Login Register Cart 0
Generic placeholder image

Recent Patents on Mechanical Engineering

Editor-in-Chief

ISSN (Print): 2212-7976
ISSN (Online): 1874-477X

Back
Journal Home About Journal Editorial Board Journal Insight Current Issue Volumes/Issues
Subscribe
Research Article

Short-term Power Load Forecasting Based on Orthogonal PCA-LPP Dimension Reduction and IGWO-BiLSTM

Author(s): Lingzhi Yi, Jiang Zhu, Yahui Wang*, Jiangyong Liu, Shitong Wang and Bo Liu

Volume 16, Issue 1, 2023

Published on: 09 December, 2022

Page: [72 - 86] Pages: 15

DOI: 10.2174/2212797615666221012091902

Price: $65

Abstract

Background: Accurate power load forecasting is significant in ensuring power load planning, reliability and economical operation. The traditional power load is easily affected by climate, environment, data type and other factors, resulting in the problem of poor forecasting accuracy. Therefore, it is necessary to study power load forecasting.

Objective: Through machine learning, dimension reduction method and intelligent optimization algorithm, the accuracy of load forecasting is improved.

Methods: In order to fully extract load information and improve the accuracy of short-term load forecasting for campus electricity, an improved combination of orthogonal dimensionality reduction and Bilstm is proposed to optimize the hyperparameters in BiLSTM using an improved gray wolf algorithm. Firstly, using the advantages of principal component analysis (PCA) and Locality Preserving Projection (LPP) to maintain the global and local structure of the data, respectively, the Orthogonal PCA-LPP (OPCA-LPP) dimensionality reduction method is proposed to reduce the dimensionality of the original multidimensional data. Finally, the dimensionality-reduced data is used as the input of BiLSTM and optimized by the improved Gray Wolf algorithm, which can enhance the model's prediction capability and thus achieve accurate prediction of short-term electric load.

Results: The Mae and RMSE of this paper are 1.6585 and 1.7602, respectively. The results show that the method proposed in this paper is reasonable.

Conclusion: This method is applied to power load forecasting. The comparative experimental results show that this method reduces the dimension of data input, simplifies the complexity of network input data, and improves load forecasting accuracy. Compared with other methods, it can improve load forecasting accuracy and provide a basis for formulating reasonable power grid operation modes and balanced power grid dispatching.

« Previous Next »
[1]
Duan XY, Li XT, Chen WJ. Improved particles swarm optimization algorithm-based VMD-GRU method for short-term load forecasting. Diangong Dianneng Xinjishu 2022; 41(05): 8-17.
[2]
Wang YX, Liu EJ, Huang YZ. Data driven short-term multiple load forecasting for integrated energy system. Comput Engin Design 2022; 43(05): 1435-42.
[3]
Wu JJ, Zhang Q, Chen F, et al. Short-term load forecasting with error correction and variational mode decomposition-long short-term memory. Kexue Jishu Yu Gongcheng 2022; 22(12): 4828-34.
[4]
Pma D, Ms B, Sd B, et al. Medium-term load forecasting in isolated power systems based on ensemble machine learning models. Science Direct 2022; 8(S1): 612-8.
[5]
Wang LY, Wang ZM, Qian W, et al. Medium and long-term load forecasting based on transfer learning. Distribut Utiliz 2022; 39(3): 69-74.
[6]
Wei CY, Wang Y, Xu H, et al. Bidding methodof electricity spot market considering uncertaintyof generalized loadand incentive-based demand response. Electric Power Auto Equip 2022; 8: 7764-72.
[7]
Ti BZ, Li GY, Wu ZY, et al. A short-term load forecasting method based on recurrent and dilated mechanism of ConvGRU-transformer. J North China Electric Power Uni 2022; 21(4): 129-43.
[8]
Li AC, Wang X, Zhang J, et al. Multi time scale optimal scheduling of automation system based on distributed control model. Manufacturing Automation 2022; 44(05): 158-61.
[9]
Lai C, Wang Y, Fan K, et al. An improved forecasting model of short-term electric load of papermaking enterprises for production line optimization. Energy 2022; 245: 123225.
[http://dx.doi.org/10.1016/j.energy.2022.123225]
[10]
Ruan QT, Mei SW, Huang XD, et al. Challenges and research prospects of resilience enhancement of low-carbon power grid. Zhongguo Dianji Gongcheng Xuebao 2022; 42(08): 2819-30.
[11]
Zhu Q, Ma WX, Xu SM, et al. A short-term load forecasting method based on VMD decomposition and improved two-layer BILSTM network. Patent CN 114330814A, 2022.
[12]
Wang Hl, Chen XY, Zhao YM. Load forecasting method based on ensemble empirical mode decomposition and ARIMA-GRNN. Electro Sci Technol 2021; (12): 42-8.
[13]
Yang D, Guo J, Sun S, Han J, Wang S. An interval decomposition-ensemble approach with data-characteristic-driven reconstruction for short-term load forecasting. Appl Energy 2022; 306: 117992.
[http://dx.doi.org/10.1016/j.apenergy.2021.117992]
[14]
Veeramsetty V, Chandra DR, Grimaccia F, et al. Short term electric power load forecasting using principal component awnalysis and recurrent neural networks. Forecasting 2022; 4(1): 4.
[15]
Liu JY, Wang SX, Li C. PCA-GM-BPNN combined forecasting model for daily load of city gas. Natural gas and oil 2018; (05): 13-9.
[16]
Wang JY, Zhang SF. Anomaly detection for power consumption patterns based on linear discriminant analysis and density peak clustering. Dianli Xitong Zidonghua 2022; 46(05): 87-98.
[17]
Wang X, Zhao L, Wang Y, et al. Self-organizing map based knowledge fusion algorithm for big data environment of power grid. J Hefei Uni Technol 2022; 45(05): 620-53.
[18]
Luo L, Tuo XG, Zhang GY, et al. Accuracy improvement of near infrared quantitative analysis model for fermented grains based on abnormal sample removal. Shipin Anquan Zhiliang Jiance Xuebao 2022; 13(09): 3017-25.
[19]
Liao QY, Wang J, Hu KQ, et al. Joint forecasting model of electrical load and thermal load based on deep parallel CNN-BiLSTM in energy internet. China measure test 2022; 48(04): 146-53.
[20]
Zhao HD, Chen XD, Li JL, et al. Analysis and forecast of aviation power consumption based on MSCNN. Northeast Electric Power Technol 2022; 43(04): 15-21.
[21]
Pan X, Zhang ML, Liu DB, et al. Interval prediction of wind farm day-ahead output based on robust multi-label generative adversarial. Dianli Xitong Zidonghua 2022; 46(10): 216-23.
[22]
Wang YH, Wang ZZ, Fu H, et al. Research on transformer fault diagnosis based on the improved multi-strategy sparrow algorithm and BiLSTM. 2020 International Conference on Control, Robotics and Intelligent System, Jan 04, 2021, New York, NY, United States. pp. 63-66.
[23]
Yang QF, Duan DW, Nan L, et al. A practical fault diagnosis method for series-connected battery packs based on principle component analysis. Electric Power Auto Equip 2022; 10: 891637.
[24]
Peng Q, Zhang H, Ren WC, et al. Wood defect recognition based on improved HOG feature and LPP algorithm. Transducer Microsys Technol 2022; 41(05): 123-6.
[25]
Li H, Hao RJ. Rolling bearing fault diagnosis based on sensor information fusion and generalized cyclic cross correntropy spectrum density. J Vibrat Shock 2022; 41(02): 200-7.
[26]
Wen K, Lin J, Zhang XC, et al. Kernel parameter optimization algorithm for chaotic strategy and nonlinear convergence factor. Mechan Sci Technol Aerospace Engin 2022; 11(11): 2459-62.
[27]
Mittal N, Singh U, Sohi BS. Modified grey wolf optimizer for global engineering optimization. Appl Comput Intell Soft Comput 2016; 2016: 1-16.

Rights & Permissions Print Cite
© 2024 Bentham Science Publishers | Privacy Policy