A Combined Method for Short-Term Load Forecasting Considering the Characteristics of Components of Seasonal and Trend Decomposition Using Local Regression
Source abstract
Abstract
In response to the complexity and high volatility of original load data affecting the accuracy of load forecasting, a combined method for short-term load forecasting considering the characteristics of components of seasonal and trend decomposition using local regression (STL) is proposed. The original load data are decomposed into a trend component, seasonal component, and residual component using STL. Then, considering the characteristics of each component, a long short-term memory (LSTM) neural network, a convolutional neural network (CNN), and Gaussian process regression (GPR) are used to predict the trend component, seasonal component, and residual component, respectively. The final outcome of the load forecasting is obtained by summing the forecasted results of each individual component. A specific case study is conducted to compare the proposed combined method with LSTM, CNN, GPR, STL-LSTM, STL-CNN, and STL-GPR prediction methods. Through comparison, the proposed combined method exhibits lower errors and higher accuracy, demonstrating the effectiveness of this method.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Energy Load and Power Forecasting · Hydrological Forecasting Using AI · Evaluation Methods in Various Fields
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Electrical Engineering, Zhejiang University, Hangzhou 310027, China
Inner Mongolia Power (Group) Co., Ltd., Hohhot 010020, China
Inner Mongolia Electric Power Economic and Technological Research Institute, Hohhot 010090, China
Funding
Inner Mongolia Electric Power (Group) Co., Ltd.
References (20)
Show source-provided references
1. Probabilistic Electric Load Forecasting: A Tutorial Review10.1016/j.ijforecast.2015.11.011 ↗
2. Short-Term Electrical Load Forecasting with Multidimensional Feature Extraction10.1109/TSG.2022.3158387 ↗
3. Principles and Algorithms for Forecasting Groups of Time Series: Locality and Globality10.1016/j.ijforecast.2021.03.004 ↗
4. Electrical Load Forecasting Models: A Critical Systematic Review10.1016/j.scs.2017.08.009 ↗
5. Application of Support Vector Machine Models for Forecasting Solar and Wind Energy Resources: A Review10.1016/j.jclepro.2018.07.164 ↗
6. Cai, C., Tao, Y., Zhu, T., and Deng, Z. (2021). Short-Term Load Forecasting Based on Deep Learning Bidirectional LSTM Neural Network. Appl. Sci., 11.10.3390/app11178129 ↗
7. Abumohsen, M., Owda, A.Y., and Owda, M. (2023). Electrical Load Forecasting Using LSTM, GRU, and RNN Algorithms. Energies, 16.10.3390/en16052283 ↗
8. Hu, L., Wang, J., Guo, Z., and Zheng, T. (2023). Load Forecasting Based on LVMD-DBFCM Load Curve Clustering and the CNN-IVIA-BLSTM Model. Appl. Sci., 13.10.3390/app13127332 ↗
9. Using Smart Meter Data to Improve the Accuracy of Intraday Load Forecasting Considering Customer Behavior Similarities10.1109/TSG.2014.2364233 ↗
10. Short-Term Load Forecasting by Wavelet Transform and Evolutionary Extreme Learning Machine10.1016/j.epsr.2015.01.002 ↗
11. The Empirical Mode Decomposition and the Hilbert Spectrum for Nonlinear and Non-Stationary Time Series Analysis10.1098/rspa.1998.0193 ↗
12. EMD–PSO–ANFIS-Based Hybrid Approach for Short-Term Load Forecasting in Microgrids10.1049/iet-gtd.2019.0869 ↗
13. A Hybrid Short-Term Load Forecasting Model Based on Variational Mode Decomposition and Long Short-Term Memory Networks Considering Relevant Factors with Bayesian Optimization Algorithm10.1016/j.apenergy.2019.01.055 ↗
14. A Hybrid Forecasting Model for Short-Term Power Load Based on Sample Entropy, Two-Phase Decomposition and Whale Algorithm Optimized Support Vector Regression10.1109/ACCESS.2020.3023143 ↗
15. Fang, Z., Zhan, J., Cao, J., Gan, L., and Wang, H. (2022, January 16–18). Research on Short-Term and Medium-Term Power Load Forecasting Based on STL-LightGBM. Proceedings of the 2022 2nd International Conference on Electrical Engineering and Control Science (IC2ECS), Nanjing, China.10.1109/IC2ECS57645.2022.10088145 ↗
16. Lin, C., Weng, K., Lin, Y., Zhang, T., He, Q., and Su, Y. (2022). Time Series Prediction of Dam Deformation Using a Hybrid STL–CNN–GRU Model Based on Sparrow Search Algorithm Optimization. Appl. Sci., 12.10.3390/app122311951 ↗
17. Long Short-Term Memory10.1162/neco.1997.9.8.1735 ↗
18. Week-ahead Daily Peak Load Forecasting Using Hybrid Convolutional Neural Network10.1016/j.ifacol.2023.10.1596 ↗
19. Electrical Load-Temperature CNN for Residential Load Forecasting10.1016/j.energy.2021.120480 ↗
20. Darab, C., Antoniu, T., Beleiu, H.G., Pavel, S., Birou, I., Micu, D.D., Ungureanu, S., and Cirstea, S.D. (2020). Hybrid Load Forecasting Using Gaussian Process Regression and Novel Residual Prediction. Appl. Sci., 10.10.3390/app10134588 ↗