Solar-powered Parking Analytics System Using Deep Reinforcement Learning

Abstract

Advances in deep vision techniques and the ubiquity of smart cameras will drive the next generation of video analytics. However, video analytics applications consume vast amounts of energy as deep learning techniques are power-hungry. In this article, we focus on a parking video analytics platform and propose RL-CamSleep, a deep reinforcement learning-based technique, to actuate the cameras to reduce the energy footprint while retaining the system’s utility. Our key insight is that many video-analytics applications do not need to be always operational, and we can design policies to activate video analytics only when necessary. We design two modes of operation for the reinforcement learning (RL) controller: (i) cloud-based mode and (ii) grid-isolated solar-powered mode. In the cloud-based mode, the controller runs on the cloud to control the cameras, whereas, in the solar-powered mode, the RL controller is constrained by the energy produced by solar. We evaluate our approach on a city-scale parking dataset having 76 streets spread across a city. Our analysis shows RL-CamSleep can learn an adaptive policy that reduces the average energy consumption by 76% and achieves an average accuracy of 98%. For the grid-isolated mode, RL-CamSleep outperforms other baseline techniques demonstrating the need for adaptive policy in energy-constrained environments.