Education, Science, Technology, Innovation and Life
Open Access
Sign In
  1. Home
  2. Journals
  3. Journal of Electrotechnology, Electrical Engineering and Management
  4. Vol 5, Issue 2, 2022

Short-term Electricity Price Forecast and Analysis Based on LSTM in Spot Electricity Market

Download as PDF

DOI: 10.23977/jeeem.2022.050208 | Downloads: 12 | Views: 528

Author(s)

Bo Gao 1, Pengyang Yan 2, Xuwen Liu 1, Changyu Qian 2, Linjie Wang 1

Affiliation(s)

1 Jiangsu Power Exchange Center Co., Ltd., No. 62, Yunnan Road, Gulou District, Nanjing, China
2 School of Electrical Engineering, Southeast University, No. 2, Sipailou, Xuanwu District, Nanjing, China

Corresponding Author

Changyu Qian

ABSTRACT

Aiming at the problem of short-term electricity price forecasting in the spot electricity market, this paper proposes a short-term electricity price forecasting algorithm based on LSTM neural network. Firstly, the algorithm constructs the electricity price correlation factor matrix, and then uses the LSTM model to forecast the electricity price. In the LSTM model, the Adam gradient descent method is used to estimate the input, forgetting and output of the LSTM model, and the node price data in the forecasting time interval are obtained. Using the PJM-RTO actual node price data of PJM website, the simulation results show that the proposed method can accurately predict the node price. Compared with the prediction interval of one week, two weeks and two months, the accuracy is the highest when the prediction interval is one month, the average absolute error percentage and average absolute error are the minimum, and the prediction effect is the best.

KEYWORDS

LSTM neural network, Electricity price forecasting, Electric spot market

CITE THIS PAPER

Bo Gao, Pengyang Yan, Xuwen Liu, Changyu Qian, Linjie Wang, Short-term Electricity Price Forecast and Analysis Based on LSTM in Spot Electricity Market . Journal of Electrotechnology, Electrical Engineering and Management (2022) Vol. 5: 57-65. DOI: http://dx.doi.org/10.23977/jeeem.2022.050208.

REFERENCES

[1] Ji Xingquan, Zeng Ruomei, Zhang Yumin, Song Feng, Sun Pengkai, Zhao Guohang. Short-term electricity price forecasting of CNN-LSTM based on attention mechanism. Power system Protection and Control, 2022jue 50 (17): 125-132.
[2] Wei Qin, Chen Shijun, Huang Weibin, Ma Guangwen, Tao Chunhua. The prediction method of clearing price in spot market based on random forest regression. Chinese Proceedings of the CSEE, 2021, 41 (04): 1360-1367, 1542. 
[3] Fu Fengyi, Zhang Zheng, Yuan Kai, Li Natural. Hybrid forecasting method of day-ahead electricity price based on Kalman filter. Electrical Automation, 2022 and 44 (04): 57-60.
[4] Chen Jieyao, Tao Chunhua, Ma Guangwen, Chen Shijun, Zhao Yonglong, Wang Jing. Prediction method of clearing price in spot market based on data mining and support vector machine. Power Grid and Clean Energy, 2020 and 36 (10): 14-19: 27. 
[5] Bai Rui, Luo Gang, Tang Lin, Bai Song. Short-term electricity price prediction of high proportion wind power based on genetic algorithm. People's Yangtze River, 2022,553 (S1): 119-124.
[6] Wang Jinxin, Jiang Ziyan, Wang Qi, Li Dong, Yu Furong, bangs, Ren Xianyuan. Price forecasting of Mengxi Electric Power spot Market based on SA-BP algorithm. Inner Mongolia Electric Power, 2021 Magi 39 (04): 4246.
[7] Li Haiping. Short-term electricity price forecasting based on ARMA-GARCH model. North China Electric Power University (Beijing), 2009.
[8] Gong Weitao. Research on Forecast method of Day-ahead electricity Price in electricity Market. Donghua University, 2019.
[9] Real-Time Hourly LMPs (PJM);http://dataminer2.pjm.com/feed/rt_hrl_lmps/definition.

Subscription
E-Mail Alert
Most popular papers
Call for Special Issue
Publication Ethics & OA Statement
Plagiarism Policy
Contact Us
Downloads: 2068
Visits: 97347

Sponsors, Associates, and Links

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.