End User
SWW
Description
The AI-Enhanced Model-Based Ancillary Services service implements a hybrid approach combining physics-based simulation (PowerFactory) with data-driven analysis to identify systematic deviations between the network model and real-world measurements. By learning recurring deviation patterns — at specific times of day, load profiles, or seasonal conditions — the service applies a correction layer on top of the physical model to improve reliability of model-based grid management processes.
Core Capabilities
Monitoring & Anomaly Detection
Predictive & Prescriptive Analytics
Business Need
Physical network models in PowerFactory may diverge from actual measured values due to outdated parameters, insufficient observability, or changing generation and load profiles. When these deviations are systematic, they undermine congestion management and flexibility activation reliability. The service provides transparent monitoring of where and when the model deviates from reality, creating a foundation for targeted recalibration.
Key Performance Indicators
MAE between corrected simulation results and actual measurements over pilot period
Documentation of network areas and operating times with significant deviations
Improvement achieved by the correction layer vs. uncorrected simulation
Note: Automated grid control is explicitly not part of this service; human oversight is preserved
Data Provided
Monitoring outputs: deviation patterns by magnitude, temporal occurrence, and affected network area
Systematic error documentation for targeted model recalibration
Inputs: PowerFactory network model, PQM measurement data via Python interface, historical SCADA records
Distribution grid topology - CIM or MATPOWER – unknown size – with documentation – N/A
TEF
TEF DSO