An optimization method for flexible interconnection planning based on improved CNN-LSTM prediction and tunable relative entropy-driven chaotic evolution

Xiaoyan Zhao, Xubin Xing, Xiaoyan Guo, Jian Chao, Dapeng Hu, Xiangtao Zhuan · 2026

Read An optimization method for flexible interconnection planning based on improved CNN-LSTM prediction and tunable relative entropy-driven chaotic evolution by Xiaoyan Zhao, Xubin Xing, Xiaoyan Guo, Jian Chao, Dapeng Hu, Xiangtao Zhuan (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0351324.txt.

Description

Linking power grids flexibly lets regions share electricity and cuts waste, but planners must first forecast demand well. Xiaoyan Zhao and colleagues paired a hybrid forecasting network with a chaos-driven search method to design such links, in this 2026 PLOS One study.

The forecaster reads past load at several time scales, mixing pattern-spotting and memory layers. A new measure scores how well regions' demands complement each other hour by hour. The search algorithm then tunes the system's layout against balance, reliability, cost, and that complementarity score. Tests showed very small forecast errors, and the authors claim the combined approach designs cheaper, steadier interconnections.

Catalog record

CREATORXiaoyan Zhao, Xubin Xing, Xiaoyan Guo, Jian Chao, Dapeng Hu, Xiangtao Zhuan
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE35254
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0351324

Browse the full library · About the Tower of Babel