Wasserstein GAN improves voltage time series forecasting under anomalies
Forecasting Voltage Time Series under Anomalies Using a WGAN Model With Lipschitz Control and Progressive Kernel Critic Strategy
Machine Learning
Summary
Predicting complex voltage changes over time is hard, especially when the data has irregular spikes or errors. The authors use a special kind of artificial intelligence model called a Wasserstein GAN that adjusts itself as new data comes in. It learns to predict future voltage values more accurately by focusing on long-term patterns and handling unusual changes. Tests show this method works better and stronger than other common forecasting techniques.
What this means in practice
- •For power grid operators: Predict voltage fluctuations accurately to help manage power distribution and detect anomalies in electrical networks.
- •For energy management teams: Improve forecasting of energy consumption patterns with adaptive models that handle irregular changes in voltage data.
Authors
Najmieh Sadat Safarabadi
Abstract
In time-series forecasting tasks, the use of recursive forecasting on high-dimensional data substantially increases the complexity of the prediction process. The main challenge is that long-term dynamics becomes harder to model, since the sequences show greater temporal variability. To counteract this limitation and improve the modeling of long-term dynamics, and more importantly, address high-dimensional recursive forecasting, this paper uses a Wasserstein GAN equipped with a progressive Lipschitz penalty and an adaptive kernel. This model is capable of taking a window of the data stream and forecasting the next values, subsequently reconstructing the time-series stream and dynamically adapting its kernel to each new window. The proopsed model is a deep learning framework based on a Wasserstein GAN (WGAN-CLP) with an adaptive kernel to model alterations in streaming voltage time series. To establish the methodological foundation, we review the WGAN-LP formulation another variant model in this class and extend its framework through an adaptive kernel critic model. We then evaluate this extended model using power ratios, correlation coefficient (CC), and relative root mean squared error (RRMSE). The experimental results demonstrate that the proposed model outperforms benchmark methods in both accuracy and robustness. The evaluation shows promising performance of the WGAN-CLP with an adaptive kernel framework in forecasting sequence alterations across the voltage and energy time-series datasets.