End User
SWW
Description
The AI-based Power Profile Nowcasting/Forecasting service creates high-fidelity virtual sensors for distribution grid assets lacking real-time metering. It delivers nowcasts (current-moment power estimates) and forecasts (up to 48h ahead) of active (P) and reactive (Q) power for unmetered assets by combining static asset metadata with dynamic weather and temporal inputs. This replaces static Standard Load Profiles with dynamic AI-driven time series that close the observability gap in distribution networks.
Core Capabilities
Monitoring & Anomaly Detection
Predictive & Prescriptive Analytics
Business Need
Many distribution assets — residential connections, small rooftop PV, legacy appliances — lack real-time metering. Without accurate load and generation profiles for these "dark" nodes, state estimation and flexibility dispatch are based on coarse assumptions that can trigger voltage violations or thermal overloads. The service provides building blocks for full network observability, enabling accurate grid state assessment even in sparsely metered environments.
Key Performance Indicators
MAE below 5% of rated asset capacity (or <0.1 kW for residential loads)
Absolute bias below 2% of total energy over the evaluation horizon
Minimum 30% improvement over traditional static Standard Load Profiles
API uptime ≥99.5% and response latency <200ms per request
Data Provided
Time-indexed active power (P_ac_kW), reactive power (Q_ac_kvar), and optional confidence bounds per asset
Nowcast at T₀ and forecast from T₀+15min to T₀+48h at 15-min resolution
Model version hash, input data hash, and inference timestamp for full traceability
Inputs: asset metadata (type, capacity, orientation, GPS), weather data (irradiance, temperature, cloud cover), historical SCADA references
TEF
TEF DSO