<p class="jove_content">This study proposes a hybrid cost-forecasting model for power grids that combines physical cost quotas with dynamic macroeconomic/technological adjustments and XGBoost-based residual compensation. Achieving 2.34% MAPE, it balances accuracy and interpretability, addressing regulatory transparency needs in tariff setting.</p>

retrospective-forecasting-using-provincial-grid-data-quota-based

Retrospective Forecasting Using Provincial Grid Data and a Quota-Based Hybrid Physical-AI Model

The global energy transition and ongoing electricity market reforms require power grid enterprises to balance reliable power supply with increasingly ...

Institution - Techno-Economic Center

Articles Published in JoVE