Deep learning-based flow disaggregation for short-term hydropower plant operations

TL;DR

This paper presents a deep learning model that disaggregates daily inflow data into hourly data to improve short-term hydropower plant operations, addressing the need for higher-resolution hydrological data.

Contribution

The study introduces a novel deep learning-based approach for inflow data disaggregation from daily to hourly resolution in hydropower management.

Findings

Preliminary results show the model's applicability.

Method offers potential for improved decision-making.

Scope for further enhancements exists.

Abstract

High temporal resolution data plays a vital role in effective short-term hydropower plant operations. In the majority of the Norwegian hydropower system, inflow data is predominantly collected at daily resolutions through measurement installations. However, for enhanced precision in managerial decision-making within hydropower plants, hydrological data with intraday resolutions, such as hourly data, are often indispensable. To address this gap, time series disaggregation utilizing deep learning emerges as a promising tool. In this study, we propose a deep learning-based time series disaggregation model to derive hourly inflow data from daily inflow data for short-term hydropower plant operations. Our preliminary results demonstrate the applicability of our method, with scope for further improvements.