Course in Electricity Demand Forecasting with AI
Online 300 h course in electricity demand forecasting with AI. 6 modules covering Regulation (EU) 2017/1485 (SO GL), Regulation (EU) 2019/943 and Python (scikit-learn). Assigned 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
Analyse the determinants of electricity demand.
Apply reference statistical models to demand time series.
Develop machine learning models with exogenous variables.
Implement deep neural networks for time series.
Evaluate forecasts using point and probabilistic metrics.
Deploy models in production with monitoring.
Communicate forecasting results to operators and the business.
Who it's for
- Energy data scientist looking to specialise in Electricity Demand Forecasting with AI.
- Demand forecasting analyst looking to specialise in Electricity Demand Forecasting with AI.
- Machine learning engineer looking to specialise in Electricity Demand Forecasting with AI.
- System operation analyst looking to specialise in Electricity Demand Forecasting with AI.
- Electricity market analyst looking to specialise in Electricity Demand Forecasting with AI.
- MLOps engineer looking to specialise in Electricity Demand Forecasting with AI.
- Engineering or science graduates seeking to enter system operators.
What you'll work with
- Regulation (EU) 2017/1485 (SO GL)
- Regulation (EU) 2019/943
- Regulation (EU) 2024/1689 on Artificial Intelligence
- Regulation (EU) 543/2013 on transparency
- ISO/IEC 23053:2022
- ISO/IEC 42001:2023
6 modules · 300 h
1.1Load curve and temporal patterns1.2Daily, weekly and annual seasonality1.3Influence of temperature1.4Working calendar and public holidays1.5Economic and demographic effects1.6Self-consumption and net demand1.7Electrification and electric vehicles1.8Forecasting horizons1.9MAPE, RMSE and pinball metrics1.10Workshop: exploratory analysis of peninsular demand
2.1Persistence and similar-day models2.2Multiple linear regression2.3ARIMA and SARIMA models2.4Exponential smoothing2.5Models with exogenous variables2.6STL decomposition2.7Prophet and additive models2.8Temporal cross-validation2.9Prediction intervals2.10Lab: SARIMAX with temperature
3.1Temporal feature engineering3.2Decision trees and random forest3.3Gradient boosting with LightGBM and XGBoost3.4Support vector machines3.5Feature selection3.6Hyperparameter tuning3.7Model ensembles3.8Interpretability with SHAP3.9Outlier management3.10Practical: next-day LightGBM model
4.1Recurrent neural networks and LSTM4.2Temporal convolutional networks4.3Transformers for time series4.4N-BEATS and N-HiTS4.5Temporal Fusion Transformer4.6Foundation models for time series4.7Probabilistic forecasting by quantiles4.8Hierarchical forecasting4.9Transfer learning between regions4.10Lab: LSTM network in PyTorch
5.1Real-time data architecture5.2Integration of weather forecasts5.3MLOps and model versioning5.4Drift monitoring5.5Automatic retraining5.6Forecasting for system operators5.7Forecasting for retailers5.8Extreme events and structural changes5.9Explaining results to the business5.10Case study: model degradation after a heatwave
6.1Definition of the use case6.2Preparation of the dataset6.3Reference models6.4Artificial intelligence model6.5Comparative evaluation6.6Deployment proposal6.7Model interpretability analysis6.8Monitoring and retraining plan6.9Report and presentation6.10Final review with the tutor
How you'll learn
100% online training on the SEIUM campus, with downloadable material, recorded classes and an assigned technical tutor. No fixed timetables: students progress at their own pace within the intake, making it possible to combine study with work.
Each module combines theory, guided reading of the original standard and applied exercises. The working software is Python (scikit-learn), LightGBM, PyTorch, Prophet, MLflow, in free, academic or evaluation versions. Assignments are based on real development procedures for a next-day forecasting model, comparison of statistical and deep learning models, and deployment of a retraining workflow. Assessment is continuous per module plus the final integrative project.
Build it end to end
Your final project follows the real engineering workflow, step by step, reviewed by your tutor.
Analyse the determinants of electricity demand.
Apply reference statistical models to demand time series.
Develop machine learning models with exogenous variables.
Implement deep neural networks for time series.
Evaluate forecasts using point and probabilistic metrics.
Where this takes you
Requirements
- No prior degree is required.
- Internet connection and a computer capable of running the programme's software.
- Sufficient Spanish 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 300 hours spread over 3 to 5 months. That is an average of 10 to 15 hours per week, compatible with a full-time job.
You will work with Python (scikit-learn), LightGBM, PyTorch, Prophet, MLflow. Free, academic or evaluation versions are used, and the tutor indicates the open-source alternative where one exists.
An SEIUM in-house diploma upon passing the continuous assessment and the integrative project. It is in-house training, not an official qualification from the Ministry.
Yes. Modules passed in a course or postgraduate diploma in the same area are recognised in the advanced programme. Check the recognition policy when you enrol.
Related programmes
NIS2 Compliance Course for the Energy Sector
Online 300-hour course in NIS2 compliance for the energy sector. 6 modules covering Directive (EU) 2022/2555 (NIS2), Implementing Regulation (EU) 2024/2690 and Eramba. Assigned tutor and…
Course on Reduction of Technical and Non-Technical Losses
The Course on Reduction of Technical and Non-Technical Losses explores comprehensive strategies to minimise energy losses in electrical systems. It addresses the analysis of technical losses,…
Course on AI Applied to Electricity Price Forecasting
Online 300 h course in AI applied to electricity price forecasting. 6 modules covering Regulation (EU) No 1227/2011 (REMIT), Regulation (EU) 2019/943 on the internal market…
More in Energy and Networks
All Energy and Networks programmes → · How to apply · Fees & financing · Scholarships