AoI-aware energy control and computation offloading for industrial IoT

Abstract

In Industrial Internet of Things (IIoT), a large volume of data is collected periodically by IoT devices, and timely data routing and processing are important requirements. Age of Information (AoI), which is a metric to evaluate the freshness of status information in data processing, has become one of the most important objectives in IIoT. In this paper, considering limited communication, computation and energy resources on IoT devices, we jointly study the optimal AoI-aware energy control and computation offloading problem within a dynamic IIoT scenario with multiple IoT devices and multiple edge servers. Based on extensive analysis of real-life IoT dataset, Markovian queueing models are constructed to capture the dynamics of IoT devices and edge servers, and their corresponding analyses are provided. With the quantitative analytical results, we formulate a dynamic Markov decision problem with the objective of minimizing the long-term energy consumption while satisfying AoI constraints for real-time data processing. To solve the problem, we apply Deep Reinforcement Learning (DRL) techniques for adapting to large-scale dynamic IIoT environments, and design an intelligent Energy Control and Computation Offloading (ECCO) algorithm. Extensive simulation experiments are conducted based on real-world dataset, and the comparison results illustrate the superiority of our ECCO algorithm over both existing DRL and non-DRL algorithms.