Using Deep Q-learning To Prolong the Lifetime of Correlated Internet of Things Devices

2019/02/07 by Jernej Hribar, Andrei Marinescu, Hribar, Jernej +5
Computer Science · #Age of Information Optimization #Context-Aware Activity Recognition Systems #Energy Efficient Wireless Sensor Networks #FOS: Computer and information sciences #Networking and Internet Architecture (cs.NI) #cs.NI

paper · pdf · doi:10.48550/arxiv.1902.02850

Under submission

arxiv created 2019/02/07 · openalex publication_date 2019/02/07 · arxiv updated 2019/02/11 · openalex created_date 2022/07/29 · openalex updated_date 2026/07/28

Abstract

Battery-powered sensors deployed in the Internet of Things (IoT) require energy-efficient solutions to prolong their lifetime. When these sensors observe a physical phenomenon distributed in space and evolving in time, the collected observations are expected to be correlated. We take advantage of the exhibited correlation and propose an updating mechanism that employs deep Q-learning. Our mechanism is capable of determining the frequency with which sensors should transmit their updates while taking into the consideration an ever-changing environment. We evaluate our solution using observations obtained in a real deployment, and show that our proposed mechanism is capable of significantly extending battery-powered sensors' lifetime without compromising the accuracy of the observations provided to the IoT service.

Citations

• Playing Atari with Deep Reinforcement Learning

Related

• Optimal Status Updates for Minimizing Age of Correlated Information in IoT Networks with Energy Harvesting Sensors
• Deep Reinforcement Learning for IoT Networks: Age of Information and Energy Cost Tradeoff
• Configuring Transmission Thresholds in IIoT Alarm Scenarios for Energy-Efficient Event Reporting
• Q-CSM: Q-Learning-based Cognitive Service Management in Heterogeneous IoT Networks
• Age-Aware Status Update Control for Energy Harvesting IoT Sensors via\n Reinforcement Learning