TransGrid-CostOpt: A hybrid transformer framework for cost prediction and optimization of distribution network assets
Wei Xiong, Jie Xia, YiBo Yu, SanMing Xiong, HaiYang Hu, Peng Wan, Dan Li · 2026
Read TransGrid-CostOpt: A hybrid transformer framework for cost prediction and optimization of distribution network assets by Wei Xiong, Jie Xia, YiBo Yu, SanMing Xiong, HaiYang Hu, Peng Wan, Dan Li (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-0350026.txt.
Description
Wei Xiong and co-authors built a forecasting and decision system to help power companies predict what their distribution networks will cost and where money is best spent. Shifting loads and supply uncertainties strain older planning methods. Their 2026 model, named TransGrid-CostOpt, fuses deep learning with load forecasting, multi-goal optimization, and a learning-based decision module fed by several data sources.
On two public load datasets, the system beat traditional and recent rival methods, with overall performance gains the authors put between fifteen and thirty percent. Removing single modules hurt results, and the forecasting and decision parts proved most important. The authors present the framework as adaptable to fast-changing electricity markets, where cost control and reliable forecasts must advance together.
Catalog record
| CREATOR | Wei Xiong, Jie Xia, YiBo Yu, SanMing Xiong, HaiYang Hu, Peng Wan, Dan Li |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 63211 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |