Electric Power System Transient Stability Assessment Based on Bi-LSTM Attention Mechanism

Mahato, Nawaraj Kumar; Dong, Jie; Song, Chunyu; Chen, Zhimin; Wang, Nan; Ma, Hongliang; Gong, Gangjun

doi:10.1109/acpee51499.2021.9437089

Cited by 7 publications

(4 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The power system TSA problem has been tackled by means of different deep learning architectures, to name here only a few prominent ones: convolutional neural networks (CNN) [56][57][58], recurrent neural networks (RNNs) [59], networks employing long shortterm memory (LSTM) layers [17,49,[60][61][62][63][64] or gated recurrent unit (GRU) layers [65][66][67], generative adversarial networks (GANs) [9,68,69], transfer learning [70], and autoencoders. These basic architectures can internally vary widely in the number of layers and their stacking order, which allows experimenting with different deep network topologies.…”

Section: Deep Learningmentioning

confidence: 99%

See 1 more Smart Citation

Artificial Intelligence Techniques for Power System Transient Stability Assessment

et al. 2022

View full text Add to dashboard Cite

The high penetration of renewable energy sources, coupled with decommissioning of conventional power plants, leads to the reduction of power system inertia. This has negative repercussions on the transient stability of power systems. The purpose of this paper is to review the state-of-the-art regarding the application of artificial intelligence to the power system transient stability assessment, with a focus on different machine, deep, and reinforcement learning techniques. The review covers data generation processes (from measurements and simulations), data processing pipelines (features engineering, splitting strategy, dimensionality reduction), model building and training (including ensembles and hyperparameter optimization techniques), deployment, and management (with monitoring for detecting bias and drift). The review focuses, in particular, on different deep learning models that show promising results on standard benchmark test cases. The final aim of the review is to point out the advantages and disadvantages of different approaches, present current challenges with existing models, and offer a view of the possible future research opportunities.

show abstract

Section: Deep Learningmentioning

confidence: 99%

“…Huang et al proposed multi-graph attention network in [20]. Mahato et al in [61] introduced a particular Bi-LSTM attention mechanism to the TSA problem, which featured LSTM layers. Wu et al proposed a deep belief network in [75].…”

Section: Deep Learningmentioning

confidence: 99%

Artificial Intelligence Techniques for Power System Transient Stability Assessment

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Since the selection probability is difficult to quantify, which increases the difficulty of model training, in this paper, we choose to use a soft attention mechanism. Combined with the sequence data information, the input information is calculated as a weighted average, and then input into the network for training, which can effectively improve the attention of the model to the input information, and achieve a reasonable allocation of resources, which is suitable for predicting temperature sequence data in this paper [32]. The flow structure of the soft attention mechanism is shown in Figure 9.…”

Section: Attentional Mechanismsmentioning

confidence: 99%

Atmospheric Temperature Prediction Based on a BiLSTM-Attention Model

et al. 2022

View full text Add to dashboard Cite

To address the problem that traditional models are not effective in predicting atmospheric temperature, this paper proposes an atmospheric temperature prediction model based on symmetric BiLSTM (bidirectional long short-term memory)-Attention model. Firstly, the meteorological data from five major stations in Beijing were integrated, cleaned, and normalized to build an atmospheric temperature prediction dataset containing multiple feature dimensions; then, a BiLSTM memory network was used to construct with forward and backward information in the time dimension. And the limitations of the traditional LSTM method in long-term time series analysis were solved by introducing the attention mechanism to achieve the prediction analysis of atmospheric temperature. Finally, by comparing the prediction results with those of BiLSTM, LSTM-Attention, and LSTM, it is revealed that the proposed model has the best prediction effect, with a MAE value of 0.013, which is 0.72%, 0.41%, and 1.24% lower than those of BiLSTM, LSTM-Attention, and LSTM, respectively; the R2 value reaches 0.9618, which is 2.73%, 1.23%, and 4.98% higher than BiLSTM, LSTM-Attention, and LSTM, respectively. The results show that the symmetrical BiLSTM-Attention atmospheric temperature prediction model can effectively improve the prediction accuracy of temperature data, and the model can also be used to predict other time series data.

show abstract

“…Additionally, the gated recurrent unit model is developed to process the time-adaptive TSA (Chen and Wang, 2021). Moreover, an attention mechanism is introduced and combined with bidirectional (Bi)-LSTM to extract more robust features (Mahato et al, 2021). Nevertheless, a power grid inherently exhibits a structured graph representation, where buses are modeled as nodes and transmission lines are modeled as edges (Ishizaki et al, 2018).…”

Section: Introductionmentioning

confidence: 99%

A multi-task transient stability assessment method adapted to topology changes using multi-graph sample and aggregate-attention network

Huang,

Dong,

Zhao

et al. 2024

Front. Energy Res.

View full text Add to dashboard Cite

Transient stability assessment (TSA) plays a pivotal role in guiding power grid risk control strategies. However, it faces challenges when dealing with complex multi-graph inputs generated by pre-fault, fault occurrence, and post-fault states. Meanwhile, most previous research studies neglected the assessment of the transient stability level. To address this, we propose a multi-task transient stability assessment (MTTSA) approach. In MTTSA, we introduce a multi-graph sample and aggregate-attention network (GraphSAGE-A) designed to capture stability features even amidst topology changes. A multi-head attention mechanism and local normalization method are adopted for a better extraction of the global and contextual information. Additionally, we introduce a quantified transient stability risk index considering the transient stability boundary and incorporate a multi-task dense structure to enhance MTTSA’s performance. Empirical tests, under changing operating conditions, conducted on the IEEE 39-bus system showcase a significant performance improvement with the proposed MTTSA method.

show abstract

Electric Power System Transient Stability Assessment Based on Bi-LSTM Attention Mechanism

Cited by 7 publications

References 13 publications

Artificial Intelligence Techniques for Power System Transient Stability Assessment

Artificial Intelligence Techniques for Power System Transient Stability Assessment

Atmospheric Temperature Prediction Based on a BiLSTM-Attention Model

A multi-task transient stability assessment method adapted to topology changes using multi-graph sample and aggregate-attention network

Contact Info

Product

Resources

About