Instability Prediction in Power Systems using Recurrent Neural Networks
Authors: Ankita Gupta, Gurunath Gurrala, Pidaparthy S Sastry
IJCAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Through extensive simulations using a standard 118-bus system, the effectiveness of the proposed system is demonstrated. We also show how we can use PCA and predictions from the RNN to identify the most critical generator that leads to transient instability. ... 4 Experimental Results |
| Researcher Affiliation | Academia | Ankita Gupta, Gurunath Gurrala, Pidaparthy S Sastry Indian Institute of Science, Bangalore {ankitagupta, gurunath, sastry}@ee.iisc.ernet.in |
| Pseudocode | No | The paper does not contain any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any explicit statement or link for open-source code related to the described methodology. |
| Open Datasets | Yes | We use detailed simulation of a standard 118-bus system [Dehghanian et al., 2015] to generate system voltage trajectories under normal operation as well as under different faults and these are used to train the RNN. |
| Dataset Splits | No | We then randomly split this data into training and test sets with one-tenth of the data kept as test set. ... Some windows are used to train the RNN and the rest are used for validation. |
| Hardware Specification | No | We use a 2 layer stacked-GRU based RNN architecture implemented in Tensor Flow 0.8 with GPU (CUDA 7.5) support. |
| Software Dependencies | Yes | We use a 2 layer stacked-GRU based RNN architecture implemented in Tensor Flow 0.8 with GPU (CUDA 7.5) support. |
| Experiment Setup | Yes | Other details of the architecture are mentioned in Table 2. Table 2: Model Parameters for RNN based OMS: Batch Size 32, Number of Hidden Layers 2, Hidden Dimensionality 128, Optimizer Adam [Kingma and Ba, 2014], Learning Rate Adaptive (Default Adam) |