Search

Machine learning approaches have exhibited high potential in power system transient stability assessment (TSA), yet their initial preparation stages of stability knowledge base generation (SKBG) based on time-domain simulations often undergo high computational costs. In fact, how to ease the heavy computational burden of SKBG without sacrificing the reliability is still a significant challenge. To address this problem, this paper develops a semi-supervised ensemble learning (SSEL) framework for reliable SKBG acceleration, without additional need for computing hardware upgrading. In particular, it performs detailed simulations for a minority of cases and fast simulations for the majority ones to reduce the total computation time. Considering the absence of stability status information of those fast simulated cases, an SSEL scheme is systematically designed to reliably label their stability status. Before implementing SSEL, two concise feature descriptors are first introduced to efficiently extract transient features from multiplex system trajectories. Then, all the cases are characterized in a unified feature space, whereby a series of semi-supervised support vector machines are trained in randomly formed subspaces. Afterward, these single machines are systematically combined to derive an enhanced SSEL model, which is able to make reliable and robust labeling decisions. Further, a backtrace strategy is carefully devised for SSEL, so as to maintain the high reliability of SKBG. Test results on the IEEE 39-bus system and the realistic GD Power Grid in South China illustrate the excellent performances of the proposed framework on SKBG acceleration. [ABSTRACT FROM AUTHOR]

Construction of the linearized state-space model is the key step of eigenvalue analysis for SSO study of power systems with large-scale renewable power generation (RPG) integrated. This paper proposes a novel method to construct the state matrix of the AC/DC hybrid power system with RPG within the discrete-time domain. The continuous-time state-space model of each AC/DC component as well as RPG units in the power system, is discretized together with their corresponding control. The discretized equation of each component is then represented by an equivalent circuit consisting of parallel historical current and conductance. According to the power system configuration, the discrete-time equivalent circuit of the whole AC/DC hybrid system is established, and the nodal analysis method is applied for the construction of the discrete-time state-space model of the power system. In this way, the state matrix can be acquired much more conveniently than that of continuous-time state-space method, which needs topology analysis to find independent state variables of the network from the proper tree. The proposed method has been applied in the eigenvalue analysis for the SSO study of a case system adapted from the AC/DC hybrid transmission system in northwest China. Eigenvalue results are in high accordance with time-domain simulation results in PSCAD/EMTDC. [ABSTRACT FROM AUTHOR]

Power system planning is essential for ensuring development of a safe and stable power system. Articles on power system planning have been published in recent decades. In this paper, bibliometric analysis is applied to power system planning to identify its basic characteristics, and to summarize the research hotspots and trends. A total of 4562 publications were obtained from the Web of Science during 1971–2020. The 4562 publications cover 8136 keywords, 1526 journals, 107 countries/territories, and 2519 institutions. IEEE Transactions on Power Systems is the key journal in power system planning; USA, China, and England are the countries that dominate publication production. Research hotspots and trends were analyzed using author-keyword co-occurrence analysis and keyword burst detection. Four clusters were identified and topics from Cluster I (central nodes as power system stability and transient stability) and Cluster IV (central nodes as power system simulation and economics) are important for power system planning research. However, their relative popularities have declined over the past two decades. This indicates that Cluster II (central nodes as renewable energy, wind power, and energy storage) and Cluster III (central nodes as distributed generation and smart grids) will be the focus of future research. [ABSTRACT FROM AUTHOR]

While many machine learning approaches have been widely applied to power system online dynamic stability assessment, how to sufficiently learn spatial-temporal correlations from system transients without losing the interpretability is still a challenging issue. In this paper, a novel networked time series shapelet learning approach is proposed to learn spatial-temporal correlations for transient stability assessment (TSA) in an interpretable manner. Specifically, a network impedance-based adjacency matrix is first introduced to characterize spatial networked correlations. Based on graph structural regularization, this matrix is effectively incorporated into the subsequent learning procedure as spatial constraints. Taking time series trajectories acquired from multiple buses as the inputs, networked shapelet learning is heuristically performed to learn critical sequential features, i.e., networked shapelets, for TSA model derivation. With the learning procedure strategically guided by inherent spatial-temporal correlations of the system, the obtained data-driven TSA model is able to perform highly reliable and interpretable online TSA. Numerical test results on the IEEE 39-bus test system and the realistic GD Power Grid in China verify the superior performances of the proposed approach. [ABSTRACT FROM AUTHOR]

Time delays are inevitable in the power systems with wide-area control signals, which may compromise the control pe-rformance and thus jeopardize the stability of the power systems. To analyze the impacts of system parameters on critical oscillation modes of a time-delayed power system (TDPS), a new method for eigenvalue trajectory tracking of TDPS is proposed in this paper based on the continuation theory of invariant subspaces. When small changes are imposed on system parameters, such as parameters of wide-area damping controllers (WADCs) and time delays, the invariant subspaces are continuously predicted and corrected, followed by the eigenvalues and eigenvectors. In the process, the predictor and corrector are computed by solving linear equations sparsely and in blocks, which is highly scalable and computationally efficient for large-scale power system applications. The 16-generator 68-bus test system and two real-world power grids in China are used to test and demonstrate the proposed method. The results show that the proposed method can accurately and efficiently track eigenvalue trajectories for TDPS, especially for large-scale power grids. In addition, the sensitivities of eigenvalues and eigenvectors with respect to WADCs’ parameters and time delays are obtained as by-products of the approach. [ABSTRACT FROM AUTHOR]

In practical power systems, it is still very challenging to figure out a cost-effective undervoltage load shedding (UVLS) scheme that can reliably and adaptively react to the short-term voltage stability (SVS) problem. Faced with this challenge, this paper develops an intelligent data-driven predictive UVLS scheme for online SVS enhancement. Inspired by valuable ideas in model predictive control and supplementary excitation control in power systems, a novel deep feedback learning machine (DFLM) is designed to precisely predict future voltage violations after UVLS execution. With the help of the DFLM, the UVLS scheme is aware of potential effects of various candidate UVLS actions. Owing to this desirable nature, it can adaptively respond to diverse SVS conditions and optimize UVLS decisions in a non-iterative way. Further, two well-designed strategies, i.e., stepwise constraint relaxation and incremental DFLM adaptation, are introduced to enhance the scheme's reliability and adaptability during online application. Numerical test results on the Nordic test system and the realistic North GZ Power Grid in China showcase the excellent performances of the proposed scheme. [ABSTRACT FROM AUTHOR]