As electrical power networks transition towards net-zero emissions, accurate prediction of harmonics is crucial in ensuring the stability and reliability of the system. This paper presents a novel approach for probabilistic harmonic prediction in transmission networks with limited monitoring, utilizing sequential artificial neural networks (ANNs). The approach proposed a predicting process that incorporates both individual-order and total harmonic distortions (THD). The primary stage involves the development of an ANN model that predicts the individual-order harmonic distortions at buses connected with renewable generators and non-linear loads, leveraging their net power injections. In the subsequent stage, a sequential ANN model is constructed to estimate the probabilistic harmonic distortions at unmonitored buses by utilizing past harmonic measurements obtained from installed power quality monitors. To enhance the performance of the model, a sensitivity analysis was conducted to identify the key parameters that significantly affect accuracy, robustness, and reliability. The results affirm the effectiveness of the proposed methodology in accurately predicting harmonic propagations within power systems with limited monitoring. This capability proves valuable in identifying and mitigating potential harmonic issues, thereby aiding the development of future power networks.

中文翻译：

---

可再生能源发电稀疏监控输电网络中谐波失真的预测


随着电力网络向净零排放过渡，准确预测谐波对于确保系统的稳定性和可靠性至关重要。本文提出了一种利用顺序人工神经网络 (ANN) 在有限监控的输电网络中进行概率谐波预测的新方法。该方法提出了一种结合了单阶谐波失真和总谐波失真 (THD) 的预测过程。第一阶段涉及开发人工神经网络模型，该模型利用其净功率注入来预测与可再生发电机和非线性负载连接的总线上的单阶谐波失真。在后续阶段，构建顺序 ANN 模型，利用从已安装的电能质量监测器获得的过去谐波测量值来估计未监控母线的概率谐波失真。为了提高模型的性能，进行了敏感性分析，以确定显着影响准确性、鲁棒性和可靠性的关键参数。结果证实了所提出的方法在通过有限监测准确预测电力系统内谐波传播方面的有效性。事实证明，这一功能对于识别和减轻潜在的谐波问题非常有价值，从而有助于未来电力网络的发展。