自适应与多目标优化的VSG低频振荡TD3控制策略

打开文本图片集

中图分类号：TM734；TP18 文献标志码：A 文章编号：1008-0562（2026）01-0098-09

Control strategy for low-frequency oscillation of VSG based on adaptive and multi-objective optimization with TD3

LI Yonggang， ZHOU Heran*， ZHOU Yichen， WEI Fanchao （StateKeyLaboratoryofAlternate ElectricalPower System withRenewable Energy Sources （North China ElectricPowerUniversity），BaodingO71oo3，China）

Abstract：Aiming at the low-frequency oscilation problem frequently occurring in the weak grid connected with virtual synchronous generator （VSG），an intelligent control method for VSG is proposed，which integrates dynamic inertia-damping cooperative adjustment and multi-modal twin delayed deep deterministic policy gradient algorithm.An enhanced VSG model including dynamic inertia-damping adjustment mechanism is constructed.Based on thereal-time monitoring of the standard deviation and change rate offrequency fluctuation， a continuous parameter adaptive algorithm is designed to realize the dynamic cooperative optimization of the inertia constant H and the damping coefficient D .The oscillation-aware deep deterministic policy gradient algorithm（TD3）is designed.The dual-state experience replay buffer structure is adopted to embed the lowfrequency oscilation feature vector into the training samples，and a multi-objective reward function including frequency deviation penalty，voltage oset suppression and oscilation energy constraint is constructed.The simulation and actual case results show that the strategy can realize the online fast and accurate evaluation of VSG low-frequency oscilation， enhance the system damping and inertia，reduce the low-frequency oscilation risk， and improve the system stability.

Keywords：virtual synchronous generator;low-frequencyoscillation suppression;damping coefficient; dynamic inertia adjustment; twin delayed deep deterministic policy gradient algorithm

0 中 引言

随着高比例新能源和电力电子设备接人电力系统1，传统火电主导的电力系统正加速向新型电力系统转型[2]。（剩余14976字）