Analysis on Impact of Renewable Energy Generation on Real-time Electricity Price: Data Empirical Research on Electricity Spot Market of Germany

被引：0
|
作者：
Liu D. [1 ,2 ]
Zhao D. [1 ,2 ]
Bai M. [1 ,2 ]
Wang Q. [1 ,2 ]
Li C. [1 ,2 ]
机构：
[1] School of Economics and Management, North China Electric Power University, Beijing
[2] Beijing Key Laboratory of New Energy and Low-Carbon Development (North China Electric Power University), Beijing
来源：
Dianli Xitong Zidonghua/Automation of Electric Power Systems | 2020年 / 44卷 / 04期
基金：
中国国家自然科学基金;
关键词：
Electricity spot market; Feature representation; Real-time electricity price; Renewable energy generation;
D O I：
10.7500/AEPS20190117001
中图分类号：
学科分类号：
摘要：
Real-time electricity trading in electricity spot market can give full play to market regulation and promote the accommodation of renewable energy. Data empirical research on the impact of renewable energy generation on real-time electricity price has an essential reference value for understanding the operation rules of the spot market and evaluating market maturity. Electricity spot market of Germany is selected to conduct data empirical research. Data of power generation, load, prediction error, price and other factors are collected. The impact analysis of renewable energy generation on real-time electricity price is studied based on feature representation method for time series. Firstly, the time domain models of time series are transformed into feature vectors by using the feature representation method. Secondly, the greedy forward feature selection algorithm is used to extract key features to maximize the differences between factors. Thirdly, the correlation among multiple factors is discussed based on the overall features and key features respectively, and the network of influence mechanism is constructed. The empirical results show that the real-time electricity price in electricity spot market of Germany is mainly affected by prediction error of wind power generation, and the correlation between factors mainly comes from features such as Fourier transformation, wavelet transformation and discrete symbolization. Finally, by the simple comparison between China and Germany, it is pointed out that the real-time electricity price in Guangdong electricity market of China is more affected by the randomness of renewable energy generation than by the prediction error. © 2020 Automation of Electric Power Systems Press.
引用
收藏
页码：126 / 133
页数：7
相关论文
共 36 条
  • [21] Fulcher B.D., Feature-based time-series analysis
  • [22] Sergios T., Konstantinos K., Pattern Recognition, (2016)
  • [23] Fulcher B.D., Jones N.S., Highly comparative feature-based time-series classification, IEEE Transactions on Knowledge and Data Engineering, 26, 12, pp. 3026-3037, (2014)
  • [24] Ye L.X., Keogh E., Time series shapelets, Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, (2009)
  • [25] Rakthanmanon T., Keogh E., Fast shapelets: a scalable algorithm for discovering time series shapelets, Proceedings of the 2013 SIAM International Conference on Data Mining, (2013)
  • [26] Xia X., Shang N., Fang J.L., Et al., Management of bilateral contracts for gencos considering the risk in spot market, Energy Procedia, 159, pp. 298-303, (2019)
  • [27] Liu Y., Liao S.Z., Granularity selection for cross-validation of SVM, Information Sciences, 378, pp. 475-483, (2017)
  • [28] Duarte E., Wainer J., Empirical comparison of cross-validation and internal metrics for tuning SVM hyperparameters, Pattern Recognition Letters, 88, pp. 6-11, (2017)
  • [29] Fulcher B.D., Jones N.S., Hctsa: a computational framework for automated time-series phenotyping using massive feature extraction, Cell Systems, 5, 5, pp. 527-531, (2017)
  • [30] Fulcher B.D., Little M.A., Jones N.S., Highly comparative time-series analysis: the empirical structure of time series and their methods, Journal of the Royal Society Interface, 10, 83, (2013)
1234