Short-Term Density Forecasting of Low-Voltage Load using Bernstein-Polynomial Normalizing Flows

TL;DR

This paper introduces a novel probabilistic load forecasting method using Bernstein polynomial normalizing flows, improving density predictions for low-voltage demand and aiding renewable energy grid management.

Contribution

It presents a flexible density forecasting approach with neural network-controlled Bernstein flows, outperforming traditional Gaussian and non-parametric methods in short-term load prediction.

Findings

Density predictions outperform Gaussian models.

Method surpasses non-parametric pinball loss approach.

Effective for 24-hour ahead load forecasting.

Abstract

The transition to a fully renewable energy grid requires better forecasting of demand at the low-voltage level to increase efficiency and ensure reliable control. However, high fluctuations and increasing electrification cause huge forecast variability, not reflected in traditional point estimates. Probabilistic load forecasts take future uncertainties into account and thus allow more informed decision-making for the planning and operation of low-carbon energy systems. We propose an approach for flexible conditional density forecasting of short-term load based on Bernstein polynomial normalizing flows, where a neural network controls the parameters of the flow. In an empirical study with 363 smart meter customers, our density predictions compare favorably against Gaussian and Gaussian mixture densities. Also, they outperform a non-parametric approach based on the pinball loss for 24h-ahead load forecasting for two different neural network architectures.