Nonparametric Probabilistic Prediction of Ultra-Short-Term Wind Power Based on MultiFusion–ChronoNet–AMC DOI Creative Commons
Yan Yan, Yi Qian, Yan Zhou

et al.

Energies, Journal Year: 2025, Volume and Issue: 18(7), P. 1646 - 1646

Published: March 25, 2025

Accurate forecasting is crucial for enhancing the flexibility and controllability of power grids. Traditional methods mainly focus on modeling based a single data source, which leads to an inability fully capture underlying relationships in wind data. In addition, current models often lack dynamic adaptability characteristics, resulting lower prediction accuracy reliability under different time periods or weather conditions. To address aforementioned issues, ultra-short-term hybrid probabilistic model MultiFusion, ChronoNet, adaptive Monte Carlo (AMC) proposed this paper. By combining multi-source fusion multiple-gated structure, nonlinear characteristics uncertainties various input conditions are effectively captured by model. Additionally, AMC method applied paper provide comprehensive, accurate, flexible predictions. Ultimately, experiments conducted multiple datasets, results show that not only improves deterministic but also enhances intervals.

Language: Английский

Nonparametric Probabilistic Prediction of Ultra-Short-Term Wind Power Based on MultiFusion–ChronoNet–AMC DOI Creative Commons
Yan Yan, Yi Qian, Yan Zhou

et al.

Energies, Journal Year: 2025, Volume and Issue: 18(7), P. 1646 - 1646

Published: March 25, 2025

Accurate forecasting is crucial for enhancing the flexibility and controllability of power grids. Traditional methods mainly focus on modeling based a single data source, which leads to an inability fully capture underlying relationships in wind data. In addition, current models often lack dynamic adaptability characteristics, resulting lower prediction accuracy reliability under different time periods or weather conditions. To address aforementioned issues, ultra-short-term hybrid probabilistic model MultiFusion, ChronoNet, adaptive Monte Carlo (AMC) proposed this paper. By combining multi-source fusion multiple-gated structure, nonlinear characteristics uncertainties various input conditions are effectively captured by model. Additionally, AMC method applied paper provide comprehensive, accurate, flexible predictions. Ultimately, experiments conducted multiple datasets, results show that not only improves deterministic but also enhances intervals.

Language: Английский

Citations

0