Education, Science, Technology, Innovation and Life
Open Access
Sign In
  1. Home
  2. Journals
  3. Advances in Computer, Signals and Systems
  4. Vol 7, Issue 11, 2023

Research on the influencing factors of wind power generation based on clustering and decision tree

Download as PDF

DOI: 10.23977/acss.2023.071106 | Downloads: 4 | Views: 229

Author(s)

Yaoqi Tan 1

Affiliation(s)

1 School of Electrical Engineering, Chongqing University, Chongqing, 400044, China

Corresponding Author

Yaoqi Tan

ABSTRACT

In this paper, the decision tree method is utilized to explore the influencing factors of wind power generation. This paper innovatively utilizes a combination of clustering and decision tree algorithms for data analysis. Firstly, the samples are categorized into three categories, high wind power generation, medium wind power generation and low wind power generation using K-means algorithm. Then, a decision tree model was applied to each category to obtain the proportion of feature importance. The results show that the key factors affecting wind power generation include motor torque, blade angle, electrical resistance and generator temperature. Compared to the traditional Adaboost algorithm, the new algorithm has a mean square error of no more than 3% and a coefficient of determination (R2) greater than 0.78. Compared to the Adaboost algorithm, the new algorithm has a 2.671% lower mean square error and an improved R2 of 0.135, which suggests that the new algorithm is more reliable in predicting wind power generation. Future research directions, this study can be extended by considering more factors that affect wind power generation, such as wind speed, wind direction, and air density.

KEYWORDS

Decision Tree, K-means, Wind Power Generation

CITE THIS PAPER

Yaoqi Tan, Research on the influencing factors of wind power generation based on clustering and decision tree. Advances in Computer, Signals and Systems (2023) Vol. 7: 35-40. DOI: http://dx.doi.org/10.23977/acss.2023.071106.

REFERENCES

[1] Han Xiaoxiao, Zhang Xiaohua, Bu Bing, et al. Factors affecting wind power generation and optimization strategy [J]. Power Equipment Management, 2023(10):63-65. 
[2] Peng L , Jing-Chao W , Bin L ,et al.Research on Data Mining of Wind Disaster of Power Transmission Line Based on Clustering Analysis[C]//2019 6th International Conference on Information Science and Control Engineering (ICISCE).2019.DOI:10.1109/ICISCE48695.2019.00098.
[3] Gu Yundong, Ma Dongfen, Cheng Hongchao. Electricity load forecasting based on similar data selection and improved gradient boosting decision tree [J]. Journal of Power System and Automation, 2019, 31(5):64-69.
[4] Yang Juanxia. Research on Vibration Fault Diagnosis of Wind Turbine Generators Based on Clustering and Decision Tree Algorithms [J]. Power Equipment Management, 2023 (16): 100-102.
[5] Liu, Hongfu, Chen, Junxiang, Dy, Jennifer, Fu, Yun.Transforming Complex Problems Into K-Means Solutions[J]. Ieee Transactions On Pattern Analysis And Machine Intelligence, 2023, 45(7):9149-9168.
[6] Ma Lichuan, Peng Jiayi, Pei Qingqi, Zhu Haojin. An efficient decision tree privacy classification service protocol [J]. Journal of Communication, 2021, 42(8):80-89.

Subscription
E-Mail Alert
Most popular papers
Call for Special Issue
Publication Ethics & OA Statement
Plagiarism Policy
Contact Us
Downloads: 13643
Visits: 260253

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.