A Deep Learning-Based Feature Extraction Framework for System Security Assessment

The ongoing decarbonisation of modern electricity systems has led to a substantial increase of operational uncertainty, particularly due to the large-scale integration of renewable energy generation. However, the expanding space of possible operating points renders necessary the development of novel...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on smart grid 2019-09, Vol.10 (5), p.5007-5020
Main Authors: Sun, Mingyang, Konstantelos, Ioannis, Strbac, Goran
Format: Article
Language:English
Subjects:
Data mining
Deep learning
Electricity
Feature extraction
Machine learning
Monte Carlo simulation
Power system stability
R-vine copulas
Security
security assessment
State variable
Stochastic processes
Training
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The ongoing decarbonisation of modern electricity systems has led to a substantial increase of operational uncertainty, particularly due to the large-scale integration of renewable energy generation. However, the expanding space of possible operating points renders necessary the development of novel security assessment approaches. In this paper we focus on the use of security rules where classifiers are trained offline to characterize previously unseen points as safe or unsafe. This paper proposes a novel deep learning-based feature extraction framework for building security rules. We show how deep autoencoders can be used to transform the space of conventional state variables (e.g., power flows) to a small number of dimensions where we can optimally distinguish between safe and unsafe operation. The proposed framework is data-driven and can be useful in multiple applications within the context of security assessment. To achieve high accuracy, a novel objective-based loss function is proposed to address the issue of imbalanced safe/unsafe classes that characterize electricity system operation. Furthermore, an R-vine copula-based model is proposed to sample historical data and generate large populations of anticipated system states for training. The superior performance of the proposed framework is demonstrated through a series of case studies and comparisons using the load and wind generation data from the French transmission system, which have been mapped to the IEEE 118-bus system.
ISSN:1949-3053
1949-3061
DOI:10.1109/TSG.2018.2873001