EdgeRL: Reinforcement Learning-driven Deep Learning Model Inference Optimization at Edge
This addresses the problem of efficient deep learning deployment at the edge for applications requiring real-time processing, though it is incremental as it applies an existing RL method to a known bottleneck.
The paper tackles the challenge of balancing latency, accuracy, and energy consumption for deep learning inference in edge environments by proposing EdgeRL, a reinforcement learning framework that optimizes runtime parameters, resulting in improvements in energy savings, accuracy, and latency reduction as evaluated on a real-world testbed.
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.