{"id":1647,"date":"2025-09-24T13:07:02","date_gmt":"2025-09-24T13:07:02","guid":{"rendered":"https:\/\/prg.inf.unibe.ch\/?page_id=1647"},"modified":"2025-09-24T13:07:02","modified_gmt":"2025-09-24T13:07:02","slug":"thesis-adaptive-online-learning-for-short-term-pv-power-prediction","status":"publish","type":"page","link":"https:\/\/prg.inf.unibe.ch\/index.php\/education\/thesis-adaptive-online-learning-for-short-term-pv-power-prediction\/","title":{"rendered":"thesis-Adaptive Online Learning for Short-Term PV Power Prediction"},"content":{"rendered":"\n
<\/div>\n\n\n\n
<\/div>
\n
<\/div>\n

Adaptive Online Learning for Short-Term PV Power Prediction<\/h1>\n\n\n\n

Co-Supervised by:<\/strong> Fereshteh Jafari<\/p>\n\n\n\n

If you are interested in this topic or have further questions, do not hesitate to contact fereshteh.jafari@unibe.ch<\/a>.<\/p>\n\n\n\n

Background \/ Context<\/strong><\/p>\n\n\n\n

Traditional photovoltaic (PV) power prediction models are trained offline using historical data and remain static during deployment. However, solar energy systems operate in dynamic environments where weather patterns, seasonal changes, equipment aging, and new PV installations continuously affect performance. Static models cannot adapt to these evolving conditions, leading to degraded prediction accuracy over time. Online learning approaches offer a solution by enabling models to continuously update their parameters as new data becomes available. This capability is particularly valuable for short-term forecasting (10 minutes to 2 hours ahead), where rapid weather changes can significantly impact prediction accuracy and energy management decisions.<\/p>\n\n\n\n

Research Question(s) \/ Goals<\/strong><\/p>\n\n\n\n

The primary goal is to develop and evaluate an adaptive online learning system for short- term PV power prediction that can:<\/p>\n\n\n\n