摘要
随着“双碳”目标的推进,随机波动的新能源接入电网的规模和容量日益提升,严重影响电网的安全稳定运行。针对大干扰故障电压稳定控制问题,文章提出了一种基于时序卷积残差网络和鹈鹕优化算法的新能源电网电压安全稳定控制策略。首先,利用时序卷积信息损失少、感受野宽以及残差网络深层特征提取能力强的优势,构建基于时序卷积残差网络的电压稳定预测模型,映射出敏感节点电压时序特征和电压稳定之间的关系;其次,构建电压稳定控制模型,利用鹈鹕优化算法收敛速度快、搜索能力强的优势求解控制模型,得出最佳切机和切负荷动作措施;最后,进行了仿真验证。验证结果表明,所提方法提高了新能源电网电压安全稳定预测的准确性,通过最佳的电压稳定控制策略提高了电网故障后的安全稳定运行水平。
With the advancement of the "dual carbon" goal,the scale and capacity of randomly fluctuating new energy connected to the power grid are increasingly increasing,seriously affecting the safe and stable operation of the power grid.This paper proposes a power grid voltage security and stability control strategy based on time series convolutional residual network and Pelican optimization algorithm for the problem of voltage stability control in large disturbance faults.Firstly,taking advantage of the advantages of low loss of temporal convolutional information,wide receptive field,and strong deep feature extraction ability of residual networks,a voltage stability prediction model based on temporal convolutional residual networks is constructed,mapping the relationship between sensitive node voltage temporal features and voltage stability;Secondly,a voltage stability control model is constructed to output control strategies,and the Pelican optimization algorithm is utilized to solve the control model with its fast convergence speed and strong search ability,resulting in the optimal measures for machine and load shedding actions.Finally,after simulation and verification,the experimental results show that the proposed method improves the accuracy of voltage safety and stability prediction in the power grid,and improves the safe and stable operation level of the power grid after faults through the optimal voltage stability control strategy.
作者
张建新
邱建
朱煜昆
朱益华
杨欢欢
徐光虎
涂亮
Zhang Jianxin;Qiu Jian;Zhu Yukun;Zhu Yihua;Yang Huanhuan;Xu Guanghu;Tu Liang(China Southern Power Grid Co.,Ltd.,Guangzhou 510663,China;National Key Laboratory of DC Transmission Technology(China Southern Power Grid Research Institute Co.,Ltd.),Guangzhou 510663,China;Guangdong Provincial Key Laboratory of Intelligent Operation and Control of New Energy Power System,Guangzhou 510663,China)
出处
《可再生能源》
CAS
CSCD
北大核心
2024年第6期845-852,共8页
Renewable Energy Resources
基金
南方电网公司重点科技项目(000000KK52210139)。
关键词
新能源
大干扰故障
时序卷积残差网络
鹈鹕优化算法
安全稳定控制
new energy
large interference fault
time series convolutional residual network
pelican optimization algorithm
security and stability control
