Search

The majority of faults on electric power systems are traceable to distribution networks due to the exposure of the networks to different adverse climatic conditions, among other factors. Power outages due to climatic factors are inevitable since a major part of a distribution network is made up of overhead lines and exposed to different unfavorable weather conditions. Climatic factors need to be fully considered when designing a power system model in order to achieve a meaningful system reliability improvement. The projection of power system outage requires a model with high accuracy, taking climatic conditions into consideration. Conventional models rely only on fault data and do not consider climatic factors, and so they have very low accuracy. This research proposes a computational intelligence model using historical fault and climatic data sets of Newcastle, South Africa. Three models are developed in this paper: the trend projection (TP) model, and two artificial neural network (ANN) models (Models 1 and 2). The performance of the models are examined using statistical parameters. The results of the ANN models were satisfactory unlike the trend projection model; thereby illustrating the efficacy of the computational methods.

Occurrence of faults in power systems is unavoidable but their timely recognition and location enhances the reliability and security of supply; thereby resulting in economic gain to consumers and power utility alike. Distribution Network (DN) is made smarter by the introduction of sensors and computers into the system. In this paper, detection and classification of faults in DN using Artificial Neural Network (ANN) is emphasized. This is achieved through the employment of Back Propagation Algorithm (BPA) of the Feed Forward Neural Network (FFNN) using three phase voltages and currents as inputs. The simulations were carried out using the MATLAB® 2017a. ANN with various hidden layers were analyzed and the results authenticate the effectiveness of the method.

The security and reliability of supply is often affected due to fault occurrence in electrical power Distribution Networks (DN). In the conventional DN, faults location takes more than the expected time, which results in economic losses to power utility companies as well as consumers. However, the advent of Intelligent Electronic Devices (IEDs) and recent advances in Information and Communication Technology (ICT) has made DN better, safer and smarter. In this paper, we present the outcome of simulation experiments carried out to locate faults in a DN. The IEEE 13 Node Test Feeder was simulated in SIMULINK with different fault conditions and the fault data acquired were utilized to develop an ANN classification model. The outcome of the experiments shows that the ANN based classification model is effective in locating faults on distribution lines with satisfactory performances.