Predictor Analysis for Electricity Price Forecasting by Multiple Linear Regression

被引：0

作者：

Ulgen, Toygar ^{[1
]}

Poyrazoglu, Gokturk ^{[1
]}

机构：

[1] Ozyegin Univ, Elect & Elect Engn, Istanbul, Turkey

来源：

2020 INTERNATIONAL SYMPOSIUM ON POWER ELECTRONICS, ELECTRICAL DRIVES, AUTOMATION AND MOTION (SPEEDAM 2020) | 2020年

关键词：

electricity price forecasting; multiple linear regression; dynamic regression; fuel price impact;

D O I：

10.1109/speedam48782.2020.9161866

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

This paper examines the multiple linear regression method on electricity price forecasting. Numerous predictors are analyzed to reduce the mean absolute percentage error. The training data includes the dates from September 2018 to September 2019 from the day-ahead electricity market in Turkey. It is proved that the lagged electricity prices such as the previous one day, one week, and lagged moving average prices play a key role in electricity price estimation. Aside from other valuable coefficients, natural gas, oil, and coal prices are tested in the forecasting model. The error rates of the fuel prices are noticeably shrunk by using multiple linear regression that generates more accurate results and crucial variables influencing hourly electricity price has determined. Different training data length is an essential part of decreasing the error proportions in the electricity price estimation. Also, it is analyzed that there is no dramatic difference regarding the error rates if it is compared to the regular regression method and dynamic regression model in the forecast of electricity prices.

引用

页码：618 / 622

页数：5

共 50 条

[41] Electricity Price Forecasting Based on AOSVR and Outlier Detection
By Zhou Dianmin
Electricity, 2005, (02) : 23 - 26
[42] Price forecasting in deregulated electricity markets - A bibliographical survey
Daneshi, H.
Daneshi, A.
2008 THIRD INTERNATIONAL CONFERENCE ON ELECTRIC UTILITY DEREGULATION AND RESTRUCTURING AND POWER TECHNOLOGIES, VOLS 1-6, 2008, : 657 - 661
[43] Ionospheric TEC forecasting using Gaussian Process Regression (GPR) and Multiple Linear Regression (MLR) in Turkey
Samed Inyurt
Mahsa Hasanpour Kashani
Aliihsan Sekertekin
Astrophysics and Space Science, 2020, 365
[44] A Singular Spectrum Analysis based Approach to Price Forecasting for a Day Ahead Electricity Market
Varshney, Harish
Sujil, A.
Kumar, Rajesh
2018 8TH IEEE INDIA INTERNATIONAL CONFERENCE ON POWER ELECTRONICS (IICPE), 2018,
[45] Forecasting of wind speed using multiple linear regression and artificial neural networks
Soukaina Barhmi
Omkaltoume Elfatni
Ismail Belhaj
Energy Systems, 2020, 11 : 935 - 946
[46] Ionospheric TEC forecasting using Gaussian Process Regression (GPR) and Multiple Linear Regression (MLR) in Turkey
Inyurt, Samed
Hasanpour Kashani, Mahsa
Sekertekin, Aliihsan
ASTROPHYSICS AND SPACE SCIENCE, 2020, 365 (06)
[47] Probabilistic Forecasting of Electricity Prices using Kernel Regression
Dudek, Grzegorz
2018 15TH INTERNATIONAL CONFERENCE ON THE EUROPEAN ENERGY MARKET (EEM), 2018,
[48] Mid-term Electricity Market Clearing Price Forecasting Using Multiple Support Vector Machine
Yan, Xing
Chowdhury, Nurul A.
2013 4TH IEEE/PES INNOVATIVE SMART GRID TECHNOLOGIES EUROPE (ISGT EUROPE), 2013,
[49] Annual Electricity and Energy Consumption Forecasting for the UK Based on Back Propagation Neural Network, Multiple Linear Regression, and Least Square Support Vector Machine
Liu, Yinlong
Li, Jinze
PROCESSES, 2023, 11 (01)
[50] MEG analysis with spatial filter and multiple linear regression
Okawa, S
Honda, S
SICE 2004 ANNUAL CONFERENCE, VOLS 1-3, 2004, : 1453 - 1457

← 1 2 3 4 5 →