Probabilistic load forecasting for the low voltage network: forecast fusion and daily peaks

TL;DR

This paper introduces a probabilistic forecasting method for low voltage network loads, focusing on accurately predicting daily peaks and improving overall forecast performance through data fusion techniques.

Contribution

It proposes a novel approach to predict peak demand timing and levels, combining conventional and peak forecasts for enhanced probabilistic accuracy.

Findings

Fusing forecasts improves CRPS by over 10% during peaks.

Method performs well on real smart meter data.

Enhanced peak prediction accuracy at feeder levels.

Abstract

Short-term forecasts of energy consumption are invaluable for the operation of energy systems, including low voltage electricity networks. However, network loads are challenging to predict when highly desegregated to small numbers of customers, which may be dominated by individual behaviours rather than the smooth profiles associated with aggregate consumption. Furthermore, distribution networks are challenged almost entirely by peak loads, and tasks such as scheduling storage and/or demand flexibility maybe be driven by predicted peak demand, a feature that is often poorly characterised by general-purpose forecasting methods. Here we propose an approach to predict the timing and level of daily peak demand, and a data fusion procedure for combining conventional and peak forecasts to produce a general-purpose probabilistic forecast with improved performance during peaks. The proposed approach is demonstrated using real smart meter data and a hypothetical low voltage network hierarchy comprising feeders, secondary and primary substations. Fusing state-of-the-art probabilistic load forecasts with peak forecasts is found to improve performance overall, particularly at smart-meter and feeder levels and during peak hours, where improvement in terms of CRPS exceeds 10%.