Short-term load forecasting using a two-stage CPO-PSO hyperparameter optimization of LSSVM
XinHao Zhang · 2026
Read Short-term load forecasting using a two-stage CPO-PSO hyperparameter optimization of LSSVM by XinHao Zhang (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/PMC13547386.txt.
Description
XinHao Zhang proposed in 2026 a two-stage tuning scheme for a support vector forecasting model used to predict electricity load hours ahead. The model's accuracy hinges on two settings that are hard to guess. A new nature-inspired optimizer first searches broadly across the setting space, borrowing the defense postures of crested porcupines, and a particle swarm method then polishes the best region locally.
On hourly data from Jiangsu and half-hourly data from Australia, the hybrid cut average errors by roughly a quarter to a half compared with the untuned model. It lifted a fit score close to perfect on the Australian set. The staged search beat either optimizer used alone. The author presents the hybrid as a robust tool for grid operators.
Catalog record
| CREATOR | XinHao Zhang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 50862 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |