English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The expansion of renewable energy could help realizing the goals of peakingcarbon dioxide emissions and carbon neutralization. Some existing griddispatching methods integrating short-term renewable energy prediction andreinforcement learning (RL) have been proved to alleviate the adverse impact ofenergy fluctuations risk. However, these methods omit the long-term outputprediction, which leads to stability and security problems on the optimal powerflow. This paper proposes a confidence estimation Transformer for long-termrenewable energy forecasting in reinforcement learning-based power griddispatching (Conformer-RLpatching). Conformer-RLpatching predicts long-termactive output of each renewable energy generator with an enhanced Transformerto boost the performance of hybrid energy grid dispatching. Furthermore, aconfidence estimation method is proposed to reduce the prediction error ofrenewable energy. Meanwhile, a dispatching necessity evaluation mechanism isput forward to decide whether the active output of a generator needs to beadjusted. Experiments carried out on the SG-126 power grid simulator show thatConformer-RLpatching achieves great improvement over the second best algorithmDDPG in security score by 25.8% and achieves a better total reward comparedwith the golden medal team in the power grid dispatching competition sponsoredby State Grid Corporation of China under the same simulation environment. Codesare outsourced in https://github.com/buptlxh/Conformer-RLpatching.

Confidence Estimation Transformer for Long-term Renewable Energy Forecasting in Reinforcement Learning-based Power Grid Dispatching