Optimisation of heat recovery from low-enthalpy aquifers with geological uncertainty using surrogate response surfaces and simple search algorithms

Babaei, Masoud; Norouzi, Amir Mohammad; Nick, Hamidreza M.; Gluyas, Jon

doi:10.1016/j.seta.2021.101754

Cited by 8 publications

(4 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore the overall CPG performance is affected. We previously studied doublet well patterns and it was observed that the I-P line parallel to channels provides the highest performance [22,59]. In the present study, effects of I-P line orientation in heterogeneous cases with a single injection-production well pair are analysed.…”

Section: Effects Of Heterogeneity Injection Rate and Channels' Orient...mentioning

confidence: 95%

See 1 more Smart Citation

CO2-plume geothermal: Power net generation from 3D fluvial aquifers

et al. 2023

View full text Add to dashboard Cite

Section: Effects Of Heterogeneity Injection Rate and Channels' Orient...mentioning

confidence: 95%

“…To generate each 3D realization, at first, five layers of randomly generated 2D braided channels with a considered width, i.e., 𝑤 = 50, 100, and 150 m, are created. The process of creating 2D channels is described in our previous studies [22,59]. Then, using the 𝑤∕𝑇 ratio of 10, a thickness is assigned to all the channels.…”

Section: Fluvial Channelsmentioning

confidence: 99%

CO2-plume geothermal: Power net generation from 3D fluvial aquifers

et al. 2023

View full text Add to dashboard Cite

“…In their work, multiple linear regression (MLR) is used with simulated data to generate a proxy model to represent the objective functions. RSM has also been widely used in subsurface flow systems for optimization or model calibration purposes (Babaei et al, 2022;Chen et al, 2015Chen et al, , 2021Schulte et al, 2020). RSM directly relates independent variables to the objective function and provides fast evaluation during optimization.…”

Section: Introductionmentioning

confidence: 99%

Efficient Optimization of Energy Recovery From Geothermal Reservoirs With Recurrent Neural Network Predictive Models

Qin

Jiang

Faulder³

et al. 2023

Water Resources Research

View full text Add to dashboard Cite

Improving the long‐term energy production performance of geothermal reservoirs can be accomplished by optimizing field development and management plans. Reliable prediction models, however, are needed to evaluate and optimize the performance of the underlying reservoirs under various operation and development strategies. In traditional frameworks, physics‐based simulation models are used to predict the energy production performance of geothermal reservoirs. However, detailed simulation models are not trivial to construct, require a reliable description of the reservoir conditions and properties, and entail high computational complexity. Data‐driven predictive models can offer an efficient alternative for use in optimization workflows. This paper presents an optimization framework for net power generation in geothermal reservoirs using a variant of the recurrent neural network (RNN) as a data‐driven predictive model. The RNN architecture is developed and trained to replace the simulation model for computationally efficient prediction of the objective function and its gradients with respect to the well control variables. The net power generation performance of the field is optimized by automatically adjusting the mass flow rate of production and injection wells over 12 years, using a gradient‐based local search algorithm. Two field‐scale examples are presented to investigate the performance of the developed data‐driven prediction and optimization framework. The prediction and optimization results from the RNN model are evaluated through comparison with the results obtained by using a numerical simulation model of a real geothermal reservoir.

show abstract

“…In CSO, a model of the geothermal reservoir is employed to assess the effect of various well placement and operation alternatives on energy recovery and reservoir longevity, and an optimization algorithm performs a systematic search for improved alternatives using one or multiple objective functions based on model outputs. Common objective functions include maximizing the net present value (Rajabi et al, 2021), maximizing power/heat production (Song et al, 2021), minimizing thermal drawdown (Samin et al, 2019), and maximizing the coefficient of performance (Babaei et al, 2022). Examples of previously used optimization algorithms in geothermal CSO include genetic algorithm (Samin et al, 2019;Song et al, 2021), simulated annealing (Akın et al, 2010) and particle swarm optimization (Schulte et al, 2020).…”

mentioning

confidence: 99%