Learning Probability Distributions of Day-Ahead Electricity Prices

• Tác giả: Jozef Barunik, Lubos Hanus
• Ngôn ngữ: eng
• Ký hiệu phân loại: 525.63 Earth (Astronomical geography)
• Thông tin xuất bản: 2023
• Bộ sưu tập: Metadata
• ID: 198300

Tóm tắt

We propose a novel machine learning approach to probabilistic forecasting of hourly day-ahead electricity prices. In contrast to recent advances in data-rich probabilistic forecasting that approximate the distributions with some features such as moments, our method is non-parametric and selects the best distribution from all possible empirical distributions learned from the data. The model we propose is a multiple output neural network with a monotonicity adjusting penalty. Such a distributional neural network can learn complex patterns in electricity prices from data-rich environments and it outperforms state-of-the-art benchmarks.