A simulation-based dataset for islanding detection in distributed generation systems. The data was generated in MATLAB/Simulink based on the IEC 61850-7-420 standard by Wen Sun, last updated on 2026-05-28. It contains time-frequency spectrum features derived from voltage and current waveforms under grid-connected and islanding conditions.
Use Cases
- Training CNN models for islanding detection based on time-frequency spectrum features.
- Benchmarking islanding detection algorithms based on simulated voltage and current waveforms.
- Analyzing the dilution effect of characteristic parameters in multi-machine grid-connected systems.
- Validating hybrid islanding detection methods to reduce non-detection zones.
Strengths
- The dataset is associated with a reported detection accuracy of 99.84% on an independent test set.
- The description provides a specific missed detection rate of 3.4% under five-fold cross-validation.
- The simulation model was built according to the IEC 61850-7-420 standard.
Limitations
- Row count is unknown, which may limit suitability assessment.
- Column-level documentation is absent; field semantics must be inferred after download.
- The dataset is very small at 5.5 KB, indicating limited scope.
Provenance
- Source
- figshare
- Collection Method
- Generated from MATLAB/Simulink simulations of a distributed generation grid-connected system.
- Freshness
- Last updated 2026-05-28 17:36:33