No abstract

No abstract

Power quality disturbances (PQDs) commonly occur in large-scale power systems and networks that rise critical issues. Therefore, an automated recognition and mitigation of PQDs is necessary. In this scenario, an efficient adaptive rate technique is proposed for viable features mining and recognition of PQDs. Event-driven A/D converters (EDADCs) are used to acquire PQD signals. To accurately segment the sampled signal, an appealing approach is used. A time-domain evaluation is carried out in the next phase to investigate the characteristics of these fragments. The mature machine learning algorithms are employed to carry out the classification. Compared to conventional counterparts, the findings indicate a decrease of 13.26 times in collected information. An average maximum identification precision of 99.33% is achieved by the proposed method. Compared to predecessors, this confirms the considerable performance of the processing and power usage of the engineered solution while achieving high recognition accuracy. Keywords Adaptive rate sampling • Time-domain features extraction • Power quality disturbances • Compression ratio • ClassificationThis article is part of the topical collection "Intelligent Systems" guest edited by

No abstract

No abstract