A Frequency Decomposition-Based Hybrid Forecasting Algorithm for Short-Term Reactive Power

This paper proposes a new frequency decomposition-based hybrid reactive power forecasting algorithm, EEMD-LSTM-RFR (ELR), which adopts a strategy of frequency decomposition prediction after ensemble empirical mode decomposition and then data reconstruction to improve the prediction ability of reacti...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Energies (Basel) Ročník 14; číslo 20; s. 6606
Hlavní autoři: Du, Jiabao, Yue, Changxi, Shi, Ying, Yu, Jicheng, Sun, Fan, Xie, Changjun, Su, Tao
Médium: Journal Article
Jazyk:angličtina
Vydáno: Basel MDPI AG 01.10.2021
Témata:
Accuracy
Algorithms
Decomposition
Energy resources
ensemble empirical mode decomposition
Forecasting
forecasting algorithm
long short-term memory
Machine learning
Neural networks
Noise
random forest regression
reactive power
Signal processing
Time series
Wavelet transforms
ISSN:1996-1073, 1996-1073
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:This paper proposes a new frequency decomposition-based hybrid reactive power forecasting algorithm, EEMD-LSTM-RFR (ELR), which adopts a strategy of frequency decomposition prediction after ensemble empirical mode decomposition and then data reconstruction to improve the prediction ability of reactive power. This decomposition process can compress the high frequency of reactive power and benefits the following separate forecasting. Long short-term memory is proposed for the high-frequency feature of reactive power to deal with the forecasting difficulty caused by strong signal disturbance and randomness. In contrast, random forest regression is applied to the low-frequency part in order to speed up the forecasting. Four classical algorithms and four hybrid algorithms based on different signal decompositions are compared with the proposed algorithm, and the results show that the proposed algorithm outperforms those algorithms. The predicting index RMSE decreases to 0.687, while the fitting degree R2 gradually approaches 1 with a step-by-step superposition of high-frequency signals, indicating that the proposed decomposition-predicting reconstruction strategy is effective.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1996-1073
1996-1073
DOI:10.3390/en14206606