AI-based power system stability assessment and GUI design

This article introduces some methods of machine learning (ML) and artificial intelligence (AI) used to assess the stability of the power system. Four models are mainly used, including Support Vector Machine (SVM), Multilayer Perceptron (MLP), Convolutional Neural Network (CNN) and Long Short-term Me...

Full description

Saved in:
Bibliographic Details
Main Author: Peng, Xuerui
Other Authors: Xu Yan
Format: Thesis-Master by Coursework
Language:English
Published: Nanyang Technological University 2023
Subjects:
Online Access:https://hdl.handle.net/10356/170219
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
Description
Summary:This article introduces some methods of machine learning (ML) and artificial intelligence (AI) used to assess the stability of the power system. Four models are mainly used, including Support Vector Machine (SVM), Multilayer Perceptron (MLP), Convolutional Neural Network (CNN) and Long Short-term Memory (LSTM). The four methods’ theoretical motivation is conceptually explained, and they are tested with the 7127 feature and label data. The results along with the accuracy, the recall rate, the mean absolute error as well as the mean squared error are being analyzed. During pre-processing procedure, Principal Components Analysis (PCA) is used to reduce dimension and select features. With the result of the AI model, a GUI is designed to display the label result directly.