Smart energy management as a means towards improved energy efficiency

TL;DR

This paper explores constructing baseline energy consumption models for supermarket refrigerators using machine learning techniques, aiming to improve energy efficiency and provide a foundation for future research.

Contribution

It demonstrates the effectiveness of off-the-shelf data mining models and short-term historical data in establishing energy consumption baselines for supermarkets.

Findings

Baseline models achieved with Linear Regression, Random Forests, and Neural Networks.

Short-term historical data can effectively create reference behaviors.

Approach validated across five supermarkets in Portugal.

Abstract

The costs associated with refrigerator equipment often represent more than half of the total energy costs in supermarkets. This presents a good motivation for running these systems efficiently. In this study, we investigate different ways to construct a reference behavior, which can serve as a baseline for judging the performance of energy consumption. We used 3 distinct learning models: Multiple Linear Regression, Random Forests, and Artificial Neural Networks. During our experiments we used a variation of the sliding window method in combination with learning curves. We applied this approach on five different supermarkets, across Portugal. We are able to create baselines using off-the-shelf data mining techniques. Moreover, we found a way to create them based on short term historical data. We believe that our research will serve as a base for future studies, for which we provide interesting directions.