Prediction of Energy Consumption for Variable Customer Portfolios Including Aleatoric Uncertainty Estimation
This addresses energy retailers' need for accurate consumption forecasts with uncertainty estimation, but it is incremental as it builds on existing probabilistic deep learning approaches.
The paper tackles the problem of predicting day-ahead energy consumption for customer portfolios using smart meter data, proposing a method that models aleatoric uncertainty with lognormal distributions via deep neural networks, enabling probabilistic forecasts for arbitrary portfolio compositions.
Using hourly energy consumption data recorded by smart meters, retailers can estimate the day-ahead energy consumption of their customer portfolio. Deep neural networks are especially suited for this task as a huge amount of historical consumption data is available from smart meter recordings to be used for model training. Probabilistic layers further enable the estimation of the uncertainty of the consumption forecasts. Here, we propose a method to calculate hourly day-ahead energy consumption forecasts which include an estimation of the aleatoric uncertainty. To consider the statistical properties of energy consumption values, the aleatoric uncertainty is modeled using lognormal distributions whose parameters are calculated by deep neural networks. As a result, predictions of the hourly day-ahead energy consumption of single customers are represented by random variables drawn from lognormal distributions obtained as output from the neural network. We further demonstrate, how these random variables corresponding to single customers can be aggregated to probabilistic forecasts of customer portfolios of arbitrary composition.