The measurement error evaluation of power metering equipment (PME) is significant for the instrument design and accurate metering of electric energy, especially under extreme environmental stresses. However, actual measurement error assessment is often disturbed by the environmental noise and insufficient input information. To address this problem, an improved local outlier factor (ILOF) method is first presented to detect potential outliers. And an optimized distance function and adaptive threshold constraint method based on box plot are used to improve the outlier detection performance of ILOF. Next, an error prediction method, namely kernel support vector regression (KSVR), is presented to fuse measurement error and multiple extreme environmental stresses by using the proposed kernel approach. Integrating the ILOF and KSVR, examples from the extreme environmental region demonstrate that the proposed evaluation framework has a higher assessment performance. Compared with several state-of-art prediction methods, our framework has profound outlier identification and error prediction performance under small sample conditions.

The continuous increase of renewable energy installation in the power system such as roof-PV systems decreases the system inertia. It is a non-negligible challenge to the system's operation stability. In addition, with the increasing number of cyber attack events reported globally, the operation of the roof-PV systems may threaten their connected AC system operation during the contingency. Utilizing the grid-connected converters (GCCs), its fast regulating characteristic could rapidly increase or decrease the solar generation output in seconds, which will bring significant influences to the system operation once the cyber attack happens, especially if the system has integrated high proportional renewable energies. This paper proposed a cyber-attack detection model to solve this problem to eliminate its effect on the roof-PV generation system. In this model, the synchrosqueezed wavelet transforms (SWT) are first applied to extract the time-frequency information of frequency measurement. Then a recurrent layer aggregation-based convolutional neural network is introduced to identify the features of cyber attacks using the results from SWT. The comparison experiments indicate that the proposed model has profound performance on the detection accuracy of the roof-PV generation system for cyber attack detection.

Operational status evaluation (OSE) is essential for the health management of smart electricity meters (SEM). This article develops a machine learning-enabled OSE method for SEM. Specifically, the Gaussian process regression (GPR) is developed for modeling analysis, where an optimized automatic relevance determination (OARD) kernel is first used. Though the conventional ARD kernel structure can capture the potential mapping relationship between running time, temperature, humidity, and measurement error (ME), it cannot extract the influence degree of different stresses on the ME. To address this problem, an OARD kernel structure is proposed to identify the contribution of each part in ARD structure to the target data. Furthermore, the quartiles line instead of 95% confidence interval is exploited to enhance the performance of GPR for long-term prediction. Combining the two above improvements, a novel OSE model is established for the future-oriented long-term operation of the SEM. It is the first-known data-driven application that utilizes the GPR with OARD kernel to perform OSE for SEM. Actual SEM datasets collected from both dry and hot region are used for model validation and prediction. The results demonstrate that the proposed GPR model with OARD Matern52 kernel outperforms other conventional kernel approaches in the aspect of interpretability. More importantly, the operational status of the SEM in future can be assessed via the proposed OSE framework.

This paper presents a novel Bayesian inference method based on Phasor Measurement Unit (PMU) data for identifying power system oscillation parameters. By leveraging synchronized data, the proposed method captures the dynamic behavior of power system in real-time. The approach integrates Variational Mode Decomposition (VMD) and Fast Fourier Transform (FFT) to efficiently separate and identify oscillation modes, which enhances the initial setup for Bayesian inference. Using No-U-Turn Sampler (NUTS) sampling, the method estimates the modal parameters, including amplitude, damping factor, and frequency, while quantifying their uncertainties. Validations with both simulated and real power system data demonstrate that the proposed method effectively identifies oscillation parameters with high accuracy. This work provides a robust tool for the real-time monitoring and dynamic analysis of power system oscillations, offering improvements in accuracy and responsiveness over traditional methods.

Accurate reliability and residual life analysis is paramount during the designing of reliability requirements and rotation of power measuring equipment (PME). However, the sample dataset of failure is usually sparse and contains inevitable pollution data, which has an adverse effect on the reliability analysis. To tackle this issue, this paper first applies nonlinear regression to fuse the failure rate and environmental features of PME collected from various locations. Then, a novel binary hierarchical Bayesian probability method is proposed to model the failure trend and identify outliers, in which the outlier identification structure is embedded into hierarchical Bayesian. Integrating binary hierarchical Bayesian and the bagging method, a binary hierarchical Bayesian with bagging (BHBB) framework is further introduced to improve predictive performance in a small sample dataset by resampling. Last, the influence of typical environmental features, failure rate, and reliability are obtained by the BHBB under the real sample dataset from multiple typical locations. Experiments show that our framework has superior performance and interpretability comparing with other typical data-based approaches.

With widespread deployments of phasor measurement units (PMUs) in power systems, the localization of power oscillations using synchrophasor measurements has become feasible. However, the classical method for source localization, known as the energy-based method, is significantly impacted by noise and other irrelevant frequency components, which are common in synchrophasor measurements. In response to this challenge, the paper proposes an adaptive Vold-Kalman filtering-based Energy method (A-VKF-Energy). Initially, the Fast Fourier Transform is employed to identify oscillation frequency in active power, offering a reference for subsequent component extraction. The Adaptive Vold-Kalman filtering is then utilized to extract oscillation components from PMU data, which are subsequently employed in computing dissipating energy for each branch. Moreover, the slope ratio of the energy is employed as an indicator of the energy flow direction in the power system, automating the process of determining the source of oscillations. The superior performance of adaptive Vold-Kalman filtering in frequency coupling is verified by simulated experiments. Furthermore, simulation using WECC 179 test case data and actual experiments using a real oscillation event are carried out to verify the effectiveness of proposed method. The results reveal that A-VKF-Energy method can successfully identify oscillation sources.