Follow us
|
|
Predict the Load Required to Heat a Building

# 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

One week

Regression

#### Customer Benefits

1. Calculate a building heating and cooling load before the building is built.
2. Get an excellent accuracy in these estimates.
3. 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.