基于长短期记忆神经网络的检修态电网暂态稳定评估方法  

Assessment method of transient stability for maintenance power system based on long short term memory neural network

作　　者：王步华 朱劭璇 熊浩清 谢岩 李晓萌 WANG Buhua;ZHU Shaoxuan;XIONG Haoqing;XIE Yan;LI Xiaomeng(State Grid He’nan Electric Power Company,Zhengzhou 450052;China Electric Power Research Institute,Beijing 100192;Electric Power Research Institute of State Grid He’nan Electric Power Company,Zhengzhou 450052)

机构地区：[1]国网河南省电力公司,郑州450052 [2]中国电力科学研究院有限公司,北京100192 [3]国网河南省电力公司电力科学研究院,郑州450052

出　　处：《电气技术》2023年第1期29-35,43,共8页Electrical Engineering

基　　金：国网河南省电力公司科技项目(5217022000A8)。

摘　　要：随着电网规模不断扩大,电力元件持续增多,电力系统检修方式日趋复杂,仅依靠传统方法难以对海量检修方式下电网的暂态稳定风险进行评估。针对此问题,提出一种基于长短期记忆(LSTM)神经网络的检修态电网暂态稳定风险评估方法。首先提出电力系统检修方式的统一编码方法,使计算机能够快速、准确识别电网在各种检修方式下的运行状态,然后建立长短期记忆神经网络并基于大量检修态电网故障样本对网络进行训练,最终实现对不同检修方式下电网暂态稳定程度的准确评估。最后,以华中地区某省级电网为算例,验证了所提方法的准确性。With the expansion of power grid scale and the increase of power components, the maintenance methods of power system become more and more complex. It is difficult to evaluate the transient stability risk of power grid under massive maintenance only by traditional methods. To solve this problem, a risk assessment method of transient stability in maintenance power network based on long short term memory(LSTM) neural network is proposed. Firstly, the unified coding method of power system maintenance mode is proposed, so that the computer can quickly and accurately identify the operation state of power grid under various maintenance modes. Then, a long short term memory neural network is established and trained based on a large number of fault samples of the power grid under maintenance. After that, the accurate evaluation of the power grid transient stability under different maintenance modes is realized. Finally, a regional power grid in Central China is taken as an example to verify the accuracy of the proposed method.

关 键 词：电力系统 检修方式 暂态稳定 长短期记忆(LSTM) 神经网络 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TM712[自动化与计算机技术—控制科学与工程]