Ensemble Methods of Classification for Power Systems Security Assessment

TL;DR

This paper introduces ensemble classification techniques, including decision trees, random forests, and boosting, to assess the security and reliability of power systems amid increasing renewable integration and smart grid components.

Contribution

It presents a novel hybrid ensemble approach for power system security assessment, combining random forests and boosting models for improved decision reliability.

Findings

Effective in evaluating power system security under steady-state conditions

Hybrid ensemble methods outperform traditional single classifiers

Applicable to modern smart grid scenarios with renewable integration

Abstract

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