为了解决利用传统频率分析方法分析新能源高占比电网频率时存在计算量大、建模困难、计算速度与计算精度矛盾突出等问题,提出一种基于卷积神经网络(CNN)的新型电力系统频率特性预测方法.首先,利用一维CNN对新能源高占比电力系统在功率扰动下的主要频率指标进行预测,包括初始频率变化率、频率极值以及频率稳态值;并通过设置合理的输入特征以及对神经网络各参数的优化调整,提高了预测精度.在此基础上,进一步考虑扰动位置以及扰动类型的影响,利用数据降维的方法建立包含扰动信息的电力系统特征数据集,借鉴三原色通道原理构建输入特征,并利用扩展的二维CNN预测频率安全指标提高CNN在高占比新能源电网频率分析中的适应性.最后,在改进的BPA 10机39节点模型中进行算例验证,并与循环神经网络预测结果进行对比,结果表明所提方法具有较高的准确度和适应性.

In order to solve the problems existing in the traditional frequency analysis method for the frequency analysis of grids with a high proportion of new energy, such as the large amount of calculation, the difficulty of modeling, and the prominent contradiction between the calculation speed and the calculation accuracy, this paper proposes a new frequency characteristic prediction method for the new power system based on convolutional neural network (CNN). First, the main frequency indexes of the power system with a high proportion of new energy under power disturbances are predicted using one-dimensional CNN, including the initial frequency change rate, frequency extremum, and frequency steady-state value. The prediction accuracy is improved by setting reasonable input characteristics and optimizing the parameters of the neural network. Then, the impact of disturbance location and disturbance type is further considered, and the power system characteristic data set containing disturbance information is established by the method of data dimensionality reduction. The input characteristics are constructed by using the principle of three primary channels for reference, and the extended two-dimensional CNN is used to predict the frequency security index, which improves the adaptability of CNN in the frequency analysis of grids with a high proportion of new energy. Finally, the method is verified by an example in the improved BPA 10-machine 39-node model, and the results are compared with the prediction results of the recurrent neural network, which proves that the proposed method has a high accuracy and adaptability.