Learning for Interval Prediction of Electricity Demand: A Cluster-based Bootstrapping Approach

TL;DR

This paper presents a novel cluster-based residual bootstrap method for generating interval predictions of day-ahead electricity demand, improving accuracy in low-aggregation, stochastic load scenarios like Microgrids.

Contribution

It introduces a residual bootstrap algorithm that leverages clustering of demand patterns to produce more reliable demand intervals, enhancing existing prediction methods.

Findings

The proposed method outperforms traditional bootstrapping techniques.

It provides tighter and more accurate demand intervals.

The approach is validated on real-world electricity demand data.

Abstract

Accurate predictions of electricity demands are necessary for managing operations in a small aggregation load setting like a Microgrid. Due to low aggregation, the electricity demands can be highly stochastic and point estimates would lead to inflated errors. Interval estimation in this scenario, would provide a range of values within which the future values might lie and helps quantify the errors around the point estimates. This paper introduces a residual bootstrap algorithm to generate interval estimates of day-ahead electricity demand. A machine learning algorithm is used to obtain the point estimates of electricity demand and respective residuals on the training set. The obtained residuals are stored in memory and the memory is further partitioned. Days with similar demand patterns are grouped in clusters using an unsupervised learning algorithm and these clusters are used to partition the memory. The point estimates for test day are used to find the closest cluster of similar days and the residuals are bootstrapped from the chosen cluster. This algorithm is evaluated on the real electricity demand data from EULR(End Use Load Research) and is compared to other bootstrapping methods for varying confidence intervals.