Postgraduate Diploma in Demand and Generation Forecasting
Online 800-hour Postgraduate Diploma in Demand and Generation Forecasting. 8 modules covering Regulation (EU) 2017/1485 (system operation), Regulation (EU) 2017/2195 (electricity balancing) and Python (scikit-learn, statsmodels). Dedicated tutor and open enrolment.
Take the controls.
Run a real engineering trade-off from this field. Move the sliders, watch the model react in real time and beat the challenge.
What you will be able to do
Understand the horizons and uses of energy forecasting.
Apply statistical time-series models to electricity demand.
Develop machine learning models for energy forecasting.
Use numerical weather predictions as model inputs.
Forecast wind and solar generation for plants and portfolios.
Build and evaluate probabilistic forecasts.
Deploy and operate a forecasting system in production.
Who it's for
- Energy forecasting analyst looking to specialise in Demand and Generation Forecasting.
- Energy data scientist looking to specialise in Demand and Generation Forecasting.
- Energy meteorologist looking to specialise in Demand and Generation Forecasting.
- Market operations engineer looking to specialise in Demand and Generation Forecasting.
- Electricity demand analyst looking to specialise in Demand and Generation Forecasting.
- Forecasting systems engineer looking to specialise in Demand and Generation Forecasting.
- Engineering or science graduates seeking to enter system operators.
What you'll work with
- Regulation (EU) 2017/1485 (system operation)
- Regulation (EU) 2017/2195 (electricity balancing)
- Regulation (EU) 1227/2011 (REMIT)
- IEC 61724-1 (photovoltaic plant monitoring)
- ISO 9060 (pyranometers)
- WMO-No. 8 (guide to meteorological instruments)
8 modules · 800 h
1.1Horizons: very short, short, medium and long term1.2Uses of forecasting in operations and markets1.3Time series: trend and seasonality1.4Electricity demand patterns1.5Variability of renewable generation1.6Explanatory variables: weather and calendar1.7Energy and meteorological data sources1.8Error metrics: MAE, RMSE and MAPE1.9Point versus probabilistic forecasting1.10Workshop: exploratory analysis of REE demand
2.1Exponential smoothing and Holt-Winters2.2ARIMA and SARIMA models2.3Models with exogenous variables (ARIMAX)2.4Multiple linear regression2.5Temperature effect models2.6Calendar and public holiday models2.7STL decomposition2.8Model selection and time-series cross-validation2.9Prophet and additive models2.10Laboratory: SARIMAX for hourly demand in Python
3.1Time-series feature engineering3.2Decision trees and random forest3.3Gradient boosting: XGBoost and LightGBM3.4LSTM and GRU neural networks3.5Transformers for time series3.6Foundation models for time series3.7Hyperparameter tuning3.8Interpretability with SHAP3.9Overfitting and data leakage risks3.10Laboratory: demand forecasting with LightGBM
4.1Numerical weather prediction (NWP) models4.2ECMWF and GFS models4.3Ensemble forecasting4.4Downscaling and bias correction4.5Solar radiation: components and measurement4.6Wind: vertical profile and extrapolation4.7Satellite imagery for nowcasting4.8Sky cameras for minute-scale forecasting4.9ERA5 reanalysis data4.10Practical: bias correction of an NWP forecast
5.1Photovoltaic forecasting: physical models5.2Transposition and PV power models5.3Wind forecasting with power curves5.4Wake effects and availability5.5Regional aggregate forecasting5.6Behind-the-meter self-consumption forecasting5.7Ramp events5.8Curtailment and its effect on data5.9Comparison of forecasting providers5.10Laboratory: PV forecasting with pvlib
6.1Quantile regression6.2Prediction intervals6.3Evaluation metrics: pinball loss and CRPS6.4Calibration and PIT diagrams6.5Scenarios with copulas6.6Conformal prediction6.7Forecast combination6.8Hierarchical forecasting and reconciliation6.9Use in reserves and markets6.10Practical: quantile forecasting of wind generation
7.1Architecture of a forecasting system7.2Real-time data pipelines7.3Model retraining and drift7.4Performance monitoring7.5Forecasting for day-ahead and intraday markets7.6Cost of imbalances and their optimisation7.7Forecasting for the system operator7.8Forecasting requirements in regulation7.9Communicating uncertainty7.10Case study: economic impact of forecast error on imbalances
8.1Problem and horizon definition8.2Data collection and cleaning8.3Exploratory analysis8.4Benchmark models8.5Advanced machine learning models8.6Probabilistic forecasting and evaluation8.7Deployment and monitoring8.8Economic value analysis8.9Report and presentation8.10Final review with the tutor
How you'll learn
100% online training on the SEIUM Institute campus, with downloadable material, recorded classes and an assigned technical tutor. No fixed timetable: students progress at their own pace within the intake, making it possible to combine with work.
Each module combines theory, guided reading of the original standard and applied exercises. The working software is Python (scikit-learn, statsmodels), R (forecast), TensorFlow, Prophet, CDO (meteorological data), in free, academic or evaluation versions. Assignments are studied on real demand forecasting procedures using historical data, wind and solar forecasting with weather models, and evaluation of probabilistic forecasts. Assessment is continuous per module plus the final integrating project.
Build it end to end
Your final project follows the real engineering workflow, step by step, reviewed by your tutor.
Understand the horizons and uses of energy forecasting.
Apply statistical time-series models to electricity demand.
Develop machine learning models for energy forecasting.
Use numerical weather predictions as model inputs.
Forecast wind and solar generation for plants and portfolios.
Where this takes you
Requirements
- Prior technical training or professional experience in the sector. No university degree is required.
- Internet connection and a computer capable of running the programme's software.
- Sufficient Spanish-language proficiency to follow technical regulatory texts.
Ready to start?
Send your application today. Our admissions team replies within 72 hours with your study plan and funding options.
Frequently asked questions
The programme totals 800 hours spread over 6 to 8 months. That is between 10 and 15 hours a week on average, compatible with a full-time job.
You work with Python (scikit-learn, statsmodels), R (forecast), TensorFlow, Prophet, CDO (meteorological data). Free, academic or evaluation versions are used, and the tutor indicates the open-source alternative where one exists.
An own diploma from SEIUM Institute upon passing the continuous assessment and the integrating project. It is in-house training, not an official Ministry qualification.
Yes. Modules passed in a course or postgraduate diploma in the same area are recognised in the advanced programme. Check the recognition policy when enrolling.
Related programmes
Postgraduate Diploma in High Renewable Penetration and Synthetic Inertia
Online 800-hour Postgraduate Diploma in High Renewable Penetration and Synthetic Inertia. 8 modules covering Regulation (EU) 2016/631 (RfG network code), Regulation (EU) 2017/1485 (SOGL operation guidelines)…
Postgraduate Diploma in Relay Coordination and Characteristic Curves
Online Postgraduate Diploma of 800 h in Relay Coordination and Characteristic Curves. 8 modules covering IEC 60255-151 (overcurrent protection), IEEE C37.112 (inverse-time curves) and ETAP. Assigned…
Postgraduate Diploma in Certifications and EU Taxonomy Compliance
Online 800-hour Postgraduate Diploma in Certifications and EU Taxonomy Compliance. 8 modules covering Regulation (EU) 2020/852 (taxonomy), Delegated Regulation (EU) 2021/2139 (technical climate criteria) and advanced…
More in Energy and Networks
All Energy and Networks programmes → · How to apply · Fees & financing · Scholarships