Towards Commoditizing Simulations of System Models Using Recurrent Neural Networks

Abstract

System modeling and simulation plays a crucial role in the engineering of large and complex systems from various fields, such as industrial automation or power systems. In this paper, we propose a method that can be used to easily deploy high fidelity simulations at scale, onto various target platforms. Out method is to approximate the behavior of the modeled system using a recurrent neural network. We use artificial neural networks as they easily lend themselves to high performance execution, thus avoiding the need to (manually) translate system models (typically a system of differential equations) to specialized hardware architectures. Moreover, this approach is generic in the sense that it is decoupled from typical modeling and simulation tools, such as Matlab Simulink or Dymola. This paper presents a proof-of-concept neural network architecture including the methodology for training that we used to approximate the behavior of different example systems originating from the electrical power systems domain. We present our evaluation results mainly regarding accuracy and to a certain extent performance on a GPU-based testbed. Furthermore, we detail limitations of the used approach and outline potential directions for research regarding the general applicability of our method.

A Review of Parallel Heterogeneous Computing Algorithms in Power Systems

“…After OPF applications, GPU usage in dynamic state estimations [191][192][193][194][195][196][197][198][199], power quality [202][203][204][205][206][207][208][209], and dynamic models [210][211][212][213][214][215] appear. Related to the dynamic state estimation of power systems, a lateral two-level dynamic state estimator based on the extended Kalman Filter method is implemented in a CPU-GPU platform [194].…”