Short-Term Power Load Forecasting Based on Hybrid ReliefF-PMI-IGWO

Chen Zichun; Li Zhen; Fu Hua

doi:doi:10.11648/j.sd.20221006.16

| Peer-Reviewed

Short-Term Power Load Forecasting Based on Hybrid ReliefF-PMI-IGWO

Chen Zichun, Li Zhen, Fu Hua

Published in Science Discovery (Volume 10, Issue 6)

Received: 14 October 2022 Accepted: 11 November 2022 Published: 29 November 2022

Views: Downloads:

Download PDF

Share This Article

Twitter
Linked In
Facebook

Abstract

With the rapid growth of power grid in China, it is becoming more and more important to forecast short-term power load. Aiming at the problems of complex causes of short-term load forecasting, large amount of data, low efficiency and poor accuracy of traditional model forecasting methods, and the single model forecasting can no longer adapt to the current power load changes, a short-term power load forecasting method based on hybrid ReliefF-PMI-IGWO was proposed. Firstly, two Filter feature selection methods based on hybrid ReliefF and Partial Mutual Information (PMI) were used to screen out irrelevant and redundant input features, and a smaller feature subset was obtained. Then the Wrapper method is used for further screening, among which the Wrapper method selects Improved Grey Wolf Optimization (IGWO) algorithm, and its accuracy is significantly improved. Combined with the case analysis of the hourly load data of China Midea HVAC and Nongfu Spring from May to August 2017, and compared with other five traditional models. The simulation results show that the MAE and MAPE obtained by the proposed model are 49.54, 1.62 and 71.34, 1.98, respectively, which are significantly better than other models, and the prediction accuracy of the proposed model is the highest and the closest to the real value.

Published in	Science Discovery (Volume 10, Issue 6)
DOI	10.11648/j.sd.20221006.16
Page(s)	414-421
Creative Commons	This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.
Copyright	Copyright © The Author(s), 2022. Published by Science Publishing Group

Keywords

Short Term Power Load Forecasting, Partial Mutual Information, ReliefF, Improved Gray Wolf Optimization Algorithm, Feature Selection

References

[1]	范海虹. 基于萤火虫算法的短期电力负荷预测方法 [J]. 中国电力, 2021, 54 (3): 144-148.
[2]	王淞瑶, 张智晟. 基于量子加权GRU神经网络的电力系统短期负荷预测 [J]. 电力系统及其自动化学报, 2022, 34 (1): 1-7.
[3]	商立群, 李洪波, 侯亚东等. 基于特征选择和优化极限学习机的短期电力负荷预测 [J]. 西安交通大学学报, 2022, 56 (4): 165-175.
[4]	杨海柱, 田馥铭, 张鹏等. 基于CEEMD-FE和AOA-LSSVM的短期电力负荷预测 [J]. 电力系统保护与控制. 2022 (13): 126-133.
[5]	段雪滢, 李小腾, 陈文洁. 基于改进粒子群优化算法的VMD-GRU短期电力负荷预测 [J]. 电工电能新技术，2022, 41 (5): 8-17.
[6]	张淑清, 李君, 姜安琪等. 基于FPA-VMD和BiLSTM神经网络的新型两阶段短期电力负荷预测 [J]. 电网技术, 2022, 46 (08): 3269-3279.
[7]	赵婧宇, 池越, 周亚通. 基于SSA-LSTM模型的短期电力负荷预测研究 [J]. 电工电能新技术，2022, 41 (6): 71-79.
[8]	Yu Zhuowei; Yang Jiajun; Wu Yufeng; Huang Yi. Short-Term Power Load Forecasting Under COVID-19 Based on Graph Representation Learning With Heterogeneous Features [J]. Frontiers in Energy Research, 2021.
[9]	Prakash N.; Vaikundaselvan B.; Sivaraju S. S. Short-Term Load Forcasting for Smart Power Systems Using Swarm Intelligence Algorithm [J]. Journal of Circuits, Systems and Computers, 2022, 31 (11).
[10]	Ghulam Hafeez, Imran Khan, Sadaqat Jan. Anovel hybrid load forecasting framework with intelligent feature engineering and optimization algorithm in smart grid [J]. 2021, Applied Energy, 299 (9): 1171778.
[11]	胡忠义. 基于文化基因算法的电力负荷预测模型及应用 [D]. 华中科技大学. 2015 (07).
[12]	KONONENKO I. Estimating attributes:Analysis and extensions of RELIEF [C]//European conference on machine learning. Springer, Berlin, Heidelberg, 1994: 171-182.
[13]	E Hancer, An improved evolutionary wrapper-filter feature selection approach with a new initialisation scheme [J]. Special Issue on Feature Engineering, 2021. 11.
[14]	胡忠义. 基于计算智能技术的电力负荷预测理论及应用 [M]. 武汉: 武汉大学出版社, 2019. 1.
[15]	Sharma A. Seasonal to interannual rainfall probabilistic forecasts for improved water supply management: Part 1-A strategy for system predictor [J]. Journal of Hydrology, 2000, 239: 232-239.
[16]	徐宇颂, 邹山花, 卢先领. 基于特征选择和组合模型的短期电力负荷预测 [J]. 中国电力, 2022, 55 (7): 121-127.
[17]	胡欣, 冯杰, 徐先峰等. 基于特征选择实现多因素电力负荷预测 [J]. 自动化仪表，2022, 43 (3): 69-74.
[18]	周传华, 柳智才, 丁敬安等. 基于filter＋wrapper模的特征选择算法 [J]. 计算机应用研究, 2019, 36 (7): 1975-2010.
[19]	杨国华, 郑豪丰, 张鸿皓等. 基于Holt-Winters指数平滑和时间卷积网络的短期负荷预测 [J]. 电力系统自动化. 2022 (06): 73-82.
[20]	Yu Binbin; Li Jianjing; Liu Che; Sun Bo. A novel short-term electrical load forecasting framework with intelligent feature engineering [J]. Applied Energy, 2022, 327.
[21]	Zhengyi Liu, Bo Chang, Fan Cheng. An interactive filter-wrapper multi-objective evolutionary algorithm for feature selection [J]. Swarm and Evolutionary Computation，2021, 65 (4): 100925.
[22]	Wang Jianzhou; Xing Qianyi; Zeng Bo; Zhao Weigang. An ensemble forecasting system for short-term power load based on multi-objective optimizer and fuzzy granulation [J]. Applied Energy, 2022, 327.
[23]	曾林俊, 许加柱, 王家禹等. 考虑区间构造的改进极限学习机短期电力负荷区间预测 [J]. 电网技术.2022 (07): 2555-2563.
[24]	Mirjalili S, Mirjalili SM, Lewis A. Grey wolf optimizer [J]. Advances in Engineering Software, 2014, 69 (3): 46-61.
[25]	王秋萍, 王梦娜, 王晓峰. 改进收敛因子和比例权重的灰狼优化算法 [J]. 计算机工程与应用, 2019, 55 (21): 60-65.

Cite This Article

Plain Text BibTeX RIS

APA Style

Chen Zichun, Li Zhen, Fu Hua. (2022). Short-Term Power Load Forecasting Based on Hybrid ReliefF-PMI-IGWO. Science Discovery, 10(6), 414-421. https://doi.org/10.11648/j.sd.20221006.16

Copy | Download

ACS Style

Chen Zichun; Li Zhen; Fu Hua. Short-Term Power Load Forecasting Based on Hybrid ReliefF-PMI-IGWO. Sci. Discov. 2022, 10(6), 414-421. doi: 10.11648/j.sd.20221006.16

Copy | Download

AMA Style

Chen Zichun, Li Zhen, Fu Hua. Short-Term Power Load Forecasting Based on Hybrid ReliefF-PMI-IGWO. Sci Discov. 2022;10(6):414-421. doi: 10.11648/j.sd.20221006.16

Copy | Download

@article{10.11648/j.sd.20221006.16,
  author = {Chen Zichun and Li Zhen and Fu Hua},
  title = {Short-Term Power Load Forecasting Based on Hybrid ReliefF-PMI-IGWO},
  journal = {Science Discovery},
  volume = {10},
  number = {6},
  pages = {414-421},
  doi = {10.11648/j.sd.20221006.16},
  url = {https://doi.org/10.11648/j.sd.20221006.16},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.sd.20221006.16},
  abstract = {With the rapid growth of power grid in China, it is becoming more and more important to forecast short-term power load. Aiming at the problems of complex causes of short-term load forecasting, large amount of data, low efficiency and poor accuracy of traditional model forecasting methods, and the single model forecasting can no longer adapt to the current power load changes, a short-term power load forecasting method based on hybrid ReliefF-PMI-IGWO was proposed. Firstly, two Filter feature selection methods based on hybrid ReliefF and Partial Mutual Information (PMI) were used to screen out irrelevant and redundant input features, and a smaller feature subset was obtained. Then the Wrapper method is used for further screening, among which the Wrapper method selects Improved Grey Wolf Optimization (IGWO) algorithm, and its accuracy is significantly improved. Combined with the case analysis of the hourly load data of China Midea HVAC and Nongfu Spring from May to August 2017, and compared with other five traditional models. The simulation results show that the MAE and MAPE obtained by the proposed model are 49.54, 1.62 and 71.34, 1.98, respectively, which are significantly better than other models, and the prediction accuracy of the proposed model is the highest and the closest to the real value.},
 year = {2022}
}

Copy | Download

TY  - JOUR
T1  - Short-Term Power Load Forecasting Based on Hybrid ReliefF-PMI-IGWO
AU  - Chen Zichun
AU  - Li Zhen
AU  - Fu Hua
Y1  - 2022/11/29
PY  - 2022
N1  - https://doi.org/10.11648/j.sd.20221006.16
DO  - 10.11648/j.sd.20221006.16
T2  - Science Discovery
JF  - Science Discovery
JO  - Science Discovery
SP  - 414
EP  - 421
PB  - Science Publishing Group
SN  - 2331-0650
UR  - https://doi.org/10.11648/j.sd.20221006.16
AB  - With the rapid growth of power grid in China, it is becoming more and more important to forecast short-term power load. Aiming at the problems of complex causes of short-term load forecasting, large amount of data, low efficiency and poor accuracy of traditional model forecasting methods, and the single model forecasting can no longer adapt to the current power load changes, a short-term power load forecasting method based on hybrid ReliefF-PMI-IGWO was proposed. Firstly, two Filter feature selection methods based on hybrid ReliefF and Partial Mutual Information (PMI) were used to screen out irrelevant and redundant input features, and a smaller feature subset was obtained. Then the Wrapper method is used for further screening, among which the Wrapper method selects Improved Grey Wolf Optimization (IGWO) algorithm, and its accuracy is significantly improved. Combined with the case analysis of the hourly load data of China Midea HVAC and Nongfu Spring from May to August 2017, and compared with other five traditional models. The simulation results show that the MAE and MAPE obtained by the proposed model are 49.54, 1.62 and 71.34, 1.98, respectively, which are significantly better than other models, and the prediction accuracy of the proposed model is the highest and the closest to the real value.
VL  - 10
IS  - 6
ER  -

Copy | Download

Author Information

Chen Zichun

School of Electrical and Control Engineering, Liaoning Technical University, Huludao, China
Li Zhen

School of Electrical and Control Engineering, Liaoning Technical University, Huludao, China
Fu Hua

School of Electrical and Control Engineering, Liaoning Technical University, Huludao, China

Download PDF

Sections

Plain Text BibTeX RIS

APA Style

Chen Zichun, Li Zhen, Fu Hua. (2022). Short-Term Power Load Forecasting Based on Hybrid ReliefF-PMI-IGWO. Science Discovery, 10(6), 414-421. https://doi.org/10.11648/j.sd.20221006.16

Copy | Download

ACS Style

Chen Zichun; Li Zhen; Fu Hua. Short-Term Power Load Forecasting Based on Hybrid ReliefF-PMI-IGWO. Sci. Discov. 2022, 10(6), 414-421. doi: 10.11648/j.sd.20221006.16

Copy | Download

AMA Style

Chen Zichun, Li Zhen, Fu Hua. Short-Term Power Load Forecasting Based on Hybrid ReliefF-PMI-IGWO. Sci Discov. 2022;10(6):414-421. doi: 10.11648/j.sd.20221006.16

Copy | Download

@article{10.11648/j.sd.20221006.16,
  author = {Chen Zichun and Li Zhen and Fu Hua},
  title = {Short-Term Power Load Forecasting Based on Hybrid ReliefF-PMI-IGWO},
  journal = {Science Discovery},
  volume = {10},
  number = {6},
  pages = {414-421},
  doi = {10.11648/j.sd.20221006.16},
  url = {https://doi.org/10.11648/j.sd.20221006.16},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.sd.20221006.16},
  abstract = {With the rapid growth of power grid in China, it is becoming more and more important to forecast short-term power load. Aiming at the problems of complex causes of short-term load forecasting, large amount of data, low efficiency and poor accuracy of traditional model forecasting methods, and the single model forecasting can no longer adapt to the current power load changes, a short-term power load forecasting method based on hybrid ReliefF-PMI-IGWO was proposed. Firstly, two Filter feature selection methods based on hybrid ReliefF and Partial Mutual Information (PMI) were used to screen out irrelevant and redundant input features, and a smaller feature subset was obtained. Then the Wrapper method is used for further screening, among which the Wrapper method selects Improved Grey Wolf Optimization (IGWO) algorithm, and its accuracy is significantly improved. Combined with the case analysis of the hourly load data of China Midea HVAC and Nongfu Spring from May to August 2017, and compared with other five traditional models. The simulation results show that the MAE and MAPE obtained by the proposed model are 49.54, 1.62 and 71.34, 1.98, respectively, which are significantly better than other models, and the prediction accuracy of the proposed model is the highest and the closest to the real value.},
 year = {2022}
}

Copy | Download

TY  - JOUR
T1  - Short-Term Power Load Forecasting Based on Hybrid ReliefF-PMI-IGWO
AU  - Chen Zichun
AU  - Li Zhen
AU  - Fu Hua
Y1  - 2022/11/29
PY  - 2022
N1  - https://doi.org/10.11648/j.sd.20221006.16
DO  - 10.11648/j.sd.20221006.16
T2  - Science Discovery
JF  - Science Discovery
JO  - Science Discovery
SP  - 414
EP  - 421
PB  - Science Publishing Group
SN  - 2331-0650
UR  - https://doi.org/10.11648/j.sd.20221006.16
AB  - With the rapid growth of power grid in China, it is becoming more and more important to forecast short-term power load. Aiming at the problems of complex causes of short-term load forecasting, large amount of data, low efficiency and poor accuracy of traditional model forecasting methods, and the single model forecasting can no longer adapt to the current power load changes, a short-term power load forecasting method based on hybrid ReliefF-PMI-IGWO was proposed. Firstly, two Filter feature selection methods based on hybrid ReliefF and Partial Mutual Information (PMI) were used to screen out irrelevant and redundant input features, and a smaller feature subset was obtained. Then the Wrapper method is used for further screening, among which the Wrapper method selects Improved Grey Wolf Optimization (IGWO) algorithm, and its accuracy is significantly improved. Combined with the case analysis of the hourly load data of China Midea HVAC and Nongfu Spring from May to August 2017, and compared with other five traditional models. The simulation results show that the MAE and MAPE obtained by the proposed model are 49.54, 1.62 and 71.34, 1.98, respectively, which are significantly better than other models, and the prediction accuracy of the proposed model is the highest and the closest to the real value.
VL  - 10
IS  - 6
ER  -

Copy | Download