Energy Efficiency Prediction for cooling & heating load

How can Machine Learning helps architects improve buildings energetic efficiency?

In order to reduce the impact of global warming, households, communities and states are constantly working to diminish energy consumption due to heating and cooling. The average US household spends between 3 and 4% of the family’s income on heating and cooling.

The increasing demands for glass walls in hotels, airports, commercial complexes has raised indoor temperatures leading to higher demand in cooling systems. Early prediction of building cooling load (CL) and heating load (HL) can help engineers and architects design energy-efficient buildings. This type of cooling load and heating load modelling allows for a variety of ‘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.

The energy performance of buildings can be estimated using predictive modelling.

Problems to solve

  • Can a building carbon footprint be reduced at conception time?
  • How can electricity and money be saved at the same time?
  • What type of construction can provide mild temperatures in a building?
  • What would be the impact of switching a wood door for a glass door? ?n terms of energy bills in an office?
  • Benefits of TADA
    in the Energy Efficiency Prediction

    For over a decade, energy professionals have been working on energy optimization in buildings and about the magnitude of the potential energy savings for owners. Engineers, architects, facility managers can benefit from using predictive models to estimate buildings energy consumption. Yet most of them are not data scientists. They usually don’t have the skills in Machine Learning and software coding to build predictive models.

    Professionals possess relevant data about existing buildings and layouts including measures of their relative density, their surface area, their wall zone, their roof zone, their total height, their orientation, their window area surface, their heating and cooling time. These data are usually available for a few dozen buildings, making them a typical case of Small Data (in contrast to Big Data which is counted in millions). Traditional Machine Learning algorithms and tools don’t work well with Small Data. TADA, MyDataModels’ solution, performs well with Small Data and helps architects, engineers and facility managers create easily predictive models based on their data. No data science training, data preprocessing or data normalization are required to use TADA. Data can be imported into TADA without any extra effort. Professionals can get convincing results on a laptop in less than a minute.

    MyDataModels brings a self-service solution for the professionals who have Small Data.

    TADA brings new possibilities for building professionals

    Effectively managing 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 major renovations are carried out. Using Artificial Intelligence (AI) and Machine Learning (ML) is an extremely effective way to model a building unique thermal equation.

    “Predictive models allow professionals to optimise energy efficiency”

    One of the benefits of using AI is that it can determine the thermal energy equation for a building in a fraction of the time required by professionals. TADA predictive models allow architects, engineers and facility managers to enhance their building know-how with optimized energy efficiency.