Using Data Envelopment Analysis to support the design of process improvement interventions in electricity distribution

Abstract

A significant number of studies have documented the use of Data Envelopment Analysis (DEA) for efficiency measurement in the context of electricity distribution, particularly at the level of the distribution utilities. However, their aim has been predominantly descriptive and classificatory, without any attempt to ‘open’ the black box of the transformation process. In contrast, our aim is to explore the potential of DEA to contribute to the design of effective process improvement interventions within a distribution utility.In particular, in this paper, we study an important question within the context of DEA analysis: that is, to investigate whether differences in efficiency can be attributed to a particular managerial programme or design feature. We use two different methodologies to undertake this type of analysis. Firstly, we apply Mann–Whitney rank statistics to the scores obtained from DEA in order to evaluate the statistical significance of the differences observed between an intervention programme and its control group programme. Secondly, we undertake dynamic analysis with the Malmquist Productivity Index in order to study the impact of the introduction of a new technology on a group of units. Our case study focuses on the performance evaluation of medium-voltage power lines belonging to one of the service areas in the Public Electricity Distribution System in Portugal. The results from our case study show that the application of DEA for process improvement interventions has great potential and should be explored in other contexts.