Predicting Peak Day and Peak Hour of Electricity Demand with Ensemble Machine Learning

TL;DR

This paper presents an ensemble machine learning method to accurately predict peak demand days and hours in power systems, aiding in energy storage management and reducing uncertainties in dispatch decisions.

Contribution

It introduces a supervised learning approach for probabilistic peak demand prediction, with guidance on data preparation, model selection, and decision thresholds, applied to real utility data.

Findings

Captured 69 out of 72 peak days in testing

On 90% of peak days, actual peak hour is among top 2 predicted hours

Successfully reduces uncertainty in peak demand forecasting

Abstract

Battery energy storage systems can be used for peak demand reduction in power systems, leading to significant economic benefits. Two practical challenges are 1) accurately determining the peak load days and hours and 2) quantifying and reducing uncertainties associated with the forecast in probabilistic risk measures for dispatch decision-making. In this study, we develop a supervised machine learning approach to generate 1) the probability of the next operation day containing the peak hour of the month and 2) the probability of an hour to be the peak hour of the day. Guidance is provided on the preparation and augmentation of data as well as the selection of machine learning models and decision-making thresholds. The proposed approach is applied to the Duke Energy Progress system and successfully captures 69 peak days out of 72 testing months with a 3% exceedance probability threshold. On 90% of the peak days, the actual peak hour is among the 2 hours with the highest probabilities.