Research on carbon emission accounting of SF₆ electrical equipment based on improved random forest algorithm
by Wenwei Zhu; Baichong Pan; Weixian Che; Chenghao Xu
International Journal of Energy Technology and Policy (IJETP), Vol. 19, No. 1/2, 2024

Abstract: Due to the large convergence error and high interference coefficient of carbon emissions accounting, research on carbon emission accounting of SF₆ electrical equipment based on improved random forest algorithm is proposed. Firstly, the arc extinguishing characteristics and insulation performance of SF₆ electrical equipment are determined. Then, the differences in the decomposition of substances in SF₆ electrical equipment under various conditions are analysed, and differential optical absorption spectroscopy is used to determine the carbon emission equivalent of the equipment. Finally, the OOB error estimation algorithm is introduced to build an improved random forest algorithm model, and the nonlinear activation function is used to determine the synapse strength, and the information function is used to adjust the convergence value of accounting error to complete the carbon emissions accounting. The results indicate that the proposed method can reduce the convergence value of accounting errors and the interference coefficient of accounting results.

Online publication date: Fri, 10-May-2024

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Energy Technology and Policy (IJETP):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com