Methodology for Evaluating Projects Aimed at Service Quality Using Artificial Intelligence Techniques

The quality of the electrical energy distribution service has a significant impact on consumer satisfaction and the guarantee of the right of concession for the distribution companies. For the utility that is the object of the case study, the main continuity of service indicators was at levels below the regulatory limits. Still, due to budget constraints, the forecast of the benefit that improvement or expansion projects bring to continuity indicators must be assertive for a proper direction of investments and decision making. In this work, a methodology for evaluating projects to improve the quality of service was proposed, with the realization of the estimated benefit associated with the reduction in continuity indicators (DEC and FEC), using concepts of artificial neural networks and evolutionary algorithms. The results were obtained from a three-year history of execution of the utility’s projects. Based on the correlation analysis, a variable selection procedure was developed, where the historical values of interruptions by cause were considered as input, and the results of the continuity indicators associated with the types of projects studied form the outputs of the model. The model was developed using an artificial neural network of the multilayer perceptron type. The results obtained by simulating the new methodology presented absolute relative errors 100 times smaller for estimating the benefits of the projects compared to the current method used by the electric power distributor.