End User
PPC
Description
The Wind Farm Event Detection service delivers automated identification, classification, and energy-loss quantification of operational events in wind turbine SCADA streams. Events are categorised into four classes: Environmental, Manufacturer, Utility, and Grid. The service enables systematic comparison of event patterns across turbines and seasons, shortens detection-to-awareness latency, and feeds availability dashboards and energy loss accounting workflows.
Core Capabilities
Monitoring & Anomaly Detection
Predictive & Prescriptive Analytics
Business Need
Manual review of SCADA records and event logs across PPC's growing wind park fleet is operationally intensive and prone to latency. Automated event detection reduces reliance on manual log review, shortens the time between event occurrence and operator awareness, and enables systematic fleet-level comparison — directly supporting maintenance scheduling, availability reporting, and energy loss accounting.
Key Performance Indicators
Precision, recall, and F1-score per event category (Environmental, Manufacturer, Utility, Grid)
Performance stratified by event duration class (short: <0.5h, medium: 0.5-4h, long: >4h)
Energy loss estimation accuracy for confirmed event periods
API availability with scheduled hourly cadence
Data Provided
Per-turbine detection package: hourly event categories with confidence scores
Detected event episodes with onset/offset timestamps, duration, and estimated energy loss
Traceability metadata per detection run
Inputs: hourly SCADA telemetry + structured event log (category, event code, timestamps, energy loss)
TEF
TEF RES