top of page

NOX

Developing predictive models to analyze and forecast energy consumption patterns for residential heat pumps and total household usage

About the project

This project with NOX Energy focused on developing predictive models to analyze and forecast energy consumption patterns for residential heat pumps and total household usage. The initiative aimed to identify the primary variables influencing heat pump performance and determine which forecasting models were most effective for 24-hour energy predictions. Additionally, the project explored the correlation between heat pump activity and overall house consumption to see if heat pump data could be used to improve the accuracy of total residential energy forecasts. By pinpointing specific parameters that drive consumption, the project provided actionable insights into optimizing energy loads within a residential environment

Project members

Project Responsible (Board):

Sam Deweirdt

Bieke Leenknegt

 

Project Leader:

Rune Wulteputte​

​

Project Members:

Lucas Labeeuw

Gloria Morales

Cédric Chen

Marcin Balint Keller

About NOX

NOX Energy specializes in optimizing heat pump energy usage by bridging the gap between electric asset manufacturers and energy markets. The company coordinates a portfolio of heat pumps to provide grid flexibility, either increasing consumption when there is excess generation or turning units off when demand exceeds supply. By collaborating with manufacturers, building management systems, and energy aggregators, NOX manages energy usage and information to generate financial value while helping stabilize the grid.

About Crunch Analytics

Founded in 2016, Crunch Analytics is a Belgian data and AI consultancy that helps businesses harness data science, machine learning, and AI to drive smarter decision-making. Specializing in retail, e-commerce, and consumer goods, they develop tailored analytics solutions, optimize pricing strategies, and provide training to empower teams in using data effectively.

image_edited.png
bottom of page