Predictive daylight harvesting system

1. A method performed by a predictive system for indoor horticulture, the method comprising:

obtaining a set of input values identifying a geographic position of a physical structure enclosing an interior environment and a target distribution for each of a set of environmental parameters for a selected plant occupant, the set of environmental parameters including at least a light level, temperature level, and humidity level within the interior environment;

obtaining a virtual representation of the physical structure including geometry and material properties of physical objects defining an enclosure of the physical structure and located within the interior environment that influence an actual distribution of the set of environmental parameters within the interior environment, and further including virtual representations of a set of one or more sensor devices and a set of one or more control devices as physically arranged with respect to the physical structure and interior environment;

iteratively over time,

updating the virtual representation based on actual plant growth or a predicted plant growth model for the selected plant occupant to incorporate changing virtual representations of the selected plant occupant that influence the actual distribution of the set of environmental parameters within the interior environment;

running a computational model to obtain a predicted distribution of the set of environmental parameters for the virtual representation based on the set of input values;

determining a target distribution of a set of artificially modulated environmental parameters including at least an artificially modulated light level, temperature level, and humidity level by way of the set of control devices to achieve the target distribution of the set of environmental parameters within the interior environment based on the predicted distribution of the set of environment parameters;

obtaining measurement data from the set of sensor devices measuring an initial distribution of the set of environmental parameters, the set of sensor devices including one or more photosensors, one or more temperature sensors, and one or more humidity sensors; and

based on the target distribution of the set of artificially modulated environmental parameters, setting one or more output parameters for the set of control devices to collectively control the actual distribution of the set of environmental parameters towards achieving the target distribution of the set of environmental parameters, the set of control devices selected from a group comprising: luminaire devices, fenestration devices, HVAC devices, humidity modulation devices.

2. The method of claim 1 , further comprising:

obtaining a set of additional inputs identifying a change to the virtual representation with respect to the physical objects, the set of sensor devices, or the set of control devices; and

updating the virtual representation based on the set of additional inputs to incorporate the change to the virtual representation.

3. The method of claim 1 , wherein setting one or more output parameters for the set of control devices includes a controller of the predictive system implementing an artificial intelligence engine that identifies control values for the one or more output parameters further based on a set of additional inputs obtained, including one or more of:

weather data, occupant usage data, plant growth data, alternative energy availability data, and/or measurement data from additional sensor devices, including one or more of soil moisture sensors, carbon dioxide and oxygen concentration sensors, and/or sensors directly monitoring plant growth and health.

4. The method of claim 3 , wherein the artificial intelligence engine applies fuzzy logic to the set of additional inputs to identify the control values for the one or more output parameters.

5. The method of claim 3 , wherein the artificial intelligence engine applies neuro-fuzzy logic to the set of additional inputs to identify the control values for the one or more output parameters.

6. The method of claim 5 , further comprising:

iteratively over time, training the controller of the predictive system based on the measurement data and the one or more output parameters for the set of control devices to establish a trained relationship between the measurement data and the one or more output parameters; and

upon establishing the trained relationship, setting the one or more output parameters for the set of control devices based on the trained relationship in place of or in addition to the target distribution of the set of artificially modulated environmental parameters.

7. The method of claim 3 , wherein the artificial intelligence engine applies deep learning methods to the set of additional inputs to identify the control values for the one or more output parameters.

8. The method of claim 7 , further comprising:

iteratively over time, training the controller of the predictive system based on the measurement data and the one or more output parameters for the set of control devices to establish a trained relationship between the measurement data and the one or more output parameters; and

upon establishing the trained relationship, setting the one or more output parameters for the set of control devices based on the trained relationship in place of or in addition to the target distribution of the set of artificially modulated environmental parameters.

9. A predictive system for indoor horticulture, the system comprising:

a computing system, including:

a logic subsystem; and

a storage subsystem having instructions stored thereon executable by the logic subsystem to:

obtain a set of input values identifying a geographic position of a physical structure enclosing an interior environment and a target distribution for each of a set of environmental parameters for a selected plant occupant, the set of environmental parameters including at least a light level, temperature level, and humidity level within the interior environment;

obtain a virtual representation of the physical structure including geometry and material properties of physical objects defining an enclosure of the physical structure and located within the interior environment that influence an actual distribution of the set of environmental parameters within the interior environment, and further including virtual representations of a set of one or more sensor devices and a set of one or more control devices as physically arranged with respect to the physical structure and interior environment;

iteratively over time,

update the virtual representation based on actual plant growth or a predicted plant growth model for the selected plant occupant to incorporate changing virtual representations of the selected plant occupant that influence the actual distribution of the set of environmental parameters within the interior environment;

run a computational model to obtain a predicted distribution of the set of environmental parameters for the virtual representation based on the set of input values;

determine a target distribution of a set of artificially modulated environmental parameters including at least an artificially modulated light level, temperature level, and humidity level by way of the set of control devices to achieve the target distribution of the set of environmental parameters within the interior environment based on the predicted distribution of the set of environment parameters;

obtain measurement data from the set of sensor devices measuring an initial distribution of the set of environmental parameters, the set of sensor devices including one or more photosensors, one or more temperature sensors, and one or more humidity sensors; and

based on the target distribution of the set of artificially modulated environmental parameters, set one or more output parameters for the set of control devices to collectively control the actual distribution of the set of environmental parameters towards achieving the target distribution of the set of environmental parameters, the set of control devices selected from a group comprising: luminaire devices, fenestration devices, HVAC devices, humidity modulation devices.

10. The system of claim 9 , wherein the instructions are further executable by the logic subsystem to:

obtain a set of additional inputs identifying a change to the virtual representation with respect to the physical objects, the set of sensor devices, or the set of control devices; and

update the virtual representation based on the set of additional inputs to incorporate the change to the virtual representation.

11. The system of claim 9 , wherein setting one or more output parameters for the set of control devices includes implementing an artificial intelligence engine of the instructions that identifies control values for the one or more output parameters further based on a set of additional inputs obtained, including one or more of:

weather data, occupant usage data, plant growth data, alternative energy availability data, and/or measurement data from additional sensor devices, including one or more of soil moisture sensors, carbon dioxide and oxygen concentration sensors, and/or sensors directly monitoring plant growth and health.

12. The system of claim 11 , wherein the instructions are further executable by the logic subsystem to:

iteratively over time, train the artificial intelligence engine based on the measurement data and the one or more output parameters for the set of control devices to establish a trained relationship between the measurement data and the one or more output parameters; and

upon establishing the trained relationship, set the one or more output parameters for the set of control devices based on the trained relationship in place of or in addition to the target distribution of the set of artificially modulated environmental parameters.

13. The system of claim 12 , wherein the artificial intelligence engine applies fuzzy logic to the set of additional inputs to identify the control values for the one or more output parameters.

14. The system of claim 12 , wherein the artificial intelligence engine applies neuro-fuzzy logic to the set of additional inputs to identify the control values for the one or more output parameters.

15. The system of claim 12 , wherein the artificial intelligence engine applies deep learning methods to the set of additional inputs to identify the control values for the one or more output parameters.

16. The system of claim 9 , further comprising:

the set of sensor devices.

17. The system of claim 9 , further comprising:

the set of control devices.