The scale of the power system has been significantly expanded in recent decades. To gain real-time insights into the power system, an increasing number of sensors have been deployed tomonitor grid states, resulting in a rapidly growing number of measurement points. Simultaneously, there has also been a rise in the penetration of renewable energy generation, with energy production that is highly variable and exhibits strong interdependence between different production locations. Such interdependence also applies to electricity demand at various network positions. Furthermore, new demandside response strategies and policies enhance the flexibility of the power system, leading to changes in load profiles. These developments, combined with the structure of the network itself, mean that measurements in the power system generally exhibit strong dependencies. This dependency means that if you know one or more values, you can infer information about others. This applies to time series with measurements that follow each other chronologically as well as to snapshots that show different states of the system at a particular moment in time. A large collection of such time series and snapshots can be represented as a probability distribution in a multidimensional data space. While larger numbers of measurements enable smarter grid operations, high-dimensional stochastic variables with complex univariate and multivariate distributions could also complicate tasks in modeling power system data.....@en

For planning of power systems and for the calibration of operational tools, it is essential to analyse system performance in a large range of representative scenarios. When the available historical data is limited, generative models are a promising solution, but modelling high-dimensional dependencies is challenging. In this paper, a multivariate load state generating model on the basis of a conditional variational autoencoder (CVAE) neural network is proposed. Going beyond common CVAE implementations, the model includes stochastic variation of output samples under given latent vectors and co-optimizes the parameters for this output variability. It is shown that this improves statistical properties of the generated data. The quality of generated multivariate loads is evaluated using univariate and multivariate performance metrics. A generation adequacy case study on the European network is used to illustrate model's ability to generate realistic tail distributions. The experiments demonstrate that the proposed generator outperforms other data generating mechanisms.@en

Generating power system states that have similar distribution and dependency to the historical ones is essential for the tasks of system planning and security assessment, especially when the historical data is insufficient. In this paper, we described a generative model for load profiles of industrial and commercial customers, based on the conditional variational autoencoder (CVAE) neural network architecture, which is challenging due to the highly variable nature of such profiles. Generated contextual load profiles were conditioned on the month of the year and typical power exchange with the grid. Moreover, the quality of generations was both visually and statistically evaluated. The experimental results demonstrate our proposed CVAE model can capture temporal features of historical load profiles and generate ‘realistic’ data with satisfying univariate distributions and multivariate dependencies.@en

State estimation is of considerable significance for the power system operation and control. However, well-designed false data injection attacks can utilize blind spots in conventional residual-based bad data detection methods to manipulate measurements in a coordinated manner and thus affect the secure operation and economic dispatch of grids. In this paper, we propose a detection approach based on an autoencoder neural network. By training the network on the dependencies intrinsic in ‘normal’ operation data, it effectively overcomes the challenge of unbalanced training data that is inherent in power system attack detection. To evaluate the detection performance of the proposed mechanism, we conduct a series of experiments on the IEEE 118-bus power system. The experiments demonstrate that the proposed autoencoder detector displays robust detection performance under a variety of attack scenarios.@en

The security of energy supply in a power grid critically depends on the ability to accurately estimate the state of the system. However, manipulated power flow measurements can potentially hide overloads and bypass the bad data detection scheme to interfere the validity of estimated states. In this paper, we use an autoencoder neural network to detect anomalous system states and investigate the impact of hyperparameters on the detection performance for false data injection attacks that target power flows. Experimental results on the IEEE 118 bus system indicate that the proposed mechanism has the ability to achieve satisfactory learning efficiency and detection accuracy.@en

Anomaly detection is of considerable significance in engineering applications, such as the monitoring and control of large-scale energy systems. This article investigates the ability to accurately detect and localize the source of anomalies, using an autoencoder neural network-based detector. Correlations between residuals are identified as a source of misclassifications, and whitening transformations that decorrelate input features and/or residuals are analyzed as a potential solution. For two use cases, regarding spatially distributed wind power generation and temporal profiles of electricity consumption, the performance of various data processing combinations was quantified. Whitening of the input data was found to be most beneficial for accurate detection, with a slight benefit for the combined whitening of inputs and residuals. For localization of anomalies, whitening of residuals was preferred, and the best performance was obtained using standardization of the input data and whitening of the residuals using the zero-phase component analysis (ZCA) or zero-phase component analysis-correlation (ZCA-cor) whitening matrix with a small additional offset.@en