Digital Commons Network^™

Development Of Reduced Order Models Using Reservoir Simulation And Physics Informed Machine Learning Techniques, Mark V. Behl Jr

LSU Master's Theses

Reservoir simulation is the industry standard for prediction and characterization of processes in the subsurface. However, simulation is computationally expensive and time consuming. This study explores reduced order models (ROMs) as an appropriate alternative. ROMs that use neural networks effectively capture nonlinear dependencies, and only require available operational data as inputs. Neural networks are a black box and difficult to interpret, however. Physics informed neural networks (PINNs) provide a potential solution to these shortcomings, but have not yet been applied extensively in petroleum engineering.

A mature black-oil simulation model from Volve public data release was used to generate training data …

Simulation Study For Wireless Sensor Networks And Load Sharing Routing Protocol To Increase Network Life And Connectivity, Ankur Suri

LSU Master's Theses

LSU SensorSimulator is a framework for simulating wireless sensor networks. It is a customizable and extendible simulator, which allows testing and analyzing software for wireless sensor networks. The users can subclass the framework classes and customize the behavior of various network layers. This subclassing gives a way to the developers an opportunity to analyze and investigate, phenomenological, networking, robustness and scaling issues, to explore arbitrary algorithms for distributed sensors, independent of hardware constraint. The results are compared against the simulation results for ns-2 for routing protocols Directed Diffusion and GEAR. Through the comparison of results for scalability, performance and memory …

Sensorsimulator: Simulation Framework For Sensor Networks, Cariappa D. Mallanda

LSU Master's Theses

Wireless sensor networks have the potential to become significant subsystems of engineering applications. Before relegating important and safety-critical tasks to such subsystems, it is necessary to understand the dynamic behavior of these subsystems in simulation environments. There is an urgent need to develop a simulation platform that is useful to explore both the networking issues and the distributed computing aspects of wireless sensor networks. Current approaches to simulating wireless sensor networks largely focus on the networking issues. These approaches use well-known network simulation tools that are often difficult to extend to explore distributed computing issues. Discrete-event simulation is a trusted …