Imperial College London
Alternate

DrIoannisKonstantelos

Faculty of Engineering, Department of Electrical and Electronic Engineering

Research Fellow
 
 
 
//

Contact

 

i.konstantelos

 
 
//

Location

 

Electrical EngineeringSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Cremer:2019:10.1109/TPWRS.2019.2911598,
author = {Cremer, J and Konstantelos, I and Strbac, G},
doi = {10.1109/TPWRS.2019.2911598},
journal = {IEEE Transactions on Power Systems},
pages = {3826--3836},
title = {From optimization-based machine learning to interpretable security rules for operation},
url = {http://dx.doi.org/10.1109/TPWRS.2019.2911598},
volume = {34},
year = {2019}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - Various supervised machine learning approaches have been used in the past to assess the power system security (also known as reliability). This is typically done by training a classifier on a large number of operating points whose post-fault status (stable or unstable) has been determined via time-domain simulations. The output of this training process can be expressed as a security rule that is used online to classify an operating point. A critical, and little-studied aspect of these approaches is the interpretability of the rules produced. The lack of interpretability is a well-known issue of some machine learning approaches, especially when dealing with difficult classification problems. In the case of the security assessment of the power system, which is a complex mission-critical task, interpretability is a key requirement for the adoption and deployment by operators ofthese approaches.In this paper, for the first time, we explore the trade-offbetween predictive accuracy and interpretability in the contextof power system security assessment. We begin by demonstratinghow Decision Trees (DTs) can be used to learn data-driven security rules and use the tree depth as a measure for interpretability.We leverage disjunctive programming to formulate novel training methods, capable of learning high-quality DTs while stillmaintaining interpretability. In particular, we propose two newapproaches: (i) Optimal Classification Trees (OCT∗) is proposedfor training DTs of low-depth and (ii) Greedy Optimizationbased Tree (GOT) is proposed for training DTs of intermediate depth, where the increased computational burden is managed by exploiting the nested tree structure. We also demonstrate that the ability to generate high-quality interpretable rules can actually translate to impressive benefits in terms of training requirements. Through case studies on the IEEE 68-bus system, we demonstrate that the proposed methods can produce DTs of higher quality compared to the state-
AU  - Cremer,J
AU  - Konstantelos,I
AU  - Strbac,G
DO  - 10.1109/TPWRS.2019.2911598
EP  - 3836
PY  - 2019///
SN  - 0885-8950
SP  - 3826
TI  - From optimization-based machine learning to interpretable security rules for operation
T2  - IEEE Transactions on Power Systems
UR  - http://dx.doi.org/10.1109/TPWRS.2019.2911598
UR  - http://hdl.handle.net/10044/1/68788
VL  - 34
ER  -
Download