Summary
The increasing use of decentralised energy sources and new load types in low voltage (LV) grids is leading to bidirectional power flows and higher loads on underground cables. These conditions accelerate ageing and increase the risk of failure. Nevertheless, LV cables are largely operated without monitoring. Power line communication (PLC), which is often used for smart metering and automation, provides a sensorless basis for condition assessment, as its signals reflect the electrical environment. However, the metadata obtained from PLC is high dimensional, unsynchronised and operationally variable, which makes conventional analysis difficult. This paper explores unsupervised machine learning (ML) methods for detecting anomalies in PLC data. Three approaches are compared: an autoencoder (AE), an isolation forest (IF) and a combined latent encoded isolation forest (LEIF). The AE learns a nonlinear latent representation of normal PLC behaviour and detects anomalies via reconstruction errors.
Read more Read lessThe IF isolates outliers through random partitioning without distribution assumptions. LEIF integrates both methods by first compressing the input data with an AE and then applying an
IF, thereby reducing dimensionality and improving isolation efficiency. The paper uses real
PLC measurements from a LV grid. Preprocessing ensures data integrity through gap handling, impulse noise retention, and frequency related standardisation. The results show that LEIF outperforms standalone methods by combining representation learning and isolation, enabling shorter paths and clearer anomaly separation. This demonstrates that PLC metadata, combined with advanced ML, enables sensorless monitoring of LV cables.
Additional informations
| Publication type | Session Materials |
|---|---|
| Reference | B1_12436_2026 |
| Publication year | |
| Publisher | CIGRE |
| Country | Germany |
| Study committees | |
| File size | 2 MB |
| Price for non member | 30 € |
| Price for member | 30 € |
Authors
KREISKÖTHER Michael K. H. - amperias GmbH Germany; PLENER Julius - amperias GmbH Germany
