Estimation of Underground MV Network Failure Types by Applying Machine Learning Methods to Indirect Observations

Electrical utilities performance is measured by various indicators, of which the most important are very dependent on the interruption time after a failure in the network has occurred, such as SAIDI. Therefore, they are constantly looking for new techniques to decrease the fault location and repair times. A possibility to innovate in this field is to estimate the failed network component when a fault occurs. This paper presents the conclusion of an analysis carried out by the authors with the aim to estimate failure types of underground MV networks based on observable indirect variables. The variables needed to carry out the analysis must be available shortly after the failure occurrence, which is facilitated by a smart-grid infrastructure, to allow for a quick estimation. This paper uses the groundwork already carried out by the authors on ambient variables, historical variables, and disturbance recordings to design an estimator to predict between four MV cable network failure types. The paper presents relevant analyses on the design and performance of various machine learning classification algorithms for estimation of the types of MV cable network failures using real-world data. Optimization of performance was carried out, resulting in an estimator with an overall 68% accuracy rate. Accuracy rates of 94% for cable failure, 63% for excavations, and 79% secondary busbar failures were achieved; as for cable joints, the accuracy was poor due to the difficulty to identify a feature that can be used to separate this failure type from cable failures. Future work to improve that accuracy is discussed