End User
City of Athens
Description
The Short-Term Building Load Forecasting service delivers probabilistic electricity consumption forecasts at 15-minute resolution for horizons spanning from one hour to twenty-four hours ahead, covering every smart-metered building in the municipal estate. Accurate short-term forecasts serve as the informational foundation for demand response scheduling, PV self-consumption optimisation, and anomaly detection baselines across the broader service portfolio. The service maintains a dedicated forecasting model per building, calibrated to each building's specific contextual drivers.
Core Capabilities
Monitoring & Anomaly Detection
Predictive & Prescriptive Analytics
Business Need
Demand response scheduling, self-consumption optimisation, and anomaly detection all depend on knowing what buildings are expected to consume before consumption occurs. Without reliable short-term forecasts, curtailment recommendations cannot be reliably sized, self-consumption schedules cannot be accurately timed, and anomaly detection thresholds must be set conservatively. The service provides the shared forecasting infrastructure layer that enables the Municipality's broader portfolio of AI energy services to operate with operational reliability.
Key Performance Indicators
Mean Absolute Error (MAE) per building, stratified by building category and forecast horizon
Mean Absolute Percentage Error (MAPE) at building and portfolio level
Probabilistic calibration: stated prediction intervals must contain the true outcome at the specified confidence rate
API availability: 99%+ uptime with 95th percentile response latency below acceptable threshold
Data Provided
15-minute historical consumption data per building (up to 12 months rolling window)
Weather data including outdoor temperature, irradiance, and humidity
Calendar and occupancy features (public holiday schedule, school term dates, building operating hours)
Net consumption forecasts for PV-equipped buildings combining load and generation predictions
Model performance dashboard with rolling accuracy metrics per building
TEF
TEF BUILD