اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدUsing Evolution Strategy with Meta-models for Well Placement Optimization
57
0
0.0
(
0
)
تأليف
Zyed Bouzarkouna
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Optimum implementation of non-conventional wells allows us to increase considerably hydrocarbon recovery. By considering the high drilling cost and the potential improvement in well productivity, well placement decision is an important issue in field development. Considering complex reservoir geology and high reservoir heterogeneities, stochastic optimization methods are the most suitable approaches for optimum well placement. This paper proposes an optimization methodology to determine optimal well location and trajectory based upon the Covariance Matrix Adaptation - Evolution Strategy (CMA-ES) which is a variant of Evolution Strategies recognized as one of the most powerful derivative-free optimizers for continuous optimization. To improve the optimization procedure, two new techniques are investigated: (1). Adaptive penalization with rejection is developed to handle well placement constraints. (2). A meta-model, based on locally weighted regression, is incorporated into CMA-ES using an approximate ranking procedure. Therefore, we can reduce the number of reservoir simulations, which are computationally expensive. Several examples are presented. Our new approach is compared with a Genetic Algorithm incorporating the Genocop III technique. It is shown that our approach outperforms the genetic algorithm: it leads in general to both a higher NPV and a significant reduction of the number of reservoir simulations.
قيم البحث
اقرأ أيضاً
The ability to walk in new scenarios is a key milestone on the path toward real-world applications of legged robots. In this work, we introduce Meta Strategy Optimization, a meta-learning algorithm for training policies with latent variable inputs th
at can quickly adapt to new scenarios with a handful of trials in the target environment. The key idea behind MSO is to expose the same adaptation process, Strategy Optimization (SO), to both the training and testing phases. This allows MSO to effectively learn locomotion skills as well as a latent space that is suitable for fast adaptation. We evaluate our method on a real quadruped robot and demonstrate successful adaptation in various scenarios, including sim-to-real transfer, walking with a weakened motor, or climbing up a slope. Furthermore, we quantitatively analyze the generalization capability of the trained policy in simulated environments. Both real and simulated experiments show that our method outperforms previous methods in adaptation to novel tasks.
Domain decomposition methods are widely used to solve sparse linear systems from scientific problems, but they are not suited to solve sparse linear systems extracted from integrated circuits. The reason is that the sparse linear system of integrated
circuits may be non-diagonal-dominant, and domain decomposition method might be unconvergent for these non-diagonal-dominant matrices. In this paper, we propose a mini-step strategy to do the circuit transient analysis. Different from the traditional large-step approach, this strategy is able to generate diagonal-dominant sparse linear systems. As a result, preconditioned domain decomposition methods can be used to simulate the large integrated circuits on the supercomputers and clouds.
Placement Optimization is an important problem in systems and chip design, which consists of mapping the nodes of a graph onto a limited set of resources to optimize for an objective, subject to constraints. In this paper, we start by motivating rein
forcement learning as a solution to the placement problem. We then give an overview of what deep reinforcement learning is. We next formulate the placement problem as a reinforcement learning problem and show how this problem can be solved with policy gradient optimization. Finally, we describe lessons we have learned from training deep reinforcement learning policies across a variety of placement optimization problems.
Uncertainty involved in computational materials modeling needs to be quantified to enhance the credibility of predictions. Tracking the propagation of model-form and parameter uncertainty for each simulation step, however, is computationally expensiv
e. In this paper, a multiscale stochastic reduced-order model (ROM) is proposed to propagate the uncertainty as a stochastic process with Gaussian noise. The quantity of interest (QoI) is modeled by a non-linear Langevin equation, where its associated probability density function is propagated using Fokker-Planck equation. The drift and diffusion coefficients of the Fokker-Planck equation are trained and tested from the time-series dataset obtained from direct numerical simulations. Considering microstructure descriptors in the microstructure evolution as QoIs, we demonstrate our proposed methodology in three integrated computational materials engineering (ICME) models: kinetic Monte Carlo, phase field, and molecular dynamics simulations. It is demonstrated that once calibrated correctly using the available time-series datasets from these ICME models, the proposed ROM is capable of propagating the microstructure descriptors dynamically, and the results agree well with the ICME models.
Computer simulation provides an automatic and safe way for training robotic control policies to achieve complex tasks such as locomotion. However, a policy trained in simulation usually does not transfer directly to the real hardware due to the diffe
rences between the two environments. Transfer learning using domain randomization is a promising approach, but it usually assumes that the target environment is close to the distribution of the training environments, thus relying heavily on accurate system identification. In this paper, we present a different approach that leverages domain randomization for transferring control policies to unknown environments. The key idea that, instead of learning a single policy in the simulation, we simultaneously learn a family of policies that exhibit different behaviors. When tested in the target environment, we directly search for the best policy in the family based on the task performance, without the need to identify the dynamic parameters. We evaluate our method on five simulated robotic control problems with different discrepancies in the training and testing environment and demonstrate that our method can overcome larger modeling errors compared to training a robust policy or an adaptive policy.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
