Machine Learning-Assisted High-Temperature Reservoir Thermal Energy Storage Optimization: Numerical Modeling and Machine Learning Input and Output Files

Description

This data set includes the numerical modeling input files and output files used to synthesize data, and the reduced-order machine learning models trained from the synthesized data for reservoir thermal energy storage site identification. In this study, a machine-learning-assisted computational framework is presented to identify High-Temperature Reservoir Thermal Energy Storage (HT-RTES) site with optimal performance metrics by combining physics-based simulation with stochastic hydrogeologic formation and thermal energy storage operation parameters, artificial neural network regression of the simulation data, and genetic algorithm-enabled multi-objective optimization. A doublet well configuration with a layered (aquitard-aquifer-aquitard) generic reservoir is simulated for cases of continuous operation and seasonal-cycle operation scenarios. Neural network-based surrogate models are developed for the two scenarios and applied to generate the Pareto fronts of the HT-RTES performance for four potential HT-RTES sites. The developed Pareto optimal solutions indicate the performance of HT-RTES is operation-scenario (i.e., fluid cycle) and reservoir-site dependent, and the performance metrics have competing effects for a given site and a given fluid cycle. The developed neural network models can be applied to identify suitable sites for HT-RTES, and the proposed framework sheds light on the design of resilient HT-RTES systems. All the simulations and the neural network model were done by Idaho National Laboratory. A detailed description of the work was reported in publication linked below.

Resources

Name Format Description Link
0 Link to journal article published in Renewable Energy detailing this work. https://doi.org/10.1016/j.renene.2022.07.118
21 Link to other GDR submission containing final report for the DOE GTO funded research on geologic thermal energy storage, or commonly known as reservoir thermal energy storage. https://gdr.openei.org/submissions/1416
21 The MOOSE-based FALCON code used in this study is open-sourced and can be used to replicate the simulation cases. FALCON is a finite-element geothermal reservoir simulation and analysis code for coupled and fully implicit Thermo-Hydro-Mechanical-Chemical (THMC) geosystems based on the MOOSE framework mainly developed by Idaho National Laboratory. It solves the coupled governing equations for fluid flow, heat transfer, rock deformation and fracturing, and chemical reactions in geological porous media. https://github.com/idaholab/falcon
57 This data set includes the numerical modeling input files (.e and .i) and output files (.csv) used to synthesize data, and the reduced-order machine learning models (.pkl format) trained from the synthesized data for reservoir thermal energy storage site identification. The input files include mesh files with fixed caprock and bedrock, and a varying reservoir thickness and two different scenarios - one with a seasonal operation case and one with a continuous operation case. See the readme file in the archive for more information. https://gdr.openei.org/files/1412/Jin2022renewable.zip

Tags

  • stochastic-simulation
  • moose
  • thermal-energy-storage
  • modeling
  • optimization
  • neural-network
  • pareto-fronts
  • stochastic
  • ann
  • artificial-neural-network-regression
  • falcon
  • reservoir-thermal-energy-storage
  • operation-scenarios
  • simulation-data
  • seasonal-operation
  • continuous-operation
  • seasonal-cycle
  • characterization
  • hydrogeologic-formation
  • high-temperature
  • simulated-data
  • numerical-model
  • tes
  • machine-learning
  • ht-rtes
  • geotes

Topics

Categories