Distributed uncertainty-aware multi-agent-inspired learning for wind power forecasting

Ege Kandemir

doi:10.1016/j.egyai.2026.100857

Distributed uncertainty-aware multi-agent-inspired learning for wind power forecasting

2026-07-30

0

OA

AI

E

Ege Kandemir *

A

Agus Hasan

T

Trond Kvamsdal

S

Saleh Alaliyat

DOI：10.1016/j.egyai.2026.100857

Original

Original request for help

Save

Abstract

En 中文

• Distributed framework improves performance over a centralized baseline LSTM. • Uncertainty is quantified at multiple levels to inform other models. • Quantile Range Representation achieves the lowest error with sharper prediction intervals.

Keywords:

Probabilistic forecasting

Wind power

Multi-agent learning

Uncertainty quantification

Distributed uncertainty-aware multi-agent-inspired learning for wind power forecasting

Abstract

Journal

Organization