Abstract
Power load forecasting plays a pivotal role in improving the safety and stability of the distribution networks. First, the Prophet and Bi-directional Long short-term memory (BiLSTM) models were established respectively. Then, the CRITIC weight method was used to linearly combine the two models. Finally, the Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) were defined evaluation indicators. Through comparing with Prophet, BiLSTM, ARIMMA forecasting model of one distribution network, the prediction accuracy of the Prophet-BiLSTM-CRITIC model proposed in this paper was significantly higher than the other single models.
Science-Technology Innovation Platform and Talents Program of Hunan Province, China, under Grant 2019TP1053.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Yenidoğan I, Çayir A, Kozan O et al (2018) Bitcoin forecasting using ARIMA and PROPHET. In: 2018 3rd international conference on computer science and engineering (UBMK). IEEE, Sarajevo, Bosnia and Herzegovina, pp 621–624
Shuvo MAR, Zubair M, Purnota AT et al (2021) Traffic forecasting using time-series analysis. In: 2021 6th international conference on inventive computation technologies (ICICT). IEEE, Coimbatore, India, pp 269–274
Parizad A, Hatziadoniu CJ (2021) Using prophet algorithm for pattern recognition and short term forecasting of load demand based on seasonality and exogenous features. In: 2020 52nd North American power symposium (NAPS). IEEE, Tempe, AZ, USA, pp 1–6
Holden K, Peel DA (2010) An empirical investigation of combinations of economic forecasts. J Forecast 5(4)
Liwen L, Dabin Z (2019) A review of construction and application of combination forecast model. Statist Decis 35(01):18–23
Taylor SJ, Letham B (2018) Forecasting at scale. Am Statist 72(1):37–45
Chang T, Guo Z, Xu L (2019) Scale prediction of AQI based on prophet-random forest optimization model. Environ Pollut Control 41(7):758–761+766
Graves A, Schmidhuber J (2005) Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural Netw 18(5–6):602–610
Li Y, Yuxi W, Junli W et al (2018) Research on recurrent neural network. J Comput Appl 38(z2):1–6, 26, 1–6+26
Siami-Namini S, Tavakoli N, Namin AS (2019) The performance of LSTM and BiLSTM in forecasting time series. In: 2019 IEEE international conference on big data (big data).IEEE, Los Angeles, CA, USA, pp 3285–3292
Kiruthiga D, Manikandan V (2021) Time series load forecasting using multitask deep neural network. In: 2021 IEEE second international conference on control, measurement
Zhang H, Lu M, Luo X et al (2019) Evaluation of black-start schemes based on prospect theory and improved TOPSIS method. In: 2019 IEEE international conference on energy internet (ICEI). IEEE, Nanjing, China, pp 339–344
Wenjie F, Xiangning X, Shun T (2018) A multi-index evaluation method of voltage sag based on the comprehensive weight. In: 2018 China international conference on electricity distribution (CICED). IEEE, Tianjin, China, pp 613–617
Li YJ, Yang Y, Zhu K et al (2021) Clothing sale forecasting by a composite GRU-prophet model with an attention mechanism. Trans Ind Inform
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Li, W., Guo, Q., Wen, M., Zhang, Y., Pan, X., Yang, S. (2022). Energy Internet-Oriented Distribution Network Long-Term Load Forecasting Method Based on Prophet-BiLSTM-CRITIC Mode. In: Hu, C., Cao, W., Zhang, P., Zhang, Z., Tang, X. (eds) Conference Proceedings of 2021 International Joint Conference on Energy, Electrical and Power Engineering. Lecture Notes in Electrical Engineering, vol 899. Springer, Singapore. https://doi.org/10.1007/978-981-19-1922-0_48
Download citation
DOI: https://doi.org/10.1007/978-981-19-1922-0_48
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-1921-3
Online ISBN: 978-981-19-1922-0
eBook Packages: EnergyEnergy (R0)