Performance analysis of a DNN classifier for power system events using an interpretability method

Author(s)

Santos, Orlem L. D. ; Dotta, Daniel ; Wang, Meng ; Chow, Joe H. ; Decker, Ildemar C.

• Document type: Journal article
• Source: INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS; v. 136, p. 15-pg., 2022-03-01.

Abstract

Nowadays, there is a clear need for Machine Learning methods capable of extracting relevant and reliable information from synchrophasor data. In this paper, the application of an explainable data-driven method is carried out in order to inspect the performance of DNN classifier for event identification using synchrophasor measurements. The DNN classifier is the Long-Short Term Memory (LSTM) which is suitable for the extraction of dynamic features. The key advantage of this approach is the use of an interpretability inspection named SHAP (SHapley Additive exPlanation) values, based on cooperative game theory (Shapley values), which provide the means to evaluate the predictions of the LSTM and detecting possible bias. The main contributions are stated as follows: (i) it explains how the LSTM classifier is making its decisions; (ii) it helps the designer to improve the training of the classifier; (iii) certify that the resulting classifier has a consistent and coherent performance according to domain knowledge of the problem; (iv) when the user understands that the classifier is making coherent decisions, it clearly reduces the concerns of the application of DNN methods in critical infrastructure. Additionally, the proposed approach is evaluated using real synchrophasor event records from the Brazilian Interconnected Power System (BIPS). (AU)

• FAPESP's process: 19/08200-5 - Identifying power system events using a long short-term memory neural network
• Grantee: Orlem Lima dos Santos
• Support Opportunities: Scholarships abroad - Research Internship - Master's degree
• FAPESP's process: 18/20104-9 - Wide-area monitoring, dynamic security analysis and control of modern power system networks
• Grantee: Luís Fernando Costa Alberto
• Support Opportunities: Research Projects - Thematic Grants
• FAPESP's process: 17/25425-5 - Analysis of artificial neural networks methodologies for event classification using Synchrophasors
• Grantee: Orlem Lima dos Santos
• Support Opportunities: Scholarships in Brazil - Master
• FAPESP's process: 16/08645-9 - Interdisciplinary research activities in electric smart grids
• Grantee: João Bosco Ribeiro do Val
• Support Opportunities: Research Projects - Thematic Grants
• FAPESP's process: 19/10033-0 - Development of data-driven metodology for improvement of pperation of EPS with high penetration of wind/solar generation
• Grantee: Daniel Dotta
• Support Opportunities: Regular Research Grants