Search

As the number of smart meters increases, compression of metering data becomes essential for data transmission, storing and processing perspectives. Specifically, feature extraction can be used for the compression of metering data and further be utilized for smart grid applications such as customer clustering. So far, there are many studies for compression and clustering based on daily load profiles. However, in order to account for long-term characteristics of electricity load, utilizing yearly load profiles (YLPs) is vital for customer load clustering and analysis. In this paper, we propose a deep learning-based YLP feature extraction that jointly captures daily and seasonal variations. By leveraging convolutional autoencoder (CAE), YLPs in 8,640-dimensional space are compressed to 100-dimensional vectors. We apply the proposed CAE framework to YLPs of 1,405 residential customers and verify that the proposed CAE outperforms other dimensionality reduction methods in terms of reconstruction errors, e.g., by 19–40%, or the compression ratio is increased by 130% or higher than other methods for the same reconstruction error. In addition, clustering analysis is performed on the encoded YLPs. Our results confirm that year-round characteristics are well captured during the clustering process and also clearly visualized with load images. [ABSTRACT FROM AUTHOR]

• Reducing uncertainty in probabilistic safety assessment strengthens nuclear safety. • For massive simulations to reduce uncertainty, a fast-running model is necessary. • A deep learning-based surrogate model of thermal–hydraulic (TH) code is proposed. • The proposed eQRNN estimates the results of TH code with their uncertain boundary. • Fast and probabilistic estimation of TH code results can improve nuclear safety. Following the Fukushima Daiichi accident, enhancing the safety of nuclear power plants has become the priority mission for the future of nuclear energy. Probabilistic safety assessment (PSA) is a well-known technique to quantify the anticipated risk of nuclear power plants according to the accident scenario. One approach to strengthening nuclear safety is reducing the uncertainty in PSA by analyzing a wide spectrum of accident scenarios. In doing this, massive simulations of thermal–hydraulic (TH) dynamics are required by running TH code. As the computation time for such large-scale simulation is a heavy burden, it is necessary to develop a fast simulation model, but related research has recently begun. For doing this, conditional autoencoder was firstly introduced, however, prediction accuracy can be further improved by exploiting temporal characteristics of simulation data. In this paper, we formalize deep learning-based fast simulation model of TH code, and propose a novel deep learning model, namely ensemble quantile recurrent neural network (eQRNN). By leveraging bi-directional long short-term memory, concatenative positional encoding, quantile regression, and model ensemble, the proposed eQRNN can provide a more accurate prediction on the simulation results and uncertain boundaries of its prediction. Compared to the base RNN model, the proposed eQRNN shows 39% and 28% lower error overall in terms of mean absolute percentage error (MAPE) and mean squared error (MSE). Finally, eQRNN achieved 75%, 79% lower MAPE and MSE than the existing conditional autoencoder-based model. [ABSTRACT FROM AUTHOR]

• Passive system reliability is important for securing the safety of nuclear power plants. • Extensive computations are generally required to evaluate the passive system reliability. • Artificial intelligence (AI) models are useful for reducing the amount of computations but a lot of training data are necessary to develop them. • A method to obtain effective training data is proposed in this study with case studies to clarify its effectiveness. Although passive safety systems (PSSs) significantly contribute to the safety of nuclear power plants, evaluating the reliability of PSSs remains difficult due to a lack of data and insufficient understanding of a phenomenon on natural forces, which are driving forces of their safety functions. Within this context, approaches that evaluate functional failures of PSSs by combining Monte Carlo simulation with a thermal-hydraulic code have been proposed. In addition, several studies are trying to develop artificial intelligence models to reduce computational burdens in evaluating functional failures of PSSs. Despite such efforts, a large amount of training data is still required to train the model accurately: class imbalance between success/failure of PSSs exacerbates this problem. To address these issues, this paper proposes a method of obtaining effective training data by dealing with the data imbalance to reduce the number of data required. Case studies were performed to show the effectiveness of the proposed method and confirmed that classification models can be efficiently constructed through effective training data. [ABSTRACT FROM AUTHOR]