Abstract
The main objective and contribution of this paper was/is the application of our knowledge-based data-mining approach (a fuzzy rule-based classification system) characterized by a genetically optimized interpretability-accuracy trade-off (by means of multi-objective evolutionary optimization algorithms) for transparent and accurate prediction of decentral smart grid control (DSGC) stability. In particular, we aim at uncovering the hierarchy of influence of particular input attributes upon the DSGC stability. Moreover, we also analyze the effect of possible "overlapping" of some input attributes over the other ones from the DSGC-stability perspective. The recently published and available at the UCI Database Repository Electrical Grid Stability Simulated Data Set and its input-aggregate-based concise version were used in our experiments. A comparison with 39 alternative approaches was also performed, demonstrating the advantages of our approach in terms of: (i) interpretable and accurate fuzzy rule-based DSGC-stability prediction and (ii) uncovering the hierarchy of DSGC-system’s attribute significance.
Highlights
The stability of electrical grids depends on the balance between electricity generation and electricity demand
Data mining approaches are well suited for decision support in management, control, and stability analysis of power systems including decentralized smart grids
The main goal and contribution of this work is the application of our knowledge-based data-mining technique, i.e., fuzzy rule-based classifiers (FRBCs) with a genetically optimized interpretability-accuracy trade-off to transparent and accurate prediction of decentral smart grid control (DSGC) stability
Summary
The stability of electrical grids depends on the balance between electricity generation and electricity demand. Data mining approaches are well suited for decision support in management, control, and stability analysis of power systems including decentralized smart grids. Many data mining methods have been used in the considered research field—see the section for a brief review Their significant shortcoming is usually their non-transparent, black-box, and accuracy-only-oriented nature. The present work is our attempt to address the smart-grid-stability prediction problem in an effective way by providing a solution coming from the knowledge-based data-mining field and characterized by both high interpretability and transparency and high accuracy. The main goal and contribution of this work is the application of our knowledge-based data-mining technique, i.e., fuzzy rule-based classifiers (FRBCs) with a genetically optimized interpretability-accuracy trade-off (see, e.g., [20,21,22,23] for details) to transparent and accurate prediction of DSGC stability. The previously outlined main goal of the paper, including the application of our approach to the DSGC-stability prediction using two aforementioned simulated data sets and a comparative analysis with as many as 39 alternative approaches, is presented and discussed
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.
