From optimization-based machine learning to interpretable security rules for operation

File Description SizeFormat 
FOMLISRO.pdfAccepted version627.77 kBAdobe PDFView/Open
Title: From optimization-based machine learning to interpretable security rules for operation
Authors: Cremer, J
Konstantelos, I
Strbac, G
Item Type: Journal Article
Abstract: 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 of these approaches. In this paper, for the first time, we explore the trade-off between predictive accuracy and interpretability in the context of power system security assessment. We begin by demonstrating how 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 still maintaining interpretability. In particular, we propose two new approaches: (i) Optimal Classification Trees (OCT∗) is proposed for 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-of-the-art approach CART, also if the DT was trained on a significant smaller database, resulting in computational savings of 80 %. Given that generating a large training database is a practical bottleneck in these data-driven approaches, this is a significant breakthrough for real-world application.
Issue Date: 31-Dec-2019
Date of Acceptance: 10-Apr-2019
URI: http://hdl.handle.net/10044/1/68788
DOI: https://dx.doi.org/10.1109/TPWRS.2019.2911598
ISSN: 0885-8950
Publisher: Institute of Electrical and Electronics Engineers
Journal / Book Title: IEEE Transactions on Power Systems
Copyright Statement: © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Sponsor/Funder: Engineering & Physical Science Research Council (E
Engineering & Physical Science Research Council (E
Funder's Grant Number: J15119 - PO:500174140
PO: 5510854 - WVR3114N
Keywords: Energy
0906 Electrical and Electronic Engineering
Publication Status: Published online
Online Publication Date: 2019-04-16
Appears in Collections:Faculty of Engineering
Electrical and Electronic Engineering
Centre for Environmental Policy
Faculty of Natural Sciences



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Creative Commonsx