Computation of Ultra-Short-Term Prediction Intervals of the Power Prosumption in Active Distribution Networks

TL;DR

This paper introduces a non-parametric method for ultra-short-term prediction intervals of power prosumption in active distribution networks, addressing the limitations of conventional forecasting at sub-second scales.

Contribution

It proposes a clustering-based approach to generate empirical prediction intervals for power prosumption, suitable for ultra-short-term forecasting in active distribution networks.

Findings

Effective prediction intervals for different building types

Clusters serve as representative pools for future power realizations

Model validation shows improved accuracy at sub-second scales

Abstract

Microgrids and, in general, active distribution networks require ultra-short-term prediction, i.e., for sub-second time scales, for specific control decisions. Conventional forecasting methodologies are not effective at such time scales. To address this issue, we propose a non-parametric method for computing ultra short-term prediction intervals (PIs) of the power prosumption of generic electrical-distribution networks. The method groups historical observations into clusters according to the values of influential variables. It is applied either to the original or to the differentiated power-prosumption time series. The clusters are considered statistically representative pools of future realizations of power prosumption (or its derivative). They are used to determine empirical PDFs and, by extracting the quantiles, to deliver PIs for respective arbitrary confidence levels. The models are validated a posteriori by carrying out a performance analysis that uses experimentally observed power-prosumption for different building types, thus allowing the identification of the dominant model.