Vertical power flow forecast with LSTMs using regular training update strategies

• Published in: Energy and AI 2022-05, Vol.8, p.100143, Article 100143
• Main Authors: Brauns, Katharina, Scholz, Christoph, Schultz, Alexander, Baier, André, Jost, Dominik
• Format: Article
• Language: English
• Subjects: Forecasting; LSTM; Vertical power flow
• ISSN: 2666-5468; 2666-5468
• DOI: 10.1016/j.egyai.2022.100143

The strong growth of renewable energy sources as well as the increasing amount of volatile energy consumption is leading to major challenges in the electrical grid. In order to ensure safety and reliability in the electricity grid, a high quality of power flow forecasts for the next few hours are needed. In this paper we investigate forecasts of the vertical power flow at transformer between the medium and high voltage grid. Forecasting the vertical power flow is challenging due to constantly changing characteristics of the power flow at the transformer. We present a novel approach to deal with these challenges. For the multi step time series forecasts a Long-Short Term Memory (LSTM) is used. In our presented approach an update process where the model is retrained regularly is investigated and compared to baseline models. The model is retrained as soon as a sufficient amount of new measurements are available. We show that this retraining mostly captures changes in the characteristic of the transformer that the model has not yet seen in the past and therefore cannot be predicted by the model without an update process. To give more weight to recent data, we examined different strategies in terms of the number of epochs and the learning rate. We show that our new approach significantly outperforms the investigated baseline models. On average, we achieved an improvement of about 8% with the regular update process compared to the approach without update process. [Display omitted] •A short-term Vertical Power Flow Forecast is proposed.•A multi step time series forecast approach with a LSTM forecasting the next 2 days.•Different update strategies are investigated where the LSTM is regularly retrained.•Our approach outperforms the baseline models to verify effectiveness.