Denne oppgaven dreier seg om prognostisering av systemprisen på Nord Pool. Vi har introdusert et kunstig nevralt nettverk som inkluderer eksogene variabler for å lage kortsiktige prisprognoser for systemprisen, og sammenligner denne prognosen med prognoser fra tradisjonelle ARIMA modeller. Forskjellen mellom vår beste tidsseriemodell, SARIMAX- modellen, og det nevrale nettverket var minimale med en MAPE på henholdsvis 5,02% og 4,65% ved statisk prognose én dag frem. Dette er vesentlig bedre enn en naiv prognosemodell med MAPE på 6,57%. Ved prognoser syv dager frem presterte alle modellene dårligere enn ved den statiske prognosen, i tillegg til at forskjellen mellom den naive modellen og modellene med eksogene variabler ble over tre p...
This paper presents neural networks applied for short term electricity price forecasting in Ontario ...
Electricity spot prices are difficult to predict since they depend on different unstable and erratic...
Nevrale Ordinære Differentiallikninger (NODE) [Chen et al., 2018] er en ny familie av nevrale nettve...
Med økende bruk av fornybare energikilder har utviklingen av prismodeller for intradag handel blitt ...
I denne oppgaven har vi bygget modeller for å predikere strømpriser i Trøndelag, inkludert en lineær...
Omleggingen fra de regulerte, lokale monopolkraftmarkedene i Norge til liberaliseringen av krafthand...
The rapid development of wind energy in Sweden created a volatile environment for the electricity ma...
A trend in increasing electricity consumption and technological innovation has resulted in automated...
With electricity markets birth, electricity price volatility becomes one of the major concerns for t...
Forecasting electricity prices is one of the most important issues in the competitive environment of...
Short-term forecasting of power consumption is an important tool for decision makers in the energy s...
In this thesis two main studies are conducted to compare the predictive capabilities of feed-forward...
The liberalization of electricity markets has launched an interest in forecasting future prices and ...
Forecasting the consumption of electric power on a daily basis allows considerable money savings for...
In this master thesis, the hourly electricity load in Norway for 2019 is forecasted a day-ahead, usi...
This paper presents neural networks applied for short term electricity price forecasting in Ontario ...
Electricity spot prices are difficult to predict since they depend on different unstable and erratic...
Nevrale Ordinære Differentiallikninger (NODE) [Chen et al., 2018] er en ny familie av nevrale nettve...
Med økende bruk av fornybare energikilder har utviklingen av prismodeller for intradag handel blitt ...
I denne oppgaven har vi bygget modeller for å predikere strømpriser i Trøndelag, inkludert en lineær...
Omleggingen fra de regulerte, lokale monopolkraftmarkedene i Norge til liberaliseringen av krafthand...
The rapid development of wind energy in Sweden created a volatile environment for the electricity ma...
A trend in increasing electricity consumption and technological innovation has resulted in automated...
With electricity markets birth, electricity price volatility becomes one of the major concerns for t...
Forecasting electricity prices is one of the most important issues in the competitive environment of...
Short-term forecasting of power consumption is an important tool for decision makers in the energy s...
In this thesis two main studies are conducted to compare the predictive capabilities of feed-forward...
The liberalization of electricity markets has launched an interest in forecasting future prices and ...
Forecasting the consumption of electric power on a daily basis allows considerable money savings for...
In this master thesis, the hourly electricity load in Norway for 2019 is forecasted a day-ahead, usi...
This paper presents neural networks applied for short term electricity price forecasting in Ontario ...
Electricity spot prices are difficult to predict since they depend on different unstable and erratic...
Nevrale Ordinære Differentiallikninger (NODE) [Chen et al., 2018] er en ny familie av nevrale nettve...