November 18, 2021
Angelo Martucci
Building Energy Modeler, Arloid Automation

What Is A Digital Twin? Why is Digital Modelling of Environments Popular?

The climate crisis is not ‘coming soon’; it is here, happening right now. And we are going to have to use innovative adaption technology to live more sustainably, and change our existing world to achieve Net Zero.

It also seems clear that we must not only rely on innovative technology to, say, clean up our energy source(s); we must also scale back our energy (and resource) usage. Indeed, scholars warn that we may not be able to roll-out renewable energy quick enough to meet the 1.5°C threshold outlined in the Paris Agreement as the economy, and with it, energy usage, continues to grow. There must also be, they argue, a reduction in overall energy usage.

This is where Digital Building Modelling and, specifically, Digital Twins can help with the climate crisis. The built environment of our world contributes hugely to carbon emissions, producing almost a fifth! Additional to this huge output, buildings are energy inefficient – around a third of energy used in commercial buildings is wasted. To reduce this energy mismanagement and carbon footprint, buildings should look at all manner of systems, including heating, ventilation and air conditioning (HVAC) systems, as well as employ innovative technologies such as Building Modelling to get a better idea of energy use and systems.

For more information on building HVAC inefficiencies, read our blog on The Race to Net Zero.

Arloid Automation is proud to deliver huge savings to the real estate industry through AI technology. We save money and energy within real estate, helping us all meet our collective sustainability goals.

Indeed, our vision is: to empower humanity to realise the lowest possible energy consumption in Real Estate as intelligently and efficiently as possible. To achieve this, we have built one of the most powerful AI platform on the market.

This article explores how this platform works. It introduces digital modelling of environments and explains how it works.

What is a Digital Twin?

Just as we are rewilding nature as a response to climate change, optimising the built environment of our future ‘smart cities’ will be of paramount importance, particularly in response to ever more intricate demands.

Digital (simulation) modelling is a prefect technology that can help with such a task, accurately representing multiple complex, interdependent and time-dependent systems.

Simply put: a Digital Twin is a digital copy of a real-life asset – e.g a building – process, or system.

Digital Twins have one fundamental purpose: to model the behaviour of real-world systems to enable people to make better decisions. The models use real-world data, to enable better understanding, learning, and reasoning of, and from, different environments.

Depending on its ‘maturity’, such behaviour modelling can be used in myriad contexts with the twin being anything from a 3D (digital) drawing of a car engine, to a fully integrated and accurate model of an entire asset – such as a high rise building in New York – or assets. Indeed, here, it is argued, is where the transformative potential of Digital Twins lies – in connecting twins together to provide a deeper insight across a broader context, moving towards networks of interconnected models for entire cities and, eventually, countries!

Why is Digital Modelling of Environments Popular?

Across industry, from asset (building) owners and managers, to operators, designers and contractors, Digital (Building) Modelling provides the opportunity for sophisticated design, combined with efficient project execution, asset operation and management.

As mentioned, Digital (Building) Modelling enables the construction of a building digitally before actuation on site meaning that the building phase, for example, can happen faster and safer; but, importantly, it also means that the whole lifecycle – from conception to inception to management – becomes greener and more efficient.

By integrating data and information throughout the lifecycle of the asset, building modelling offers both short and long term efficiency and productivity value-added.

In particular, Digital Twins are a data resource that can (as well as improving the initial design of new buildings) better-understand the existing condition of a given asset; through to carrying out ‘what if’ scenarios and simulations; as well as providing a digital snapshot of future works to be done. This has the potential to vastly reduce errors, discontinuities, expenditure, and overall footprint.

To help better understand this, take the case of Arloid’s application of digital modelling to buildings and their HVAC systems mentioned in the introduction.

Traditionally, HVAC systems have either rule-based models or managed and constantly adjusted manually by staff. As HVAC systems get more complex, it is increasingly challenging for the site facilities teams to follow the changes. For a given building, said staff monitor the temperature and adjust settings reactively – i.e. it feels warm, so the air con is turned on. But, no doubt, not everyone in the room agrees, and soon everyone may feel too cold. In other words, it is a constant game of catching up. This is inefficient, unsuccessful and, ultimately, wasteful.

The effect is tenfold when various zones within a building are considered. Different areas of a building will require different settings in order to achieve occupant comfort. A gym, for example, is likely to require a cooler temperature than an office, full of stationary people.

This is where building a digital model of a physical site and running AI algorithm to find the optimal parameters, comes handy.

Innovative HVAC Optimisation with Digital Twins

Digital Twin calibration is one of the most challenging tasks in BEM (Building Energy Modelling) as it requires countless number of iteration cycles to ensure the model and it’s thermal behaviour are identical to the physical site. Once these are achieved, we run simulations to find the optimal parameters for every HVAC device in the building.

Using Deep Reinforcement Learning, enables us to half the time, usually required to train AI and to create predictions for HVAC devices. Additional to granular HVAC control, arloid.ai also helps to optimise the energy use within buildings, offering up to 30% cost saving and carbon footprint reduction.

To see Digital Twins in action with cost and environmental benefits for your premises, try arloid.ai today! Our simple onboarding process, requiring zero CAPEX or historical data, can have you set up in only 30 days.

FAQs >

About arloid.ai >

Start saving today!


    © 2022 Arloid Automation Ltd | 71-75 Shelton Street, Covent Garden, London, United Kingdom

    ISO 27001:2013 certified
    logo-arloid-iso

    Complete the form below to talk with one of our experts:







      Achieving Net Zero with