Research on analysis of power and water consumption data for group tenant identification based on federated learning

Jian Ma; Jian Zheng; Yifan Yang; Chunting Kang; Yuxin Wang; Yang Wang; Yutong Li

doi:10.1117/12.2627667

11 March 2022 Research on analysis of power and water consumption data for group tenant identification based on federated learning

Jian Ma, Jian Zheng, Yifan Yang, Chunting Kang, Yuxin Wang, Yang Wang, Yutong Li

Author Affiliations +

Proceedings Volume 12160, International Conference on Computational Modeling, Simulation, and Data Analysis (CMSDA 2021); 121602C (2022) https://doi.org/10.1117/12.2627667
Event: International Conference on Computational Modeling, Simulation, and Data Analysis (CMSDA 2021), 2021, Sanya, China

Abstract

The protection of user privacy is more and more important, which restricts the effective application of traditional methods in some fields. Federated learning is an effective method to solve such problems. The vertical federated learning method can be effectively applied to the joint analysis of multiple energy data. This paper discusses the application of this method in identifying group tenants in the research of urban energy big data, proposes an address based data matching method and corresponding coding rules, and implements an example based on SecureBoost. The results show that vertical federated learning has a good effect in the joint modeling of electricity and water data.

Citation Download Citation

Jian Ma, Jian Zheng, Yifan Yang, Chunting Kang, Yuxin Wang, Yang Wang, and Yutong Li "Research on analysis of power and water consumption data for group tenant identification based on federated learning", Proc. SPIE 12160, International Conference on Computational Modeling, Simulation, and Data Analysis (CMSDA 2021), 121602C (11 March 2022); https://doi.org/10.1117/12.2627667

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available