Education, Science, Technology, Innovation and Life
Open Access
Sign In

User variable load forecasting based on FPA-DELM

Download as PDF

DOI: 10.23977/jeeem.2022.050108 | Downloads: 6 | Views: 604

Author(s)

Xiaohan Wang 1

Affiliation(s)

1 School of Computer Science and Technology, Heilongjiang University, Harbin, 150080, China

Corresponding Author

Xiaohan Wang

ABSTRACT

Load forecasting is an important hotspot in the field of energy management. Aiming at the problem that user variable load is difficult to predict and the prediction accuracy is low, this paper proposes a deep extreme learning machine model based on the Flower Pollination Algorithm (FPA). When Deep Extreme Learning Machine (DELM) solves the problem, the large number of nodes leads to high resource utilization and slow convergence speed. Combined with the FPA algorithm, it is used to optimize the parameters of the hidden layer, which improves the convergence speed of the algorithm and optimization accuracy. This paper conducts prediction experiments on the load data of household appliances. The experimental results show that FPA-DELM has better prediction accuracy than DELM. 

KEYWORDS

FPA, Deep Extreme Learning Machine(DELM), variable load forecasting

CITE THIS PAPER

Xiaohan Wang, User variable load forecasting based on FPA-DELM. Journal of Electrotechnology, Electrical Engineering and Management (2022) Vol. 5: 48-55. DOI: http://dx.doi.org/10.23977/jeeem.2022.050108.

REFERENCES

[1] Gao Chao, Sun Yili, Zhao Hongfeng, Cao Peifang. Research on short-term load forecasting based on ICOA-LSTM. Electronic Measurement Technology: 2019, 1-8.
[2] Du Ting, Zhao Shousheng, Li Yongqi, et al. Development and application of power load forecasting software based on Matlab GUI. Electrical Technology, 2018, 19(06): 1-6+31.
[3] Li Zewen, Hu Rang, Liu Xiang, et al. Multi-factor short-term load forecasting model based on PCA-BILSTM. Journal of Electric Power Systems and Automation, 2020, 32(12): 32-39.
[4] Wang Yanling, Wu Mengkai. Medium and long-term load forecasting model based on partial least squares regression under the new economic normal. Electric Power Automation Equipment, 2018,38(03):133-139.
[5] Wang Shouxiang, Sun Zhimin, Liu Zhe. Home Energy Coordinated Scheduling Strategy for Smart Electricity. Automation of Electric Power Systems, 2015, 39(17): 108-113.
[6] MOLLA T,KHAN B,MOGES B,et al.Integrated energy optimization of smart home appliances with cost-effective energy management system[J].CSEE Journal of Power and Energy Systems,2019,2(5):249-258.
[7] Zhang Tian, Zhao Qi, Chen Zhong. Hierarchical optimization strategy for household energy management based on deep reinforcement learning. Automation of Electric Power Systems, 2021, 45(21): 149-158.
[8] Shao Liangshan, Lan Tingyang, Li Chenhao. Extreme Learning Machine Model Based on Improved Flower Pollination Algorithm. Computer Engineering, 2019, 45(12): 281-288.
[9] Zou Weidong, Li Yuxiang, Xia Yuanqing. Extreme Learning Machine Based on State Transfer Algorithm. Journal of Beijing Institute of Technology: 2020, 1-9.
[10] Xiao Huihui, Wan Changxuan, Duan Yanming. An improved new meta-heuristic flower pollination algorithm. Computer Application Research, 2016, 33(01): 126-131.
[11] Li Kewen, Liang Yongqi, Li Shaohui. Improved flower pollination algorithm based on mixed strategy. Computer Application Research, 2022, 39(02): 361-366.
[12] Niu Chunyan, Xia Kewen, Zhang Jiangnan, He Ziping. Extreme Learning Machine Algorithm Based on Cloud Quantum Flower Pollination. Computer Applications, 2020, 40(06): 1627-1632.
[13] NREL Computational Science Center Data,’Power measurements for various residential appliances in the System Performance Lab(SPL) in the Energy System Integration Facolity(ESIF)’[online]. Available: https://cscdata.nrel.gov/#/datasets/275b23f4-99fb-4366-a16b-935ec72d95a2.
[14] Wang Zhigang, Yuan Xu, Shen Xiangjun, Zhao Zengmin, Ji Bin. Research on normalization technology of deep network decorrelation layer. Small Microcomputer System, 2022,43(05):1075-1080.

Downloads: 1969
Visits: 93798

Sponsors, Associates, and Links


All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.