Phasic Policy Gradient Based Resource Allocation for Industrial Internet\n of Things

2021/12/02 by Lokesh Bommisetty, Bommisetty, Lokesh, TG Venkatesh +1
Computer Science · Engineering · #FOS: Computer and information sciences #Networking and Internet Architecture (cs.NI) #Smart Grid Security and Resilience #Wireless Body Area Networks #Wireless Networks and Protocols

paper · pdf · doi:10.48550/arxiv.2112.01361

openalex publication_date 2021/12/02 · openalex created_date 2022/11/14 · openalex updated_date 2026/07/28

Abstract

Time Slotted Channel Hopping (TSCH) behavioural mode has been introduced in\nIEEE 802.15.4e standard to address the ultra-high reliability and ultra-low\npower communication requirements of Industrial Internet of Things (IIoT)\nnetworks. Scheduling the packet transmissions in IIoT networks is a difficult\ntask owing to the limited resources and dynamic topology. In this paper, we\npropose a phasic policy gradient (PPG) based TSCH schedule learning algorithm.\nThe proposed PPG based scheduling algorithm overcomes the drawbacks of totally\ndistributed and totally centralized deep reinforcement learning-based\nscheduling algorithms by employing the actor-critic policy gradient method that\nlearns the scheduling algorithm in two phases, namely policy phase and\nauxiliary phase.\n

Related

• HRL-TSCH: A Hierarchical Reinforcement Learning-based TSCH Scheduler for IIoT
• A Deep Reinforcement Learning based Scheduler for IoT Devices in Co-existence with 5G-NR
• A Practical AoI Scheduler in IoT Networks with Relays
• Intent-Aware DRL-Based NOMA Uplink Dynamic Scheduler for IIoT
• GT-TSCH: Game-Theoretic Distributed TSCH Scheduler for Low-Power IoT Networks