METHODS AND SYSTEMS FOR ZONE LEVEL OCCUPANCY PREDICTION AND ENERGY OPTIMIZATION

Description

TECHNOLOGICAL FIELD

The present invention relates to building management systems (BMS), and more particularly relates to a method and system for predicting zone level occupancy for energy optimization.

BACKGROUND

HVAC (heating, ventilation, and air conditioning) system refers to the technology used to provide indoor comfort and maintain air quality in buildings, vehicles, and other enclosed spaces. The HVAC system provides heating by various means, such as furnaces, boilers, heat pumps, and electric heaters. The HVAC system generates heat to warm the indoor environment during colder weather conditions. Typically, the HVAC system facilitates to exchange indoor air with outdoor air to improve air quality and remove contaminants such as odors, moisture, and pollutants. The HVAC system include fans, ductwork, and filters to distribute fresh air and remove stale air from buildings. Moreover, the HVAC system also involves cooling and dehumidifying indoor air to maintain comfortable temperatures during hot weather. The HVAC system uses air conditioners, chillers, evaporative coolers, and heat pumps to remove heat from indoor air and circulate cool air throughout the space.

Efficiency of individual HVAC components, such as furnaces, boilers, air conditioners, heat pumps, and ventilation fans, plays a significant role in overall system efficiency. However, to maintain a comfortable temperature inside the enclosed space, it becomes essential to keep the HVAC system activated by a building's manager such that when the enclosed space is occupied, the enclosed space is already has a comfortable temperature for the occupants to live. However, by keeping the HVAC system activated, the energy consumption of the building increases drastically. Managing a building's HVAC system means finding a balance between keeping people comfortable and not spending too much money on heating or cooling. However, in big buildings, it is difficult to estimate when each zone of the building will be occupied. Therefore, HVAC managers usually pick a time in the morning to start heating or cooling and then keep it going all day, even when some zones are not being utilized. The big buildings use a lot of energy for heating and cooling, that costs a lot of money, due to which HVAC managers want to wait as long as possible before starting heating or cooling the zone to avoid wasting energy on empty zones. Adding to the limitation, HVAC managers can only choose one time for the whole building to start heating or cooling, even though not every zone becomes occupied at the same time as a result, some zones end up using energy to stay comfortable even when nobody is there.

The inventors have identified numerous areas of improvement in the existing technologies and processes, which are the subjects of embodiments described herein. Through applied effort, ingenuity, and innovation, many of these deficiencies, challenges, and problems have been solved by developing solutions that are included in embodiments of the present disclosure, some examples of which are described in detail herein.

BRIEF SUMMARY

The following presents a simplified summary in order to provide a basic understanding of some aspects of the present disclosure. This summary is not an extensive overview and is intended to neither identify key or critical elements nor delineate the scope of such elements. Its purpose is to present some concepts of the described features in a simplified form as a prelude to the more detailed description that is presented later.

In one example embodiment, a method is disclosed. The method comprises receiving, via at least one processor, an occupancy data of one or more zones via a plurality of sensors for a first period of time. The occupancy data comprises at least a number of occupants within each zone for the first period of time. The method comprises determining, via the at least one processor, one or more occupancy trends for each zone for the first period of time using a trained machine learning (ML) model. The occupancy trends comprises occupancy of the one more zones and a number of occupants within each of the one or more zones within the first time period. The method further comprises mapping, via the at least one processor, the determined one or more occupancy trends for each of the one or more zones for the first period of time with fluctuations in occupancy of each of the one or more zones in real-time and booking status of each of the one or more zones. Further, the method comprises predicting, via the at least one processor, occupancy of each of the one or more zones for a second period of time and a threshold time required for each of the one or more zones to heat or cool at one or more temperature set points using the trained ML model based at least on the mapping. Thereafter, the method comprises adjusting, via the at least one processor, the one or more temperature set points for each of the one or more zones at the threshold time based at least on the prediction.

In some embodiments, the ML model for each of the one or more zones is trained based at least on the received occupancy data. In some embodiments, the at least one processor is configured to train the ML model using one or more Artificial Intelligence (AI)/Machine Learning (ML) techniques.

In some embodiments, the booking status of the one or more zones corresponds to the one or more zones pre-booked to be occupied by one or more users.

In some embodiments, the plurality of sensors corresponds to a plurality of zone level occupancy sensors comprising at least one lightning sensors, Wi-Fi Access Points and Bluetooth low energy (BLE) sensors, access readers, or carbon dioxide (CO₂) sensors. In some embodiments, the one or more zones comprises at least one of a building, a warehouse, a storage unit, or an office space. In some embodiments, opening within each zone corresponds to a number of windows and doors present in each zone.

In some embodiments, the first period of time corresponds to historical time zone and the second period of time corresponds to future time period. Further, the time period comprises at least day, time, season, months, years.

In some embodiments, the one or more temperature set points comprises at least one heating set point that initializes a heating cycle to increase temperature of the one or more zones, and at least one cooling set point that initializes a cooling cycle to decrease temperature of the one or more zones. Further, the heating cycle or the cooling cycle is initialized based at least on the threshold time required for each of the one or more zones to heat or cool at the one or more temperature set points.

In some embodiments, the heating cycle and the cooling cycle are identified based at least on the change in the one or more temperature set points. In some embodiments, the heating cycle and the cooling cycle end when the temperature of the one or more zones reaches the one or more temperature set points.

In another example embodiment, a system is disclosed. The system comprises a memory and at least one processor communicatively coupled to the memory. The at least one processor is configured to receive an occupancy data of one or more zones via a plurality of sensors for a first period of time. The occupancy data comprises at least a number of occupants within each zone for the first period of time. The at least one processor is configured to determine one or more occupancy trends for each zone for the first period of time using a trained machine learning (ML) model. The occupancy trends comprises occupancy of the one more zones and a number of occupants within each of the one or more zones within the first time period. The at least one processor is further configured to map the determined one or more occupancy trends for each of the one or more zones for the first period of time with fluctuations in occupancy of each of the one or more zones in real-time and booking status of each of the one or more zones. Further, the at least one processor is configured to predict occupancy of each of the one or more zones for a second period of time and a threshold time required for each of the one or more zones to heat or cool at one or more temperature set points using the trained ML model based at least on the mapping. Thereafter, the at least one processor is configured to adjust the one or more temperature set points for each of the one or more zones at the threshold time based at least on the prediction.

In some embodiments, the at least one processor is further configured to train the ML model for each of the one or more zones based at least one the received occupancy data using one or more Artificial Intelligence (AI)/Machine Learning (ML) techniques. In some embodiments, the booking status of the one or more zones corresponds to the one or more zones pre-booked to be occupied by one or more users. In some embodiments, the plurality of sensors corresponds to a plurality of zone level occupancy sensors comprising at least one lightning sensors, Wi-Fi Access Points and Bluetooth low energy (BLE) sensors, access readers, or carbon dioxide (CO₂) sensors. In some embodiments, the one or more zones comprises at least one of a building, a warehouse, a storage unit, or an office space. In some embodiments, opening within each zone corresponds to a number of windows and doors present in each zone.

In some embodiments, the first period of time corresponds to historical time zone and the second period of time corresponds to future time period. Further, the time period comprises at least day, time, season, months, years. In some embodiments, the one or more temperature set points comprises at least one heating set point that initializes a heating cycle to increase temperature of the one or more zones, and at least one cooling set point that initializes a cooling cycle to decrease temperature of the one or more zones. Further, the heating cycle or the cooling cycle is initialized based at least on the threshold time required for each of the one or more zones to heat or cool at the one or more temperature set points.

In some embodiments, the heating cycle and the cooling cycle are identified based at least on the change in the one or more temperature set points. In some embodiments, the heating cycle and the cooling cycle end when the temperature of the one or more zones reaches the one or more temperature set points.

In another example embodiment, a non-transitory machine-readable information storage medium is disclosed. The non-transitory machine-readable information storage medium comprising one or more instructions which when executed by at least one processor to perform operations comprising receiving an occupancy data of one or more zones via a plurality of sensors for a first period of time, wherein the occupancy data comprises at least a number of occupants within each zone for the first period of time; determining one or more occupancy trends for each zone for the first period of time using a trained machine learning (ML) model, wherein the occupancy trends comprises occupancy of the one more zones and a number of occupants within each of the one or more zones within the first time period; mapping the determined one or more occupancy trends for each of the one or more zones for the first period of time with fluctuations in occupancy of each of the one or more zones in real-time and booking status of each of the one or more zones; predicting occupancy of each of the one or more zones for a second period of time and a threshold time required for each of the one or more zones to heat or cool at one or more temperature set points using the trained ML model based at least on the mapping; and adjusting the one or more temperature set points for each of the one or more zones at the threshold time based at least on the prediction.

In some embodiments, the booking status of the one or more zones corresponds to the one or more zones pre-booked to be occupied by one or more users. In some embodiments, the first period of time corresponds to historical time zone and the second period of time corresponds to future time period, wherein the time period comprises at least day, time, season, months, or years.

The above summary is provided merely for purposes of summarizing some example embodiments to provide a basic understanding of some aspects of the invention. Accordingly, it will be appreciated that the above-described embodiments are merely examples and should not be construed to narrow the scope or spirit of the invention in any way. It will be appreciated that the scope of the invention encompasses many potential embodiments in addition to those here summarized, some of which will be further described below.

BRIEF DESCRIPTION OF THE DRAWINGS

Having thus described certain example embodiments of the present disclosure in general terms, reference will hereinafter be made to the accompanying drawings, which are not necessarily drawn to scale, and wherein:

FIG. 1 illustrates a network diagram of a system in accordance with an example embodiment of the present disclosure;

FIG. 2 illustrates a block diagram of a server in accordance with an example embodiment of the present disclosure;

FIGS. 3-4 illustrate an architecture of the system for zone level optimization in accordance with an example embodiment of the present disclosure;

FIGS. 5-6 illustrate an occupancy flow and zone level optimization of the system in accordance with an example embodiment of the present disclosure;

FIG. 7 illustrates a flowchart showing an operation of a machine learning (ML) model for predicting occupancy by using at least one processor in accordance with an example embodiment of the present disclosure;

FIG. 8 illustrates a flowchart showing a method for predicting occupancy in accordance with an example embodiment of the present disclosure; and

FIGS. 9A and 9B illustrate a graphical representation of weekly and daily seasonality respectively of the trained ML model in accordance with an example embodiment of the present disclosure.

DETAILED DESCRIPTION

Some embodiments will now be described more fully hereinafter with reference to the accompanying drawings, in which some, but not all, embodiments are shown. Indeed, various embodiments may be embodied in many different forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will satisfy applicable legal requirements. As discussed herein, the protection devices may be referred to use by humans, but may also be used to raise and lower objects unless otherwise noted.

The components illustrated in the figures represent components that may or may not be present in various embodiments of the invention described herein such that embodiments may include fewer or more components than those shown in the figures while not departing from the scope of the invention. Some components may be omitted from one or more figures or shown in dashed line for visibility of the underlying components.

The present disclosure provides various embodiments of methods and systems to predict occupancy. Embodiments may be configured to be executed by at least one processor for predicting the occupancy of the one or more zones. Embodiments may be configured to predict the occupancy of the one or more zones, the one or more zones comprises at least one of a building, a warehouse, a storage unit, or an office space, wherein opening within each zone corresponds to number of windows and doors present in each zone. Embodiments may be configured to receive an occupancy data of one or more zones via a plurality of sensors for a first period of time. Embodiments may be configured to receive the occupancy data that comprises at least a number of occupants within each zone for the first period of time.

Embodiments may be configured to receive the occupancy data of the one or more zones via the plurality of sensors that corresponds to a plurality of zone level occupancy sensors comprising at least one lightning sensors, Wi-Fi Access Points and Bluetooth low energy (BLE) sensors, access readers, and/or CO₂ sensor. Embodiments may be configured to generate at least one machine learning (ML) model for each of the one or more zones for the first period of time by using the at least one processor. Embodiments may be configured to train via the at least one processor, the ML model for each of the one or more zones based at least on the received occupancy data. Embodiments may be configured to determine one or more occupancy trends for each zone for the first period of time using a trained machine learning (ML) model.

Embodiments may be configured to determine the one or more occupancy trends that comprises occupancy of the one more zones and number of occupants within each of the one or more zones within the first time period. Embodiments may be configured to map the determined occupancy trends for each of the one or more zones for the first period of time with fluctuations in occupancy of each of the one or more zones in real-time and booking status of each of the one or more zones. Embodiments may be configured to map the map the booking status of the one or more zones that corresponds to the one or more zones pre-booked to be occupied by one or more users. Embodiments may be configured to predict occupancy of each of the one or more zones for a second time period and a threshold time required for each of the one or more zones to heat or cool at one or more temperature set points using the trained ML model based at least on the mapping. Embodiments may be configured to adjust one or more temperature set points for each of the one or more zones at the threshold time based at least on the prediction.

FIG. 1 illustrates a network diagram of a system 100, in accordance with an example embodiment of the present disclosure. The system 100 may comprise a network 102 communicatively coupled to a heating, ventilation, and air conditioning (HVAC) unit (not shown) installed within a building 104, a plurality of sensors 106, a server 108, and a user device 110.

In some embodiments, the network 102 may be a communication network such as internet or a cloud network, that may be configured to allow computing devices and processing systems to communicate with each other through wired network, wireless network, or a combination of both. In some embodiments, the network 102 may refer to as a distributed infrastructure that is configured to exchange of data, information, and resources among interconnected computing devices and systems. The network 102 may be designed to facilitate communication and collaboration across various locations, devices, and platforms. Those skilled in the art will recognize that wired devices may include, but are not limited to, wired networks such as Wide Area Networks (WANs) or Local Area Networks (LANs), while wireless devices may include wireless communications established via Radio Frequency (RF) signals or infrared signals. Various devices in the system 100 may connect to the network 102 in accordance with various wired and wireless communication protocols such as Transmission Control Protocol and Internet Protocol (TCP/IP), User Datagram Protocol (UDP), and 2G, 3G, or 4G communication protocols.

Further, the HVAC unit may be installed within the building 104 for regulating and maintaining internal temperatures. In some embodiments, the HVAC unit may be configured to provide heating by various means, such as furnaces, boilers, heat pumps, and electric heaters. The HVAC unit may be configured to generate heat to warm the indoor environment during colder weather conditions. Further, the HVAC unit may be configured to facilitate to exchange indoor air with outdoor air to improve air quality and remove contaminants such as odors, moisture, and pollutants. In some embodiments, the HVAC unit may include one or more fans (not shown), a ductwork (not shown), and one or more filters (not shown) to distribute fresh air and remove stale air from the building 104. In some embodiments, the HVAC may also be configured to cool and dehumidify indoor air to maintain comfortable temperatures during hot weather. The HVAC unit may be configured to use air conditioners, chillers, evaporative coolers, and heat pumps to remove heat from indoor air and circulate cool air throughout the space.

In some embodiments, the plurality of sensors 106 may be communicatively coupled to the HVAC unit via the network 102. The plurality of sensors 106 may be configured to determine occupancy data of one or more zones within the building 104 and may also be configured to determine one or more temperature set points for each of the one or more zones within the building 104. In some embodiments, the plurality of sensors may further be configured to be communicatively coupled to the server 108 for communicating the determined occupancy data of one or more zones within the building 104 one or more temperature set points for each of the one or more zones to the server 108 for further computing. In some embodiments, the plurality of sensors 106 may include plurality of zone level occupancy sensors comprising at least one lightning sensors, Wi-Fi Access Points and Bluetooth low energy (BLE) sensors, access readers, and/or CO₂ sensor. The zone level occupancy sensors comprising the at least one lightning sensors, the Wi-Fi Access Points and Bluetooth low energy (BLE) sensors, the access readers, and/or the CO₂ sensor may be configured to collectively detect the presence of occupants and measure environmental parameters within the one or more zones of the building 104.

In some embodiments, the lightning sensors may include motion sensors, occupancy sensors, infrared sensors, ultrasonic sensors, and video camera sensors. The motion sensors are configured to detect movement within a threshold detection range. Further, the occupancy sensors are configured to detect the presence or absence of people within a defined area of the one or more zones. Further, the infrared sensors may be configured to detect the presence of human by detecting changes in infrared radiation, such as body heat emitted by humans. Further, the ultrasonic sensors may be configured to emit ultrasonic waves and detect changes in the reflected waves caused by moving objects, including people within the one or more zones. Further, the video camera sensors may be configured to be equipped with image processing algorithms that may be configured to detect the presence of people by analyzing video footage and detecting human shapes or movements.

In some embodiments, the server 108 may be a computer or software module that is configured to provide centralized resources, data, or services to the user device 110 operated by a user. The server 108 may be configured to handle and manage one or more computational tasks and data processing within the system 100. In some embodiments, the server 108 may include storage systems, such as hard drives or storage arrays, to store and manage large volumes of data and information accessible to network users. In some embodiments, the server 108 may further provide centralized control and management capabilities, allowing network administrators to configure, monitor, and maintain network resources, security settings, and user access permissions from a single location.

In some embodiments, the server 108 may be configured to receive the occupancy data of one or more zones via the plurality of sensors 106 for a first period of time. In some embodiments, the first period of time may correspond to historical time zone. The time period may comprise at least day, time, season, months, years. Further, the server 108 may be configured to determine one or more occupancy trends for each zone for the first period of time using a trained machine learning (ML) model. The server 108 may be configured to generate at least one machine learning (ML) model for each of the one or more zones for the first period of time. Further, the server 108 may be configured to train the ML model for each of the one or more zones based at least one the received occupancy data.

In some embodiments, the server 108 may be configured to generate and train the at least one model using one or more Artificial Intelligence (AI)/Machine Learning (ML) techniques. For instance, the server 108 may employ supervised learning algorithms such as linear regression or decision trees to predict occupancy levels based on historical occupancy data collected from the plurality of sensors 106 within each zone. Additionally, unsupervised learning techniques like clustering may be utilized to identify patterns and anomalies in occupancy behavior. Through iterative training and refinement processes, the server 108 may enhance the accuracy and effectiveness of the ML models, to enable the system to make more informed decisions regarding resource allocation and building management strategies tailored to each zone's specific occupancy patterns.

In some embodiments, the server 108 may be configured to map the determined occupancy trends for each of the one or more zones for the first period of time with fluctuations in occupancy of each of the one or more zones in real-time and booking status of each of the one or more zones. In some embodiments, the booking status of the one or more zones corresponds to the one or more zones pre-booked to be occupied by one or more users. Further, the server 108 may be configured to predict occupancy of each of the one or more zones for a second time period. In some embodiments, the second period of time may correspond to future time period. Further, the server 108 may be configured to predict a threshold time required for each of the one or more zones to heat or cool at one or more temperature set points using the trained ML model based at least on the mapping. The server 108 may be configured to adjust one or more temperature set points for each of the one or more zones at the threshold time based at least on the prediction.

In some embodiments, the one or more temperature set points may comprise at least one heating set point that initializes a heating cycle to increase the temperature of the one or more zones. Further, the one or more temperature set points may comprise at least one cooling set point that initializes a cooling cycle to decrease the temperature of the one or more zones. The heating cycle or the cooling cycle may be initialized based at least on the threshold time required for each of the one or more zones to heat or cool at one or more temperature set points. In some embodiments, the heating cycle and the cooling cycle may be identified by change in the one or more temperature set points. Further, the heating cycle and the cooling cycle may end when the temperature of the one or more zones reaches the one or more temperature set points.

In some embodiments, the server 108 may further be configured to send determined occupancy data and determined temperature set points to the user device 110. The user device 110 may be equipped by an operator, manager of the building or other service professionals responsible for monitoring and operating the HVAC unit. In some embodiments, the occupancy data and the determined temperature set points may provide data regarding the expected occupancy in each of the one or more zones and based on which the temperature set points can be validated to improve efficiency of the HVAC unit installed within the building 104. In some embodiments, the user device 110 may include personal computers such as desktop computers, laptop computers, tablets, smartphones, or mobile devices.

It will be apparent to one skilled in the art that above-mentioned components of the system 100 have been provided only for illustration purposes, without departing from the scope of the disclosure.

FIG. 2 illustrates a block diagram of the server 108, in accordance with an example embodiment of the present disclosure. The server 108 may comprise at least one processor 202, a memory 204, an input/output circuitry 206, and a communication circuitry 208.

In some embodiments, the plurality of sensors 106 may be configured to detect occupancy data of one or more zones. The plurality of sensors 106 may correspond to a plurality of zone level occupancy sensors. Further, the plurality of zone level occupancy sensors may comprise at least one lightning sensors, Wi-Fi Access Points and Bluetooth low energy (BLE) sensors, access readers, and/or CO₂ sensor. In some embodiments, the one or more zones may comprise at least one of a building, a warehouse, a storage unit, or an office space. Further, opening within each zone of the one or more zones may correspond to number of windows and doors present in each zone.

As discussed earlier, the lightning sensors may include motion sensors, occupancy sensors, infrared sensors, ultrasonic sensors, and video camera sensors. The motion sensors may be configured to detect movement within a threshold detection range. Further, the occupancy sensors are configured to detect the presence or absence of people within a defined area of the one or more zones. Further, the infrared sensors may be configured to detect the presence of human by detecting changes in infrared radiation, such as body heat emitted by humans. Further, the ultrasonic sensors may be configured to emit ultrasonic waves and detect changes in the reflected waves caused by moving objects, including people within the one or more zones. Further, the video camera sensors may be configured to be equipped with image processing algorithms that may be configured to detect the presence of people by analyzing video footage and detecting human shapes or movements.

In some embodiments, the at least one processor 202 may be operationally coupled to the plurality of sensors 106. The at least one processor 202 may be configured to receive the occupancy data of one or more zones via the plurality of sensors 106 for a first period of time. In some embodiments, the first period of time may correspond to historical time zone. The time period may comprise at least day, time, season, months, years. The one or more processors 202 may be configured to determine one or more occupancy trends for each zone for the first period of time using a trained machine learning (ML) model. The at least one processor 202 may be configured to generate at least one machine learning (ML) model for each of the one or more zones for the first period of time. Further, the at least one processor 202 may be configured to train the ML model for each of the one or more zones based at least one the received occupancy data.

In some embodiments, the at least one processor 202 may be configured to generate and train the at least one model using one or more Artificial Intelligence (AI)/Machine Learning (ML) techniques. For instance, the at least one processor 202 may employ supervised learning algorithms such as linear regression or decision trees to predict occupancy levels based on historical occupancy data collected from the plurality of sensors 106 within each zone. Additionally, unsupervised learning techniques like clustering may be utilized to identify patterns and anomalies in occupancy behavior. Through iterative training and refinement processes, the at least one processor 202 may enhance the accuracy and effectiveness of the ML models, to enable the server 108 to make more informed decisions regarding resource allocation and building management strategies tailored to each zone's specific occupancy patterns.

The at least one processor 202 may be configured to map the determined occupancy trends for each of the one or more zones for the first period of time with fluctuations in occupancy of each of the one or more zones in real-time and booking status of each of the one or more zones. In some embodiments, the booking status of the one or more zones corresponds to the one or more zones pre-booked to be occupied by one or more users. The at least one processor 202 may be configured to predict occupancy of each of the one or more zones for a second time period. In some embodiments, the second period of time may correspond to future time period. Further, the at least one processor 202 may be configured to predict a threshold time required for each of the one or more zones to heat or cool at one or more temperature set points using the trained ML model based at least on the mapping. The at least one processor 202 may be configured to adjust one or more temperature set points for each of the one or more zones at the threshold time based at least on the prediction.

In some embodiments, the one or more temperature set points may comprise at least one heating set point that initializes a heating cycle to increase the temperature of the one or more zones. Further, the one or more temperature set points may comprise at least one cooling set point that initializes a cooling cycle to decrease the temperature of the one or more zones. The heating cycle or the cooling cycle may be initialized based at least on the threshold time required for each of the one or more zones to heat or cool at one or more temperature set points. In some embodiments, the heating cycle and the cooling cycle may be identified by change in the one or more temperature set points. Further, the heating cycle and the cooling cycle may end when the temperature of the one or more zones reaches the one or more temperature set points.

The at least one processor 202 may include suitable logic, circuitry, and/or interfaces that are operable to execute one or more instructions stored in the memory 204 to perform predetermined operations. In one embodiment, the at least one processor 202 may be configured to decode and execute any instructions received from one or more other electronic devices or server(s). The at least one processor 202 may be configured to execute one or more computer-readable program instructions, such as program instructions to carry out any of the functions described in this description. Further, the processor may be implemented using one or more processor technologies known in the art. Examples of the at least one processor 116 include, but are not limited to, one or more general purpose processors (e.g., INTEL® or Advanced Micro Devices® (AMD) microprocessors) and/or one or more special purpose processors (e.g., digital signal processors or Xilinx® System On Chip (SOC) Field Programmable Gate Array (FPGA) processor).

In some embodiments, the memory 204 may be configured to store a set of instructions and data executed by the at least one processor 202. Further, the memory 204 may include the one or more instructions that are executable by the at least one processor 202 to perform specific operations. The memory 204 may be configured to include the instructions to receive an occupancy data of one or more zones via the plurality of sensors 106 for a first period of time. The memory 204 may be configured to include the instructions to determine one or more occupancy trends for each zone for the first period of time using the trained machine learning (ML) model. Further, the memory 204 may be configured to include the instructions to map the determined occupancy trends for each of the one or more zones for the first period of time with fluctuations in occupancy of each of the one or more zones in real-time and booking status of each of the one or more zones.

The memory 204 may be configured to include the instructions to predict occupancy of each of the one or more zones of the building 104 for a second time period and a threshold time required for each of the one or more zones to heat or cool at one or more temperature set points using the trained ML model based at least on the mapping. The memory 204 may be configured to include the instructions to adjust one or more temperature set points for each of the one or more zones at the threshold time based at least on the prediction. It is apparent to a person with ordinary skill in the art that the one or more instructions stored in the memory 204 enable the hardware of the server 108 to perform the predetermined operations. Some of the commonly known memory implementations include, but are not limited to, fixed (hard) drives, magnetic tape, floppy diskettes, optical disks, Compact Disc Read-Only Memories (CD-ROMs), and magneto-optical disks, semiconductor memories, such as ROMs, Random Access Memories (RAMs), Programmable Read-Only Memories (PROMs), Erasable PROMs (EPROMs), Electrically Erasable PROMs (EEPROMs), flash memory, magnetic or optical cards, or other type of media/machine-readable medium suitable for storing electronic instructions.

In some embodiments, the server 108 may further comprise the input/output circuitry 206. The input/output circuitry 206 may enable a user to communicate or interface with the server 108, via the user device 110. The user device 110 may include N number of user devices. In some embodiments, the input/output circuitry 206 may act as a medium to transmit input from the interface to and from the server 108. In some embodiments, the input/output circuitry 206 may refer to the hardware and software components that facilitate the exchange of information between user device 110 and the server 108. In one example, the user device 110 may include a graphical user interface (GUI) (not shown) as input circuitry to allow the one or more users to input data. The input/output circuitry 206 may include various input devices such as keyboards, barcode scanners, GUI for the one or more users to provide data and various output devices such as displays, printers for the one or more users to receive data. In another example, the input/output circuitry 206 may include various output circuitry such as a display to show the adjusted one or more temperature set points.

In some embodiments, the server 108 may further comprise the communication circuitry 208. The communication circuitry 208 may allow the server 108 to exchange data or information with other systems or apparatuses. Further, the communication circuitry 208 may include network interfaces, protocols, and software modules responsible for sending and receiving data or information. In some embodiments, the communication circuitry 208 may include Ethernet ports, Wi-Fi adapters, or communication protocols like HTTP or MQTT for connecting with other systems. The communication circuitry 208 may further include components such as communication modules (e.g., Wi-Fi, Ethernet, cellular), transceivers, antennas, and protocols (e.g., TCP/IP, MQTT, SNMP) for exchanging data with other systems or network devices. The communication circuitry 208 may allow the server 108 to stay up-to-date and accurately track the at least one normalized alerts.

In some embodiments, the input/output circuitry 206 and the communication circuitry 208 may be configured to integrate the at least one normalized alarm data with other systems such as Supervisory Control and Data Acquisition (SCADA), Building Management Systems (BMS), Enterprise Asset Management (EAM) systems, or third-party monitoring platforms for centralized monitoring, analysis, and control by operators and automated processes. It will be apparent to one skilled in the art the above-mentioned components of the server 108 have been provided only for illustration purposes, without departing from the scope of the disclosure.

FIGS. 3-4 illustrate an architecture of the system 100 for zone level optimization, in accordance with an example embodiment of the present disclosure. FIGS. 3-4 are described in conjunction with FIGS. 1-2. In some embodiments, the architecture of the system 100 may include one or more zones 300, a plurality of sensors comprising an occupancy sensor 302, and a temperature/humidity sensor 304. Further, the architecture of the system 100 may include a HVAC unit 306, a HVAC controller 308, and the user device 110.

In some embodiments, the occupancy sensor 302 and the temperature/humidity sensor 304 may collect real-time data within the one or more zones 300. In some embodiments, the occupancy sensor 302 may be configured to detect the presence or absence of people within a defined area of the one or more zones 300. Further, the temperature/humidity sensor 304 may be configured to determine environmental conditions and additionally also be configured to assist in detecting the occupancy within the one or more zones 300. In some embodiments, when people occupy a space, their body heat can cause slight increases in temperature within the room. The temperature/humidity sensor 304 may be configured to detect these changes, especially if they are distributed strategically throughout the space to capture variations in temperature. Rapid changes in temperature could indicate the presence of occupants, especially in areas where temperature fluctuations are not expected due to external factors.

In some embodiments, as discussed earlier, the at processor 202 may be configured to determine one or more occupancy trends for one or more zones 300 for the first period of time using a trained machine learning (ML) model. In an example embodiment, the one or more zones 300 herein is a conference hall as shown in the FIG. 3. The at least one processors may be configured to configured to determine one or more occupancy trends for a time period of one month e.g. 1 Jan. 2024 to 31 Jan. 2024. Further, the at least one processor 202 may be configured to map the determined occupancy trends for the one or more zones 300 for the first period of time with fluctuations in occupancy of each of the one or more zones in real-time and booking status of each of the one or more zones 300.

In some embodiments, the at least one processor 202 may be configured to predict occupancy of each of the one or more zones 300 for a second time period and a threshold time required for each of the one or more zones 300 to heat or cool at one or more temperature set points using the trained ML model based at least on the mapping. In an example embodiment, at least one processor 202 based at least one the prediction occupancy of the one or more zones 300 i.e. the occupancy of the conference room for 1 Feb. 2024. The at least one processor 202 by using the trained ML model may determine that on 1 Feb. 2024, the conference room will be occupied by 23 people between a duration of 10 AM to 11 AM. In some embodiments, the at least one processor 202 may further be configured to heat or cool the one or more zones 300 at one or more temperature set points using the trained ML model.

In some embodiments, the user device 110 may be communicatively coupled to the server 108 comprising the at least one processor 202. In some embodiments, the user device 110 may be configured to receive the determined one or more temperature set points for the HVAC unit 306. Further, the user device 110 may be operated by the user to further instruct the HVAC controller 308 and feed the determined one or more temperature set points. In some embodiments, the HVAC controller 308 may further be configured to operate the HVAC unit 306 to actuate in the determined one or more temperature set points to set the temperature inside the one or more zones 300 based on the determined occupancy level trends.

The HVAC controller 308 may be configured to adjust the airflow to the one or more zones 300 based at least on the occupancy levels and environmental conditions. The airflow may be adjusted for optimal comfort while minimizing energy consumption. Further, the server 108 may work in tandem with the HVAC controller 308 to regulate the intensity of conditioned air delivered to one or more zones 300, to optimize the system 100 efficiency. Further, a building management supervisor by using the user device 110 may monitor and coordinate the operation of the components of the architecture to facilitate communication and integration within the system 100.

Further, the plurality of sensors and the HVAC controller 308 may operate synergistically to predict occupancy and maintaining a comfortable indoor environment. By continuously monitoring occupancy levels and environmental factors, the plurality of sensors may provide valuable inputs to the server 110 and the HVAC controller 308 to dynamically adjust airflow and ventilation strategies in response to changing environmental conditions. The HVAC unit 306 may serve as a critical intermediary, allowing the HVAC controller 308 to modulate the airflow delivered to individual zone of the one or more zones 300, thereby ensuring precise climate control tailored to predict occupancy. Further, the user device 110 may provide the supervision option to the building management supervisor to manage and maintain the interactions between components and ensures the smooth operation of the system 100. The architecture may provide an integrated framework to enhance one or more occupants comfort to optimize energy efficiency, and enable management of one or more zones 300.

Further, the architecture of the system 100 may comprise a power over Ethernet (POE) switch 402 that is connected to the occupancy sensor 302. In some embodiments, the POE switch 402 is a networking unit that is configured to provide power and network connectivity to power over Ethernet (POE) devices (i.e., the occupancy sensor 302) over a single Ethernet cable and sends occupancy data to the cloud via intermediate unit 418. In some embodiments, the POE switch 402 eliminates the need for separate power cables, simplifying installation and reducing infrastructure costs, especially in situations where power outlets may be limited or difficult to access. Further, data of the occupancy sensor 302 may be stored in the memory 204 via the network 102. In some embodiments, the ML model for predicting the occupancy of the one or more zones 300 may further comprise mixed-mode outdoor air (MM OA) set point optimization model 404, energy optimization (EO) set point optimization model 406, an energy baseline model 408, a ZL setback optimization model 410, and an occupancy prediction model 412.

In some embodiments, the MM OA set point optimization model 404, the EO set point optimization model 406, the energy baseline model 408, the ZL setback optimization model 410, and the occupancy prediction model 412 are configured to optimize the temperature set points or control parameters of the HVAC unit 306 based on various factors, including outdoor air conditions, indoor occupancy, thermal comfort requirements, and energy consumption goals. In some embodiments, the MM OA set point optimization model 404, the EO set point optimization model 406, the energy baseline model 408, the ZL setback optimization model 410, and the occupancy prediction model 412 is configured to integrate mixed methods or modeling techniques to optimize the temperature set points of the HVAC unit 306 based on outdoor air conditions. The models may involve mathematical algorithms, data analysis, and possibly machine learning techniques to dynamically adjust set points in response to changing outdoor air parameters and indoor environmental conditions.

In some embodiments, a forge gateway 414 may be connected to the ML model. In some embodiments, the forge gateway 414 is an intermediate between the ML model and a supervisor unit 416 that facilitates communication and data exchange. Further, the supervisor unit 416 is designed to supervise and manage the HVAC unit 306 of the building 104 for a specific tenant within a multi-tenant building. The supervisor unit 416 allows to monitor and control the HVAC unit 306 and parameters to meet their individual needs and preferences while benefiting from the overarching infrastructure. Further, the RL model may be communicatively in communication with the user device 110. Further, the user device 110 may be communicatively coupled with the HVAC unit 306 via a controller 420 which is a configurable and programmable controller. Further, a single control unit 422 may be connected to the user device 110 via a programmable logic controller 424. Further, indoor air quality sensors 426 and an energy monitoring unit 428 may be linked with the user device 110 via another controller 430. In some embodiments, the HVAC unit 306, the single control unit 422, the indoor air quality sensors 426 and the energy monitoring unit 428 may send data to the ML model through a secure VPN tunnel 432 to provide a secured, encrypted connection establishment.

FIGS. 5-6 illustrate an occupancy flow and zone level optimization of the system 100, in accordance with an example embodiment of the present disclosure. FIGS. 5-6 are described in conjunction with FIGS. 1-4.

In some embodiments, the occupancy sensor 302, a carbon dioxide sensor 502, an access reader 504, WIFI access point and Bluetooth low energy (BLE) sensor 506, and a lightning sensor 508 may be configured to send determined data to an access control system 510, a space connector 512 and to a cloud 514 for zone optimization and energy saving. In some embodiment, the lightning sensor 508 may provide accurate data that may be categorized as “BEST” in terms of accuracy. Further, the BLE sensor 506 may be categorized as “BETTER” and the occupancy sensor 302, the carbon dioxide sensor 502, the access reader 504 may be categorized as “GOOD”. Further, the data may be used by zone optimization monitor and controller 516, and zone optimization and energy saving KPI metrics 518 for data optimization.

In some embodiments, the zone optimization monitor and controller 516 may comprise integration with controller, integration with DNA space, integration with other 3^rd party occupancy, access control events, BMS occupancy sensor events and occupancy data ingestion. Further, the zone optimization and energy saving KPI metrics 518 may comprise VAV set point optimization, plant set point optimization, lightning optimization, energy optimization, occupancy zone to HVAC zone mapping, building and equipment model and EOM occupancy data model. In some embodiments, upon optimization of data via the zone optimization monitor and controller 516 and the zone optimization and energy saving KPI metrics 518, the optimization data may be received by a supervisor gateway 520 and to a lightning controller 522.

Further, as described in FIG. 6, initially at operation 602, the at least one processor 202 may be configured to receive occupancy data of one or more zones 300 via the occupancy sensor 302, the access reader 504, the WIFI access point and Bluetooth low energy (BLE) sensor 506, and the lightning sensor 508. Further, at operation 604, the at least one processor 202 may be configured to compute the received occupancy data by using the ML model to determine one or more occupancy trends. In some embodiments, the lightning sensor 508 may show high accuracy, the BLE sensor 506 may show medium accuracy and the access reader 504 may show low accuracy. In some embodiments, all the hardware options may be used in multiple combinations based on the requirement. Further, at operation 606, the at least one processor 202 may be configured to map the determined occupancy trends for each of the one or more zones for the first period of time with fluctuations in occupancy of each of the one or more zones in real-time and booking status of each of the one or more zones.

Further, at operation 608, the at least one processor may be configured alter temperature set points or turn on/off multiple equipment based on predicted occupancy of each of the one or more zones for a second time period and a threshold time required for each of the one or more zones to heat or cool at one or more temperature set points using the trained ML model based at least on the mapping. Further, at operation 610, the at least one processor may be configured to reset default schedule based on real-time occupancy determined.

FIG. 7 illustrates a flowchart showing an operation of a ML model 702 for predicting occupancy by using the at least one processor 202, in accordance with an example embodiment of the present disclosure. FIG. 7 is described in conjunction with FIGS. 1-6.

At operation 704, the ML model 702 may be trained using occupancy data for cooling and heating operations within one or more zones 300 of the building 104. At operation 706, the ML model 702 may be trained using occupancy data for ventilation operations within one or more zones 300 of the building 104. In some embodiments, the ML model 702 may be configured to receive the occupancy data of one or more zones via the plurality of sensors 106 for a first period of time. In some embodiments, the first period of time may correspond to historical time zone. The time period may comprise at least day, time, season, months, years.

At operation 708, the ML model 702 may be configured to predict occupancy of each of the one or more zones 300 for a second time period and a threshold time required for each of the one or more zones 300 to heat or cool at one or more temperature set points. At operation 710, the ML model 702 may be configured to predict occupancy of each of the one or more zones 300 for a second time period and a threshold time required for each of the one or more zones 300 to ventilate the one or more zones 300. In some embodiments, the ML model 702 may be configured to determine one or more occupancy trends for each zone for the first period of time.

The ML model 702 may be configured to predict occupancy of each of the one or more zones 300 for the second time period. In some embodiments, the second period of time may correspond to future time period. Further, the ML model 702 may be configured to predict a threshold time required for each of the one or more zones 300 to heat or cool at one or more temperature set points based at least on the mapping. The ML model 702 may be configured to adjust one or more temperature set points for each of the one or more zones 300 at the threshold time based at least on the prediction by using the HVAC controller 308 as described in FIG. 3 to optimize energy saving potential at step 712.

In some embodiments, the one or more temperature set points may comprise at least one heating set point that initializes a heating cycle to increase the temperature of the one or more zones. Further, the one or more temperature set points may comprise at least one cooling set point that initializes a cooling cycle to decrease the temperature of the one or more zones. The heating cycle or the cooling cycle may be initialized based at least on the threshold time required for each of the one or more zones to heat or cool at one or more temperature set points. In some embodiments, the heating cycle and the cooling cycle may be identified by change in the one or more temperature set points. Further, the heating cycle and the cooling cycle may end when the temperature of the one or more zones reaches the one or more temperature set points.

FIG. 8 illustrates a flowchart showing a method 800 for predicting occupancy, in accordance with an example embodiment of the present disclosure. FIG. 8 is described in conjunction with FIGS. 1-7.

At operation 802, the at least one processor 202 may be configured to receive the occupancy data of one or more zones 300 via the plurality of sensors 106 for the first period of time. In some embodiments, the occupancy data may comprise at least a number of occupants within each zone for the first period of time. In some embodiments, the plurality of sensors may correspond to a plurality of zone level occupancy sensors comprising at least one lightning sensors, Wi-Fi Access Points and Bluetooth low energy (BLE) sensors, access readers, and/or CO₂ sensor. In some embodiments, the one or more zones 300 may comprise at least one of the building 104, a warehouse, a storage unit, or an office space. Further, opening within each zone may correspond to number of windows and doors present in each zone. In some embodiments, the first period of time may correspond to historical time zone.

For example, the at least one processor 202 receives occupancy data from lightning sensors 508, Wi-Fi Access Points, Bluetooth low energy sensors, access readers, and CO2 sensors for a meeting room in an office building. The sensors detect the presence of occupants and measure environmental parameters in the meeting room.

At operation 804, the at least one processor 202 may be configured to determine one or more occupancy trends for each zone for the first period of time using a trained machine learning (ML) model. In some embodiments, the occupancy trends may comprise occupancy of the one more zones 300 and number of occupants within each of the one or more zones 300 within the first time period. In some embodiments, the at least one processor 202 may be configured to generate at least one machine learning (ML) model for each of the one or more zones 300 for the first period of time. Further, the at least one processor 202 may be configured to train the ML model 702 for each of the one or more zones 300 based at least on the received occupancy data. In some embodiments, the at least one processor 202 may be configured to generate and train the at least one model using one or more Artificial Intelligence (AI)/Machine Learning (ML) techniques. For example, the at least one processor 202 determines occupancy trends for the meeting room in the office building, during a historical period of 10 days, using a trained neural network.

At operation 806, the at least one processor 202 may be configured to map the determined occupancy trends for each of the one or more zones 300 for the first period of time with fluctuations in occupancy of each of the one or more zones 300 in real-time and booking status of each of the one or more zones 300. In some embodiments, the booking status of the one or more zones 300 may correspond to the one or more zones 300 pre-booked to be occupied by one or more users. For example, the at least one processor 202 maps the determined occupancy trend for individual offices, meeting rooms, and common areas in the office building of 10 days with a fluctuation of 10 occupants in the occupancy of the meeting room and a booking status of 60 occupants in the meeting room in real-time.

At operation 808, the at least one processor 202 may be configured to predict occupancy of each of the one or more zones 300 for a second time period and a threshold time required for each of the one or more zones 300 to heat or cool at one or more temperature set points using the trained ML model 702 based at least on the mapping. In some embodiments, the second period of time may correspond to future time period. Further, the time period may comprise at least day, time, season, months, years. For example, the at least one processor 202 predicts the occupancy of the meeting room as 56 occupants on 3^rd day from the real-time and a threshold time of 3 hours for the meeting room to cool at a temperature set point of 19 degrees Celsius using the trained neural network.

At operation 810, the at least one processor 202 may be configured to adjust one or more temperature set points for each of the one or more zones 300 at the threshold time based at least on the prediction. In some embodiments, the one or more temperature set points may comprise at least one heating set point that initializes a heating cycle to increase the temperature of the one or more zones 300. Further, the one or more temperature set points may comprise at least one cooling set point that initializes a cooling cycle to decrease the temperature of the one or more zones 300. The heating cycle or the cooling cycle may be initialized based at least on the threshold time required for each of the one or more zones 300 to heat or cool at one or more temperature set points. In some embodiments, the heating cycle and the cooling cycle may be identified by change in the one or more temperature set points. Further, the heating cycle and the cooling cycle may end when the temperature of the one or more zones 300 reaches the one or more temperature set points. For example, the at least one processor 202 adjusts the temperature set point of 19° C. of the meeting room before 3 hours to cool the meeting room by the time the meeting room is occupied.

FIGS. 9A-9B illustrate a graphical representation 900, 904 of weekly and daily seasonality respectively of the trained ML model 702, in accordance with an example embodiment of the present disclosure.

In some embodiments, the graphical representation 900, 904 of the system 100 may represent weekly and daily seasonality parts of the trained ML model 702 to determine occupancy trends. In some embodiments, the curve 902 may correspond to a day to week standpoint of the trained ML model 702. Further, the curve 906 as illustrated in FIG. 9B may represent a time of day standpoint of the trained ML model 702.

In some embodiments, the system 100 may comprise at least one non-transitory machine-readable medium including data, which when used by at least one processor, causes the at least one processor to perform instructions that cause the at least one processor to perform operations comprising receiving, via at least one processor, an occupancy data of one or more zones 300 via one or more sensors for a first period of time. The occupancy data may comprise at least a number of occupants within each zone for the first period of time. Further, the operations may comprise determining, via at least one processor, one or more occupancy trends for each zone for the first period of time using a trained machine learning (ML) model. The occupancy trends may comprise occupancy of the one more zones 300 and number of occupants within each of the one or more zones 300 within the first time period.

Further, the operations may comprise mapping, via the at least one processor, the determined occupancy trends for each of the one or more zones 300 for the first period of time with fluctuations in occupancy of each of the one or more zones 300 in the real-time and booking status of each of the one or more zones 300. Further, the operations may comprise predicting, via at least one processor, occupancy of each of the one or more zones 300 for a second time period and a threshold time required for each of the one or more zones 300 to heat or cool at one or more temperature set points using the trained ML model 702 based at least on the mapping. Thereafter, the operations may comprise adjusting, via the at least one processor, one or more temperature set points for each of the one or more zones 300 at the threshold time based at least on the prediction.

The present disclosure may provide efficiency, comfort, and resource optimization. Firstly, by accurately predicting the occupancy through the integrated sensor network and VAV controller, the system may optimize airflow and ventilation to match real-time occupancy demands. Further, the system may provide improved energy efficiency by preventing over-conditioning of unoccupied zones, reducing unnecessary energy consumption and operational costs. Further, the system 100 may maintain optimal indoor environmental conditions to enhance occupant comfort and productivity, contributing to a healthier and more conducive working or living environment. Additionally, the system's ability to adapt and respond dynamically to changing occupancy patterns may allow for better utilization of space and resources within the building, maximizing operational efficiency and space utilization. Further, the system 100 may provide a centralized management provided by the building management supervisor to streamline system operation, and thereby facilitating remote monitoring and control, and enabling proactive maintenance and troubleshooting, ensuring continuous and reliable performance.

Many modifications and other embodiments of the inventions set forth herein will come to mind to one skilled in the art to which these inventions pertain having the benefit of the teachings presented in the foregoing descriptions and the associated drawings. Therefore, it is to be understood that the inventions are not to be limited to the specific embodiments disclosed and that modifications and other embodiments are intended to be included within the scope of the appended claims. Moreover, although the foregoing descriptions and the associated drawings describe example embodiments in the context of certain example combinations of elements and/or functions, it should be appreciated that different combinations of elements and/or functions may be provided by alternative embodiments without departing from the scope of the appended claims. In this regard, for example, different combinations of elements and/or functions than those explicitly described above are also contemplated as may be set forth in some of the appended claims. Although specific terms are employed herein, they are used in a generic and descriptive sense only and not for purposes of limitation.