Rapid evaluation method for the carrying capacity of 5G base station load scale connected to the distribution network
With the continuous promotion of “new infrastructure”, high-density and high-energy consumption loads represented by 5 G base stations are being connected to urban distribution networks on a large scale, which has a significant impact on the safety and economic operation of the distribution network. This article proposes a fast evaluation method for the carrying capacity of 5G base station load scale connected to the distribution network based on a data-driven fast power flow calculation model. Firstly, the power consumption of 5G base stations was modeled; Secondly, a stack denoising autoencoder model is adopted to achieve fast power flow calculation in the distribution network; Then, based on the results of power flow analysis, a multi-dimensional and multi-level evaluation system for the carrying capacity of the distribution network was designed, and a quantitative score for the carrying capacity of the distribution network was given; Finally, the IEEE119 node simulation testing system was selected, and a simulation analysis of the 5G base station load scale access scenario was conducted in conjunction with the distribution network grid distribution in a certain region. Simulation shows that during peak periods of 5G base station communication tasks, when the voltage at the end nodes of distribution network branches exceeds the limit, the overall carrying capacity of the distribution network shows a downward trend. The simulation also verified that the method proposed in this article can effectively and quickly evaluate and provide the carrying capacity of urban distribution networks.
Authors
- Tao Li (ORCID: https://orcid.org/0000-0001-7431-9493)
- Chao Liu (ORCID: https://orcid.org/0000-0001-8203-5546)
- Tian Tian (ORCID: https://orcid.org/0009-0004-8418-1802)
- Xin Chen (ORCID: https://orcid.org/0000-0002-6034-2710)
- Yang Xu (ORCID: https://orcid.org/0009-0003-3642-9044)
Institutions
- Chongqing University of Posts and Telecommunications (CN)
Publication Details
- Published
- 2024-12-13
- DOI
- https://doi.org/10.1109/icpe64565.2024.10929460
- Primary Topic
- Machine Learning and ELM
- Type
- article
- Field-Weighted Citation Impact
- 0.00