Towards static-security assessment of a large-scale power system using neural networks

Abstract

A neural-network-aided solution to the problem of static-security assessment of a large scale power system is proposed. It is based on a pattern-recognition technique where a group of neural networks is trained to classify the secure/insecure status of the power system for specific contingencies based on the precontingency system variables. The large dimensionality of the input data is reduced by partitioning the problem into smaller subproblems at different stages. When each trained NN is queried online, it can provide the power-system operator with the security status of the current operating point for a specified contingency. Parallel network architecture and the adaptive capability of the neural networks can be combined to achieve high speeds of execution and good classification accuracy.