An official website of the United States government
This paper presents a practical framework that integrates wind speed forecasting with proton exchange membrane (PEM) electrolyzer design to optimize hydrogen production. Due to wind speed fluctuations, excess electrical energy is sometimes produced and left unused. A wind-to-hydrogen system addresses this challenge by converting surplus energy into storable hydrogen using a PEM electrolyzer. The proposed approach employs a multivariate supervisory control and data acquisition (SCADA) dataset and applies a convolutional neural network with bi-directional long short-term memory (CNN-Bi-LSTM) for multivariate wind speed temporal forecasting, enabling more efficient PEM operations. Compared to standard deep learning models, the CNN-Bi-LSTM architecture reduces the root mean square error by 52.5% and the mean absolute error by 56%, thereby enhancing hydrogen production forecasting. Simulation results show that a membrane thickness of 0.0252 mm and an operating temperature of 70% achieve the highest overall PEM efficiency of 63.611%. This study demonstrates the integration of deep learning-based forecasting with electrochemical modeling and SCADA datasets as a novel approach for wind-to-hydrogen production systems.
more »
« less
This content will become publicly available on July 8, 2026
Time-Series AI Forecasting of Wind-to-Hydrogen Production
Abstract The transition to carbon-neutral energy has increased the reliance upon renewable sources of energy, e.g., wind power, placing added demands on resilience and stability of the power grid. Wind-to-hydrogen production systems can be a solution for addressing these demands. By converting excess wind energy into hydrogen via electrolysis, these systems can effectively store the intermittent energy generated by wind turbines. This study discusses the application of two time-series prediction models, i.e., long short-term memory (LSTM) and bidirectional long short-term memory (Bi-LSTM), in forecasting the energy of wind farms, subsequently used for an assessment of hydrogen production means of a proton exchange membrane (PEM) electrolyzer. Using a dataset comprising wind speed, active power, and wind direction, inputs were normalized, and wind direction was transformed into sine and cosine components to retain circular characteristics. Bi-LSTM demonstrated superior accuracy with lower testing RMSE than LSTM. Integrating wind forecasts with a PEM electrolyzer model, incorporating critical electro-chemical parameters, revealed an optimal efficiency of 63.611% at a membrane thickness of 0.00254 cm and a temperature of 70°C. Bi-LSTM forecasts boosted hydrogen production by 5% to 8% compared to LSTM.
more »
« less
- Award ID(s):
- 2429540
- PAR ID:
- 10652863
- Publisher / Repository:
- American Society of Mechanical Engineers
- Date Published:
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Green hydrogen, produced using renewables through electrolysis, can be used to reduce emissions in the hard-to-abate industrial sector. Efficient production and large-scale deployment require storage to mitigate electrolyzer degradation and ensure stable hydrogen supply. This paper explores the impacts and trade-offs of battery and hydrogen storage in off-grid wind-to-hydrogen systems, considering degradation of batteries and electrolyzers. Utilizing an optimization model, we examine system performance and costs over a wide range of storage capacities and wind profiles. Our results show that batteries smooth short-term fluctuations and minimize electrolyzer degradation but can experience significant degradation resulting from frequent charge/discharge cycles. Conversely, hydrogen storage provides long-term energy buffering, essential for sustained hydrogen production, but can increase electrolyzer cycling and degradation. Combining battery and hydrogen storage enhances system reliability, reduces component degradation, and reduces operational costs. This highlights the importance of strategic storage investments to improve the performance and costs of green hydrogen systems.more » « less
-
Power grid operators rely on solar irradiance forecasts to manage uncertainty and variability associated with solar power. Meteorological factors such as cloud cover, wind direction, and wind speed affect irradiance and are associated with a high degree of variability and uncertainty. Statistical models fail to accurately capture the dependence between these factors and irradiance. In this paper, we introduce the idea of applying multivariate Gated Recurrent Units (GRU) to forecast Direct Normal Irradiance (DNI) hourly. The proposed GRU-based forecasting method is evaluated against traditional Long Short-Term Memory (LSTM) using historical irradiance data (i.e., weather variables that include cloud cover, wind direction, and wind speed) to forecast irradiance forecasting over intra-hour and inter-hour intervals. Our evaluation on one of the sites from Measurement and Instrumentation Data Center indicate that both GRU and LSTM improved DNI forecasting performance when evaluated under different conditions. Moreover, including wind direction and wind speed can have substantial improvement in the accuracy of DNI forecasts. Besides, the forecasting model can accurately forecast irradiance values over multiple forecasting horizons.more » « less
-
null (Ed.)Abstract Floating offshore wind turbines hold great potential for future solutions to the growing demand for renewable energy production. Thereafter, the prediction of the offshore wind power generation became critical in locating and designing wind farms and turbines. The purpose of this research is to improve the prediction of the offshore wind power generation by the prediction of local wind speed using a Deep Learning technique. In this paper, the future local wind speed is predicted based on the historical weather data collected from National Oceanic and Atmospheric Administration. Then, the prediction of the wind power generation is performed using the traditional methods using the future wind speed data predicted using Deep Learning. The network layers are designed using both Long Short-Term Memory (LSTM) and Bi-directional LSTM (BLSTM), known to be effective on capturing long-term time-dependency. The selected networks are fine-tuned, trained using a part of the weather data, and tested using the other part of the data. To evaluate the performance of the networks, a parameter study has been performed to find the relationships among: length of the training data, prediction accuracy, and length of the future prediction that is reliable given desired prediction accuracy and the training size.more » « less
-
null (Ed.)Floating offshore wind turbines hold great potential for future solutions to the growing demand for renewable energy production. Thereafter, the prediction of the offshore wind power generation became critical in locating and designing wind farms and turbines. The purpose of this research is to improve the prediction of the offshore wind power generation by the prediction of local wind speed using a Deep Learning technique. In this paper, the future local wind speed is predicted based on the historical weather data collected from National Oceanic and Atmospheric Administration. Then, the prediction of the wind power generation is performed using the traditional methods using the future wind speed data predicted using Deep Learning. The network layers are designed using both Long Short-Term Memory (LSTM) and Bi-directional LSTM (BLSTM), known to be effective on capturing long-term time-dependency. The selected networks are fine-tuned, trained using a part of the weather data, and tested using the other part of the data. To evaluate the performance of the networks, a parameter study has been performed to find the relationships among: length of the training data, prediction accuracy, and length of the future prediction that is reliable given desired prediction accuracy and the training size.more » « less
