Day Ahead Market price scenario generation using a Combined Quantile Regression Deep Neural Network and a Non-parametric Bayesian Network

In this manuscript we propose a methodology to generate electricity price scenarios from probabilistic forecasts. Using a Combined Quantile Regression Deep Neural Network, we forecast hourly marginal price distribution quantiles for the DAM on which we fit parametric distributions. A Non-parametric Bayesian Network (BN) is applied to sample from these distributions while using the observed rank-correlation in the data to condition the samples. This results in a methodology that can create an unbounded amount of price-scenarios that obey both the forecast hourly marginal price distributions and the observed dependencies between the hourly prices in the data. The BN makes no assumptions on the marginal distribution, allowing us to flexibly change the marginal distributions of hourly forecasts while maintaining the dependency structure.