Search

Abstract: The presence of fractures within the host matrix may strongly affect the radionuclide mobility in the far-field of the current proposed solutions for underground radioactive waste repositories. In this paper a Monte Carlo simulation approach, based on analogies with neutron transport, has been developed for describing radionuclide transport in fractured media. The Monte Carlo approach here adopted is verified by means of comparison with analytic and numerical solutions for two different case studies. An application to a more complex and realistic case is also reported to show the potential of the proposed approach. [Copyright &y& Elsevier]

Abstract: In the current proposed solutions of radioactive waste repositories, the protective function against the radionuclide water-driven transport back to the biosphere is to be provided by an integrated system of engineered and natural geologic barriers. The occurrence of several nonlinear interactions during the radionuclide migration process may render burdensome the classical analytical–numerical approaches. Moreover, the heterogeneity of the barriers’ media forces approximations to the classical analytical–numerical models, thus reducing their fidelity to reality. In an attempt to overcome these difficulties, in the present paper we adopt a Monte Carlo simulation approach, previously developed on the basis of the Kolmogorov–Dmitriev theory of branching stochastic processes. The approach is here extended for describing transport through unsaturated porous media under transient flow conditions and in presence of nonlinear interchange phenomena between the liquid and solid phases. This generalization entails the determination of the functional dependence of the parameters of the proposed transport model from the water content and from the contaminant concentration, which change in space and time during the water infiltration process. The corresponding Monte Carlo simulation approach is verified with respect to a case of nonreactive transport under transient unsaturated flow and to a case of nonlinear reactive transport under stationary saturated flow. Numerical applications regarding linear and nonlinear reactive transport under transient unsaturated flow are reported. [Copyright &y& Elsevier]

Highlights • Operations and maintenance of grids is framed as a Sequential Decision Problem. • Prognostics and health management capabilities support maintenance decision-making. • Q-learning with neural networks tackle high dimensional and continuous problems. • A grid with prognostics and health management is considered as test case study. • Comparison with Bellman's optimality highlights the doability of the method. Abstract We develop a Reinforcement Learning framework for the optimal management of the operation and maintenance of power grids equipped with prognostics and health management capabilities. Reinforcement learning exploits the information about the health state of the grid components. Optimal actions are identified maximizing the expected profit, considering the aleatory uncertainties in the environment. To extend the applicability of the proposed approach to realistic problems with large and continuous state spaces, we use Artificial Neural Networks (ANN) tools to replace the tabular representation of the state-action value function. The non-tabular Reinforcement Learning algorithm adopting an ANN ensemble is designed and tested on the scaled-down power grid case study, which includes renewable energy sources, controllable generators, maintenance delays and prognostics and health management devices. The method strengths and weaknesses are identified by comparison to the reference Bellman's optimally. Results show good approximation capability of Q-learning with ANN, and that the proposed framework outperforms expert-based solutions to grid operation and maintenance management. [ABSTRACT FROM AUTHOR]