Research on the detection and identification of anomalies in electric power systems is crucial for ensuring their secure and stable operation. Anomaly detection models based on Support Vector Machines (SVMs) effectively process high-dimensional data while maintaining strong generalization capabilities. However, the performance of SVMs significantly depends on the choice of parameters, where improper parameter settings can lead to overfitting or underfitting, consequently decreasing the accuracy of anomaly detection. Furthermore, the dimensions of anomaly data in electric power systems are often unknown, making it difficult for existing methods to maintain a high precision in multidimensional data detection, and the segmentation of such data lacks intuitive display. In response, this article proposes an improved SVM model for electric power system anomaly detection, enhanced by parameter optimization algorithms, alongside a method for nonlinear dimension reduction and visualization using t-Distributed Stochastic Neighbor Embedding (t-SNE). Initially, traditional SVM parameters are optimized using the following four algorithms: Grid Search (GS), Particle Swarm Optimization (PSO), Genetic Algorithms (GAs), and Artificial Bee Colony (ABC) algorithms, in order to establish the optimized SVM model for electric power system anomaly detection. Finally, the effectiveness of the proposed method is verified through simulations. The simulation results indicate that, in the IEEE-14 node system case study, the accuracy for normal data reaches 97.58%, the accuracy for load step change detection reaches 99.52%, the accuracy for bad data detection reaches 99.92%, and the accuracy under fault conditions reaches 100%.

Coordinating various controllable distributed resources to reduce network losses is crucial to the secure and economical operation of modern power systems. This paper proposes a bi-level optimization model for power system loss reduction based on “source-grid-load-storage” coordinated optimization. The upper level aims to minimize the total annual planning cost of the system, determining the location and capacity of distributed photovoltaic systems, energy storage devices, and electric vehicle charging stations. The lower level aims to minimize the load curve smoothness and node voltage deviation of the distribution network, optimizing intraday operation strategies. For this complex optimization problem, this paper designs a particle swarm optimization (PSO) algorithm with adaptive weights and improved evolutionary strategies. The simulation results of case studies demonstrate that the proposed method has significant loss reduction effects in distribution networks of various scales and complexities. The algorithm performance comparison results show that the improved particle swarm algorithm outperforms traditional algorithms in terms of solution quality and computational efficiency, providing an effective solution for the coordinated optimization of “source-grid-load-storage”.

Permanent Magnet Synchronous Motors (PMSMs) have been widely applied across various electrical systems due to their significant advantages, including high power density, high-efficiency conversion, and easy controllability. However, the issue of ‘parameter asymmetry’ (a mismatch between the controller’s preset parameters and the actual system parameters) in PMSMs can lead to performance problems, such as delayed speed response and increased overshoot. The destruction of symmetry, including the asymmetric weight distribution between new and old data in the moment-of-inertia identification algorithm and the asymmetry between “measured values and true values” caused by sampling delay, is the core factor limiting the system’s control performance. All these factors significantly affect the accuracy of parameter identification and the system’s stability. To address this, this study focuses on the mechanical parameter identification of PMSMs with the core goal of “symmetric matching between set values and true values”. Firstly, a current-speed dual closed-loop vector control system model is constructed. The PI parameters are tuned to meet the symmetric tracking requirements of “set value-feedback” in the dual loops, and the influence of the PMSM’s moment of inertia on the loop symmetry is analyzed. Secondly, the symmetry defects of traditional algorithms are highlighted, such as the imbalance between “data weight and working condition characteristics” in the least-squares method and the mismatch between “set inertia and true inertia” caused by data saturation. Finally, a Forgetting Factor Recursive Least Squares (FFRLS) scheme is proposed: the timing asymmetry of signals is corrected via a first-order inertial link, a forgetting factor λ is introduced to balance data weights, and a recursive structure is adopted to avoid data saturation. Simulation results show that when λ = 0.92, the identification accuracy reaches +5% with a convergence time of 0.39 s. Moreover, dynamic symmetry can still be maintained under multiple multiples of inertia, thereby improving identification performance and ensuring symmetry in servo control.

With the trend toward miniaturization and high integration in urban distribution networks, the thermal management of three-phase voltage-source converter (VSC) faces severe challenges due to high switching frequency and power loss-driven junction temperature (T_j) fluctuations. Traditional discontinuous pulse width modulation (DPWM) strategies often suffer from a misalignment between clamping windows and peak current regions under non-unity power factor conditions, leading to suboptimal cooling performance. This paper proposes an improved DPWM strategy with two-degree-of-freedom (2-DOF) adjustment characteristics. By introducing the clamping width angle ψ and the offset angle δ as independent control variables, the proposed strategy enables flexible reshaping of the power device commutation logic. An adaptive phase compensation mechanism is established to ensure the clamping window tracks the load current peaks in real-time, effectively maximizing switching loss suppression. Furthermore, the variable ψ provides a quantitative trade-off between conversion efficiency and total harmonic distortion (THD). The proposed algorithm is based on instantaneous logic judgment with low computational overhead, making it suitable for digital control platforms. Simulation results obtained from the PLECS electro-thermal coupling platform verify that the proposed strategy reduces the average junction temperature by approximately 10.3°C compared to traditional 30° DPWM while maintaining a low THD of 3.08%. The research demonstrates that the 2-DOF regulation mechanism successfully achieves collaborative optimization of thermal reliability and power quality.

Artificial intelligence technologies provide efficient technical support for transient stability assessment (TSA) in power systems. However, the accuracy of TSA is severely affected by two issues: the scarcity of unstable samples in practical power grids and the insufficient learning capability of models in high-dimensional feature spaces. To address these issues, this paper proposes a method for Transformer-based TSA of power systems under sample imbalance conditions. First, a feature dimensionality reduction method using t-distributed stochastic neighbor embedding (t-SNE) with sparsity weights is employed to identify sparsely distributed unstable samples. Gaussian perturbations are then applied to these sparse unstable samples to generate new samples, thereby augmenting the training dataset. Second, a two-stage feature selection process based on random forest (RF) is employed to screen high-dimensional sample features, retaining the key features that contribute significantly to the TSA task and thereby reducing the feature dimensionality. Finally, a TSA model is constructed based on the RF-Transformer framework, in which the feature importance information provided by RF is incorporated into the attention mechanism of the Transformer to enhance the model’s ability to learn the key operating features of the power system. The effectiveness of the proposed method is validated using a simplified provincial power system in China, the IEEE 39-bus system, and the Northwest China power grid as case studies.

With the rapid development of new energy, high-proportion new energy power systems have significantly reduced inertia and voltage support capacity, facing severe stability challenges. Virtual Synchronous Generator (VSG) control, which simulates the inertia and voltage source characteristics of traditional synchronous generators, enables friendly grid connection of new energy converters and has become a key technology for large-scale new energy applications. This paper addresses two key issues in low-voltage ride through (LVRT) of grid-forming converters under VSG control: (1) converter overcurrent suppression during LVRT; (2) reduced reactive power support due to retaining voltage-reactive power droop control during faults. It proposes an adaptive virtual impedance-based overcurrent suppression method and a frozen reactive power–voltage droop-based reactive support method. Based on the converter’s mathematical model, a DIgSILENT/PowerFactory simulation model is built. Time-domain simulations verify the converter’s operating characteristics and the improved LVRT strategy’s effect, providing theoretical and technical support for large-scale applications of grid-forming converters.