Hierarchical Demand Forecasting Benchmark for the Distribution Grid

TL;DR

This paper introduces a benchmark for hierarchical demand forecasting in distribution grids, comparing various probabilistic methods and hierarchical techniques to improve load prediction accuracy, with datasets made publicly available.

Contribution

It provides a comprehensive benchmark dataset and evaluation framework for hierarchical probabilistic demand forecasting in low voltage distribution grids, including a comparison of multiple methods.

Findings

Hierarchical techniques can improve bottom-level forecast accuracy.

Probabilistic forecasting methods are evaluated using standard KPIs.

Public datasets enable standardized benchmarking for demand forecasting.

Abstract

We present a comparative study of different probabilistic forecasting techniques on the task of predicting the electrical load of secondary substations and cabinets located in a low voltage distribution grid, as well as their aggregated power profile. The methods are evaluated using standard KPIs for deterministic and probabilistic forecasts. We also compare the ability of different hierarchical techniques in improving the bottom level forecasters' performances. Both the raw and cleaned datasets, including meteorological data, are made publicly available to provide a standard benchmark for evaluating forecasting algorithms for demand-side management applications.