A Novel Combined Electricity Price Forecasting Method Based on Data Driven Algorithms

In the deregulated electricity market, accurate knowledge of electricity price tend helps maximize the profitability of the participants in the electricity market, so electricity price forecasting becomes extremely important. On the basis of not considering the situation of the electricity market it...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2019 IEEE Transportation Electrification Conference and Expo, Asia-Pacific (ITEC Asia-Pacific) s. 1 - 7
Hlavní autoři: Zhnag, Liang, Zou, Bin, Wang, Hongtao
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.05.2019
Témata:
Accuracy
BP Neural Network
Data models
Electricity
Electricity price forecasting
Electricity supply industry
Forecasting
Lasso
Load modeling
Neural networks
Prediction algorithms
Predictive models
Random Forest
SVM
Transportation
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:In the deregulated electricity market, accurate knowledge of electricity price tend helps maximize the profitability of the participants in the electricity market, so electricity price forecasting becomes extremely important. On the basis of not considering the situation of the electricity market itself and many factors affecting the electricity price, the historical load and electricity price are used as inputs to predict the electricity price from the perspective of data driven. The Lasso, Random Forest, Support Vector Machine and BP Neural Network methods are used to establish a single algorithmic electricity price model respectively, and then the linear Lasso and nonlinear BP neural network are used to make combined the prediction results of four single algorithmic electricity price models. Finally, the actual electricity price and load data from Queensland are used for simulation. The simulation results show that: (i) Among the four electricity price models, BP neural network model has the highest accuracy, and the average absolute error is 6.034. The Random Forests model has the worst accuracy, with an average absolute error of 9.669. (ii) The combined nonlinear BP neural network model can predict the electricity price more accurately with an average absolute error of 4.641.
DOI:10.1109/ITEC-AP.2019.8903690