A Data-Driven Machine Learning Approach for Consumer Modeling with Load Disaggregation

TL;DR

This paper introduces a novel two-stage machine learning method for disaggregating residential load data into fixed and shiftable components, enhancing demand modeling for energy management applications.

Contribution

It presents a generic, data-driven semi-parametric model combining NMF, GMM, and regression techniques for load disaggregation, improving upon arbitrary parameter choices in prior work.

Findings

Effective load disaggregation demonstrated on real residential data

Hybrid NMF and GMM approach accurately separates load components

Model shows potential for improved demand response and energy planning

Abstract

While non-parametric models, such as neural networks, are sufficient in the load forecasting, separate estimates of fixed and shiftable loads are beneficial to a wide range of applications such as distribution system operational planning, load scheduling, energy trading, and utility demand response programs. A semi-parametric estimation model is usually required, where cost sensitivities of demands must be known. Existing research work consistently uses somewhat arbitrary parameters that seem to work best. In this paper, we propose a generic class of data-driven semiparametric models derived from consumption data of residential consumers. A two-stage machine learning approach is developed. In the first stage, disaggregation of the load into fixed and shiftable components is accomplished by means of a hybrid algorithm consisting of non-negative matrix factorization (NMF) and Gaussian mixture models (GMM), with the latter trained by an expectation-maximization (EM) algorithm. The fixed and shiftable loads are subject to analytic treatment with economic considerations. In the second stage, the model parameters are estimated using an L2-norm, epsilon-insensitive regression approach. Actual energy usage data of two residential customers show the validity of the proposed method.