Quantile-Mixer: A Novel Deep Learning Approach for Probabilistic Short-Term Load Forecasting

被引:8
作者
Ryu, Seunghyoung [1 ,2 ]
Yu, Yonggyun [1 ]
机构
[1] Korea Atom Energy Res Inst, Appl Artificial Intelligence Sect, Daejeon 34057, South Korea
[2] Sejong Univ, Dept Intelligent Mechatron Engn, Seoul 05006, South Korea
基金
新加坡国家研究基金会;
关键词
Deep learning; short-term load forecasting; MLP-mixer; probabilistic forecasting; quantile regression; uncertainty; energy AI; ENERGY-STORAGE SYSTEMS; ADAPTIVE DROOP CONTROL; STATE; MICROGRIDS; ARCHITECTURES; BATTERIES; SOC;
D O I
10.1109/TSG.2023.3290180
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
As the power grid becomes more complex and dynamic, accurate short-term load forecasting (STLF) with probabilistic information is a prerequisite for various smart grid applications. For doing this, various deep learning models have been proposed, and recent models increase model size and complexity to achieve better accuracy which could also increase the burden on model design, computation time, and resources. To this end, we propose a novel deep learning model for accurate and efficient probabilistic STLF (PSTLF). First, we develop an STLF model utilizing the multi-layer perceptron (MLP)-mixer structure, i.e., MLP-mixer for STLF (MM-STLF), that has an advantage in forecasting accuracy and efficiency compared to the other deep learning models. Then, we propose a random quantile regression (RQR) method that takes a cumulative probability tau as an input to the model and is trained on random tau s. By combining MM-STLF and RQR, we develop a novel deep-PSTLF model, namely quantile-mixer (Q-mixer). We evaluate the overall performance of the proposed model with seven load datasets in terms of prediction error, model size, and inference time, respectively. Through experiments, various STLF models and probabilistic forecasting methods are compared, and the experimental results demonstrate the effectiveness of Q-mixer in load forecasting.
引用
收藏
页码:2237 / 2250
页数:14
相关论文
共 50 条
[41]   Short-Term Load Forecasting Based on VMD and Combined Deep Learning Model [J].
Wang, Nier ;
Xue, Sheng ;
Li, Zhanming .
IEEJ TRANSACTIONS ON ELECTRICAL AND ELECTRONIC ENGINEERING, 2023, 18 (07) :1067-1075
[42]   Multiscale-integrated deep learning approaches for short-term load forecasting [J].
Yang, Yang ;
Gao, Yuchao ;
Wang, Zijin ;
Li, Xi'an ;
Zhou, Hu ;
Wu, Jinran .
INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS, 2024, 15 (12) :6061-6076
[43]   Deep Learning Based on Multi-Decomposition for Short-Term Load Forecasting [J].
Kim, Seon Hyeog ;
Lee, Gyul ;
Kwon, Gu-Young ;
Kim, Do-In ;
Shin, Yong-June .
ENERGIES, 2018, 11 (12)
[44]   Deep Learning-Assisted Short-Term Load Forecasting for Sustainable Management of Energy in Microgrid [J].
Moradzadeh, Arash ;
Moayyed, Hamed ;
Zakeri, Sahar ;
Mohammadi-Ivatloo, Behnam ;
Aguiar, A. Pedro .
INVENTIONS, 2021, 6 (01) :1-11
[45]   Deep Learning with Stacked Denoising Auto-Encoder for Short-Term Electric Load Forecasting [J].
Liu, Peng ;
Zheng, Peijun ;
Chen, Ziyu .
ENERGIES, 2019, 12 (12)
[46]   Short-Term Load Forecasting for Electric Vehicle Charging Stations Based on Deep Learning Approaches [J].
Zhu, Juncheng ;
Yang, Zhile ;
Guo, Yuanjun ;
Zhang, Jiankang ;
Yang, Huikun .
APPLIED SCIENCES-BASEL, 2019, 9 (09)
[47]   Stacking Ensemble Methodology Using Deep Learning and ARIMA Models for Short-Term Load Forecasting [J].
Bento, Pedro M. R. ;
Pombo, Jose A. N. ;
Calado, Maria R. A. ;
Mariano, Silvio J. P. S. .
ENERGIES, 2021, 14 (21)
[48]   Novel approach considering load-relative factors in short-term load forecasting [J].
Kang, CQ ;
Cheng, X ;
Xia, Q ;
Huang, YH ;
Gao, F .
ELECTRIC POWER SYSTEMS RESEARCH, 2004, 70 (02) :99-107
[49]   A Novel Short-Term Residential Electric Load Forecasting Method Based on Adaptive Load Aggregation and Deep Learning Algorithms [J].
Hou, Tingting ;
Fang, Rengcun ;
Tang, Jinrui ;
Ge, Ganheng ;
Yang, Dongjun ;
Liu, Jianchao ;
Zhang, Wei .
ENERGIES, 2021, 14 (22)
[50]   A novel combined model for probabilistic load forecasting based on deep learning and improved optimizer [J].
Zhang, Dongxue ;
Wang, Shuai ;
Liang, Yuqiu ;
Du, Zhiyuan .
ENERGY, 2023, 264