A method of multivariate short-term voltage stability assessment based on heterogeneous graph attention deep network

Zhong, Zhi; Guan, Lin; Su, Yinsheng; Yu, Jingxing; Huang, Jiyu; Guo, Mengxuan

doi:10.1016/j.ijepes.2021.107648

Cited by 17 publications

(8 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [20] and [21], artificial intelligence was applied to a classification problem to evaluate the voltage stability after large disturbances. To further extract time series features, a spatiotemporal series model representing the short-term voltage evolution trend was proposed in [22,23] to accurately capture the time features of the voltage response and accurately assess the voltage stability [24]. Some studies have developed a data-fault-tolerant method for voltage stability assessment after a fault occurs, which also has high assessment accuracy when data are missing [25].…”

Section: Literature Reviewmentioning

confidence: 99%

Online Assessment of Short-Term Voltage Stability Based on Hybrid Model and Data-Driven Approach

Cai,

Cao,

Liu

et al. 2023

Preprint

View full text Add to dashboard Cite

Section: Literature Reviewmentioning

confidence: 99%

Online Assessment of Short-Term Voltage Stability Based on Hybrid Model and Data-Driven Approach

Cai,

Cao,

Liu

et al. 2023

Preprint

View full text Add to dashboard Cite

“…This study employs the temporal ensembling, semisupervised fuzzy c-means clustering (SFCM), k-means clustering algorithm (K-means), and the engineering criteria outlined in [26] to discern four distinct labeled datasets. In this experiment, the SCs of these four labeled datasets are computed and utilized as performance metrics.…”

Section: Performance Testing Of Temporal Ensemblingmentioning

confidence: 99%

“…Reference [25] developed a data-driven STVSA method based on graph convolution network (GCN). Reference [26] introduced an STVSA model based on graphical neural network (GNN), which can quickly identify fast voltage collapses (FVC) and delayed voltage recovery events caused by faults. Reference [27] proposed a real-time STVSA method by combining temporal convolutional neural network (CNN) and LSTM.…”

Section: Introductionmentioning

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

“…Graph neural networks (GNNs) [16], which have emerged in recent years, can model nonEuclidean spatial data and capture the spatial-temporal connections of data, providing a new idea to solve the problem of topology feature extraction. The advantage of the GNN is recognized by some researchers and leveraged in several different applications in power systems, including power system transient stability assessment [17,18], fault location [19], fault classification [20], feeder generation [21], power flow calculation [22], stability control [23] etc. Particularly, graph sample and aggregate (GraphSAGE) [24] is a general inductive framework that can efficiently generate node embeddings for previously unseen nodes by using node feature attribute information.…”

Section: Introductionmentioning

confidence: 99%

An emergency control strategy for undervoltage load shedding of power system: A graph deep reinforcement learning method

Pei

Yang

Wang

et al. 2023

IET Generation Trans & Dist

View full text Add to dashboard Cite

Undervoltage load shedding (UVLS) is the last line of defense to ensure the safe and stable operation of the power system. The existing UVLS technique has difficulty adapting and generalizing to new topology variation scenarios of the power network, which greatly affects the reliability of the control strategy. This paper proposes a UVLS emergency control scheme based on a graph deep reinforcement learning method named GraphSAGE‐D3QN (graph sample and aggregate‐double dueling deep q network). During offline training, a GraphSAGE‐based feature extraction mechanism of the power grid with topology variation is designed that can better capture the changes in system state characteristics. A novel reinforcement learning framework based on D3QN is developed for UVLS modeling, which reduces overestimations of control action and leads to a better control effect. Then, online emergency decision‐making is achieved. The simulation results on the modified IEEE 39‐bus system and IEEE 300‐bus power system show that the proposed UVLS scheme can always provide more economical and reliable control strategies for power networks with topology variations and achieves better benefits in both adaptability and generalization performances for previously unseen topology variation scenarios.

show abstract

A method of multivariate short-term voltage stability assessment based on heterogeneous graph attention deep network

Cited by 17 publications

References 20 publications

Online Assessment of Short-Term Voltage Stability Based on Hybrid Model and Data-Driven Approach

Online Assessment of Short-Term Voltage Stability Based on Hybrid Model and Data-Driven Approach

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

An emergency control strategy for undervoltage load shedding of power system: A graph deep reinforcement learning method

Contact Info

Product

Resources

About