decision MakingReinforcement Learning (RL)In-Edge AI: Intelligentizing Mobile Edge Computing, Caching and Communication by Federated Learning
Recently, along with the rapid development of mobile communication technology, edge computing theory and techniques have been attracting more and more attentions from global researchers and engineers, which can significa…
Deep Reinforcement LearningEdge-computingFederated LearningReinforcement LearningData-Driven Estimation of Conditional Expectations, Application to Optimal Stopping and Reinforcement Learning
When the underlying conditional density is known, conditional expectations can be computed analytically or numerically. When, however, such knowledge is not available and instead we are given a collection of training dat…
Stochastic Optimization