Introduksjon av en mellomlangsiktig prognose for etterspørsel etter strøm i Norden

Hvor mye energi folk bruker, eller snarere hvor mye de vil bruke har potensielt store innvirkninger på energipris, produksjon og infrastruktur. Eirik Sjåvik har i sin masteroppgave ved UiO jobbet med en mellomlangsiktig prognose for etterspørsel etter strøm.

Foto: Anja van de Gronde/Unsplash

I masteroppgaven Electricity Demand Forecasting – Probabilistic Demand Forecasting Using Principal Components of Seasonal Temperature Forecasts har Sjåvik har sett på hvordan man kan bruke temperaturprognoser som funksjoner i en prognosemodell for strømbehov. Disse prognosene har en bred anvendelighet for aktører innen industri, energimarkeder, regjeringen og den bredere offentligheten.

Abstract:
In this thesis we introduce a medium-term forecast model for electricity demand in the Nordic region utilizing seasonal Numerical Weather Prediction (NWP) temperature forecasts. Our demand model is composed of two integral parts.

The first part is a structural demand model, which seeks to model electricity demand, at a specific target time, by utilizing temperature at the same target time. The temperature data consist of observations across a grid over the Nordic countries. By employing a principal component transformation of the temperature grid we seek to describe the relation between demand and the temperature field as a whole by a small subset of principal components. We model this relation through a Generalized Additive Model.

The second part is a probabilistic temperature forecast model utilizing NWP forecasts in principal component space. By combing the two parts we can form a probabilistic forecast of demand for the Nordic region.

We show that the models employed show great performance when compared to relevant baseline models. We also introduce a re-weighting scheme for NWP forecasts in principal component space. By re-weighing temperature forecasts after how well they recently have performed, we can ‘update’ the forecast and obtain short-term improvements in skill at any time point.

Norsk regnesentral er en av partnerne i Climate Futures, og masteroppgaven ble skrevet som en del av dette samarbeidet.

Last ned masteroppgaven.

Skroll til toppen