Edgerl: Reinforcement Learning-driven Deep Learning Model Inference Optimization At Edge

Abstract

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.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keymounesan2024edgerl

Related papers

• To Train Or Not To Train: Balancing Efficiency And Training Cost In Deep Reinforcement Learning For Mobile Edge Computing (2024)0.00
• Deep Reinforcement Learning At The Edge Of The Statistical Precipice (2021)0.00
• Co-adaptation Of Algorithmic And Implementational Innovations In Inference-based Deep Reinforcement Learning (2021)0.00
• Edge-compatible Reinforcement Learning For Recommendations (2021)0.00
• Reducing The Deployment-time Inference Control Costs Of Deep Reinforcement Learning Agents Via An Asymmetric Architecture (2021)0.00
• Maximizing The Promptness Of Metaverse Systems Using Edge Computing By Deep Reinforcement Learning (2025)0.00
• SEED RL: Scalable And Efficient Deep-rl With Accelerated Central Inference (2019)0.00
• Digital Twin-assisted Efficient Reinforcement Learning For Edge Task Scheduling (2022)9.23