Predict the Load Required to Heat a Building

MyDataModels

Solutions

Predict the Load Required to Heat a Building

Europe spends 50% of its energy for heating and cooling purposes. Most of it in Europe is produced by fossil fuels, i.e., 66%, and only 13% comes from renewable energy sources. Quaartz can help architects predict and quantify the heating load of a building before it is even built.

Industry

Environment

Project Duration and Effort

One week

Type of Prediction

Regression

Customer Benefits

Calculate a building heating and cooling load before the building is built.
Get an excellent accuracy in these estimates.
Evaluate in seconds the heating impact of doubling the window surface on a new building.

Problem to solve

The typical US household pays between 3 and 4% of the family’s income on heating and cooling. Single-family houses spend twice as much energy for heating as multi-family houses. In EU houses, heating and hot water alone account for 79% of total final energy use. Cooling is a comparatively small share of full final energy use, but demand from households and businesses such as the food industry is rising during the summer months. This trend is also linked to climate change and temperature increases.

We use Quaartz to estimate a building’s heating load. The dataset considered includes 538 records and the following features are provided for each record:

Heating load,
Cooling load,
Relative density,
Surface area,
Wall zone,
Roof zone,
Total height,
Direction,
Window area,
Window area rate.

The rising demands for glass walls in hotels, airports, and commercial complexes have elevated indoor temperatures leading to higher demand for cooling systems. Advanced prediction of building cooling time and heating time can help engineers and architects design energy-efficient buildings. This type of cooling load and heating load modelling permits various ‘what-if’ scenarios without even laying the first stone. The impact of a bigger glass ceiling in an airport can be modelled in a few clicks, and the resulting cooling load estimated seamlessly.

Objectives

Estimate a building heating and cooling load in a few clicks without the use of equations,
Understand what impacts the heating and cooling load in a building design,
Test architectural hypotheses concerning energy consumption.

It poses the following construction question:

Can the heating load of a building-to-be be estimated?

Solution

The Quaartz predictive models provide good results: an R2 of 99%, a MAPE of 5%, and a RMSE of 1,04 for a mean of 22,13. Effectively managing the thermal behaviors of a building is a complex process. These behaviors are expressed in a collection of thermal energy equations, which, once calculated, will not change over time for a building unless significant renovations are carried out.

Quaartz is a simple alternative to the use of these complex equations.

Quaartz has selected the following six main criteria out of the ten available in the dataset:

The relative density, with a weight of 21% in Quaartz’ decision,
The surface area, with a weight of 21% in Quaartz’ decision,
The wall zone, with a weight of 20% in Quaartz’ decision,
The roof zone, with a weight of 16% in Quaartz’ decision,
The total height, with a weight of 14% in Quaartz’ decision,
The window area, with a weight of 7% in Quaartz’ decision.

An R2 of 99% means that the predictions are very accurate. It is interesting to note that the building’s relative density is a significant criterion in Quaartz’ decision, before the window area with three times the weight in Quaartz’ decision.

Customer Benefits

In one week, architects gained significant support in their energy consumption estimates for buildings-to-be:

Calculate a building heating load before the building is built with an R2 of 99%.
Evaluate in seconds the heating impact of doubling the window surface on a new building.

Talk to us on how you can make sense of your data and achieve success.

More use cases

Breast Cancer Prediction for Improved Diagnosis

Breast cancer prediction is a diagnosis help tool. Oncologists and medical staff face the challenge of identifying breast cancer as soon as possible. ...

Customer recommendation: key drivers identification

The world of ISPs is highly competitive. Customers trust, above all else, other customers’ recommendations. ...

Retaining Customers: Churn Prediction

Anytime a client cuts ties, you encounter the negative consequence of customer churn. While some churn is a natural component of any company, a vast churn rate can cripple any organization's growth. ...

Boosting Lead Qualification with Prediction

On average, the cost of one lead is $198 in 2020. The better the lead qualification, the higher the chances of closing with the customer and generating revenue from these $198 invested. ...

Estimating your House Listing Price

In 2019, 5.34 million existing private homes changed owners, according to data from the National Association of REALTORS®. 89% of sellers were helped by a real estate agent when trading their home....

Predicting the Selling Price of a Used Car

Sales of used light vehicles in the United States grew to about 40.8 million units in 2019. The same year, the average selling price of used cars came to nearly 21,000 U.S. dollars. ...