Building data platform with digital twin based historical scenario generation

1 . A building system of a building comprising one or more non-transitory storage devices storing instructions thereon that, when executed by one or more processors, cause the one or more processors to:

receive historical data values of a plurality of data points for a plurality of historical times;

generate a plurality of different operating scenarios at the plurality of historical times for operating equipment of the building;

execute a plurality of artificial intelligence agents to read data from a digital twin of the building, execute machine learning models to simulate a plurality of values of data points of a building space at the plurality of historical times based on the plurality of different operating scenarios and the historical data values, generate at least one simulated performance indicator based on the plurality of values of the data points, and save the plurality of values of the data points and the at least one simulated performance indicator to the digital twin; and

cause a user device to display a graphic representation of the building space and a selectable element to select a historical time of the plurality of historical times, wherein a selection of the historical time causes the user device to display, via the graphic representation of the building space, the at least one simulated performance indicator with an actual performance indicator in the digital twin at the building space.

2 . The building system of claim 1 , wherein the instructions cause the one or more processors to:

generate a plurality of performance scores for the plurality of different operating scenarios based on the plurality of values of the data points; and

execute an artificial intelligence agent of the plurality of artificial intelligence agents to determine a future recommendation for the building based on the plurality of performance scores for the plurality of different operating scenarios.

3 . The building system of claim 2 , wherein the instructions cause the one or more processors to:

compare a first performance score for a first operating scenario of the plurality of different operating scenarios to a second performance score for a second operating scenario of the plurality of different operating scenarios;

select the first operating scenario responsive to determining that the first performance score is greater than the second performance score; and

generate a recommendation to implement an update to the building based on a selection of the first operating scenario.

4 . The building system of claim 1 , wherein the instructions cause the one or more processors to:

generate a user interface to display multiple operating scenarios in parallel, wherein the user interface includes a first portion configured to display a first operating scenario and a second portion configured to display a second operating scenario at the same time.

5 . The building system of claim 1 , wherein the instructions cause the one or more processors to:

generate a user interface to display multiple operating scenarios singularly, wherein the user interface includes one portion configured to display a first operating scenario at a first time, and a second operating scenario at a second time.

6 . The building system of claim 1 , wherein the plurality of different operating scenarios include at least one of different control algorithms for the building, different control schedules for the building, installation of new equipment in the building, or maintenance of equipment for the building.

7 . The building system of claim 1 , wherein the instructions further cause the one or more processors to store the digital twin of the building in the one or more non-transitory storage devices, the digital twin comprising a virtual representation of the building with a plurality of entities of the building, the plurality of data points, and an interrelationship between the plurality of entities of the building and the plurality of data points, wherein the digital twin further includes the plurality of artificial intelligence agents configured to generate a plurality of inference values.

8 . The building system of claim 7 , wherein the digital twin includes a building graph data structure including a plurality of nodes representing the plurality of entities of the building and a plurality of edges between the plurality of nodes representing the interrelationship between the plurality of entities of the building.

9 . The building system of claim 7 , wherein the digital twin generates one or more predicted future states or simulated past states of the building space.

10 . The building system of claim 9 , wherein the one or more predicted future states of the building space include at least one of:

a predicted occupant level, a predicted air quality level, or a predicted reproductive number.

11 . The building system of claim 9 , wherein the selectable element comprises representations of a plurality of historical days and a plurality of future days.

12 . The building system of claim 9 , wherein the instructions further cause the one or more processors to generate a space indicator configured to describe the at least one simulated performance indicator using one or more colors.

13 . A method comprising:

receiving historical data values of a plurality of data points for a plurality of historical times;

generating a plurality of different operating scenarios at the plurality of historical times for operating equipment of a building;

executing a plurality of artificial intelligence agents to read data from a digital twin of the building, execute machine learning models to simulate a plurality of values of data points of a building space at the plurality of historical times based on the plurality of different operating scenarios and the historical data values, generate at least one simulated performance indicator based on the plurality of values of the data points, and save the plurality of values of the data points and the at least one simulated performance indicator to the digital twin; and

causing a user device to display a graphic representation of the building space and a selectable element to select a historical time of the plurality of historical times, wherein a selection of the historical time causes the user device to display, via the graphic representation of the building space, the at least one simulated performance indicator with an actual performance indicator in the digital twin at the building space.

14 . The method of claim 13 , further comprising:

generating a plurality of performance scores for the plurality of different operating scenarios based on the plurality of values of the data points; and

executing an artificial intelligence agent of the plurality of artificial intelligence agents to determine a future recommendation for the building based on the plurality of performance scores for the plurality of different operating scenarios.

15 . The method of claim 14 , further comprising:

comparing a first performance score for a first operating scenario of the plurality of different operating scenarios to a second performance score for a second operating scenario of the plurality of different operating scenarios;

selecting the first operating scenario responsive to determining that the first performance score is greater than the second performance score; and

generating a recommendation to implement an update to the building based on a selection of the first operating scenario.

16 . The method of claim 13 , further comprising generating a user interface to display multiple operating scenarios in parallel, wherein the user interface includes a first portion configured to display a first operating scenario and a second portion configured to display a second operating scenario at the same time.

17 . The method of claim 13 , further comprising storing the digital twin of the building in one or more non-transitory storage devices, the digital twin comprising a virtual representation of the building with a plurality of entities of the building, the plurality of data points, and an interrelationship between the plurality of entities of the building and the plurality of data points, wherein the digital twin further includes at least one of the plurality of artificial intelligence agents configured to generate a plurality of inference values.

18 . One or more non-transitory computer readable media containing program instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:

receiving historical data values of a plurality of data points for a plurality of historical times;

generating a plurality of different operating scenarios at the plurality of historical times for operating equipment of a building;

executing a plurality of artificial intelligence agents to read data from a digital twin of the building, execute machine learning models to simulate a plurality of values of data points of a building space at the plurality of historical times based on the plurality of different operating scenarios and the historical data values, generate at least one simulated performance indicator based on the plurality of values of the data points, and save the plurality of values of the data points and the at least one simulated performance indicator to the digital twin; and

causing a user device to display a graphic representation of the building space and a selectable element to select a historical time of the plurality of historical times, wherein a selection of the historical time causes the user device to display, via the graphic representation of the building space, the at least one simulated performance indicator with an actual performance indicator in the digital twin at the building space.

19 . The one or more non-transitory computer readable media of claim 18 , wherein the program instructions further cause the one or more processors to:

generate a plurality of performance scores for the plurality of different operating scenarios based on the plurality of values of the data points; and

execute an artificial intelligence agent of the plurality of artificial intelligence agents to determine a future recommendation for the building based on the plurality of performance scores for the plurality of different operating scenarios.

20 . The one or more non-transitory computer readable media of claim 18 , wherein the program instructions further cause the one or more processors to generate a user interface to display multiple operating scenarios in parallel, wherein the user interface includes a first portion configured to display a first operating scenario and a second portion configured to display a second operating scenario at the same time.