Ensemble Methods of Classification for Power Systems Security Assessment

      Research output: Research - peer-reviewArticle

      Early online date
      • Aleksei Zhukov
      • Nikita Tomin
      • Viktor Kurbatsky
      • Denis Sidorov
      • Daniil Panasetsky
      • Aoife Foley

      View graph of relations

      One of the most promising approaches for complex technical systems analysis employs ensemble methods of classification. Ensemble methods enable a reliable decision rules construction for feature space classification in the presence of many possible states of the system. In this paper the novel techniques based on decision trees are used to evaluate power system reliability. In this work a hybrid approach based on random forests models and boosting model is proposed. Such techniques can be applied to predict the interaction of increasing renewable power, storage devices and intelligent switching of smart loads from intelligent domestic appliances, storage heaters and air-conditioning units and electric vehicles with grid to enhance decision making. This ensemble classification method was tested on the modified 118-bus IEEE power system to examine whether the power system is secured under steady-state operating conditions.


      • Ensemble Methods of Classification for Power Systems Security Assessment

        Rights statement: Copyright 2017 Elsevier. This manuscript is distributed under a Creative Commons Attribution-NonCommercial-NoDerivs License (https://creativecommons.org/licenses/by-nc-nd/4.0/), which permits distribution and reproduction for non-commercial purposes, provided the author and source are cited.

        Accepted author manuscript, 869 KB, PDF-document


      Original languageEnglish
      Number of pages9
      JournalApplied Computing and Informatics
      Journal publication date19 Sep 2017
      Early online date19 Sep 2017
      StateEarly online date - 19 Sep 2017

        Research areas

      • power system, ensemble methods, boosting, Classification, heuristics, random forests, security assessment

      ID: 135601803