A computational offloading optimization scheme based on deep reinforcement learning in perceptual network

Abstract

Currently, the deep integration of the Internet of Things (IoT) and edge computing has improved the computing capability of the IoT perception layer. Existing offloading techniques for edge computing suffer from the single problem of solidifying offloading policies. Based on this, combined with the characteristics of deep reinforcement learning, this paper investigates a computation offloading optimization scheme for the perception layer. The algorithm can adaptively adjust the computational task offloading policy of IoT terminals according to the network changes in the perception layer. Experiments show that the algorithm effectively improves the operational efficiency of the IoT perceptual layer and reduces the average task delay compared with other offloading algorithms.

Optimization Mobility in Sensor Actor Networks: A Comprehensive Framework

“…Wu et al's [19] thorough analysis of the technology of digital twins covers data, models, relationships, and applications from the standpoint of the entire process. Although not specifically aimed at sensor-actor networks, the research offers valuable perspectives on the comprehensive incorporation of digital twin notions, potentially yielding benefits for improving the design and simulation of elements of sensor-actor systems.A deep reinforcement learning-based computational dumping optimization scheme for perceptual networks is presented by Xing et al [20]. By addressing the difficulties in maximizing computations in perceptual networks, this work advances our knowledge of how machine learning methods can improve sensor-actor systems' efficiency.A thorough overview of the development of wireless networks, from 5G to beyond, is provided by Ali et al [22].…”