Wordbook‐based light‐duty time series learning machine for short‐term voltage stability assessment

Zhu, Lipeng; Lü, Chao; Liu, Yongjun; Wu, Wei; Chen, Hong

doi:10.1049/iet-gtd.2016.2074

Cited by 17 publications

(17 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1) Accuracy Accuracy is widely used to evaluate the performance of the STVS assessment approaches [7][8][9][10][11][12][13][14]. (15) Accuracy is the proportion of cases that are correctly predicted in the assessment process, which provides an overall performance evaluation of the STVS assessment approach.…”

Section: Evaluation Indexmentioning

confidence: 99%

Deep Learning for Short-Term Voltage Stability Assessment of Power Systems

Zhang

et al. 2021

IEEE Access

View full text Add to dashboard Cite

To fully learn the latent temporal dependencies from post-disturbance system dynamic trajectories, deep learning is utilized for short-term voltage stability (STVS) assessment of power systems in this paper. First of all, a semi-supervised cluster algorithm is performed to obtain class labels of STVS instances due to the unavailability of reliable quantitative criteria. Secondly, a long short-term memory (LSTM) based assessment model is built through learning the time dependencies from the post-disturbance system dynamics. Finally, the trained assessment model is employed to determine the systems stability status in real time. The test results on the IEEE 39-bus system suggest that the proposed approach manages to assess the stability status of the system accurately and timely. Furthermore, the superiority of the proposed method over traditional shallow learning-based assessment methods has also been proved.

show abstract

Section: Evaluation Indexmentioning

confidence: 99%

Deep Learning for Short-Term Voltage Stability Assessment of Power Systems

Zhang

et al. 2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Assuming that the critical sag duration is t crit when the voltage drops to U sag , the induction motor will remain stable if the sag duration t sag is less than t crit , and the motor will stall if t sag is larger than t crit . The expression of t crit is Equation (14).…”

Section: Stability Boundary Based On Voltage Magnitude and Sag Durationmentioning

confidence: 99%

“…However, data-driven intelligent algorithms are usually based on a large amount of accurate data, which requires a large-scale application of power management units. In some works, [13,14], machine learning methods were applied to the transient voltage stability assessment. The intelligence algorithm can be applied to online monitoring to prevent transient voltage instability [15,16].…”

Section: Introductionmentioning

confidence: 99%

Research on Applicability of the Practical Transient Voltage Stability Criterion Based on Voltage Magnitude and Sag Duration

Wang

Zhang

2021

Applied Sciences

View full text Add to dashboard Cite

Voltage sags threaten the transient voltage stability of power systems. To evaluate the transient voltage stability, practical criteria based on voltage magnitude and sag duration are widely used in practical engineering. However, the applicability of practical criteria needs to be studied. In this paper, in a single-load system, a theoretical derivation was first made to obtain the transient voltage stability boundary. Then, by studying the relationship between the practical criteria and the stability boundary, the application scope of the practical criteria was determined. The application scope described in this paper can guide operators to use the practical criteria correctly and avoid misjudgment of the transient voltage stability as much as possible. Finally, a case study based on PSCAD/EMTDC is presented, and the simulation results verified the conclusions proposed in this paper.

show abstract

“…In recent years, a wide variety of machine learning‐based (ML‐based) data‐driven methods, such as Shapelet‐based classification [10], Lyapunov exponent method [11], imbalanced ML [12], multi‐state classification [13] and wordbook‐based light‐duty time series learning machine [14], have been proposed for data‐driven assessment. However, these conventional data‐driven methods are based on a fixed long observation window [15] after the fault, which usually suffers from slow assessment speed.…”

Section: Introductionmentioning

confidence: 99%