Today, the regulatory and environmental context is pushing owners to collect their energy consumption data. Indeed, the appearance of the tertiary decree has forced real estate players to obtain this data and make efforts on the energy performance of their tertiary real estate assets. In addition, the environmental aspect is increasingly a societal issue but also an economic issue with the ongoing energy crisis. It is therefore essential to have access to your consumption data in order to better understand, manage and reduce it.
Data Reliability: What Does It Mean?
For our customers, the reliability of their consumption data is based on two important aspects: spatial and temporal reliability.
Spatial reliability is based on having knowledge of the consumption of all the spaces in your building. In the case of a multi-tenant building, in addition to the common areas, it is essential to know the consumption of the private areas occupied by each tenant. Indeed, the lack of knowledge of a single tenant undermines the reliability of the consumption of the entire building.
Temporal reliability, on the other hand, focuses on the completeness of the data over time. Indeed, having a missing invoice or data for a month, for example, significantly impacts the reliability of the data. The higher the collection frequency, the lower the risk of missing data.
To ensure this technically, we compare invoices and take index readings on the meters in order to verify the reliability of the readings sent by our IoT sensors.
Benefits of reliable data for building managers
Having reliable data is essential to have a real impact on the environmental performance of your real estate portfolio.
Indeed, reliability leads to relevant actions in terms of energy management. By adding the finesse of analysis thanks to monitoring by zone and a high frequency, it is all the easier to make adjustments that allow you to save energy. At iQspot, we use IoT sensors to ensure that we automatically collect this reliable and detailed data. Our team of energy experts can therefore advise our clients to have the maximum impact on their real estate portfolio.
For example, on the Dock en Seine building of BNP Paribas REIM, we delayed the fan coil ignition time and lowered the base set temperature by 2°C thanks to a detailed analysis of consumption by our energy managers. This resulted in a saving of 136 MWh or €12,000 for the building’s tenants in just 4 months.
This data reliability also makes it possible to produce qualitative and relevant reports. In the world of real estate investment, figures are very important and make it possible to differentiate between players. Having a level of reliability and detail is therefore essential to stand out from the competition and establish credibility.
Data Reliability: Processes and Technologies
To ensure the reliability of the data, we make sure we have the right information about the building. To do this, we systematically go on site to create a reliable counting plan listing all the measurement points and tenants. This allows us to have a high reliability rate because the knowledge on the ground allows us to remove any doubts that may exist. This is a real differentiating point compared to a simple invoice statement for example.
This approach is supplemented by anomaly detection using machine learning. This method makes it possible to learn from a batch of data from buildings considered functional and to predict “normal” consumption. Thus, we verify the veracity of the data by comparing consumption predictions created by AI and the consumption recorded by our sensors. This can make it possible to detect a coefficient problem for example, a poorly executed counting plan or a configuration error whether on our application or on our sensors.
In line with this approach, we set up index readings on the meters during each of our visits, whether for an installation or maintenance, in order to ensure the reliability of the data recorded by our sensors.
We also have alerts set up on our sensors in order to detect breakdowns and intervene quickly to resolve the problem and maintain data continuity.
Finally, to obtain an optimal reliability rate, we also sometimes set up the use of several data sources. For example, we cross-reference the data from invoices with that from our sensors. This way, we ensure that we are talking about the same measurement points and that the data is correct. This allows us to have an accuracy rate of 99%. We can therefore ensure a high reliability rate to our customers on an ongoing basis.
The important thing to remember is that the more numerous and diversified the verification processes are, the more they can provide reliable data. All the more so since the reliability of energy data is necessary to have an impact on the environmental performance of its portfolio. It is therefore essential in the context of decarbonization that real estate is currently experiencing.
Finally, with the strong rise in importance of AI, the need for reliable data will be all the more essential to use developments in this field wisely.
