Search NASA⌕ Search

SEARCH · Search NASA

Results for “scenario optimization”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 253 records · Page 14
All sourcesNASA NTRSDOE OSTI
DOE OSTI2015

An Assessment of the Impact of Stochastic Day-Ahead SCUC on Economic and Reliability Metrics at Multiple Timescales

This paper incorporates the stochastic day-ahead security-constrained unit commitment (DASCUC) within a multi-timescale, multi-scheduling application with commitment, dispatch, and automatic generation control. The stochastic DASCUC is solved using a progressive hedging algorithm with constrained ordinal optimization to accelerate the individual scenario solution. Sensitivity studies are performed in the RTS-96 system, and the results show how this new scheduling application would impact costs and reliability with a closer representation of timescales of system operations in practice.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2025

Cost-optimized energy storage operation for a grid-connected solar PV system at community and individual scales

This study provides a comparative analysis of grid-connected PV-integrated battery storage at individual and community scales. The paper addresses the challenge of managing energy demand-generation mismatch by using a battery energy storage optimization algorithm, which minimizes operational costs while accounting for battery degradation. Also, this work introduces a broader evaluation basis that includes seasonal variability, grid exchange smoothness, and scalability across different battery capacities. Results show that community-scale storage more effectively dampens grid exchange power fluctuations and reduces system costs, particularly with moderate price differences between electricity buying and selling prices and low battery capacities. The paper also analyzes the impacts of static control versus cost-optimized battery system management. Here, it is shown that the gap in system costs between the cost-optimized and static control scenarios widens as the price difference increases.

25 ENERGY STORAGE↗
DOE OSTI2024

Optimization of District Heating Network Parameters in Steady-State Operation

Here we examine the modeling, simulation, and optimization of district heating systems, which are widely used for thermal transport using steam or hot water as a carrier. We propose a generalizable framework to specify network models and scenario parameters, and develop an optimization method for evaluating system states including pressures, fluid flowrates, and temperatures throughout the network. The network modeling includes pipes, thermal plants, pumps, and passive or controllable loads as system components. We propose basic models for thermodynamic fluid transport and enforce the balance of physical quantities in steady-state flow over co-located outgoing and return networks. We formulate an optimization problem with steam and hot water as the outgoing and return carriers, as in legacy twentieth century systems. The physical laws and engineering limitations are specified for each component type, and the thermal network flow optimization problem is formulated and solved for a realistic test network under several scenarios.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2020

Distribution Feeder-Scale Fast Frequency Response via Optimal Coordination of Net-load Resources Part II: Large-Scale Demonstration

This work is the second of a two-part series in which we develop and experimentally demonstrate a hierarchical control solution for optimally coordinating thousands of deferrable loads and distributed energy resources (DERs) to provide fast frequency response (FFR) from an entire distribution feeder. In Part I, we developed and proved practical algorithms for fast, cost-based optimal dispatch and for determining the optimal amount of headroom to operate solar inverters with to support FFR dispatch while minimizing opportunity cost. Simulation results in Part I demonstrated the advantages of the hierarchical dispatch approach in being able to maintain fast solution times needed for FFR even when the problem size increases. In Part II, we implement the algorithms developed in Part I in a novel, large-scale power hardware-in-the-loop experiment including embedded controllers and more than 100 powered appliance loads and DER connected to a simulated real-world distribution system with more than 10,000 controlled devices. Experimental results from multiple scenarios confirm that the optimal FFR dispatch approach scales well and can optimally coordinate more than 10,000 net-load resources across a distribution network while achieving hardware response times within 500 ms, which is not possible using state-of-the-art optimal coordination approaches.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2021

Evaluating Manual Sampling Locations for Regulatory and Emergency Response

Drinking water systems commonly use manual or grab sampling to monitor water quality, identify or confirm issues, and verify that corrective or emergency response actions have been effective. In this paper, the effectiveness of regulatory sampling locations for emergency response is explored. An optimization formulation based on the literature was used to identify manual sampling locations to maximize overall nodal coverage of the system. Results showed that sampling locations could be effective in confirming incidents for which they were not designed. When evaluating sampling locations optimized for emergency response against regulatory scenarios, the average performance was reduced by 3%–4%, while using optimized regulatory sampling locations for emergency response reduced performance by 7%–10%. Secondary constraints were also included in the formulation to ensure geographical and water age diversity with minimal impact on the performance. This work highlighted that regulatory sampling locations provide value in responding to an emergency for these networks.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2019

Applicability Evaluation of the In-can Vitrification to Fukushima Waste - 19016

The in-can vitrification process has been developed by the CEA for an internal application (alpha waste treatment) since 2005 and can be rated TRL 7. On these basis the DEM'n'MELT consortium which gathers Orano, CEA and ECM technologies is currently developing and qualifying a robust, simple and versatile in situ vitrification process dedicated to D and D waste. The DEM'n'MELT vitrification process is developed with a modular design, the main characteristics are presented hereafter: - Suitable for high or medium level waste. - Heated by a simple and robust resistance furnace. - Offering homogeneity to the melted mixture. - Suitable for solid or liquid wastes, including zeolites and sludge. - Flexible enough to accommodate uncertainties on waste composition. - Designed in order to produce a small amount of secondary waste. - Implementing proven technological solutions from French high level vitrification shops. - Requiring low investment and operation costs. Regarding this features, the in-can process has been deemed as an appropriate tool for the vitrification of the Fukushima water treatment secondary waste (mineral adsorbants, sludge). The evaluation of the In-can process for Fukushima waste is a project led by Orano, CEA and ANADEC. The main phases are: - Scenarios and glass formulation studies to optimize waste loading and matrix homogeneity. - Bench scale tests on several scenarios of blended waste. - Pilot scale test on one selected scenario (reference scenario). - Feasibility evaluation to Fukushima Daiichi Nuclear Power Station implementation. This paper presents the first results of this project with a highlighting on glass waste loading, glass properties, bench tests and pilot test results, process parameters, and material balance. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2016

Ensuring Workforce Readiness for the Energy Industry Through 3D Simulations

In February 2009, during his joint address to Congress, President Obama challenged every American to commit to at least one year of college education and set a goal that the United States should once again have the highest proportion of college graduates in the world by the year 2020. This push by the Obama administration reflected the understanding that while a college degree was becoming a prerequisite to obtain many of the jobs in the 21. century economy; the United States still lagged behind other countries with respect to higher education attainment. Because of this, the U.S. is facing a skills gap between the credentials required for the jobs of today and tomorrow, and the number of skilled workers eligible to fill those jobs. Within the energy industry, the skills gap is compounded by two factors: an expanding domestic industry in energy generation and transmission, and an aging workforce set to retire in large numbers. In fact, a 2013 survey administered by Center for Energy Workforce Development (CEWD) estimates that 36% of the workforce may need to be replaced in the next five years, and nearly 50% will need to be replaced by the year 2023. As a 2014 report by CEWD notes, 'The message for workforce development is clear: qualified and skilled utility technicians and engineers will continue to be in high demand in all types of energy generation, transmission, and distribution jobs'. Simulations provide students the ability to practice proper procedure in a safe environment, test out multiple scenarios to determine an optimal outcome, and repeat practice to solidify learning. Industry currently applies simulation (i.e., 3D Electrical Substation Simulation) as it affords an opportunity for technicians to train in a safe, virtual environment, thus eliminating risks associated with arc flash hazards. The intent of 3D simulation is to enhance the students' understanding of the concepts learned in the course and better prepare students for field work in a related technical discipline. The 3D simulation will reinforce the concepts learned during a specific course and are intended to add real world context to the curriculum. The 3D simulation will be designed such that a student will perform specific job activities incorporating concepts learned during the course. This method of instruction ensures students have an understanding of the concepts and are able to apply the concepts in a real world context. Different scenarios will be developed to ensure a thorough understanding of the concepts with real time feedback when there is a misunderstanding of the concepts. (authors)

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2018

Highway Eco-Driving of an Electric Vehicle Based on Minimum Principle

The digital map in the on-board navigation system on passenger vehicles nowadays gives controllers access to detailed information of a planned route. Connected automated vehicles equipped with high computing power, are able to process data and leverage high control freedom available through automation. This paper proposes a fast optimization algorithm for eco-driving of electric vehicles in highway cruising scenarios. The algorithm is based on optimal control theory and takes into account road grades as well as state constraints imposed by speed limits and safe headway to the preceding car. Using Autonomie, the proposed algorithm is evaluated by simulating two example scenarios. The first result demonstrates an energy saving potential of 4.4%.

connected automated vehicle↗
DOE OSTI2013

ON THE COMPLEMENTARITY OF PULSAR TIMING AND SPACE LASER INTERFEROMETRY FOR THE INDIVIDUAL DETECTION OF SUPERMASSIVE BLACK HOLE BINARIES

Gravitational waves coming from supermassive black hole binaries (SMBHBs) are targeted by both the Pulsar Timing Array (PTA) and Space Laser Interferometry (SLI). The possibility of a single SMBHB being tracked first by PTA, through inspiral, and later by SLI, up to merger and ring-down, has been previously suggested. Although the bounding parameters are drawn by the current PTA or the upcoming Square Kilometer Array (SKA), and by the New Gravitational Observatory (NGO), derived from the Laser Interferometer Space Antenna (LISA), this paper also addresses sequential detection beyond specific project constraints. We consider PTA-SKA, which is sensitive from 10{sup -9} to p Multiplication-Sign 10{sup -7} Hz (p = 4, 8), and SLI, which operates from s Multiplication-Sign 10{sup -5} up to 1 Hz (s = 1, 3). An SMBHB in the range of 2 Multiplication-Sign 10{sup 8}-2 Multiplication-Sign 10{sup 9} M {sub Sun} (the masses are normalized to a (1 + z) factor, the redshift lying between z = 0.2 and z = 1.5) moves from the PTA-SKA to the SLI band over a period ranging from two months to fifty years. By combining three supermassive black hole (SMBH)-host relations with three accretion prescriptions, nine astrophysical scenarios are formed. They are then related to three levels of pulsar timing residuals (50, 5, 1 ns), generating 27 cases. For residuals of 1 ns, sequential detection probability will never be better than 4.7 Multiplication-Sign 10{sup -4} yr{sup -2} or 3.3 Multiplication-Sign 10{sup -6} yr{sup -2} (per year to merger and per year of survey), according to the best and worst astrophysical scenarios, respectively; put differently this means one sequential detection every 46 or 550 years for an equivalent maximum time to merger and duration of the survey. The chances of sequential detection are further reduced by increasing values of the s parameter (they vanish for s = 10) and of the SLI noise, and by decreasing values of the remnant spin. The spread in the predictions diminishes when timing precision is improved or the SLI low-frequency cutoff is lowered. So while transit times and the SLI signal-to-noise ratio (S/N) may be adequate, the likelihood of sequential detection is severely hampered by the current estimates on the number-just a handful-of individual inspirals observable by PTA-SKA, and to a lesser extent by the wide gap between the pulsar timing and space interferometry bands, and by the severe requirements on pulsar timing residuals. Optimization of future operational scenarios for SKA and SLI is briefly dealt with, since a detection of even a single event would be of paramount importance for the understanding of SMBHBs and of the astrophysical processes connected to their formation and evolution.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2012

Optimizing Normal Tissue Sparing in Ion Therapy Using Calculated Isoeffective Dose for Ion Selection

Purpose: To investigate how the selection of ion type affects the calculated isoeffective dose to the surrounding normal tissue as a function of both normal tissue and target tissue {alpha}/{beta} ratios. Methods and Materials: A microdosimetric biologic dose model was incorporated into a Geant4 simulation of parallel opposed beams of protons, helium, lithium, beryllium, carbon, and neon ions. The beams were constructed to give a homogeneous isoeffective dose to a volume in the center of a water phantom for target tissues covering a range of cobalt equivalent {alpha}/{beta} ratios of 1-20 Gy. Concomitant normal tissue isoeffective doses in the plateau of the ion beam were then compared for different ions across the range of normal tissue and target tissue radiosensitivities for a fixed isoeffective dose to the target tissue. Results: The ion type yielding the optimal normal tissue sparing was highly dependent on the {alpha}/{beta} ratio of both the normal and the target tissue. For carbon ions, the calculated isoeffective dose to normal tissue at a 5-cm depth varied by almost a factor of 5, depending on the {alpha}/{beta} ratios of the normal and target tissue. This ranges from a factor of 2 less than the isoeffective dose of a similar proton treatment to a factor of 2 greater. Conclusions: No single ion is optimal for all treatment scenarios. The heavier ions are superior in cases in which the {alpha}/{beta} ratio of the target tissue is low and the {alpha}/{beta} ratio of normal tissue is high, and protons are superior in the opposite circumstances. Lithium and beryllium appear to offer dose advantages similar to carbon, with a considerably lower normal tissue dose when the {alpha}/{beta} ratio in the target tissue is high and the {alpha}/{beta} ratio in the normal tissue is low.

62 RADIOLOGY AND NUCLEAR MEDICINE↗
DOE OSTI2024

Potential Adoption and Benefits of Co-Optimized Multimode Engines and Fuels for U.S. Light-Duty Vehicles

Exploring a diverse portfolio of technologies for decarbonization is crucial to understanding the potential impacts of different technological solutions and their associated environmental implications. Using high-octane, high-sensitivity biofuel blends in co-optimized multimode engines can increase engine efficiency and reduce vehicle emissions. Here, the multimode engine research focuses on the benefits of light-duty vehicle engines, which can operate in multiple modes depending on the vehicle's load. Low-temperature combustion can improve efficiency and reduce emissions (such as those from oxides of nitrogen and particulate matter) during low-load operation, while spark ignition performance is maintained in high-load operation. These advanced engines can be optimized to run on blends of biobased fuels. This analysis models scenarios for potential market adoption of co-optimized multimode vehicles fueled by three different bioblendstocks: ethanol, isopropanol, and isobutanol. An integrated modeling approach is used to forecast the energy and environmental impacts of the deployment of co-optimized multimode vehicles and fuels in the light-duty sector over the 2020-to-2050 time horizon. The multidisciplinary approach combines vehicle sales modeling, system dynamics modeling of the biorefining industry, and life cycle assessment to estimate the emissions and energy benefits. The models consider market forces such as consumer preferences for vehicle attributes, biofuel supply and demand dynamics subject to biorefinery capacity build-out and bioresource constraints, and forecasted changes to the U.S. bulk energy system over time. Market adoption of co-optimized vehicles is evaluated across a wide parameter space for incremental vehicle cost and engine efficiency improvement. This analysis reveals that the deployment of co-optimized multimode fuels and vehicles results in up to a 5% reduction in annual sector-wide life cycle greenhouse gas (GHG) emissions by 2050, relative to a business-as-usual scenario, but is also indicates environmental trade-offs, such as higher life cycle water-use. Emission benefits could potentially increase beyond 2050, as the new technologies penetrate the market and gain a foothold. Results also show that, under certain circumstances, vehicles with engines co-optimized for use with high-octane, high-sensitivity biofuel blends can be cost-competitive with conventional gasoline, while reducing GHG emissions. Our modeling results indicate that co-optimized multimode fuels and engines can be strategically leveraged in tandem with electrification to decarbonize the light-duty sector. Co-optimized vehicles could play a role in the early years of the time horizon, while electric vehicles (EVs) could become more competitive in the later years, highlighting the complementary benefits of these technologies for GHG reductions.

Oke, Doris↗
DOE OSTI2026

First DIII-D-West hybrid scenario similarity experiments for iter-relevant long-pulse operation

For the first time, similarity experiments between DIII-D and WEST were performed in the ITER "hybrid-like" regime during dedicated campaigns in April and May 2025. The matched parameters include elongation, triangularity, ion ∇B drift direction toward the X-point, qprofile, and core normalized physics quantities in terms of normalized pressure, normalized gyroradius, electron collisionality, ratio of ion to electron temperature, T i /T e . Core transport physics is explored with different aspect ratio (R/a) values (typically 3 at DIII-D and 5 on WEST). DIII-D explored high-beta conditions (electromagnetic effect) with low torque injection (~0 ± 0.5 N•m) using high heating power (up to 6 MW NBI and 2 MW ECRH powers), while scanning the heating mix (ion vs electron), beta, T i /T e , core radiation via controlled tungsten injection using the Laser Blow-Off system. WEST extended operation toward long-duration pulses using its actively cooled tungsten divertor, achieving dominated electron heating regimes with reduced tungsten contamination. Boron impurity injection were scanned on WEST to control edge conditions and core performance. It is found that core confinement improves-manifested by higher electron temperature, total energy content, neutron rate, and ion temperatureunder conditions of low separatrix density, consistent with previous observations [Bourdelle et al., Nucl. Fusion 63 (2023) 056021]. Conditions for Hmode access and for ion heating in electron-dominated regimes in both WEST and DIII-D will be discussed and compared. The ratio of the thermal energy confinement time (τ E ) to the volume-averaged electron-ion collisional heat exchange time (τ e-i ) is a key parameter to enhance ion heating and potentially facilitate H-mode access in electron-heated regimes. These first-of-a-kind coordinated DIII-D and WEST experiments provide a unique multi-machine dataset to validate predictive models and to optimize ITER hybrid-scenario performance under diverse core and edge conditions.

DIII-D↗
DOE OSTI2022

Optimal economic dispatch policy for prosumer with energy storage considering self-consumption demand

This paper analyzed the effects of self-consumption demand on the joint economic dispatch of prosumers (energy consumers who are also producers), particularly for prosumers with both energy storage and distributed energy sources (DERs). Studies in the existing literature on the economic dispatch scheduling policy of energy storage, mostly from the perspective of electricity merchants, do not address the impacts of self-consumption demand. However, due to the intermittent and high levels of uncertainty regarding DERs generation and the dynamic demand of the prosumer, production and consumption are not always simultaneous; there are two possible scenarios in each period depending on whether DERs generation can meet prosumers' self-consumption or not. Incorporating the self-consumption demand will pose modeling challenges since these two scenarios cannot occur simultaneously in each period, and different scenarios require different decisions for prosumers. Further, this paper analyzed the two scenarios separately to find the optimal storage scheduling strategy, and the results were combined to get the optimal global solution. We focused on prosumers' economic decision-making while considering self-consumption demand and the physical constraints of a battery based on dynamic programming. Our study showed that the feasible state of charge (SOC) range of storage can be segmented into several sub-ranges by SOC reference points under the above two scenarios. As a result, a prosumer's optimal scheduling can be uniquely and conveniently selected based on the sub-ranges within which the current SOC falls. The results, therefore, provided multistage decision-making guidance for prosumers with energy storage.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2013

Effectiveness of robust optimization in intensity-modulated proton therapy planning for head and neck cancers

Purpose: Intensity-modulated proton therapy (IMPT) is highly sensitive to uncertainties in beam range and patient setup. Conventionally, these uncertainties are dealt using geometrically expanded planning target volume (PTV). In this paper, the authors evaluated a robust optimization method that deals with the uncertainties directly during the spot weight optimization to ensure clinical target volume (CTV) coverage without using PTV. The authors compared the two methods for a population of head and neck (H and N) cancer patients. Methods: Two sets of IMPT plans were generated for 14 H and N cases, one being PTV-based conventionally optimized and the other CTV-based robustly optimized. For the PTV-based conventionally optimized plans, the uncertainties are accounted for by expanding CTV to PTV via margins and delivering the prescribed dose to PTV. For the CTV-based robustly optimized plans, spot weight optimization was guided to reduce the discrepancy in doses under extreme setup and range uncertainties directly, while delivering the prescribed dose to CTV rather than PTV. For each of these plans, the authors calculated dose distributions under various uncertainty settings. The root-mean-square dose (RMSD) for each voxel was computed and the area under the RMSD-volume histogram curves (AUC) was used to relatively compare plan robustness. Data derived from the dose volume histogram in the worst-case and nominal doses were used to evaluate the plan optimality. Then the plan evaluation metrics were averaged over the 14 cases and were compared with two-sided paired t tests. Results: CTV-based robust optimization led to more robust (i.e., smaller AUCs) plans for both targets and organs. Under the worst-case scenario and the nominal scenario, CTV-based robustly optimized plans showed better target coverage (i.e., greater D{sub 95%}), improved dose homogeneity (i.e., smaller D{sub 5%}- D{sub 95%}), and lower or equivalent dose to organs at risk. Conclusions: CTV-based robust optimization provided significantly more robust dose distributions to targets and organs than PTV-based conventional optimization in H and N using IMPT. Eliminating the use of PTV and planning directly based on CTV provided better or equivalent normal tissue sparing.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2013

Improving the efficiency of single and multiple teleportation protocols based on the direct use of partially entangled states

We push the limits of the direct use of partially pure entangled states to perform quantum teleportation by presenting several protocols in many different scenarios that achieve the optimal efficiency possible. We review and put in a single formalism the three major strategies known to date that allow one to use partially entangled states for direct quantum teleportation (no distillation strategies permitted) and compare their efficiencies in real world implementations. We show how one can improve the efficiency of many direct teleportation protocols by combining these techniques. We then develop new teleportation protocols employing multipartite partially entangled states. The three techniques are also used here in order to achieve the highest efficiency possible. Finally, we prove the upper bound for the optimal success rate for protocols based on partially entangled Bell states and show that some of the protocols here developed achieve such a bound. -- Highlights: •Optimal direct teleportation protocols using directly partially entangled states. •We put in a single formalism all strategies of direct teleportation. •We extend these techniques for multipartite partially entangle states. •We give upper bounds for the optimal efficiency of these protocols.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2024

Bayesian Optimization for Anything (BOA): An open-source framework for accessible, user-friendly Bayesian optimization

We introduce Bayesian Optimization for Anything (BOA), a high-level Bayesian Optimization (BO) framework and model wrapping toolkit, which presents a novel approach to simplifying BO, with the goal of making it more accessible and user-friendly, particularly for those with limited expertise in the field. BOA addresses common barriers in implementing BO, focusing on ease of use, reducing the need for deep domain knowledge, and cutting down on extensive coding requirements. A notable feature of BOA is its language-agnostic architecture, which facilitates broader application in various fields and to a wider audience. We showcase BOA's application through three examples: a high-dimensional optimization with parameters of the SWAT+ watershed model, a highly parallelized optimization of this intrinsically non-parallel model, and a multi-objective optimization of the FETCH Tree-Crown Hydrodynamics model. Furthermore, these test cases illustrate BOA's effectiveness in addressing complex optimization challenges in diverse scenarios.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2017

Optimal current profile control for enhanced repeatability of L-mode and H-mode discharges in DIII-D

In this work, model-based control techniques are used to obtain target current profiles in low-confinement-mode (L-mode) as well as high-confinement-mode (H-mode) DIII-D discharges. The control problem is formulated as a trajectory optimization problem to search for a feasible path from the expected initial condition to the desired target. The result comprises a sequence of feedforward (open-loop) control requests and a corresponding state evolution from the initial condition to the desired target. On top of this optimal feedforward control sequence a feedback (closed-loop) controller based on a linearized model and optimal control design techniques is added to track the desired state evolution. Furthermore, the effectiveness of the control approach is demonstrated with experiments.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2022

Recurrent neural networks for short-term and long-term prediction of geothermal reservoirs

Accurate prediction of geothermal reservoir responses to alternative energy production scenarios is critical for optimizing the development of the underlying resources. While the conventional physics-based models offer a comprehensive prediction tool, data-driven models provide an efficient alternative to build fit-for-purpose predictive models by extracting and using the statistical patterns in the collected data to make predictions. The recurrent neural network (RNN) is a data-driven model that is commonly applied to predict time series sequences. This paper presents a variant of RNN that also utilizes the efficiency of convolutional neural networks (CNN) for the prediction of energy production from geothermal reservoirs. Specifically, a CNN–RNN architecture is developed that takes historical well controls as input (features) and their corresponding production response data as output (labels) to learn an input-output mapping that can predict the future well production responses/performance for any given future well control inputs. The model is paired with a labeling scheme to handle real field disturbances that create data gaps. In addition to the model structure, we introduce a thorough workflow for applying the model, which includes data pre-processing, feature selection, as well as different training strategies for short-term and long-term prediction. Finally, the performance and accuracy of the model are evaluated by applying it to multiple datasets, including a field reservoir model.

15 GEOTHERMAL ENERGY↗