End-to-End Delay Minimization for IPv6 Power Communication Networks Based on Deep Deterministic Policy Gradient
TL;DR
An end-to-end delay minimization method for IPv6 power communication networks based on Deep Deterministic Policy Gradient (DDPG) is proposed to address the problems of poor dynamic adaptability, low efficiency in high-dimensional resource optimization, and insufficient convergence of delay in complex business scenarios in existing delay optimization methods.
Abstract
The IPv6 power communication network is the core infrastructure supporting smart grid dispatch and control, data transmission, and business linkage. In this environment, substations, distributed-energy devices, and edge terminals use IPv6 for unified addressing and end-to-end interconnection, while Traffic Class and Flow Label provide network-layer identifiers for differentiated services and flow-level scheduling. End to end latency is the core indicator for measuring the quality of power communication services, which directly affects the safe and stable operation of key power services such as relay protection, remote measurement and control, and fault alarm. This paper proposes an end-to-end delay minimization method for IPv6 power communication networks based on Deep Deterministic Policy Gradient (DDPG) to address the problems of poor dynamic adaptability, low efficiency in high-dimensional resource optimization, and insufficient convergence of delay in complex business scenarios in existing delay optimization methods. The protocol-aware MDP represents address prefixes, Traffic Class, Flow Label, link load, queue state, and current route information, and jointly adjusts bandwidth share, route weight, and queue service ratio. Thus, IPv6 fields participate directly in differentiated delay control rather than serving only as packet-header descriptions.