PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
April 19, 20260 citations

Sensor-Independent One-Hour-Ahead Forecasting and Anomaly Detection of Grid-Connected PV Inverters Using an Interpretable Random Forest Framework

View Full Paper
SAS. ArunkumarAEA. John Pradeep EbenezerSMS. Mayakannan

Key Points

  • The study aims to develop a machine learning model for forecasting the performance and detecting anomalies in grid-connected photovoltaic inverters without meteorological sensors.
  • Constructed a machine learning model based on electrical measurements from 30 kW and 40 kW PV inverters.
  • Utilized a five-minute resolution dataset including active/reactive power and phase voltages/currents.
  • Applied regression, classification, and Z-score anomaly detection using Random Forest with feature engineering and one-hour-ahead label shifting.
  • Validated the method through temporal splits and 5-fold Time Series cross-validation.
  • Achieved high predictive accuracy (MAE = 0.12 kW, R2 = 0.995) in the regression model.
  • Demonstrated robustness in cross-validation (R2 = 0.9802, MAE = 0.1024 kW).
  • Identified anomalies using Z-score analysis (z = 3) indicating 2.77% of samples were anomalous.
  • Static classification accuracy reached 86%, while time-varying forecasting accuracy dropped to 33% (macro F1 = 0.33).

Abstract

Dependable tracking of grid-linked photovoltaic (PV) systems is also unfeasible because it relies on meteorological sensors and rule-based management, especially in sensorlimited situations. The study constructs a machine learning model interpretable to humans based on electrical measurements of a PV plant of 30 kW and 40 kW inverters, and a five-minute resolution dataset of active and reactive power, phase voltages and phase currents and time dependent features during January 2025. An application of the regression, classification, and Z-score anomaly detection method was conducted using the Random Forest and conditioned on the timestamp alignment, feature engineering, percentile-based categorization of the output, and a one-hour-ahead label shifting, and the method was validated with the aid of the temporal splits and 5-fold Time Series cross-validation. The regression model was found to have great predictive accuracy (MAE = 0.12 kW, R2 = 0.995), and cross-validation performed showed great robustness (R2 = 0.9802, MAE = 0.1024 kW). The Z-score analysis (z = 3) revealed the presence of anomalous samples (2.77%). Though the accuracy of a static classification was 86 percent, time-varying forecasting lowered the accuracy to 33 % ( macro F1 = 0.33) which points to the impact of dynamic environmental variability. The suggested light and interpretable structure allows predicting the performance of inverters in real-time, early detecting anomalies, and intelligent planning of PV systems maintenance without the use of external meteorological devices.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Arunkumar et al. (2026) studied this question.

synapsesocial.com/papers/69e47282010ef96374d8e93fhttps://doi.org/10.1051/epjconf/202636301022/pdf
Ask AI
Helpful
Bookmark
Share
View Full Paper