Application of Artificial Intelligence in Gas Storage Management

Abstract

TX 75083-3836 U.S.A., fax 01-972-952-9435. AbstractAn approach is investigated, to reduce the amount of CPU time needed to execute a numerical full field model in an optimization loop.To demonstrate the power of this approach, a real life example is presented. Data from a gas storage reservoir have been used to setup a single tank material balance program. Then, a limited number of simulation runs is carried out. These simulation runs are intended to span over the whole range of input parameter variation (app. 25 runs).In a next step, a Neural Network (NN) model is setup. By training a Neural Network on the so gained simulation outputs, a model, which is able to interpolate between the individual simulation scenarios is created. In this way, a large variety of different scenarios can be represented with a limited amount of model runs.The trained Neural Network model is used as a proxy function for an optimization routine. The trained Neural Network has been used as fitness function for the Genetic Algorithm to minimize the output parameter, which is in this example the RMS-error of measured and calculated tank pressure. Due to the very low CPU consumption of the Neural Network, a large number of realisations can be calculated in a short amount of time. By this, the absolute minimum of the desired output parameter (in this case the RMS-error) can be evaluated in a few seconds.The Genetic Algorithm has succeeded to find a minimum, which is located very close to the absolute minimum of all possible solutions.

Applications of Machine Learning in Subsurface Reservoir Simulation—A Review—Part I

“…Following the indirect HM approach, Costa et al [106] and Zangl et al [107] developed an ANN model to speed up the HM process. The input datasets were generated using the Box Behnken (BB) and Latin Hypercube (LH) sampling techniques and an experimental design process, respectively.…”

“…ANNs with stochastic optimization [106,107] ANNs with dimensionality reduction methods [108] Ensembles of ANNs [109] RBFNNs, Generalized Regression ANNs, FSSC and ANFIS stochastic optimization [110][111][112] Direct history matching Supervised ANNs [114][115][116][117][118][119][120]126] Bayesian ML models [121,122,124,125] MARS, DTs, single-pass GRNNs [127] Unsupervised Self-Organizing Map (SOM) [131] Supervised SVR with dimensionality reduction and optimization [135] RNN [142,143] CNN [148,158] Unsupervised GAN [149,159] Piecewise Reconstruction from a Dictionary (PRaD) with pluri-PCA [151] Convolutional AutoEncoders [152,157] Reinforcement learning Reinforcement learning models [103,162] Currently, dozens of professional products used to set up ML models are available to developers, might that be related to research or commercial products. This palette includes client tools developed by major players in the market such as Google and Microsoft (Google cloud AI platform, Azure machine learning) as well as free tools such as TensorFlow by Google and the Anaconda distribution for Python.…”

Development of software for analysis and optimization of operating modes of underground gas stores

“…Most of the foreign works that are involved in solving the considered problems are mainly devoted to improving the technology of gas storage, control, optimization and innovation, which improve the efficiency of the gas storage process [9][10][11][12][13]. Interesting was the work on the use of inert gas as a buffer gas for underground storage, which addressed practical and economic issues [14].…”

Characterizing Reservoir Connectivity and Forecasting Waterflood Performance Using Data-Driven and Reduced-Physics Models

“…Several areas of application included reservoir characterization (Artun and Mohaghegh 2011;Raeesi et al 2012;Alizadeh et al 2012), candidate well selection for hydraulic fracturing treatments (Mohaghegh et al 1996), well-placement/trajectory optimization (Centilmen et al 1999;Doraisamy et al 2000;Johnson and Rogers 2001;Guyaguler and Horne 2000;Yeten et al 2003;Gokcesu et al 2005;Mohaghegh et al 2006), screening and optimization of secondary/enhanced oil recovery processes (Ayala and Ertekin 2005;Patel et al 2005;Demiryurek et al 2008;Artun et al 2010Artun et al , 2012Parada and Ertekin 2012;Amirian et al 2013), history matching (Cullick et al 2006Silva et al 2007;Zhao et al 2015), reservoir modeling, monitoring and management (Zangl et al 2006;Mohaghegh 2011;Mohaghegh et al 2014;Zhao et al 2015;Kalantari-Dhaghi et al 2015;Esmaili and Mohaghegh 2016). Most of these problems presented in the literature are based on development of artificial neural network (ANN) based proxy models that can accurately mimic reservoir models within a reasonable amount of accuracy and computational efficiency.…”