近年来不断增多的强台风天气给沿海及部分内陆地区配电网带来了愈发严重的损失,造成大规模重要负荷长时间失电,提高含多元源荷的主动配电网恢复能力成为亟待解决的问题。针对现有配电网负荷损失评估方法在强台风弱通信条件下无法准确获取节点信息而造成灾损分析精度不高的问题,提出一种基于Transformer深度学习网络的主动配电网多元源荷灾损辨识方法,充分利用深度学习网络去模型化的特点并发挥其在灾损预测精度方面的优势。考虑地面粗糙程度和高度,结合弱通信条件下的台风灾害气象数据,构建主动配电网所处地理环境的风速、降雨强度等气象信息修正模型;在此基础上考虑强台风致灾机理和主动配电网拓扑结构,利用Transformer深度学习方法构建配电网灾损辨识模型,实现强台风弱通信条件下的主动配电网多元源荷灾损辨识精度提升。通过对改进的IEEE 33节点主动配电网算例进行仿真测试,对损失负荷、损坏节点数等特征量进行计算,验证了所提主动配电网多元源荷灾损辨识方法能够满足台风多发配电网灾损评估精度。

In recent years, the increasing strong typhoon weather has brought more and more serious losses to the distribution network in coastal and some inland areas, resulting in large-scale power loss of important load for a long time. Improving the recovery capacity of active distribution networks containing multiple sources and loads has become an urgent problem to be solved. To deal with the problem that the existing power outage evaluation methods of distribution networks failed to obtain the information of the nodes, this paper proposes a novel evaluation method of power outage in active distribution networks containing multiple sources and loads on the basis of deep learning method, such as the Transformer model. Considering the ground roughness and height, meteorological information correction model of the geographical environment of the active distribution network is constructed combined with the typhoon disaster meteorological data under the condition of weak communication. On this basis, considering the disaster mechanism of strong typhoons and the topology of active distribution networks, the Transformer model is used to construct the power outage model of active distribution networks to improve the accuracy of power outage evaluation in active distribution networks containing multiple sources and loads. Through the simulation tests of the improved IEEE 33-node active distribution network, it is verified that the proposed power outage evaluation method for active distribution networks can meet the accuracy requirement of power outage evaluation in typhoon-prone distribution networks.

直流输电线路发生早期绝缘故障时电流波动小、故障现象不明显,难以快速识别以采取保护措施,光伏电站线路拓扑结构复杂,不易准确定位故障发生位置。该文提出一种连续小波变换和混合神经网络模型结合的方法,可在尽可能短的时间完成故障识别与定位。该方法首先利用连续小波变换对暂态零模电流信号提取二维时频矩阵特征,压缩为彩色图像;然后,将图像送入神经网络模型中进行训练。该混合神经网络模型通过结合卷积神经网络和门控循环单元,提高识别精度并减少训练时间。最后,为验证本方法的优势,在高噪声环境下选取4条直流输电线路分别进行4种时频分析方法、3种神经网络模型仿真对比后,又对早期绝缘故障单独进行识别仿真试验,结果表明该方法可有效识别出早期绝缘故障并定位至发生线路,且具有较强的抗噪能力。

When an early insulation fault occurs in a DC transmission line, the current fluctuation is small and the fault phenomenon is not obvious, so it is difficult to quickly identify and take protective measures. The topology of the photovoltaic power station line is complex, and it is difficult to accurately locate the fault location. In this paper, a method combining continuous wavelet transform and hybrid neural network model is proposed to identify and locate faults in the shortest possible time. The method first uses continuous wavelet transform to extract two-dimensional time-frequency matrix features from the transient zero-mode current signal, compresses it into a color image, and then sends the image to a neural network model for training. This hybrid neural network model improves recognition accuracy and reduces training time by combining convolutional neural networks and gated recurrent units. Finally, in order to verify the advantages of this method, four HVDC transmission lines are selected in a high noise environment to carry out four time-frequency analysis methods and three neural network model simulation comparisons, and then a separate simulation test is carried out to identify early insulation faults. The results show that this method can effectively identify the early insulation fault and locate the line where it occurs, and has strong anti-noise ability.