Power quality (PQ) data analysis has become an issue of great interest in past few years. Due to numerous impacts, PQ can exhibit rare and significant deviations of a time series from its typical characteristic. Such unusual deviations are known as anomalies and the process of identifying such changes is referred to anomaly detection. In this paper, four proximity-based machine learning (ML) techniques are applied to original (nontransformed) PQ data for automatic anomaly detection. In contrast to standard classification tasks, these techniques are applied on unlabeled data, taking only the characteristics of the PQ data into account. The process of parameters tuning and their influence on methods performance are described. The methods performance has been evaluated on different time series, which represent the typical variation in PQ data. Finally, the ability to detect different types of anomalies is analyzed.