GOOML Big Kahuna Forecast Modeling and Genetic Optimization Files

Description

This submission includes example files associated with the Geothermal Operational Optimization using Machine Learning (GOOML) Big Kahuna fictional power plant, which uses synthetic data to model a fictional power plant. A forecast was produced using the GOOML data model framework and fictional input data, and a genetic optimization is included which determines optimal flash plant parameters. The inputs and outputs associated with the forecast and genetic optimization are included. The input and output files consist of data, configuration files, and plots. A link to the Physics-Guided Neural Networks (phygnn) GitHub repository is also included, which augments a traditional neural network loss function with a generic loss term that can be used to guide the neural network to learn physical or theoretical constraints. phygnn is used by the GOOML framework to help integrate its machine learning models into the relevant physics and engineering applications. Note that the data included in this submission are intended to provide a demonstration of GOOML's capabilities. Additional files that have not been released to the public are needed for users to run these models and reproduce these results. Units can be found in the readme data resource.

Resources

Name Format Description Link
47 File including a list of the components and their types, along with the units associated with the data files. https://gdr.openei.org/files/1314/readme.txt
57 Archive of plots produced by forecast model run on the fictional Big Kahuna geothermal power plant https://gdr.openei.org/files/1314/bgk_output_plots.zip
57 Archive containing well configuration files for the fictional Big Kahuna geothermal power plant. These files include enthalpy, mass flow, and other relevant parameters associated with each fictional well for use by GOOML framework. https://gdr.openei.org/files/1314/bgk_well_config.zip
8 Input dataset representing operational data for the fictional Big Kahuna geothermal power plant. Pressure is in units of absolute bar. https://gdr.openei.org/files/1314/timeseries_data.csv
34 Diagram showing the layout of the fictional Big Kahuna geothermal power plant used in GOOML forecasting and genetic optimization experiments. https://gdr.openei.org/files/1314/component_diagram.png
57 Archive containing flash plant configuration files for the fictional Big Kahuna geothermal power plant. These files include flash plant dimensions and other parameters for use by GOOML framework. https://gdr.openei.org/files/1314/bgk_flash_plant_config.zip
8 Output data from forecast model run on the fictional Big Kahuna geothermal power plant. Mass flow is in [1000 kg/hr], pressure is in [absolute bar], and power is in [MWe]. These units can be found on the dataset's respective plots found in "Big Kahuna Forecast Output Plots". https://gdr.openei.org/files/1314/forecast_output_data.csv
21 Energies journal article, "A New Modeling Framework for Geothermal Operational Optimization with Machine Learning (GOOML)" describing the GOOML framework and model setup. https://doi.org/10.3390/en14206852 https://www.mdpi.com/1996-1073/14/20/6852
57 Archive of plots produced by genetic optimization run on the fictional Big Kahuna geothermal power plant. https://gdr.openei.org/files/1314/bgk_genetic_optimization_output_plots.zip
23 Plant configuration file for the fictional Big Kahuna geothermal power plant which maps components together for use by GOOML framework. https://gdr.openei.org/files/1314/bgk_components.json
21 Link to physics-guided neural networks (phygnn) GitHub repo that is used by GOOML to aid with machine learning. This implementation of physics-guided neural networks augments a traditional neural network loss function with a generic loss term that can be used to guide the neural network to learn physical or theoretical constraints. phygnn enables scientific software developers and data scientists to easily integrate machine learning models into physics and engineering applications. This framework should help alleviate some challenges that are often encountered when applying purely data-driven machine learning models to scientific applications, such as when machine learning models produce physically inconsistent results or have trouble generalizing to out-of-sample scenarios. https://github.com/NREL/phygnn

Tags

  • phygnn
  • data
  • big-kahuna
  • synthetic-data
  • steam-field
  • genetic-optimization
  • processed-data
  • power-plant
  • optimization
  • neural-network
  • example
  • physics-guided-neural-networks
  • operations
  • inputs
  • python
  • wells
  • code
  • model
  • steamfield
  • configuration
  • flash-plants
  • forecast
  • gooml
  • outputs
  • simulation
  • machine-learning
  • geothermal
  • energy

Topics

Categories