BMS agnostic building optimisation

Solution using hardware and calibrated Digital Twins to automate and optimise building controls.

Climate Change Mitigation Retrofit

Problem Addressed

Commercial buildings currently represent 23% of built environment carbon emissions in the UK. After construction, commercial real estate lapses into inefficiency within 6 months of commissioning, and there is often inadequate measuring, reporting, and benchmarking. With a changing regulatory landscape, it is important asset owners are able to quickly and efficiently measure and improve on the performance of their assets.

Solution Overview

re:sustain is an AI and Machine Learning solution that delivers significant carbon reductions and cost savings at scale, typically 20-65% ROI. It achieves this by providing a detailed, calibrated Digital Twin of every building. These can be used for accurate and affordable capital expenditure impact analysis and portfolio decarbonisation target modelling. These twins can be created for individual buildings or an entire portfolio of properties.

Firstly, re:sustain will deploy hardware into a building. To connect, the building must have a BMS, be over 5,000m², have access to the internet, and have centralised ventilation or central boilers/chillers. The solution can also be used with virtually any building management system (BMS). Their hardware can integrate with a wide variety of data sources that provide API information including utility meters and can even factor in the weather to provide a comprehensive outlook of a building’s performance and consumption. re:sustain will then stream the BMS data to their platform and build the calibrated Digital Twin. After a feasibility analysis, re:sustain will report on potential carbon savings and activate optimisation measures. These measures include realigning the BMS controls, stabilising the building, and setting up alerts for 24/7 monitoring. Within weeks of optimisation, re:sustain will perform realignments for seasonal changes and provide monthly reporting.

re:sustain is BMS agnostic and uses Machine Learning to automate building controls. Troubleshooting and predictive maintenance of the system can be accomplished remotely or on-site depending on the need. By creating a digital twin of a building, re:sustain is able to benchmark and monitor hypothetical building performance to help make decisions about historic and future projections. With this technology, they can model the effects of adding double glazed windows or installing a new BMS and determine the cost impact of these changes. re:sustain can also recommend the solutions that will best achieve a user’s decarbonisation goals either as quickly as possible or help them select the best value solutions. Their capital expenditure modelling tool enables portfolio-wide sustainable investment decisions at the click of a button.

The solution uses very little hardware and is primarily a Software as a Service solution that takes less than a day to install. It is geography and BMS agnostic and both scalable and affordable. This means that whole portfolios can be saving money and CO2 in weeks, not years (with a typical ROI of under 3 months).

Company name

re:sustain

UK availability

Yes

Date added

Mar, 2024

Solutions submitted by

REsustain

Case Study

re:sustain was deployed on a 17,600m2 office in Croydon in September 2022. The building’s existing control operations were accessed via re:sustain’s gateway, the BMS data collected on the re:sustain platform, and combined with other data sets (e.g. weather, utility bills, structural plans) in the re:sustain Engine, and a Digital Twin of the building was created, enabling a detailed Energy & Carbon Assessment. Their forecast estimated annual energy savings of £140,000 or 210 tonnes of CO2 emissions (26% total energy). The re:sustain Optimisation Service then recalibrated the existing settings of the building remotely, continuously streaming BMS data through re:sustain’s engine algorithms, so control optimisations could be efficiently adjusted for air handling units and the hot water system based on occupancy and season. Over 12 months (October 2022 – October 2023), the optimisations resulted in a 28% reduction in energy usage, which was a saving of 240 tonnes of CO2 emissions and £171,000. The Optimisation Service will continue to monitor and adjust the building’s controls, while the Asset Manager uses the Digital Twin and re:sustain’s Capex Modelling tools to further decarbonise the building in 2024.

More information can be found at the link below:

https://www.cibsejournal.com/technical/back-in-control-how-bms-optimisation-saved-171000-in-nine-months/

<3 months

24/7

BMS %

This page presents data, evidence, and solutions that are provided by our partners and members and should therefore not be attributed to UKGBC. While we showcase these solutions for inspiration, to build consensus, and create momentum for climate action, UKGBC does not offer commercial endorsement of individual solutions. If you would like to quote something from this page, or more information, please contact our Communications team at media@ukgbc.org.