Controller and method for proactively controlling indoor temperature of a facility

Abstract

A model predictive controller (202) proactively controls indoor temperature (118, 410) of a facility. An input component (318) receives an air temperature for a zone of a facility. A processor (306) identifies a solar irradiance (314) for the zone of the facility and determines an air temperature prediction based on the air temperature for the zone and the solar irradiance (314). An output component (320) controls a building automation system (204) based on the air temperature prediction.

Description

CONTROLLER AND METHOD FOR PROACTIVELY CONTROLLING INDOOR TEMPERATURE OF A FACILITYFIELD OF THE INVENTION

[0001] This application relates to the field of building automation systems and, more particularly, to systems and method for controlling indoor temperatures of facilities.BACKGROUND

[0002] For programming logic of a conventional heating, ventilation, and air conditioning (HVAC) unit, the programming logic reacts after a comfort violation occurs. This reactive approach of the programming logic causes multiple problems. On the one hand, the occupants of the building are exposed to an uncomfortable environment for a variable timespan until the temperature goes back to the expected range. On the other hand, the energy consumption of the HVAC system during that off-range period is more intense than during normal operation.

[0003] Most conventional units are based on a “closed loop” approach. In particular, the HVAC unit reads data from building sensors at a constant frequency, and the unit adjusts to varying environmental conditions that deviate from a desired set point. Each HVAC unit include proportional integral derivative (PID) controllers that process incoming data and produce outputs to control actuators of the HVAC unit. The HVAC unit generates a set point based on the processed data to manage its indoor temperature and avoid any comfort violation. The reading-processing-writing loop is executed throughout the lifespan of the unit.SUMMARY

[0004] In accordance with one embodiment of the disclosure, there is provided a proactive approach for optimizing indoor temperatures of a facility. In contrast to set points or boundaries of conventional systems, a model predictive controller (MPC) operates with a building automation system to use both historical data as well asfuture or forecast data to proactively control a building’s indoor temperature and keep it within a target range.

[0005] One aspect is a model predictive controller for proactively controlling indoor temperature of a facility comprising an input component, a processor coupled to the input component, and an output component coupled to the processor. The input component receives an air temperature for a zone of a facility. The processor identifies a solar irradiance for the zone of the facility and determines an air temperature prediction based on the air temperature for the zone and the solar irradiance. The output component controls the building automation system based on the air temperature prediction.

[0006] Another aspect is a method of a model predictive controller for proactively controlling indoor temperature of a facility. An air temperature for a zone of a facility is received. A solar irradiance for the zone of the facility is identified. An air temperature prediction is determined based on the air temperature for the zone and the solar irradiance. An HVAC controller of the building automation system is controlled based on the air temperature prediction.

[0007] Yet another aspect is a non-transitory computer readable medium including executable instructions which, when executed, causes one or more processors of a model predictive controller to proactively control indoor temperature of a facility by performing the above method.

[0008] The above-described features and advantages, as well as others, will become more readily apparent to those of ordinary skill in the art by reference to the following detailed description and accompanying drawings. While it would be desirable to provide one or more of these or other advantageous features, the teachings disclosed herein extend to those embodiments which fall within the scope of the appended claims, regardless of whether they accomplish one or more of the above-mentioned advantages.BRIEF DESCRIPTION OF THE DRAWINGS

[0009] For a more complete understanding of the present disclosure, and the advantages thereof, reference is now made to the following descriptions taken in conjunction with the accompanying drawings, wherein like numbers designate like objects.

[0010] FIG. 1 is a graphic representation of environmental conditions of an area within a facility in an example implementation that is operable to employ techniques described herein.

[0011] FIG. 2 is a system view of an example implementation of model predictive controller operating with a building automation system.

[0012] FIG. 3 is a block diagram of example components of the model predictive controller of FIG. 2.

[0013] FIG. 4 is a timing diagram of an example operation of the model predictive controller of FIG. 2.

[0014] FIG. 5 is a representation of an example floor layout of a facility which indicates the impact of solar irradiance on areas of the facility.

[0015] FIG. 6 a flow diagram representing an example operation of the model predictive controller of FIG. 2.

[0016] FIG. 7 is flow diagram representing an example operation of the model predictive controller operating with the building automation system.DETAILED DESCRIPTION

[0017] Various technologies that pertain to systems and methods that facilitate optimization of indoor temperatures of a facility in a proactive way will now be described with reference to the drawings, where like reference numerals represent like elements throughout. The drawings discussed below, and the various embodiments used to describe the principles of the present disclosure in this patent document are byway of illustration only and should not be construed in any way to limit the scope of the disclosure. Those skilled in the art will understand that the principles of the present disclosure may be implemented in any suitably arranged apparatus. It is to be understood that functionality that is described as being carried out by certain system elements may be performed by multiple elements. Similarly, for instance, an element may be configured to perform functionality that is described as being carried out by multiple elements. The numerous innovative teachings of the present application will be described with reference to exemplary non-limiting embodiments.

[0018] Referring to FIG. 1, there is shown environmental conditions of an area within a facility in an example implementation that is operable to employ techniques described herein. A building automation system may have boundaries, such as a heating set point 102 and a cooling set point 104, to control temperature of the area. The temperature of the area may be controlled within a narrow temperature range 106 during normal business hours 108 and have a wider temperature range 110 during other hours 112 of operation. In this manner, the environmental conditions of the area may provide comfortable surroundings for occupants when the number of occupants in the area is significant.

[0019] Outside environmental conditions 114 and facility occupation 116 impact the comfort and efficiency of indoor temperatures 118 of areas throughout the facility. Outside environmental condition 114 change in view of solar irradiance and weather conditions. Occupation 116 of the facility often increase during normal business hours 108 and decrease during other hours 112 of operation. Conventional systems are often reactive and do not provide sufficient control of indoor temperatures 1 18 in anticipation of outside environmental conditions and facility occupation. For example, as outdoor temperatures and occupancy increase throughout the day, conventional systems do not manage conventional temperatures 120 to keep up with outside solar and temperature variations.

[0020] A model predictive controller (MPC) anticipates future disturbances that will negatively affect the indoor temperature 118 and adjusts the building automation system accordingly. Specifically, the model predictive controller proactively controlsthe HVAC unit to adapt HVAC indoor temperatures 122 in view of outside solar and temperature variations. The model predictive controller proactively avoids eventual comfort violations and ensures a pleasant environment. The model predictive controller further achieves energy savings by using the HVAC unit in an optimal way.

[0021] FIG. 2 is a system view of an example implementation of a system 200 that includes a model predictive controller 202 operating with a building automation system 204. The building automation system 204 manages an HVAC unit to control environmental conditions and, in some cases, may also include other building functions, such a lighting, fire safety, and / or security functions. The model predictive controller 202 includes an optimization engine 206 that receives incoming data 208 associated with environmental conditions of the building automation system 204 and provides outgoing data 210 associated with control commands of the HVAC unit. The model predictive controller 202 may receive the incoming data 208 on a periodic basis from the building automation system 204, such as every 15 minutes. The model predictive controller 202 may receive data from each zone, from a central system, or both. Examples of incoming data 208 from each zone include, but are not limited to, heating and cooling set points, room temperature, room status, valve position, and set point shift. Examples of incoming data 208 from the central system include, but are not limited to, building operation mode, supply water temperature, discharge air temperature, and heating / cooling capacity.

[0022] The model predictive controller 202, particularly the optimization engine 206, processes a substantial quantity of datapoints and creates a tailored thermal model of each area or zone in the facility. The incoming data 208 is associated with devices of the building automation system 204, such as radiator units 212, fan coil units 214, and variable air volume units 216. The model predictive controller 202 delivers custom optimization strategies for each zone based on additional factors or data 218 received from an external source 220. Examples of additional data 218 include, but are not limited to, solar irradiance forecast 222, weather (air temperature, wind, humidity, etc.) forecast 224, and space utilization (i.e., occupancy) forecast 226, one or more valve positions, and the like.

[0023] The processor of the model predictive controller 202 or optimization engine 206 identifies a solar irradiance for the zone of the facility and determines an air temperature prediction based on, in part, the solar irradiance 222. For some embodiments, the model predictive controller 202 relies, among other factors, on the Global Tilted Irradiance (GTI) to deliver better prediction results. For each space or area in a facility, the model predictive controller 202 may use the GTI data to accurately calculate the effect of the solar irradiance in the space taking into consideration factors such as the orientation of the space regarding the position of the sun and the specific angle in which the solar irradiance impacts the building’s facade throughout a particular day.

[0024] Solar irradiance is the power of electromagnetic radiation received from the Sun for a particular area, measured in watts per square meter. Global tilted irradiance (GTI) is the total radiation received on a surface with defined zenith and azimuth angle. For the building use case, the tilt angel is usually fixed to about 90 degrees, since the building facade is perpendicular to the horizontal plane.

[0025] FIG. 3 is a block diagram of example components of the model predictive controller 302. The controller components 300 comprise one or more communication lines 302 for interconnecting other controller components directly or indirectly. The other controller components include one or more communication components 304 communicating with other entities via a wired or wireless network, one or more processors 306, and one or more memory components 308. The communication component 304 communicates (i.e., receives and / or transmits) data associated with one or more devices of the system 100 and its associated devices. The communication component 304 may utilize wired or wireless technology for communication.Examples of wireless communication technologies include, but are not limited to, Bluetooth (including BLE), ultrawide band (UWB), Wi-Fi (including Wi-Fi Direct), Zigbee, cellular, mesh networks, PAN, WPAN, WAN, near-field communications, and other types of radio communications and their variants.

[0026] The processor or processors 306 may send data to, and process commands received from, other components of the controller components 300, such asinformation of the communication component 304 or the memory component 308. Each application includes executable code to provide specific functionality for the processor 306 and / or remaining components of the controller 202. Examples of applications executable by the processor 306 include, but are not limited to, a solar irradiance identifier module 310 and an air temperature predictor module 312. The solar irradiance identifier module 310 identifies a solar irradiance for the zone of the facility. The air temperature predictor module 312 determines an air temperature prediction based on the air temperature for the zone and the solar irradiance.

[0027] For some embodiments, the air temperature predictor module 312 of the processor 306 may be part of the model predictive controller 202 and operate as the optimization engine 206. Thus, the air temperature predictor module 312 may determine an air temperature prediction using artificial intelligence (Al) or, more particularly, a machine learning process such as a deep learning process. The deep learning process may include generative Al and the like. The HVAC model of the air temperature predictor module 312 may be trained to determine the air temperature prediction by analyzing historical data for the air temperature for the zone and the solar irradiance relative to corresponding ground truth data. For some embodiments, the HVAC model may be trained using additional data such as weather (air temperature, wind, humidity, etc.) and / or one or more valve positions. During or subsequent to training the HVAC model of the air temperature predictor module 312, the module may operate to determine the air temperature prediction based collected data for the air temperature for the zone and the solar irradiance. Technologies that may be utilized for the machine learning process include, but are not limited to chatbots, neural networks, k-nearest neighbors, decision trees, Bayesian learning, linear and polynomial regression, mathematical optimization, support vector machines, and robotics. For example, linear and polynomial regression may be used to build models, and mathematical optimization may be used to get room temperature prediction.

[0028] Data stored at the memory component 308 is information that may be referenced and / or manipulated by a module of the processor 306 for performing functions of the controller 202. Examples of data associated with the controller 202and stored by the memory component 308 may include, but are not limited to, solar irradiance data 314, weather / occupancy data 316, and valve position data. The solar irradiance data 314 includes one or more predictive factors associated with an orientation of the Sun relative to the zone. For some embodiments, the solar irradiance data 314 may include radiation data associated with a zenith angle of solar irradiance on the zone, an azimuth angle of solar irradiance on the zone, or both. An example of solar irradiance data 314 is, but are not limited to, Global tilted irradiance (GTI) data. For some embodiments, the weather / occupancy data includes a weather forecast for an area outside of the facility, an occupancy indicating the density of occupants with the zone of the facility, or both.

[0029] The controller components 300 may include an input component 318 that manages one or more input components and / or an output component 320 that manages one or more output components. The input components 318 and output components 320 of the controller components 300 may include one or more visual, audio, mechanical, and / or other components. For some embodiments, the input and output components 318, 320 may include a user interface 322 for interaction with a user. The user interface 322 may include a combination of hardware and software to provide a user with a desired user experience.

[0030] It is to be understood that FIG. 3 is provided for illustrative purposes only to represent an example implementation of the model predictive controller 202 and is not intended to be a complete diagram of the various components that may be utilized by the controller. The controller 202, may include various other components not shown in FIG. 3, may include a combination of two or more components, or a division of a particular component into two or more separate components, and still be within the scope of the present invention. Also, the components 300 may be coupled directly or indirectly to each other to perform the operations of the controller 202.

[0031] FIG. 4 is a timing diagram 400 of an example operation of the model predictive controller of FIG. 2. The timing diagram 400 includes a y-axis 402 indicating a temperature level, in degrees, of a given area of the facility, and an x-axis 404 indicating a base time for each temperature reading. The timing diagram 400shown in FIG. 4 illustrates past temperature readings 406 before a given time k and future temperature readings 408 after the given time k. The past temperature readings 406 represent measured readings by the model predictive controller 202, and the future temperature readings 408 represent predicted readings by the model predictive controller. Readings from sensors of the HVAC equipment, such as air conditioning components, radiators, variable air volume units, and the like, are collected as data points every given time period, and input to an optimization engine 206 and / or model predictive controller 202.

[0032] The indoor temperature 410 of an area or zone of the facility is maintained within a comfort band 412 for the occupants of the zone. The model predictive controller 202 achieves this task of maintaining the indoor temperature 410 within the comfort band 412 by providing the appropriate set point values 414 to the HVAC system of the building automation system. The model predictive controller 202 determines the appropriate set point values 414. For some embodiments, the model predictive controller 202 may determine the appropriate set point values 414 based, at least in part, on the solar irradiance associated with each zone. For some embodiments, the model predictive controller 202 may also determine the appropriate set point values 414 using additional data, such as weather forecast, occupancy information 416, and / or valve position(s). The prediction horizon 418 for making the determination may be predetermined for a certain period of time in the future.

[0033] FIG. 5 is a representation of an example floor layout 500 of a facility which indicates the impact of solar irradiance on areas of the facility. By identifying how the Sun impacts a facility or, more particularly, a given area or zone of the facility, the model predictive controller 202 generates an accurate prediction of the appropriate setting or control for optimal indoor room temperature. Referring the floor layout 500 of FIG. 5, the Sun may irradiate the facility from a particular direction. The zenith angle of solar irradiance and the azimuth angle of solar irradiance on a particular zone depends on location of the Sun relative to the zone. For example, a given facility may have a facade at each side, such as a southwest facade 510, a northwest facade 520, a northeast facade 530, and a southeast facade 540. It should be noted that facades areany type of surface of a facility that may be impacted by solar irradiance, such as a skylight located at a ceiling of a zone.

[0034] Each zone may be associated with one or more facades. For example, some southwest zones 512, 514, 516, may be associated with the southwest facade 510, northwest zones 522, 524, 526, 528 may be associated with the northwest facade, and southeast zones 542, 544, 546 may be associated with the southeast facade 540. Zones 552, 554, 556, 558 located at the intersection of two or more facades, such as a corner office, may be associated with multiple facades. Each of these zones may be impacted by radiation received from the Sun based on the zenith angle and the azimuth angle of solar irradiance for each zone, particularly those zones having portal, such as windows, that allow radiation to pass. The facility may further include one or more inner zones 560 that are not associated with any facade 510, 520, 530, 540 of the facility and, thus, have minimal impact from solar irradiance.

[0035] FIG. 6 a flow diagram representing an example operation 600 of the model predictive controller 202. The example operation 600 represents a method of a model predictive controller 202 for proactively controlling indoor temperature of a facility. The model predictive controller 202 receives (610) an air temperature for a zone of a facility. The model predictive controller 202 identifies (620) a solar irradiance for the zone of the facility in response to receiving (610) the air temperature of the zone of the facility. For some embodiments, the solar irradiance may include one or more predictive factors (622) associated with an orientation of the Sun relative to the zone. For some embodiments, one or more predictive factors may include radiation data associated with a zenith angle of sol ar irradiance and an azimuth angle of solar irradiance on the zone (624). For some embodiments, one or more predictive factors may further include a weather forecast for an area outside of the facility (626), an occupancy within the zone (628), a valve position, or a combination of two or more of these factors.

[0036] In response to identifying (620) the solar irradiance of the zone of the facility, the model predictive controller 202 determines (630) an air temperature prediction based on the air temperature for the zone and the solar irradiance. For someembodiments, the model predictive controller 202 may determine (632) a set point value for an indoor temperature for the zone based on the air temperature and the solar irradiance.

[0037] In response to determining (630) the air temperature prediction, the model predictive controller 202 controls (630) an HVAC controller of the building automation system based on the air temperature prediction. For embodiments that determine (632) the set point value for the indoor temperature for the zone, the model predictive controller 202 may send (642) the set point value to the HVAC controller. By sending the set point value for the indoor temperature to the HVAC controller, the model predictive controller 202 may proactively control the indoor temperatures of the facility without taking full control of HVAC operation of the facility.

[0038] For some embodiments, the model predictive controller 202 may determine an air temperature prediction using artificial intelligence (Al) or, more particularly, a machine learning process such as a deep learning process. The deep learning process may include large language models and / or generative Al. The model predictive controller 202 may train the HVAC model of the optimization engine 206 to determine the air temperature prediction by analyzing historical data for the air temperature for the zone and the solar irradiance relative to corresponding ground truth data. For some embodiments, the HVAC model may be trained using additional data such as weather (air temperature, wind, humidity, etc.) and / or one or more valve positions. During or subsequent to training the HVAC model of the optimization engine 206, the model predictive controller 202 may operate the trained HVAC model to determine the air temperature prediction based collected data for the air temperature for the zone and the solar irradiance.

[0039] As stated above, the model predictive controller 202 may include the optimization engine 206 and / or the air temperature predictor module 312 of the processor 306 and, thus, utilize the machine learning process such as a deep learning process to determine the air temperature prediction. For the machine learning process, the model predictive controller 202 includes, or have access to, system information about the HVAC unit or units. The model predictive controller 202 identifies one ormore global equipment for each facility, an automation station of each room for control automation points, and one or more local equipment for each room. The controller 202 also identifies supplies relationships from global to local equipment and assigns data points to equipment. Examples of assigned data points include, but are not limited to, heating and cooling data points to all equipment (local, global), solar irradiance, indoor temperature, set points, occupancy, and the like. For example, global equipment may include a cooling circuit (such as a chiller) and a heating circuit (such as a boiler), and local equipment may include cooling equipment (such as a cooling coil), heating equipment (such as a heating coil or radiator), and / or a terminal unit for a variable airflow volume unit.

[0040] The model predictive controller 202 includes, or has access to, tagged data for the building, room, and data points associated with the HVAC unit or units. For the building and / or room, the tagged data may include a direction tag corresponding to the orientation of the building or room as numeral value or values and / or a country tag having a country code corresponding to a particular country. For the direction tag, a value may not be included if a room is not adjacent to an outside wall. Each data point is associated with a particular equipment of the HVAC unit or units, such as the automation station, cooling equipment, and heating equipment. Examples of data points associated with the automation station include, but are not limited to, room temperature, temperature set point, temperature set point shift, present set point for heating, present set point for cooling, heating set point for comfort, cooling set point for comfort, delta heating set point for pre-comfort, delta cooling set point for precomfort, window contact, plant operation mode, heating cooling state, and presence detector. Examples of data points associated with the cooling equipment include, but are not limited to, chilled water zone vale position (for cooling coil), fan multi speed (for cooling coil), chilled water temperature entering, chilled water temperature leaving, and chilled water mixing valve position. Examples of data points associated with the heating equipment include, but are not limited to, hot water zone valve position (radiator / heating coil), hot water temperature entering, hot water temperature leaving, and hot water mixing valve position.

[0041] The model predictive controller 202 includes, or has access to, schedule information associated with the HVAC unit or units. The schedule information may include, for example, mode information, a specified time period (such as military time) for each mode, and a minimum and maximum set point in degrees Celsius, Fahrenheit, Kelvin, and the like) for each specified time period for each mode. Examples of modes include, but are not limited to, economy mode and comfort mode.

[0042] FIG. 7 is flow diagram representing an example operation 700 that includes a controller function (702) of the model predictive controller 202 and a system function (704) of the building automation system 204. A feature of the model predictive controller 202 is the way it controls an indoor temperature of a zone without controlling the underlying physical devices directly. The model predictive controller 202 receives and / or identifies comfort bounds and disturbances (706). For example, the controller 202 may receive air temperature for a particular zone and identify a solar irradiance for the zone. For some embodiments, further factors may be considered such as weather, occupancy, and / or valve position information. The controller 202 performs the controller function 702 of determining an air temperature prediction based on the air temperature and solar irradiance. In particular, the controller 202 may determine a desired effect (708) to the building automation system 204 in view of the air temperatures and solar irradiance. An example of the desired effect (708) is, but is not limited to, opening a valve at 60% (710).

[0043] In response to receiving (708) the desired effect, the translating function (712) may then process (714) the desired effect (708). In particular, the translating function (712) converts the desired effect (708) to a set point value (716) that would cause such a desired effect in the system 204. A device controller (718) of the system, such as a proportional integral derivative (PID) controller, may receive the set point value (716) or a command including the set point value and cause device function (720) corresponding to the desired effect to occur in the system. In this manner, the system allows other applications executing a facility to operate normally without the model predictive controller 202 taking control of the HVAC operation. Accordingly, the building automation system 204 may perform (722) other functions and / or provide(724) feedback to the model predictive controller 202 in response to operation of the PID controller (718) based on the set point value (716).

[0044] Those skilled in the art will recognize that, for simplicity and clarity, the full structure and operation of all data processing systems suitable for use with the present disclosure are not being depicted or described herein. Also, none of the various features or processes described herein should be considered essential to any or all embodiments, except as described herein. Various features may be omitted or duplicated in various embodiments. Various processes described may be omitted, repeated, performed sequentially, concurrently, or in a different order. Various features and processes described herein can be combined in still other embodiments as may be described in the claims.

[0045] It is important to note that while the disclosure includes a description in the context of a fully functional system, those skilled in the art will appreciate that at least portions of the mechanism of the present disclosure are capable of being distributed in the form of instructions contained within a machine-usable, computer-usable, or computer-readable medium in any of a variety of forms, and that the present disclosure applies equally regardless of the particular type of instruction or signal bearing medium or storage medium utilized to actually carry out the distribution. Examples of machine usable / readable or computer usable / readable mediums include nonvolatile, hard-coded type mediums such as read only memories (ROMs) or erasable, electrically programmable read only memories (EEPROMs), and user- recordable type mediums such as floppy disks, hard disk drives and compact disk read only memories (CD-ROMs) or digital versatile disks (DVDs).

[0046] Although an example embodiment of the present disclosure has been described in detail, those skilled in the art will understand that various changes, substitutions, variations, and improvements disclosed herein may be made without departing from the spirit and scope of the disclosure in its broadest form.

Claims

CLAIMSWhat is claimed is:

1. A model predictive controller (202) for proactively controlling indoor temperature (118, 410) of a facility comprising: an input component (318) configured to receive an air temperature for a zone of a facility; a processor (306) coupled to the input component (318), the processor (306) identifying a solar irradiance (314) for the zone of the facility and determining an air temperature prediction based on the air temperature for the zone and the solar irradiance (314); and an output component (320) coupled to the processor (306), the output component (320) controlling a building automation system (204) based on the air temperature prediction.

2. The model predictive controller (202) according to claim 1 , wherein the solar irradiance (314) includes at least one predictive factor associated with an orientation of the Sun relative to the zone.

3. The model predictive controller (202) according to claim 2, wherein the at least one predictive factor includes radiation data associated with a zenith angle of solar irradiance (314) and an azimuth angle of solar irradiance (314) on the zone.

4. The model predictive controller (202) according to claims 2 or 3, wherein the at least one predictive factor includes at least one of a weather forecast for an area outside of the facility, an occupancy within the zone, or a valve position.

5. The model predictive controller (202) according to any of the claims 1 to 4, wherein: the processor (306) determines a set point value (414) for an indoor temperature (118, 410) for the zone based on the air temperature and the solar irradiance (314); and the output component (320) sends the set point value (414) to the HVAC controller.

6. The model predictive controller (202) according to any of the claims 1 to 5, wherein the output component (320) proactively controls the indoor temperatures (118, 410) of the facility without taking full control of HVAC operation of the facility.

7. The model predictive controller (202) according to any of the claims 1 to 6, wherein the processor (306) includes an HVAC model that is trained to determine the air temperature prediction by analyzing historical data for the air temperature for the zone and the solar irradiance (314) relative to corresponding ground truth data and operated after training to determine the air temperature prediction based collected data for the air temperature for the zone and the solar irradiance (314).

8. A method of a model predictive controller (202) for proactively controlling indoor temperature (118, 410) of a facility, the method comprising: receiving an air temperature for a zone of a facility; identifying a solar irradiance (314) for the zone of the facility; determining an air temperature prediction based on the air temperature for the zone and the solar irradiance (314); and controlling an HVAC controller of a building automation system (204) based on the air temperature prediction.

9. The method according to claim 8, wherein the solar irradiance (314) includes at least one predictive factor associated with an orientation of the Sun relative to the zone.

10. The method according to claim 9, wherein the at least one predictive factor includes radiation data associated with a zenith angle of solar irradiance (314) and an azimuth angle of solar irradiance (314) on the zone.

11. The method according to claims 9 or 10, wherein the at least one predictive factor further includes at least one of a weather forecast for an area outside of the facility, an occupancy within the zone, or a valve position.

12. The method according to any of the claims 8 to 11, wherein: determining the air temperature prediction includes determining a set point value (414) for an indoor temperature (118, 410) for the zone based on the air temperature and the solar irradiance (314); and controlling the HVAC controller includes sending the set point value (414) to the HVAC controller.

13. The method according to any of the claims 8 to 12, wherein sending the set point value (414) for the indoor temperature (118, 410) to the HVAC controller includes proactively controlling the indoor temperatures (118, 410) of the facility without taking full control of HVAC operation of the facility.

14. The method according to any of the claims 8 to 13, wherein determining an air temperature prediction comprises: training an HVAC model to determine the air temperature prediction by analyzing historical data for the air temperature for the zone and the solar irradiance (314) relative to corresponding ground truth data; and operating the trained HVAC model to determine the air temperature prediction based collected data for the air temperature for the zone and the solar irradiance (314).

15. A non-transitory computer readable medium including executable instructions which, when executed, causes at least one processor (306) of a model predictive controller (202) to proactively control indoor temperature (118, 410) of a facility by: receiving an air temperature for a zone of a facility; identifying a solar irradiance (314) for the zone of the facility; determining an air temperature prediction based on the air temperature for the zone and the solar irradiance (314); and controlling an HVAC controller of a building automation system (204) based on the air temperature prediction.

16. The method according to claim 15, wherein the solar irradiance (314) includes at least one predictive factor associated with an orientation of the Sun relative to the zone.

17. The method according to claim 16, wherein the at least one predictive factor includes radiation data associated with a zenith angle of solar irradiance (314) and an azimuth angle of solar irradiance (314) on the zone.

18. The method according to claims 16 or 17, wherein the at least one predictive factor further includes at least one of a weather forecast for an area outside of the facility, an occupancy within the zone, or a valve position.

19. The method according to any of the claims 15 to 18, wherein: determining the air temperature prediction includes determining a set point value (414) for an indoor temperature (118, 410) for the zone based on the air temperature and the solar irradiance (314); and controlling the HVAC controller includes sending the set point value (414) to the HVAC controller.

20. The method according to any of the claims 15 to 19, wherein sending the set point value (414) for the indoor temperature (118, 410) to the HVAC controller includes proactively controlling the indoor temperatures (118, 410) of the facility without taking full control of HVAC operation of the facility.

Images