Enhanced twin delayed DDPG with prioritized experience replay and Noisy Nets for regional economic dispatch
Chang Xu, Naoki Hayashi, Masahiro Inuiguchi, Wong Jee Keen Raymond, Hazlie Mokhlis, Hazlee Azil Illias · 2025
Read Enhanced twin delayed DDPG with prioritized experience replay and Noisy Nets for regional economic dispatch by Chang Xu, Naoki Hayashi, Masahiro Inuiguchi, Wong Jee Keen Raymond, Hazlie Mokhlis, Hazlee Azil Illias (2025) 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/pmc-12699030.txt.
Description
Chang Xu and five co-authors shared a study in twenty twenty-five on smart dispatch for a small grid with solar power. Adding green power makes it hard to balance cost and grid stability. The team used a learning method called twin delayed DDPG. They made it stronger with two added tricks.
One trick, prioritized experience replay, let the learner reuse its most useful past choices. The other, Noisy Nets, added adaptive noise to the model and helped it explore. Together they cut testing operation cost by over half. They also nearly wiped out cumulative power imbalance next to the baseline method. The authors call the approach a scalable framework for microgrid control.
Catalog record
| CREATOR | Chang Xu, Naoki Hayashi, Masahiro Inuiguchi, Wong Jee Keen Raymond, Hazlie Mokhlis, Hazlee Azil Illias |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 76 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |