AND/OR HEATING SYSTEM

TECHNICAL FIELD

[0001] The present invention generally relates to a system and a method of controlling an air-conditioning and/or heating system.

BACKGROUND

[0002] Buildings consume a large amount of energy, more particularly, in air- conditioning and/or heating system, and contribute significantly to the total greenhouse gas emissions. Generally, an air-conditioning system control is time-based with pre configured set points based on the industry best practice or knowledge of facility managers. However, conventional air-conditioning system control mechanism with pre-configured set points may unnecessarily consume more energy, for example, in the case where the preconfigured set points (i.e., the same preconfigured set points) of the air-conditioning and/or heating system are used throughout the day.

[0003] For example, conventional techniques may not effectively address the dynamic changing situations or circumstances.

[0004] For example, in US 10,254,726, an air-conditioning control system based on occupant’s feedback is disclosed. The system appears to first create a comfort map, which is a list of air-conditioning temperature set points in a non-overlap time sequence (e.g., referred to as time episode). In each time episode, the system sets the initial air- conditioning temperature set point based on the comfort map. If the system receives a feedback from the occupant, e.g., either “too cool” or “too warm”, the system then adjusts the air-conditioning temperature set point based on the feedback.

[0005] For example, in WO 2019/157514, an air-conditioning control system based on the measurement of occupant’s thermal comfort is disclosed. The system appears to periodically calculate occupant’s thermal comfort level using occupant physiological data (such as heart rate variability and skin temperature) and environmental condition data (such as air temperature and relative humidity). Based on the calculated occupant’s thermal comfort level, the system then changes the air-conditioning set points, such as temperature and ventilation rate. [0006] However, for example, both US 10,254,726 and WO 2019/157514 are re active control and are not able to proactively adjust air-conditioning set points based on dynamic changing situations or circumstances.

[0007] For example, in US 10,444,712, an air-conditioning control system based on the prediction of zone state is disclosed. The system appears to periodically predict the zone state (such as air temperature, relative humidity, and CO2 level) for a next time period, based on the current zone state. The system then changes air-conditioning set points (such as temperature and air flow rate) based on the prediction for the next time period.

[0008] In US 10,094,586, an air-conditioning control system based on the prediction of energy consumption is disclosed. The system appears to periodically predict the heat load in the next time period, using forecasting models of external heat load (heat transfer from weather) and internal heat load (heat gain from occupants, computers, lighting, and so on). The system then changes air-conditioning set points (such as temperature, relative humidity, and air quality) to minimize the energy consumption.

[0009] For example, both US 10,444,712 and US 10,094,586 may proactively forecast the cooling demand for the next time period, and may change air-conditioning set points to reduce energy consumption. However, neither of them considers personal thermal comfort.

[0010] A need therefore exists to provide a system and a method of controlling an air-conditioning and/or heating system that seek to overcome, or at least ameliorate, one or more of the deficiencies in conventional system and method of controlling an air-conditioning and/or heating system, such as but not limited to, optimizing (e.g., dynamically and proactively) a control parameter for controlling the air-conditioning and/or heating system, for example, for improving or optimizing building energy consumption and personal thermal comfort. It is against this background that the present invention has been developed. SUMMARY

[0011] According to a first aspect of the present invention, there is provided a method of controlling an air-conditioning and/or heating system in a region (which may interchangeably be referred to herein as a zone) within a building using at least one processor, the method comprising: obtaining occupancy information for the region at a current time; determining future occupancy information for the region with respect to a subsequent time based on the occupancy information; obtaining future weather information for the region with respect to the subsequent time; and determining common thermal comfort preference information with respect to occupants in the region with respect to the subsequent time based on the future weather information and the future occupancy information.

[0012] According to a second aspect of the present invention, there is provided a system of controlling an air-conditioning and/or heating system in a region within a building, the system comprising: a memory; and at least one processor communicatively coupled to the memory and configured to: obtain occupancy information for the region at a current time; determine future occupancy information for the region with respect to a subsequent time based on the occupancy information; obtain future weather information for the region with respect to the subsequent time; and determine common thermal comfort preference information with respect to occupants in the region with respect to the subsequent time based on the future weather information and the future occupancy information.

[0013] According to a third aspect of the present invention, there is provided a computer program product, embodied in one or more non-transitory computer-readable storage mediums, comprising instructions executable by at least one processor to perform a method of controlling an air-conditioning and/or heating system in a region within a building, the method comprising: obtaining occupancy information for the region at a current time; determining future occupancy information for the region with respect to a subsequent time based on the occupancy information; obtaining future weather information for the region with respect to the subsequent time; and determining common thermal comfort preference information with respect to occupants in the region with respect to the subsequent time based on the future weather information and the future occupancy information.

BRIEF DESCRIPTION OF THE DRAWINGS [0014] Embodiments of the present invention will be better understood and readily apparent to one of ordinary skill in the art from the following written description, by way of example only, and in conjunction with the drawings, in which:

FIG. 1A depicts a schematic flow diagram of a method (computer-implemented method) of controlling an air-conditioning and/or heating system in a region within a building using at least one processor according to various embodiments of the present invention;

FIG. IB depicts a schematic flow diagram of a method (computer-implemented method) of controlling an air-conditioning and/or heating system in a region within a building using at least one processor according to various embodiments of the present invention;

FIG. 2A depicts a schematic block diagram of a control system for controlling an air-conditioning and/or heating system in a region within a building according to various embodiments of the present invention, such as corresponding to the method shown in FIG.1A;

FIG. 2B depicts a schematic block diagram of a control system for controlling an air-conditioning and/or heating system in a region within a building according to various embodiments of the present invention, such as corresponding to the method shown in FIG. IB;

FIG. 3 depicts an example computer system which the system according to various embodiments of the present invention (such as the system as shown in FIG. 2A or 2B) may be embodied in;

FIG. 4 illustrates a schematic block diagram of an example system of controlling an air-conditioning and/or heating system in a region within a building according to various example embodiments of the present invention; FIG. 5 shows a schematic block diagram illustrating exemplary components of an example air-conditioning and/or heating control system according to various example embodiments of the present invention;

FIG. 6 illustrates an exemplary flow diagram of operations of an example thermal comfort learning program or method according to various example embodiments of the present invention;

FIG. 7 A illustrates an exemplary data structure of an example thermal comfort log according to various example embodiments of the present invention;

FIG. 7B shows an exemplary data structure of an example occupant profile according to various example embodiments of the present invention;

FIG. 8 shows an exemplary thermal comfort prediction model according to various example embodiments of the present invention;

FIG. 9 illustrates an exemplary data structure of individual thermal comfort preference information associated with each occupant according to various example embodiments of the present invention;

FIG. 10 shows an exemplary process flow diagram for an example occupant presence pattern analysis program or method according to various example embodiments of the present invention;

FIG. 11 shows an exemplary data structure of an example occupant presence log associated with each occupant according to various example embodiments of the present invention;

FIG. 12 shows a schematic drawing of example occupant presence in a control zone according to various example embodiments of the present invention;

FIG. 13 shows an exemplary data structure of an occupant presence probability table according to various example embodiments of the present invention;

FIG. 14 shows an exemplary process flow diagram for an example configuration program or method according to various example embodiments of the present invention;

FIG. 15 shows an exemplary process flow diagram illustrating optimization by an example control optimizer according to various example embodiments of the present invention;

FIG. 16 illustrates a schematic drawing illustrating a common thermal comfort preference with respect to occupants in a region according to various example embodiments of the present invention; and FIG. 17 illustrates a schematic diagram of an example control action learning program according to various example embodiments of the present invention.

DETAILED DESCRIPTION

[0015] Various embodiments of the present invention provide a method (computer- implemented method) of controlling an air-conditioning and/or heating system in a region within a building, and a system (including a memory and at least one processor communicatively coupled to the memory) thereof. According to various embodiments, the method of controlling the air-conditioning and/or heating system in a region within a building and system thereof may determine future occupancy information for the region with respect to a subsequent time, obtain future weather information for the region with respect to the subsequent time, and determine common thermal comfort preference information with respect to occupants in the region with respect to the subsequent time based on the future weather information and the future occupancy information. According to various embodiments, the method may proactively or dynamically change or update a control parameter for the air-conditioning and/or heating system with respect to the subsequent time based on the future weather information, the future occupancy information (e.g., future occupant presence information) and personal thermal comfort preference of each of the occupants at the subsequent time. The control parameter may comprise one or more setting values associated with the air-conditioning and/or heating system relating to, but not limited to, air temperature, air ventilation or flow rate, relative humidity, carbon dioxide level, or combinations thereof. Various embodiments may thus optimize or adjust (e.g., automatically or dynamically) a control parameter for the air-conditioning and/or heating system, for improving or optimizing building energy consumption and personal thermal comfort of occupants.

[0016] FIG. 1A depicts a schematic flow diagram of a method 100a (computer- implemented method) of controlling an air-conditioning and/or heating system in a region within a building using at least one processor according to various embodiments of the present invention. The method 100a comprises obtaining (at 102) occupancy information for the region at a current time; determining (at 104) future occupancy information for the region with respect to a subsequent time based on the occupancy information; obtaining (at 106) future weather information for the region with respect to the subsequent time; and determining (at 108) common thermal comfort preference information with respect to occupants in the region with respect to the subsequent time based on the future weather information and the future occupancy information.

[0017] In relation to 102, for example, the occupancy information may comprise, for each of the occupants, an occupant identifier associated with the occupant, the occupant identifier identifying the occupant present in the region at the current time. [0018] In relation to 104, in various embodiments, the future occupancy information may be determined based on the presence of occupants at the current time and, for each of the occupants, the probability of the occupant to be (e.g., continuously) present with respect to the subsequent time. In various embodiments, an occupant presence log associated to each of the occupants may be obtained based on the occupancy information at the current time. For example, the occupant presence log, for each of the occupants, may be obtained based on the occupant identifier associated with the occupant. The occupant presence log may be analyzed to obtain a probability of occupant presence associated with the occupant with respect to the subsequent time. For example, the probability of occupant presence associated with the occupant with respect to the subsequent time may be obtained by determining an occupant presence pattern.

[0019] In relation to 106, the future weather information may comprise weather condition associated with the region with respect to the subsequent time. The weather condition may comprise outdoor air temperature, outdoor relative humidity, and/or wind speed. In other words, the future weather information for the region may be relating to future weather conditions in the vicinity (or geographical area) of the building in which the region is located, and therefore associated to the region, i.e., for the region. In various embodiments, the above-mentioned obtaining future weather information for the region with respect to the subsequent time comprises predicting weather condition for the region with respect to the subsequent time. In other embodiments, the above-mentioned obtaining future weather information for the region with respect to the subsequent time comprises acquiring or retrieving data relating to the weather condition for the region with respect to the subsequent time from an external data source provided by a third party such as a weather forecast station.

[0020] In relation to 108, the above-mentioned determining common thermal comfort preference information may comprise determining, for each of the occupants, individual thermal comfort preference information associated with the occupant based on the future occupancy information for the region with respect to the subsequent time. In various embodiments, the individual thermal comfort preference information associated with the occupant may include a preferred zone air temperature range. [0021] The individual thermal comfort preference information associated with the occupant may be predicted using a thermal comfort prediction model trained based on occupant information associated with the occupant, weather information relating to weather condition associated with the occupant, and environmental information relating to environmental condition associated with the occupant. The occupant information associated to each occupant may include an occupant profile (e.g., race, age, gender, height, weight), physiological information (or human vital sign information) (e.g., skin temperature, heart rate), clothing, activity level (e.g., walking steps per minute), and/or thermal comfort feedback. The weather condition may comprise outdoor air temperature and outdoor relative humidity. The environmental condition of the region may comprise region (or zone) air temperature, region (or zone) relative humidity, region (or zone) air velocity, region (or zone) carbon dioxide level. In other words, the individual thermal comfort preference information may be predicted for each of the occupants with respect to the subsequent time based on occupant information, weather condition and environmental condition.

[0022] FIG. IB depicts a schematic flow diagram of a method 100b (computer- implemented method) of controlling an air-conditioning and/or heating system in a region within a building using at least one processor according to various embodiments of the present invention. The method 100b comprises obtaining (at 102) occupancy information for the region at a current time; determining (at 104) future occupancy information for the region with respect to a subsequent time based on the occupancy information; obtaining (at 106) future weather information for the region with respect to the subsequent time; determining (at 108) common thermal comfort preference information with respect to occupants in the region with respect to the subsequent time based on the future weather information and the future occupancy information; determining (at 110) a control parameter for controlling the air-conditioning and/or heating system with respect to the subsequent time based on the common thermal comfort preference information using a control parameter determining model; and updating (at 112) the control parameter for the air-conditioning and/or heating system at the subsequent time based on the control parameter determined.

[0023] The steps 102 to 108 may be similar as described with respect to FIG. 1A, and will not be described with respect to FIG. IB in the interest of brevity. [0024] In relation to 110, in various embodiments, the control parameter determining model may be a reward function, and the above-mentioned determining a control parameter for controlling the air-conditioning and/or heating system with respect to the subsequent time based on the common thermal comfort preference information may be based on maximizing thermal comfort associated to the occupants with respect to the subsequent time while minimizing energy consumption in the building using the reward function.

[0025] In relation to 112, in various embodiments, the control parameter for the air- conditioning and/or heating system may be updated at the subsequent time so as to take into account the thermal comfort preference of each of the occupants based on the determined future occupancy information.

[0026] In various embodiments, the control parameter comprises one or more setting values associated with the air-conditioning and/or heating system relating to at least one of air temperature, relative humidity, air ventilation rate, and carbon dioxide level.

[0027] In various embodiments, the method 100b may further comprise predicting, for each of the occupants, individual thermal comfort preference of the occupant with respect to the subsequent time to obtain predicted individual thermal comfort preference information using a thermal comfort prediction model trained based on occupant information associated with the occupant, weather information relating to weather condition associated with the occupant, and environmental information relating to environmental condition associated with the occupant.

[0028] In various embodiments, the method 100b may further comprise measuring, for each of the occupants, actual individual thermal comfort preference of the occupant at the subsequent time to obtain measured individual thermal comfort preference information; and optimizing the control parameter determining model based on, for each of the occupants, a difference between the predicted individual thermal comfort preference information and the measured individual thermal comfort preference information associated with the occupant.

[0029] In various embodiments, the occupant information associated with the occupant comprises human vital sign information.

[0030] In various embodiments, the common thermal comfort preference information with respect to the occupants in the region comprises a common preference of (zone) air temperature range. [0031] In various embodiments, the above-mentioned determining the common thermal comfort preference information may further comprise determining, for each of the occupants, individual thermal comfort preference information associated with the occupant based on the future occupancy information for the region with respect to the subsequent time; and determining the common thermal comfort preference information with respect to the occupants in the region with respect to the subsequent time is further based on the individual thermal comfort preference information associated with each of the occupants.

[0032] In various embodiments, the above-mentioned obtaining future weather information for the region with respect to the subsequent time comprises predicting weather condition for the region with respect to the subsequent time.

[0033] In various embodiments, the above-mentioned obtaining future weather information for the region with respect to the subsequent time comprises acquiring data relating to weather condition for the region with respect to the subsequent time from an external data source. In other words, a forecast weather data may be acquired, for example, from a weather station.

[0034] The presence of occupants in a commercial building may vary dynamically within a typical business day depending on its business activities. It is common to find spaces partially occupied or even unoccupied for significant time periods. For example, average occupancy in office buildings may be as low as 50% of their design occupancy, even at peak times of the day. Further, personal thermal comfort may vary depending on factors such as race, gender, age, and body mass. With the same room temperature, some occupants may feel comfortable, whereas others may feel cold and prefer warmer temperature setting. According to various embodiments, air-conditioning set points updated at the subsequent time may be optimized based on the thermal comfort of occupants with respect to the subsequent time, and therefore may provide comfort for the occupants present at the subsequent time.

[0035] According to various embodiments, the air-conditioning and/or heating control system may be implemented in office buildings, in which the control system proactively and automatically changes the air-conditioning set points based on the prediction of weather condition, occupant presence and personal thermal comfort preference, so that building energy consumption and personal thermal comfort of the occupants may be optimized. [0036] According to various embodiments, the air-conditioning and/or heating control system may be implemented in airports, in which occupant presence may be determined or predicted based on flight arriving time and departure time, and personal thermal comfort preference may be learned from feedback collected through a mobile App provided by an airport.

[0037] According to various embodiments, the air-conditioning and/or heating control system may be implemented in hotels, in which occupant presence may be determined or predicted based on hotel booking information, potential check-in/check- out time, and personal thermal comfort preference may be learned from feedback collected through a Mobile App or other touchpoint provided in the hotel room, in various non-limiting examples.

[0038] According to various embodiments, the air-conditioning and/or heating control system may be implemented for the transportation service, such as train and bus services, in which occupant presence may be determined or predicted based on passenger’ s travel pattern using ticketing data, and personal thermal comfort preference may be learned from feedback collected through a Mobile App provided by the transportation service provider.

[0039] FIG. 2A depicts a schematic block diagram of a control system 200a for controlling an air-conditioning and/or heating system in a region within a building according to various embodiments of the present invention, such as corresponding to the method 100a for controlling an air-conditioning and/or heating system in a region within a building as described hereinbefore according to various embodiments of the present invention.

[0040] The control system 200a comprises a memory 204, and at least one processor 206 communicatively coupled to the memory 204 and configured to: obtain an occupancy information for the region with respect to a current time; determine future occupancy information for the region with respect to a subsequent time based on the occupancy information; obtain future weather information for the region with respect to the subsequent time; and determine common thermal comfort preference information with respect to occupants in the region with respect to the subsequent time based on the future weather information and the future occupancy information.

[0041] It will be appreciated by a person skilled in the art that the at least one processor 206 may be configured to perform the required functions or operations through set(s) of instructions (e.g., software modules) executable by the at least one processor 206 to perform the required functions or operations. Accordingly, as shown in FIG. 2A, the system 200a may further comprise a data obtaining module (or circuit) 208 configured to obtain occupancy information for the region with respect to a current time and/or future weather information for the region with respect to a subsequent time; a prediction module (or circuit) 210 configured to determine future occupancy information for the region with respect to the subsequent time based on the occupancy information and/or predict future weather condition for the region with respect to the subsequent time; a thermal comfort determining module (or circuit) 212 configured to determine common thermal comfort preference information with respect to occupants in the region with respect to the subsequent time based on the future weather information and the future occupancy information.

[0042] FIG. 2B depicts a schematic block diagram of a control system 200b for controlling an air-conditioning and/or heating system in a region within a building according to various embodiments of the present invention, such as corresponding to the method 100b for controlling an air-conditioning and/or heating system in a region within a building as described hereinbefore according to various embodiments of the present invention.

[0043] The control system 200b comprises a memory 204, and at least one processor 206 communicatively coupled to the memory 204 and configured to: obtain occupancy information for the region at a current time; determine future occupancy information for the region with respect to a subsequent time based on the occupancy information; obtain future weather information for the region with respect to the subsequent time; determine common thermal comfort preference information with respect to occupants in the region with respect to the subsequent time based on the future weather information and the future occupancy information; determine a control parameter for controlling the air-conditioning and/or heating system with respect to the subsequent time based on the common thermal comfort preference information using a control parameter determining model; and update the control parameter for the air- conditioning and/or heating system at the subsequent time based on the control parameter determined.

[0044] The system 200b may further comprise a data obtaining module (or circuit) 208 configured to obtain occupancy information for the region at a current time and/or obtain future weather information for the region with respect to the subsequent time; a prediction module (or circuit) 210 configured to determine future occupancy information for the region with respect to a subsequent time based on the occupancy information and/or predict future weather condition for the region with respect to the subsequent time; a thermal comfort determining module (or circuit) 212 configured to determine common thermal comfort preference information with respect to occupants in the region with respect to the subsequent time based on the future weather information and the future occupancy information; and a control parameter determining module (or control optimizer) (or circuit) 214 configured to determine a control parameter for controlling the air-conditioning and/or heating system with respect to the subsequent time based on the common thermal comfort preference information using a control parameter determining model and/or update the control parameter for the air- conditioning and/or heating system at the subsequent time based on the control parameter determined.

[0045] It will be appreciated by a person skilled in the art that the above-mentioned modules (or circuits) are not necessarily separate modules, and two or more modules may be realized by or implemented as one functional module (e.g., a circuit or a software program) as desired or as appropriate without deviating from the scope of the present invention. For example, the data obtaining module 208, the prediction module 210, the thermal comfort determining module 212, and/or the control parameter determining module 214 may be realized (e.g., compiled together) as one executable software program (e.g., software application or simply referred to as an “app”), which for example may be stored in the memory 204 and executable by the at least one processor 206 to perform the functions/operations as described herein according to various embodiments.

[0046] In various embodiments, the system 200a corresponds to the method 100a as described hereinbefore with reference to FIG. 1A, and the system 200b corresponds to the method 100b as described hereinbefore with reference to FIG. IB, therefore, various functions/operations configured to be performed by the least one processor 206 may correspond to various steps or operations of the method 100a or method 100b described hereinbefore according to various embodiments, and thus need not be repeated with respect to the system 200a or system 200b for clarity and conciseness. In other words, various embodiments described herein in context of the methods are analogously valid for the respective systems (e.g., which may also be embodied as devices). [0047] For example, in various embodiments, the memory 204 may have stored therein the data obtaining module 208, the prediction module 210, the thermal comfort determining module 212, and/or the control parameter determining module 214, which respectively correspond to various steps or operations of the method 100a or method 100b as described hereinbefore, which are executable by the at least one processor 206 to perform the corresponding functions/operations as described herein.

[0048] A computing system, a controller, a microcontroller or any other system providing a processing capability may be provided according to various embodiments in the present disclosure. Such a system may be taken to include one or more processors and one or more computer-readable storage mediums. For example, the system 200a and the system 200b described hereinbefore may include a processor (or controller) 206 and a computer-readable storage medium (or memory) 204 which are for example used in various processing carried out therein as described herein. A memory or computer- readable storage medium used in various embodiments may be a volatile memory, for example a DRAM (Dynamic Random Access Memory) or a non-volatile memory, for example a PROM (Programmable Read Only Memory), an EPROM (Erasable PROM), EEPROM (Electrically Erasable PROM), or a flash memory, e.g., a floating gate memory, a charge trapping memory, an MRAM (Magnetoresistive Random Access Memory) or a PCRAM (Phase Change Random Access Memory).

[0049] In various embodiments, a “circuit” may be understood as any kind of a logic implementing entity, which may be special purpose circuitry or a processor executing software stored in a memory, firmware, or any combination thereof. Thus, in an embodiment, a “circuit” may be a hard-wired logic circuit or a programmable logic circuit such as a programmable processor, e.g., a microprocessor (e.g., a Complex Instruction Set Computer (CISC) processor or a Reduced Instruction Set Computer (RISC) processor). A “circuit” may also be a processor executing software, e.g., any kind of computer program, e.g., a computer program using a virtual machine code, e.g., Java. Any other kind of implementation of the respective functions which will be described in more detail below may also be understood as a “circuit” in accordance with various alternative embodiments. Similarly, a “module” may be a portion of a system according to various embodiments in the present invention and may encompass a “circuit” as above, or may be understood to be any kind of a logic -implementing entity therefrom. [0050] Some portions of the present disclosure are explicitly or implicitly presented in terms of algorithms and functional or symbolic representations of operations on data within a computer memory. These algorithmic descriptions and functional or symbolic representations are the means used by those skilled in the data processing arts to convey most effectively the substance of their work to others skilled in the art. An algorithm is here, and generally, conceived to be a self-consistent sequence of steps leading to a desired result. The steps are those requiring physical manipulations of physical quantities, such as electrical, magnetic or optical signals capable of being stored, transferred, combined, compared, and otherwise manipulated.

[0051] Unless specifically stated otherwise, and as apparent from the following, it will be appreciated that throughout the present specification, discussions utilizing terms such as “determining”, “obtaining”, “predicting”, “updating”, or the like, refer to the actions and processes of a computer system, or similar electronic device, that manipulates and transforms data represented as physical quantities within the computer system into other data similarly represented as physical quantities within the computer system or other information storage, transmission or display devices.

[0052] The present specification also discloses a system (which may also be embodied as a device or an apparatus) for performing the operations/functions of the methods described herein. Such a system may be specially constructed for the required purposes, or may comprise a general purpose computer or other device selectively activated or reconfigured by a computer program stored in the computer. The algorithms presented herein are not inherently related to any particular computer or other apparatus. Various general-purpose machines may be used with computer programs in accordance with the teachings herein. Alternatively, the construction of more specialized apparatus to perform the required method steps may be appropriate. [0053] In addition, the present specification also at least implicitly discloses a computer program or software/functional module, in that it would be apparent to the person skilled in the art that the individual steps or operations of the methods described herein may be put into effect by computer code. The computer program is not intended to be limited to any particular programming language and implementation thereof. It will be appreciated that a variety of programming languages and coding thereof may be used to implement the teachings of the disclosure contained herein. Moreover, the computer program is not intended to be limited to any particular control flow. There are many other variants of the computer program, which can use different control flows without departing from the spirit or scope of the invention. It will be appreciated by a person skilled in the art that various modules described herein (e.g., the data obtaining module 208, the prediction module 210, the thermal comfort determining module 212, and/or the control parameter determining module 214) may be software module(s) realized by computer program(s) or set(s) of instructions executable by a computer processor to perform the required functions, or may be hardware module(s) being functional hardware unit(s) designed to perform the required functions. It will also be appreciated that a combination of hardware and software modules may be implemented.

[0054] Furthermore, one or more of the steps or operations of a computer program/module or method described herein may be performed in parallel rather than sequentially. Such a computer program may be stored on any computer readable medium. The computer readable medium may include storage devices such as magnetic or optical disks, memory chips, or other storage devices suitable for interfacing with a general-purpose computer. The computer program when loaded and executed on such a general-purpose computer effectively results in an apparatus that implements the steps or operations of the methods described herein.

[0055] In various embodiments, there is provided a computer program product, embodied in one or more computer-readable storage mediums (non-transitory computer-readable storage medium), comprising instructions (e.g., the data obtaining module 208, the prediction module 210, the thermal comfort determining module 212, and/or the control parameter determining module 214) executable by one or more computer processors to perform a method 100a or method 100b of controlling an air- conditioning and/or heating system in a region within a building as described hereinbefore with reference to FIG. 1A or FIG. IB. Accordingly, various computer programs or modules described herein may be stored in a computer program product receivable by a system (e.g., a computer system or an electronic device) therein, such as the control system 200a as shown in FIG. 2B or the control system 200b as shown in FIG. 2B, for execution by at least one processor 206 of the system 200 to perform the required or desired functions.

[0056] The software or functional modules described herein may also be implemented as hardware modules. More particularly, in the hardware sense, a module is a functional hardware unit designed for use with other components or modules. For example, a module may be implemented using discrete electronic components, or it can form a portion of an entire electronic circuit such as an Application Specific Integrated Circuit (ASIC). Numerous other possibilities exist. Those skilled in the art will appreciate that the software or functional module(s) described herein can also be implemented as a combination of hardware and software modules.

[0057] In various embodiments, the above-mentioned computer system may be realized by any computer system (e.g., portable or desktop computer system), such as a computer system 300 as schematically shown in FIG. 3 as an example only and without limitation. Various methods/operations or functional modules (e.g., the data obtaining module 208, the prediction module 210, the thermal comfort determining module 212, and/or the control parameter determining module 214) may be implemented as software, such as a computer program being executed within the computer system 300, and instructing the computer system 300 (in particular, one or more processors therein) to conduct the methods/functions of various embodiments described herein. The computer system 300 may comprise a computer module 302, input modules, such as a keyboard 304 and a mouse 306, and a plurality of output devices such as a display 308, and a printer 310. The computer module 302 may be connected to a computer network 312 via a suitable transceiver device 314, to enable access to e.g. the Internet or other network systems such as Local Area Network (LAN) or Wide Area Network (WAN). The computer module 302 in the example may include a processor 318 for executing various instructions, a Random Access Memory (RAM) 320 and a Read Only Memory (ROM) 322. The computer module 302 may also include a number of Input/Output (I/O) interfaces, for example I/O interface 324 to the display 308, and I/O interface 326 to the keyboard 304. The components of the computer module 302 typically communicate via an interconnected bus 328 and in a manner known to the person skilled in the relevant art.

[0058] It will be appreciated by a person skilled in the art that the terminology used herein is for the purpose of describing various embodiments only and is not intended to be limiting of the present invention. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising", or the like such as “includes” and/or “including”, when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.

[0059] In order that the present invention may be readily understood and put into practical effect, various example embodiments of the present invention will be described hereinafter by way of examples only and not limitations. It will be appreciated by a person skilled in the art that the present invention may, however, be embodied in various different forms or configurations and should not be construed as limited to the example embodiments set forth hereinafter. Rather, these example embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the present invention to those skilled in the art.

[0060] FIG. 4 illustrates a schematic block diagram of an example system 400 of controlling an air-conditioning and/or heating system in a region within a building according to various embodiments of the present invention. The system 400 includes an air-conditioning and/or heating control system 410, one or more control regions or zones 420, a weather station 430, and a communication network 440. The communication network 440 may support various connectivity, such as Ethernet, Wi Fi, BLE (Bluetooth Low Energy), Zigbee, and various protocols, such as BACnet, HTTP, MQTT (Message Queueing Telemetry Transport), TCP/UDP, in various non limiting examples. It should be noted that a building may be divided into multiple control zones (multiple regions in the building), based on the space function and actual position of air-conditioning and/or heating devices, which provide conditioned air to the space. The weather station 430 may collect and provide weather data, such as outdoor air temperature, outdoor relative humidity, wind speed, etc.

[0061] In various example embodiments, each control zone 420 may comprise a plurality of air-conditioning and/or heating devices (herein referred to as an air- conditioning and/or heating system) 422, such as but not limited to, Air Handling Unit (AHU), Variable Air Volume (VAV) boxes, etc. The control parameter (e.g., one or more setting values or set points) of the air-conditioning and/or heating system 422 may be adjusted or updated by the control system 410. The set points may relate to, but are not limited to, supply air temperature, relative humidity, air ventilation or flow rate, carbon dioxide level, or combinations thereof. Each control zone 420 may further comprise a plurality of environmental sensors 424 for collecting and providing environmental information relating to environmental condition of the zone, such as zone air temperature, zone relative humidity, zone air velocity, zone carbon dioxide level, etc.

[0062] Each control zone 420 may further comprise a plurality of occupants, each associated with a personal device 426, such as smart phones, smart wearable devices, etc. Each personal device 426 associated to each occupant may collect and provide personal data (or occupant information) associated with the occupant. The occupant information with the occupant may include, but is not limited to, occupant’s profile (e.g., race, age, gender, height, weight), human vital sign information (e.g., skin temperature, heart rate), clothing, activity level (e.g., walking steps per minute). In various example embodiments, an occupant may use the personal device 426 to provide thermal comfort feedback, such as “too cold”, “too warm”, etc.

[0063] FIG. 5 shows a schematic block diagram illustrating exemplary components of the air-conditioning and/or heating control system 410. The control system 410 may include, but is not limited to, a thermal comfort learning program 511, an occupant presence pattern analysis program 512, a weather forecast program 513, a configuration program 514, a control action learning program 515, an air-conditioning control optimizer 516, and a database 520. The database 520 may further comprise an occupant profile table 521, an occupant presence log table 522, a thermal comfort log table 523, an occupant presence probability table 524, a thermal comfort preference table 525, a control action table 526.

[0064] FIG. 6 illustrates an exemplary flow diagram 600 of the operations of the thermal comfort learning program 511. At 610, the control system may collect and store the thermal comfort log 523 for each of the occupants. The thermal comfort log 523 may comprise weather information relating to weather condition associated with the occupant (e.g., from weather station 430), environmental information relating to environmental condition of the region or zone associated with the occupant (e.g., from environment sensors 424), and occupant information (occupant data) associated with the occupant (e.g., from personal devices 426). FIG. 7A illustrates an exemplary data structure 700 of the thermal comfort log 523 according to various example embodiments of the present invention. The thermal comfort log 523 may comprise weather information relating to weather condition (e.g., an outdoor air temperature 710, an outdoor relative humidity 715) associated with the occupant, environmental information relating to environmental condition of the region (e.g., a region or zone air temperature 722, a region or zone relative humidity 724, a region or zone carbon dioxide level 726, a region or zone air velocity 728) associated with the occupant, and occupant information associated with the occupant in the region or zone. The occupant information associated with each occupant may include occupant profile such as a race 732, an age 734, a gender 736 (e.g., M: male, F: female), a height 738, a weight 739, physiological information (or human vital sign information) including but not limited to a skin temperature 742, a heart rate 744, as well as information relating to a clothing worn by the occupant 752 (e.g., which may be normalized clothing insulation value based on ASHRAE standard), an activity level of the occupant 754 (e.g., Low, Medium, High, based on walking steps per minutes), a thermal comfort feedback from the occupant 756. In various example embodiments, the thermal comfort feedback may be normalized in scales to represent thermal sensation (e.g., -3: cold, -2: cool, -1: slightly cool, 0: neutral, 1: slight warm, 2: warm, 3: hot).

[0065] FIG. 7B shows an exemplary data structure 760 of an example occupant profile according to various example embodiments of the present invention. The data structure 760 may comprise occupant profile relating to each occupant including an occupant identifier (ID) 770 associated to and identifying the occupant (e.g., a unique ID assigned to a personal device or mobile application which is associated to each occupant), a race 732, an age 734, a gender 736, a height 738, a weight 739 of the occupant.

[0066] Referring back to FIG. 6, at 620, the control system may train a thermal comfort prediction model. The thermal comfort prediction model may be a machine learning model such as neural network.

[0067] FIG. 8 shows an exemplary thermal comfort prediction model 800 according to various example embodiments of the present invention. The thermal comfort prediction model may be a neural network, comprising an input layer, hidden layers, and an output layer. The input layer may comprise neurons, one for each input data, including weather information or data relating to weather condition 810, environmental information or data relating to environmental condition 820, and occupant information or data 830. In various example embodiments, the input data may be normalized as numeric value. The activation function for a hidden layer may be sigmoid function. The activation function for the output layer may be a linear function, so that the output of the neural network is a numeric value in a thermal sensation value range, such as in the range of -3 to 3 (e.g., [-3, 3]), in a non-limiting example. In various example embodiments, if the output value falls within a predefined or preconfigured thermal comfort value range (e.g., [-0.5, 0.5]), the control system may determine or predict that an occupant feels comfort.

[0068] Referring back to FIG. 6, at 630, using the trained thermal comfort prediction model, the control system may predict thermal comfort associated to each occupant, using occupant information (e.g., occupant’s profile, activity level, human vital sign information) associated to the occupant and under various conditions (e.g., weather condition associated to the occupant, environmental condition associated to the occupant). At 640, the control system may update each occupant’s thermal comfort preference information based on the predicted or determined thermal comfort using the thermal comfort prediction model. The steps 610 to 640 may be performed periodically, for example, for retraining.

[0069] FIG. 9 illustrates an exemplary data structure 900 of the individual thermal comfort preference information associated with each occupant according to various example embodiments of the present invention. The individual thermal comfort preference information associated with each occupant may be stored in the database 520. The data structure 900 may comprise individual thermal comfort preference information with respect to each occupant including an occupant ID 910, an outdoor air temperature range 920 associated with the occupant, an outdoor relative humidity range 930 associated with the occupant, an activity level 940 associated with the occupant, a clothing worn by the occupant 950, and a thermal comfort preference associated with the occupant such as a preferred zone air temperature range 960 (in which the occupant feels comfort). It should be understood that the individual thermal comfort preference information associated with the occupant may further comprise a preferred zone relative humidity, preferred zone carbon dioxide level, preferred zone air velocity, or combinations thereof.

[0070] FIG. 10 shows an exemplary process flow diagram 1000 illustrating of an occupant presence pattern analysis program according to various example embodiments of the present invention. At 1010, the control system may collect and store an occupant presence log associated with each occupant. For example, the occupant presence log may be obtained when receiving data from a personal device (or mobile application) associated with each occupant. The occupant presence log may be collected or acquired continuously.

[0071] FIG. 11 shows an exemplary data structure 1100 of occupant presence log associated with each occupant according to various example embodiments of the present invention. The data structure 900 may comprise occupant presence log information associated with respect to each occupant including an occupant ID 1110, an outdoor air temperature 1120, an outdoor relative humidity 1130, an activity level 1140 of the occupant, a day of the week 1150 (e.g., Monday to Friday) in which the occupant was present in the control zone, and a timestamp 1160 (on which the occupant data is received). FIG. 12 shows a schematic drawing 1200 of example occupant presence in a control zone (e.g., at a time Tl, a subsequent time T2 with respect to time Tl, and a further subsequent time T3 with respect to time Tl and T2). For example, an occupant C who is present at time Tl may continue to be present at time T2, but may be absent from the zone or region at time T3.

[0072] Referring back to FIG. 10, at 1020, the control system may analyze occupant presence pattern, for example, using a pattern recognition method such as statistical techniques, in a non-limiting example. For example, the control system may analyze occupant presence pattern using a probability classifier. At 1030, the control system may update information or data relating to occupant presence probability table 524. The steps 1010 to 1030 may be performed periodically, for example, for retraining and/or obtaining an updated occupant presence probability table.

[0073] FIG. 13 shows an exemplary data structure 1300 of an example occupant presence probability table according to various example embodiments of the present invention. The information or data relating to the occupant presence probability may be stored in the database 520. The data structure 1300 may comprise occupant presence probability information with respect to each occupant at a respective region or zone in the building including an occupant ID 1310, an outdoor air temperature range 1320, an outdoor relative humidity range 1330, an activity level 1340 of the occupant, a day of the week 1350 (e.g., Monday to Friday), a time period or interval 1360 (e.g., time period interval may be preconfigured in the configuration program 514 of the control system 410 based on the response time for the change of the air-conditioning set point or based on occupant’s activities in the control zone), and a probability to appear in the next time period 1370.

[0074] FIG. 14 shows an exemplary process flow diagram 1400 for an example configuration program according to various example embodiments of the present invention. For example, the configuration program may be configured by a system administrator via a user interface. In various example embodiments, each control zone may have different configurations. At 1410, a default thermal comfort preference range may be configured. The default thermal comfort preference range may be input via the user interface. For example, default thermal comfort preference range may be based on industry best practice (e.g., air temperature range of 23°C to 25°C [23°C, 25°C]). At 1420, a time period or interval (e.g., 15 minutes) may be configured. For example, the time period may be determined based on the response time for the change of the air- conditioning set point or based on occupant’s activities in the control zone. At 1430, the thermal comfort value range (e.g. [-0.5, 0.5], [-0.3, 0.3], [-0.7, 0.7]) may be configured (predefined or preconfigured thermal comfort value range). The predefined thermal comfort value range may be used by the thermal comfort learning program 511 to determine if an occupant feels comfort. The thermal comfort value range, for example, may be used as a predefined threshold by the thermal comfort prediction model to determine if an occupant feels comfort as described with respect to FIG. 8. For example, the thermal comfort value range preconfigured between -0.5 to 0.5 may be in between slightly cool and slightly warm, and close to neutral (in the case where the thermal comfort value is normalized in scales to represent thermal sensation which includes -3: cold, -2: cool, -1: slightly cool, 0: neutral, 1: slight warm, 2: warm, 3: hot). The larger the range, the more flexible in air-conditioning control, as occupants accept [slightly cool, slightly warm] as comfort. The thermal comfort value range may be preconfigured depending on geolocation, regulation, etc.

[0075] At 1440, air-conditioning control actions (control parameter) may be defined, and data related to the control actions may be stored in the database 520. In various example embodiment, a control action may be any combination of set point values for air temperature, relative humidity, carbon dioxide level, air ventilation rate, including actions to turn on/off the air-conditioning and/or heating devices. The set point values may be relative values or absolute values. In a non-limiting example, a control action may include increase air temperature by 0.5 °C, increase air ventilation rate by 5%, set carbon dioxide level to 800 ppm.

[0076] At 1450, a reward function may be defined in relation to an executed control action. A reward function may be a function of R(thermal comfort, energy consumption). The reward function R may be as follows: where given a preconfigured thermal comfort value range [VI, V2], and an occupant’s thermal comfort value TC calculated using the thermal comfort prediction model as aforementioned, where R _EC is a total energy consumption in a time period, n is a total number of occupants in a time period, and a and b are parameters to control the relative importance between thermal comfort and energy consumption. [0077] In various example embodiments, a value of the reward function may be higher when more occupants are feeling comfort, and the value may be lower when more energy is consumed.

[0078] FIG. 15 shows an exemplary process flow diagram 1500 illustrating optimization by the control optimizer 516 according to various example embodiments of the present invention.

[0079] At 1510, the control optimizer 516 may obtain data at a current time period, including weather information or data relating to weather condition (e.g., from the weather station 430), environmental information or data relating to environmental condition (e.g., from environment sensors 524) as well as occupant information or data (e.g., from personal devices 426). At 1520, the control optimizer 516 may obtain weather forecast for the subsequent time period. In various example embodiments, the control system may forecast the weather for the subsequent time period, for example, using a weather forecast program 513, such as a Numerical weather prediction (NWP) method. In other embodiments, the control system may acquire weather forecast from an external data source such as a third party weather information system. For example, the weather station 430 may be implemented by a third party weather information system which provides weather forecast service. The weather forecast program 513, for example, may obtain the weather forecast data from the third party weather information system. [0080] At 1530, the control optimizer 516 may determine occupant presence in the subsequent time period (future occupancy information), using the occupant presence pattern analysis program 512. It should be noted that occupant presence prediction results may be further fine-tuned based on other data (e.g., data relating to meeting schedule, business trip schedule, etc.). At 1540, the control optimizer 516 may determine the common thermal comfort preference information with respect to occupants in the control zone with respect to the subsequent time. [0081] In various example embodiments, the common thermal comfort preference with respect to occupants in the control zone with respect to the subsequent time may be determined based on the individual thermal comfort preference information of each of the occupants with respect to the subsequent time.

[0082] FIG. 16 illustrates a schematic drawing 1600 illustrating a common thermal comfort preference with respect to occupants in a region, according to various example embodiments of the present invention. FIG. 16 also illustrates an example technique for determining the occupants’ common thermal comfort preference information according to various example embodiments of the present invention. In various example embodiments, the occupants’ common thermal comfort preference information may comprise a common preference range such as a common preference of air temperature range for all the occupants in the control zone. The common preference of air temperature range for all the occupants in the control zone with respect to the subsequent time may be determined based on the individual preference of air temperature range for each occupant predicted to be present with respect to the subsequent time. It is noted that, in summer, the minimum value of the common preference range may not go below the minimum value of the preconfigured default thermal comfort preference range, while in winter, the maximum value of the common preference range may not go beyond the maximum value of the preconfigured default thermal comfort preference range.

[0083] Referring back to FIG. 15, at 1550, the control optimizer 516 may determine a control action that maximizes the reward function as discussed above. At 1560, the control optimizer 516 predicts each occupant’s thermal comfort (TC_p). For example, the thermal comfort may be predicted for each occupant after the control action is implemented. At 1570, the control optimizer 516 may calculate each occupant’s actual thermal comfort (TC_a) when entering the next time period. For example, step 1560 and 1570 may be used as a benchmark to determine whether retraining is required. For example, retraining may be required due to various factors such as, including but not limited to, seasonal change, occupant changes (e.g., employee leave, new employee join, etc.). At 1580, the control optimizer 516 may determine whether the mean variance between the predicted occupant’s thermal comfort and actual occupant’s thermal comfort is larger than a predefined threshold. If no, the control optimizer 516 may repeat the process from step 1510. If yes, at 1590, the control optimizer 516 may activate the control action learning program 515. In various example embodiments, activating the control action learning program may include triggering the operations as described with respect to FIG.6 and FIG.10 for retraining.

[0084] FIG. 17 illustrates a schematic diagram 1700 of the control action learning program according to various example embodiments of the present invention. In various example embodiments, the control action learning program may be a reinforcement learning process. For each zone state 1710 at a time period Tl, the control optimizer 516 may select an air-conditioning control action 1731, to change the air-conditioning set points in a control zone. At the next time period, the control optimizer 516 may then compute the thermal comfort of each occupant and energy consumption 1720. Using the reward function, the control optimizer 516 may compute the reward 1732. The control optimizer 516 may continually learn from this process and updates its decision to select a control action for a given zone state, so that a maximum reward value may be achieved.

[0085] While embodiments of the invention have been particularly shown and described with reference to specific embodiments, it should be understood by those skilled in the art that various changes in form and detail may be made therein without departing from the scope of the invention as defined by the appended claims. The scope of the invention is thus indicated by the appended claims and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced.