Carnegie Mellon University
file.pdf (222.23 kB)

Large-scale Probabilistic Forecasting in Energy Systems using Sparse Gaussian Conditional Random Fields

Download (222.23 kB)
journal contribution
posted on 1989-01-01, 00:00 authored by Matt Wytock, J. Zico Kolter

Short-term forecasting is a ubiquitous practice in a wide range of energy systems, including forecasting demand, renewable generation, and electricity pricing. Although it is known that probabilistic forecasts (which give a distribution over possible future outcomes) can improve planning and control, many forecasting systems in practice are just used as “point forecast” tools, as it is challenging to represent high-dimensional non-Gaussian distributions over multiple spatial and temporal points. In this paper, we apply a recently-proposed algorithm for modeling high-dimensional conditional Gaussian distributions to forecasting wind power and extend it to the non-Gaussian case using the copula transform. On a wind power forecasting task, we show that this probabilistic model greatly outperforms other methods on the task of accurately modeling potential distributions of power (as would be necessary in a stochastic dispatch problem, for example).


Publisher Statement

All Rights Reserved



Usage metrics