A Dynamic Surrogate Model Technique for Power Systems Modeling and Simulation

Document Number: 2008-01-2887

Date Published: November 2008

Author(s):
Michael Balchanos - Georgia Institute of Technology
Kyungjin Moon - Georgia Institute of Technology
Neil Weston - Georgia Institute of Technology
Dimitri Mavris - Georgia Institute of Technology

Abstract:
Heterogeneous physical systems can often be considered as highly complex, consisting of a large number of subsystems and components, along with the associated interactions and hierarchies amongst them. The simulation of a large-scale, complex system can be computationally expensive and the dynamic interactions may be highly nonlinear. One approach to address these challenges is to increase the computing power or resort to a distributed computing environment. An alternative to improve the simulation computational performance and efficiency is to reduce CPU required time through the application of surrogate models. Surrogate modelling techniques for dynamic simulation models can be developed based on Recurrent Neural Networks (RNN). This study will present a method to improve the overall speed of a multi-physics, time-domain simulation of a complex naval system using a surrogate modelling technique. For the purpose of demonstration, a small-scale dynamic model of a power system has been developed as a monolithic implementation in Simulink\sR. The surrogate modelling technique will be evaluated by comparing time-dependent responses of the surrogate against the original monolithic with respect to the approximation accuracy and computational performance.

File Size: 258K
Product Status: In Stock

See other papers presented at Power Systems Conference, November 2008, Seattle, WA, USA, Session: Modeling, Simulation, Analysis & Control (Part 3 of 5)

Purchase more technical papers and save! With TechSelect, you decide what SAE Technical Papers you need, when you need them, and how much you want to pay. Learn more >