Abstract
Supervised machine learning has been successfully used in the past to infer a system's security boundary by training classifiers (also referred to as security rules) on a large number of simulated operating conditions. Although significant research has been carried out on using classifiers for the detection of critical operating points, using classifiers for the subsequent identification of suitable preventive/corrective control actions remains underdeveloped. This paper focuses on addressing the challenges that arise when utilizing security rules for control purposes. Illustrative examples and case studies are used to show how even very accurate security rules can lead to prohibitively high risk exposure when used to identify optimal control actions. Subsequently, the inherent tradeoff between operating cost and security risk is explored in detail. To optimally navigate this tradeoff, a novel approach is proposed that uses an ensemble learning method (AdaBoost) to infer a probabilistic description of a system's security boundary. Bias in predictions is compensated by the Platt Calibration method. Subsequently, a general-purpose framework for building probabilistic and disjunctive security rules of a system's secure operating domain is developed that can be embedded within classic operation formulations. Through case studies on the IEEE 39-bus system, it is showcased how security rules derived from supervised learning can be efficiently utilized to optimally operate the system under multiple uncertainties while respecting a user-defined balance between cost and risk. This is a fundamental step toward embedding data-driven models within classic optimisation approaches.
Highlights
T HE increasing complexity of power systems as well as the growing uncertainty that surrounds operation, introduced by renewable sources of energy and changing demand patterns, has rendered critical the use of advanced operation tools for ensuring system stability [1], known as operational reliabilityManuscript received April 16, 2018; revised July 23, 2018; accepted August 19, 2018
Data-driven work-flows follow three main steps: (i) Generate a population of possible operating points that may arise in the hours/days by sampling from statistical models fitted to past historical data. (ii) For each sampled operating point, perform a simulation for each credible contingency scenario and determine post-fault security. (iii) Using the system’s pre-fault state variables as features and the post-fault security status as a label, construct classifiers using standard machine learning algorithms such as Decision Trees (DTs)
The concept is to balance the pre-fault operating cost and expected probability of operating within an acceptable region via a multi-objective optimization framework. This entails a fundamental shift from deterministic to probabilistic treatment of security which is enabled by moving from the use of DTs, which have traditionally been used in the past, to ensemble methods such as AdaBoost [17]
Summary
T HE increasing complexity of power systems as well as the growing uncertainty that surrounds operation, introduced by renewable sources of energy and changing demand patterns, has rendered critical the use of advanced operation tools for ensuring system stability [1], known as operational reliability. Manuscript received April 16, 2018; revised July 23, 2018; accepted August 19, 2018. Date of publication August 27, 2018; date of current version December 19, 2018. We are thankful to Nicolas Omont and colleagues from Reseau de Transport d’Electricitewho provided expertise that greatly assisted the research. Color versions of one or more of the figures in this paper are available online at http://ieeexplore.ieee.org. A new breed of security assessment approaches has emerged, combining data-driven statistical inference and machine learning within a Monte Carlo framework
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
