Large-scale probabilistic forecasting in energy systems using sparse Gaussian conditional random fields

Abstract

Abstract-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 highdimensional non-Gaussian distributions over multiple spatial and temporal points. In this paper, we apply a recentlyproposed 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).

Very-Short-Term Probabilistic Wind Power Forecasts by Sparse Vector Autoregression

“…Using multiple wind farms as 'spatial sensors' was shown to improve wind power forecast skill at a target site in [16]. Recent contributions have sought to build efficient probabilistic spatial models with sparse Gaussian random fields, but are limited to modest spatial dimension [17], [18]. However, with the abundance of wind farms on many power systems today it is desirable to build a spatial predictor for tens, or hundreds, of wind farms, making computational cost and automated model fitting serious considerations.…”

Neural Gaussian Conditional Random Fields

“…In the computational advertising field, GCRF significantly improved accuracy of click through rate estimation by taking into account relationship among advertisements [11]. An extension of GCRF to the non-Gaussian case using the copula transform was used in forecasting wind power [16]. In combination with decision trees, GCRF was successfully applied to short-term energy load forecasting [17], while in combination with support vector machines it was applied on automatic recognition of emotions from audio and visual features [18].…”

Gaussian conditional random fields extended for directed graphs

“…However, this work is focused on advancing the GCRF model because it produces high accuracy and it is the most scalable learning approach of all listed above (Glass et al 2015). GCRF has been used on a broad set of applications: climate (Radosavljevic et al 2010(Radosavljevic et al , 2014Djuric et al 2015), energy forecasting (Wytock and Kolter 2013;Guo 2013), healthcare (Gligorijevic et al 2015;Polychronopoulou and Obradovic 2014), speech recognition (Khorram et al 2014), computer vision (Tappen et al 2007;Wang et al 2014), etc. There are other works that capture asymmetric dependencies, such as Asym-MRF model (Heesch and Petrou 2010).…”

“…Each approach takes different inputs and has various benefits and drawbacks. Some of these methods (Wytock and Kolter 2013) learn relationships between nodes from attributes. These are referred to as generative networks.…”