An Integrated DEA-COLS-PCA Model for Performance Assessment and Optimization of Electricity Distribution Units

Abstract

This paper presents an integrated Data Envelopment Analysis (DEA) - Corrected Ordinary Least Squares (COLS) - Principal Component Analysis (PCA) model for performance assessment, ranking and optimization of electricity distribution units. Previous studies have generally used input-output DEA models for benchmarking and evaluation of electricity distribution units. However, this study considers an integrated DEA-COLS-PCA approach since the DEA and COLS efficiency scores are combined by a robust multivariate methodology such as PCA The DEA- COLS-PCA model used in this paper provides better ranking than DEA and COLS and provides a mechanism to exact ranking for the units to be considered. In addition, to select the best DEA optimization model for performance assessment of units, indicators importance in PCA model is applied. To illustrate the usability of the proposed model, thirty eight electricity distribution units in Iran have been considered, ranked and optimized by the approach of this study.