An online, data-driven algorithm for tracking voltage sensitivity in active distribution networks is presented. This algorithm, based on power flow analysis and recursive least squares with a forgetting factor (FFRLS), extracts voltage sensitivity from measurement data. Its adaptive nature ensures accuracy despite changing operating conditions. Outlier mitigation with the Isolation Forest algorithm enhances the methods reliability. Simulation results on a 33-node test system validate the approachs effectiveness.

The accuracy and reliability of the Q/V sensitivity for voltage security assessment is influenced by the outliers present in the calculation results. An unsupervised machine learning approach, empirical- cumulative- distribution- based outlier detection (ECOD), is introduced in this letter to detect and eliminate outliers to address this issue. A comparison of the results with those of the proposed approaches on the standard test power system CSEE-VS demonstrate that, compared with advanced outlier detection algorithms, ECOD can eliminate outliers from the Q/V sensitivities with higher accuracy and less computation time and realize online voltage security assessment with superior accuracy and reliability.

Reliable and accurate extraction of ambient modes is an essential means of assessing the safety and stability of smart grids. While previous works have mainly concentrated on the introduction of novel identification tools. In this paper, the isolation forest ( iForest ) was presented to build an intelligent ambient mode extraction scheme with high reliability, which aims at detecting and eliminating abnormal ambient modes from extracted results. As the core technology of the proposed intelligent scheme, iForest exploits the concept of isolation and intends to combine the features of the outliers, which are ‘few’ and ‘different’, with the technique of ensemble learning to isolate them precisely. And the abnormal modes can be eliminated according to their anomaly scores in the proposed intelligent ambient mode extraction scheme. The evaluation of the proposed scheme is carried out through the database constructed by an IEEE 16-generator system and a real power system, the results of which indicate that the proposed scheme is intelligent enough to deal with a large amount of data with high accuracy and improve the reliability of existing identification tools.

The data-driven method for security monitoring is promising for power system voltage stability estimation, whereas the reliability of such method is greatly affected due to the generalizability weakened by operational variability. In this article, a mechanism knowledge enhanced machine learning method for load margin estimation is established by integrating power system mechanism into intelligent neural network (NN) model. Firstly, the correlation between the load power factor and load margin explored from curve P-V were analyzed, from which the mechanism knowledge of voltage stability is extracted. Then, the mathematical logical representation of mechanism knowledge is given, which was further integrated into the loss function of the NN model. The proposed enhanced model constrains the NN model to provide mechanistically consistent results, as well as helps achieve an excellent generalizability performance. The effectiveness of the proposed method is verified by numerical simulations using the IEEE 39-bus test system and the IEEE 145-bus test system, the results of which shows that the generalization ability of the enhanced NN is significantly improved with the proposed method, thus the accuracy, reliability and robustness of the load margin estimation are greatly enhanced.

Synchrophasor-based sub-synchronous oscillation (SSO) parameter identification is effective for monitoring SSOs, while its performance can be significantly affected by measurement noise, posing serious challenges to reliable identification. This study proposes an improved identification scheme that combines adaptive empirical Fourier decomposition (AEFD) with the Prony method to enable accurate and simultaneous estimation of sub/super-synchronous modes. First, the AEFD method is applied to oscillation signals, effectively decomposing the signals into sub-synchronous and super-synchronous modal components. Particularly, the sparsity index (SI) is introduced to determine the number of oscillation modes contained in the signal. Subsequently, the Prony method is employed on the decomposed components to extract modal parameters. The proposed method effectively suppresses modal aliasing and improves noise robustness of the empirical wavelet transform by employing an improved spectrum segmentation technique and a zero-phase filter bank, thereby enhancing the extraction accuracy of the estimation results. Through comparisons with existing methods and simulated case studies, it is verified that the proposed method performs exceptionally well in terms of accuracy, mode mixing suppression and noise robustness, demonstrating its superiority and effectiveness in the extraction of sub/super-synchronous oscillation parameters.

Traditional load margin estimation approaches, which require a retraining process under dynamic operation variation with increasing uncertainties and consuming excessive time, are insufficient to guarantee the smart grid operates in a stable region. To address this challenge, this article proposes an incremental learning-enhanced LightGBM (IL-LightGBM) method for online load margin estimation utilizing synchronized measurement data. As the key to achieving accurate load margin estimation using the LightGBM algorithm under operation variations, the weight parameters of the pre-trained model are updated online by IL technique through efficiently digesting synchrophasor measurements. The proposed method makes full use of the capability of LightGBM to handle massive measurements, while effectively improving the adaptability to large-scale operational variability. Case studies to evaluate the proposed approach are presented through the numerical simulations of the IEEE 39-bus test system and a larger IEEE 145-bus power system, demonstrating the effectiveness and robustness of the proposed method.