Control load distribution method and system based on user random behavior

Abstract

This invention belongs to the field of power system technology and discloses a distributed control method and system for control loads based on user random behavior. The method involves dividing a building into multiple temperature-controlled zones, generating a first control reference sequence based on user and environmental information for each zone, determining whether a control reference sequence with a similarity greater than a first preset value exists in the historical operation data table, and defining the control reference sequence corresponding to the maximum similarity as a second control reference sequence if it does. A first temperature control command is generated based on the air conditioning operation mode corresponding to the second control reference sequence; otherwise, a second temperature control command is generated based on user information and the temperature control mode corresponding to the temperature-controlled zone. The method periodically checks whether user feedback information is received; if so, a third temperature control command is generated for the temperature-controlled zone based on the feedback information. This invention enables intelligent and personalized control of building temperature loads, improving building energy efficiency while enhancing user satisfaction.

Description

Technical Field

[0001] This invention belongs to the field of power system technology, specifically relating to a distributed control method and system for control load based on user random behavior. Background Technology

[0002] In modern buildings, especially large commercial buildings and smart homes, temperature control systems are crucial for improving living and working comfort. However, traditional temperature control methods often rely on preset fixed schedules or simple sensor feedback, ignoring the diversity and randomness of user behavior and lacking the precision to adjust building temperature loads. Therefore, how to achieve intelligent and distributed control of building temperature loads based on users' random behavior and building energy conditions has become an important issue in the field of building energy conservation and optimization.

[0003] A similar prior art is Chinese patent application CN117190280A, which discloses a distributed control method and system for building heating. This method acquires environmental information and building structural information at each air outlet within the building; determines a corresponding proportionality coefficient based on the environmental and structural information of each air outlet and its relationship to the heating supply; calculates the heating area of ​​each air outlet based on the obtained proportionality coefficient; and adjusts the heat load at the corresponding air outlet based on the calculated heating area. This method can regulate the heat load at the air outlets, preventing excessively high or low temperatures in certain areas, but it lacks consideration for the user conditions within the controlled area. Another Chinese patent application, CN118705732A, discloses an intelligent zoned temperature control method and system for central air conditioning. It utilizes BIM to obtain detailed floor plans of the building, divides the space into zones, and determines the temperature control requirements for each zone based on usage needs, orientation, and floor level. Temperature, humidity, and CO2 sensors are installed in each zone to acquire environmental data. Indoor occupant detection sensors are installed at key locations to detect the number of people and their activity levels within the zone. The sensors periodically collect environmental data and transmit it to the central control system via a wireless network. Based on sensor data and historical data, a temperature control model for each zone is established. Machine learning algorithms are used to predict future temperature changes. Based on the zone temperature control model and user-preset comfort requirements, an intelligent temperature control strategy is formulated. The central control system translates the temperature control strategy into specific control commands and sends them to the air conditioning equipment within the zone. Upon receiving the control commands, the equipment adjusts its cooling and heating power, fan speed, and airflow direction. This method comprehensively considers the user situation within the controlled zone but lacks analysis of individual user differences.

[0004] Therefore, providing a distributed control method and system for control load based on user random behavior to improve building energy efficiency, enhance user satisfaction, and increase the automation level of building temperature control load is an urgent problem to be solved. Summary of the Invention

[0005] To address the aforementioned technical problems, this invention provides a distributed control method and system for control load based on user random behavior.

[0006] In a first aspect, the present invention provides a distributed control method for control load based on user random behavior, the method comprising the following steps:

[0007] Step 1: Divide the building into multiple temperature-controlled zones based on its physical structure;

[0008] Step 2: Obtain user information and environmental information for any temperature control zone, and generate a first control reference sequence based on the user information and environmental information;

[0009] Step 3: Determine whether there is a control reference sequence in the historical operation data table that has a similarity greater than the first preset value to the first control reference sequence. If yes, proceed to step 4; otherwise, proceed to step 5.

[0010] Step 4: Define the control reference sequence corresponding to the maximum similarity as the second control reference sequence, take the air conditioning operation mode corresponding to the second control reference sequence as the first air conditioning operation mode for any temperature control area, generate a first temperature control command based on the first air conditioning operation mode, and send it to the corresponding air conditioning equipment.

[0011] Step 5: Obtain the corresponding first temperature control mode based on the identification information of any temperature control zone, generate the second air conditioner operation mode based on the user information and the first temperature control mode, generate the second temperature control command based on the second air conditioner operation mode, and send it to the corresponding air conditioning equipment.

[0012] Step 6: Periodically check whether user feedback information has been received. If yes, proceed to step 7. If no, store the current air conditioning operation mode in the historical operation data table corresponding to the first control reference sequence.

[0013] Step 7: Generate a third air conditioning operation mode for any temperature control zone based on the feedback information, generate a third temperature control command based on the third air conditioning operation mode, and send it to the corresponding air conditioning equipment. Then, store the third air conditioning operation mode in the historical operation data table in correspondence with the first control reference sequence.

[0014] Specifically, the first environmental information is collected through data acquisition equipment, and the method for acquiring the environmental information is as follows:

[0015] Obtain the device identifier of the data acquisition device, and extract the corresponding calibration function of the data acquisition device from the calibration function table based on the device identifier;

[0016] Obtain the first environmental value and acquisition time from the first environmental information, calculate the calibration value based on the calibration function, the first environmental value and acquisition time, and use the sum of the calibration value and the first environmental value as the second environmental value of the data acquisition device;

[0017] Environmental information is generated based on device identifier, secondary environmental value, and collection time.

[0018] Specifically, the calibration function is generated as follows:

[0019] Step 21: Perform calibration tests on the data acquisition device at preset time intervals, obtain test results, and store the test results in the calibration information table corresponding to the device identifier. The test results include the actual value, the measured value, and the calibration time.

[0020] Step 22: When the test results are received, determine whether the number of all test results corresponding to the device identifier in the calibration information table is 1. If so, calculate the initial calibration value based on the test results, assign the initial calibration value to the calibration function, and store the calibration function and the device identifier in the calibration function table accordingly. If not, proceed to step 23.

[0021] Step 23: Extract all test results corresponding to the device identifier from the calibration information table, perform machine learning on all test results to generate a new calibration function, and update the calibration function table based on the new calibration function.

[0022] Specifically, step 2 includes: obtaining air conditioning equipment information for any temperature control area, and dividing any temperature control area into multiple sub-areas based on the air conditioning equipment information.

[0023] Specifically, user information includes the number of users and user location information, and the method for generating the temperature control mode is as follows:

[0024] Step 511: Extract any temperature control zone and divide the air conditioning setting conditions of any temperature control zone into N types based on user information;

[0025] Step 512: Extract any air conditioning setting condition and obtain the building structure information corresponding to any air conditioning setting condition. Based on any air conditioning setting condition and building structure information, generate M types of fourth air conditioning operation modes according to preset standards. The fourth air conditioning operation mode includes the temperature setting and fan speed setting of the air conditioning equipment related to the sub-area corresponding to any air conditioning setting condition.

[0026] Step 513: Calculate the energy consumption reduction rate corresponding to any fourth air conditioning operation mode;

[0027] Step 514: After traversing all the fourth air conditioning operation modes, sort all the fourth air conditioning operation modes in descending order of energy consumption reduction rate;

[0028] Step 515: After traversing all air conditioning settings, group the fourth air conditioning operating modes with the same serial number in different air conditioning settings into one group.

[0029] Step 516: Assign identifiers to all fourth air conditioning operation modes after grouping and processing, and then generate K temperature control modes based on the air conditioning operation modes after assigning identifiers.

[0030] Specifically, before step 5, the administrator sets the first temperature control mode for any temperature control area, or dynamically sets the first temperature control mode for any temperature control area according to the time period.

[0031] Specifically, the user information includes a user identifier, and step 7 includes:

[0032] Step 71: Define the user who sends feedback information as the first user, and calculate the somatosensory parameter value of any first user based on the personal and environmental information of any first user;

[0033] Step 72: Based on the user identifier of any first user, obtain the first somatosensory value distribution table of any first user from the historical somatosensory data table;

[0034] Step 73: Based on the feedback information and somatosensory parameter values ​​of any first user, determine whether a specific somatosensory interval in the first somatosensory value distribution table has changed. If so, update the first somatosensory value distribution table based on the feedback information and somatosensory parameter values.

[0035] Step 74: After traversing all first users, extract the distribution table of the body temperature values ​​of all users in any temperature control area, and cluster all users based on a specific body temperature interval to divide them into multiple user groups;

[0036] Step 75: Extract any user group, calculate the first average of the lower limit of the specific somatosensory interval and the second average of the upper limit of the specific somatosensory interval for all users in the user group, and generate the specific somatosensory interval for the group based on the first average and the second average.

[0037] Step 76: After traversing all user groups, generate a region-specific somatosensory interval based on the specific somatosensory interval of each group;

[0038] Step 77: Based on the specific regional somatosensory range, learn the current air conditioning operation mode to generate a third air conditioning operation mode, so that the somatosensory parameter values ​​of all users fall within the specific regional somatosensory range.

[0039] Specifically, step 76 includes:

[0040] Determine if there is any overlap in the specific sensory intervals of all groups. If there is, use the overlapping area as the specific sensory interval of the region. If not, obtain the number of users in each user group, set the weight parameter for each user group based on the number of users, and perform a weighted average of the upper and lower limits of the specific sensory interval of the group based on the weight parameter to generate the specific sensory interval of the region.

[0041] Secondly, the present invention also provides a distributed control load control system based on user random behavior, the system comprising: a region division module, a data acquisition module, an information judgment module, a first control module, a second control module, an adjustment judgment module, and a control adjustment module;

[0042] The zone division module is used to obtain detailed floor plans of the building and divide the building into multiple temperature-controlled zones based on the building's physical structure.

[0043] The data acquisition module is used to extract any temperature control zone, acquire user information and environmental information of any temperature control zone, and generate a first control reference sequence based on the user information and environmental information;

[0044] The information judgment module is used to traverse the historical operation data table according to the first control reference sequence and determine whether there is a control reference sequence in the historical operation data table that has a similarity greater than the first preset value to the first control reference sequence. If so, it enters the first control module; otherwise, it enters the second control module.

[0045] The first control module is used to define the control reference sequence corresponding to the maximum similarity as the second control reference sequence, take the air conditioning operation mode corresponding to the second control reference sequence as the first air conditioning operation mode of any temperature control area, generate a first temperature control command based on the first air conditioning operation mode, and send the first temperature control command to the corresponding air conditioning equipment.

[0046] The second control module is used to obtain the first temperature control mode corresponding to any temperature control zone according to the identification information of any temperature control zone, generate the second air conditioning operation mode of any temperature control zone based on user information and the first temperature control mode, generate the second temperature control command based on the second air conditioning operation mode, and send the second temperature control command to the corresponding air conditioning equipment.

[0047] The adjustment judgment module is used to periodically determine whether user feedback information has been received. If not, the current air conditioning operation mode is stored in the historical operation data table in correspondence with the first control reference sequence. If yes, the control adjustment module is entered, where the current air conditioning operation mode is either the first air conditioning operation mode or the second air conditioning operation mode.

[0048] The control adjustment module is used to generate a third air conditioning operation mode for any temperature control zone based on feedback information, generate a third temperature control command based on the third air conditioning operation mode, and send the third temperature control command to the corresponding air conditioning equipment. Then, the third air conditioning operation mode is stored in the historical operation data table in correspondence with the first control reference sequence.

[0049] Compared with the prior art, the beneficial effects of the present invention are at least as follows:

[0050] 1. Based on user information and environmental information, a control reference sequence is generated. By judging the similarity of historical data, the air conditioning operation mode is intelligently set according to historical operating data or preset temperature control mode. This realizes the intelligent selection of air conditioning operation mode, improves the system's operating efficiency, and enhances the intelligent control of building temperature load.

[0051] 2. By subdividing the temperature control zone and generating multiple air conditioning operation modes based on data such as the number of users and location information, the operation of the air conditioning equipment can be precisely controlled. Managers can select the temperature control mode according to their needs or dynamically set the temperature control mode according to the time period, which improves the personalized setting of the temperature control zone or the adaptability to environmental changes at different times. While focusing on user comfort, the energy efficiency of the temperature control equipment is also taken into consideration.

[0052] 3. Periodically assess user feedback and dynamically adjust the air conditioner's operating mode based on that feedback to achieve real-time temperature control, accurately respond to user needs, improve user satisfaction, and achieve a high degree of automation.

[0053] 4. By collecting environmental information through data acquisition equipment and performing calibration using calibration functions, the accuracy and reliability of the acquired environmental information can be ensured. Decisions can be made based on accurate data, thereby improving the precision of control. Attached Figure Description

[0054] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0055] Figure 1 This is a flowchart of the distributed control method for control load based on user random behavior according to the present invention;

[0056] Figure 2 This is a modular schematic diagram of the distributed control system for user random behavior based on the present invention. Detailed Implementation

[0057] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. Obviously, the specific embodiments described herein are merely illustrative of the invention and represent only a portion, not all, of the embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without inventive effort are within the scope of protection of this invention.

[0058] It should be noted that if the embodiments of the present invention involve descriptions such as "first" and "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first" or "second" may explicitly or implicitly include at least one of those features. Furthermore, the technical solutions of the various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. When the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed by the present invention.

[0059] Figure 1 The diagram shows a flowchart of an embodiment of the distributed control method for control load based on user random behavior provided by the present invention. The flowchart specifically includes the following steps:

[0060] Step 1: Divide the building into multiple temperature-controlled zones based on its physical structure.

[0061] Specifically, obtain detailed floor plans of the building, and divide the independent building spaces into temperature-controlled zones based on the building's physical structure. The types of independent building spaces include corridors, rooms, staircases, etc.

[0062] Step 2: Obtain user information and environmental information for any temperature control zone, and generate a first control reference sequence based on the user information and environmental information.

[0063] For example, environmental information includes temperature, humidity, sunshine duration, air velocity, etc.

[0064] User information includes user identifiers and user location. For example, user identifiers are obtained through smart cards, mobile devices (such as mobile apps), wearable devices, or biometric systems (such as facial recognition) to uniquely identify the user. Indoor positioning technologies (such as Bluetooth beacons, Wi-Fi positioning, infrared sensors, or cameras) or image recognition are used to track the user's location in the temperature-controlled area in real time. Sensors within the area (such as infrared thermal imaging, people counters, and cameras combined with AI analysis) are used to count the number of users in the current temperature-controlled area. Other information (such as activity level and clothing thickness) may be obtained through wearable devices (monitoring heart rate and exercise status), environmental sensors (combined with temperature feedback to infer clothing), or manual input by the user (such as app feedback). The methods for obtaining user information can be selected and combined according to the actual application scenario and system design to meet the system's needs for user information.

[0065] Specifically, the first environmental information is collected through data acquisition equipment, and the method for acquiring the environmental information is as follows:

[0066] Obtain the device identifier of the data acquisition device, and extract the corresponding calibration function of the data acquisition device from the calibration function table based on the device identifier;

[0067] Obtain the first environmental value and acquisition time from the first environmental information, calculate the calibration value based on the calibration function, the first environmental value and acquisition time, and use the sum of the calibration value and the first environmental value as the second environmental value of the data acquisition device;

[0068] Environmental information is generated based on device identifier, secondary environmental value, and collection time.

[0069] Due to differences in manufacturers, models, and hardware, errors are inevitable between the measured values ​​and actual values ​​collected by data acquisition equipment. Furthermore, aging caused by prolonged use can also lead to discrepancies. To achieve precise control, the accuracy of environmental information must be ensured. Therefore, calibration is performed before controlling the air conditioning operation mode to eliminate or reduce measurement errors.

[0070] Preferably, the usage time of the data acquisition device is obtained based on the above-mentioned acquisition time, and the usage time and the first environmental value are input into the calibration function to obtain the calibration value.

[0071] Specifically, the calibration function is generated as follows:

[0072] Step 21: Perform calibration tests on the data acquisition device according to the preset time interval, obtain the test results, and store the test results in the calibration information table corresponding to the device identifier. The test results include the actual value, the measured value, and the calibration time.

[0073] Step 22: When the test result is received, determine whether the number of all test results corresponding to the device identifier in the calibration information table is 1. If so, calculate the initial calibration value based on the test result, assign the initial calibration value to the calibration function, and store the calibration function and the device identifier in the calibration function table accordingly. If not, proceed to step 23.

[0074] Step 23: Extract all test results corresponding to the device identifier from the calibration information table, perform machine learning on all test results to generate a new calibration function, and update the calibration function table based on the new calibration function.

[0075] The preset time interval is set based on the experience of those skilled in the art or according to the actual application scenario, and this application embodiment is not limited in this regard. Preferably, the preset time interval is set according to the application environment of the data acquisition device.

[0076] The calibration value of the same data acquisition device may be different when measuring different actual values, and the measurement error will increase over time. Therefore, the independent variables of the calibration function obtained by training the test results are the measured value, the usage time, etc., and the dependent variable is the calibration value (i.e., the error value).

[0077] According to the technical solution of this invention, by comparing test results at different time points and using machine learning technology to generate an accurate calibration function, the impact of the fundamental characteristics of the data acquisition equipment and time variations on the measured values ​​can be reduced. Furthermore, by periodically calibrating and updating the calibration function, the long-term accuracy of the measurement data can be maintained. Over time, the calibration function becomes more accurate, thereby improving the control effect of the entire temperature control system. Simultaneously, different data acquisition devices may have different error characteristics; by customizing the calibration function for each data acquisition device, the adaptability and flexibility of the system can be improved.

[0078] Step 3: Determine whether there is a control reference sequence in the historical operation data table that has a similarity greater than the first preset value to the first control reference sequence. If yes, proceed to step 4; otherwise, proceed to step 5.

[0079] Specifically, based on the first control reference sequence, the historical operation data table is traversed to determine whether there is a control reference sequence in the historical operation data table that has a similarity greater than a first preset value to the first control reference sequence.

[0080] The first preset value is set based on the experience of those skilled in the art or according to the actual application scenario, and the embodiments of this application are not limited in this regard.

[0081] Step 4: Define the control reference sequence corresponding to the maximum similarity as the second control reference sequence, take the air conditioning operation mode corresponding to the second control reference sequence as the first air conditioning operation mode for any temperature control area, generate a first temperature control command based on the first air conditioning operation mode, and send it to the corresponding air conditioning equipment.

[0082] When a control reference sequence with a similarity greater than the first preset value exists, it indicates that there is an operating environment in the historical operation data table that is highly similar to the current user and environmental information, suggesting that the user's needs may be consistent. Therefore, the corresponding historical air conditioning operation mode is adopted as the current primary air conditioning operation mode for the temperature-controlled area. This operation mode includes the air conditioning equipment identifier, set temperature, fan speed, and operating time. This achieves intelligent adjustment of the air conditioning operation mode, with a high degree of automation, improving the accuracy and efficiency of temperature control.

[0083] Step 5: Obtain the corresponding first temperature control mode based on the identification information of any temperature control zone, generate a second air conditioning operation mode based on user information and the first temperature control mode, generate a second temperature control command based on the second air conditioning operation mode, and send it to the corresponding air conditioning equipment.

[0084] Specifically, the first temperature control mode mentioned above is the temperature control mode corresponding to any temperature control zone.

[0085] Specifically, step 2 includes: obtaining air conditioning equipment information for any temperature control area, and dividing any temperature control area into multiple sub-areas based on the air conditioning equipment information.

[0086] If the temperature control area is large, multiple air outlets will be installed to ensure better temperature control. Each air outlet corresponds to one air conditioning unit. In this case, the temperature control area is divided into multiple sub-zones based on the location of the air conditioning units. By dividing the temperature control area into smaller sub-zones, more precise temperature control can be achieved for each sub-zone, reducing unnecessary energy consumption.

[0087] Specifically, user information includes the number of users and user location information, and the method for generating the temperature control mode is as follows:

[0088] Step 511: Extract any temperature control zone and divide the air conditioning setting conditions of any temperature control zone into N types based on user information.

[0089] Step 512: Extract any air conditioning setting condition and obtain the building structure information corresponding to any air conditioning setting condition. Based on any air conditioning setting condition and building structure information, generate M fourth air conditioning operation modes according to preset standards. The fourth air conditioning operation mode includes the temperature setting and fan speed setting of the air conditioning equipment related to the sub-area corresponding to any air conditioning setting condition.

[0090] Step 513: Calculate the energy consumption reduction rate corresponding to any fourth air conditioning operation mode.

[0091] Step 514: After traversing all the fourth air conditioning operation modes, sort all the fourth air conditioning operation modes in descending order of energy consumption reduction rate.

[0092] Step 515: After traversing all air conditioning settings, group the fourth air conditioning operating modes with the same serial number among the different air conditioning settings.

[0093] Step 516: Assign identifiers to all fourth air conditioning operation modes after grouping and processing, and then generate K temperature control modes based on the air conditioning operation modes after assigning identifiers.

[0094] For example, the temperature control area is divided into four sub-areas in a grid pattern: the upper left sub-area is A1, the upper right sub-area is A2, the lower left sub-area is A3, and the lower right sub-area is A4. The maximum capacity of any sub-area is 10 people. When dividing the air conditioning control conditions based on user information, a user located in sub-area A1 with 0-3 people is considered one air conditioning setting condition; a user located in sub-area A1 with 4-10 people is considered another air conditioning setting condition; and so on. Similarly, a user located in sub-area A4 with 0-3 people is considered another air conditioning setting condition, and so on. In other words, the air conditioning setting conditions for the temperature control area can be divided into eight types.

[0095] In a cooling environment, a smaller number of people in a sub-area results in less heat generation and less energy consumption to reach the target temperature; conversely, a larger number of people in a sub-area results in more heat generation and greater energy consumption to reach the target temperature. If a sub-area has windows or doors, cold air will escape, leading to poor insulation and increased energy consumption to reach the target temperature. Based on these factors, setting the air conditioning operation mode for the temperature-controlled area according to the air conditioning setup conditions and building structure information can generate a temperature control mode that better meets the actual needs of users, thereby improving user satisfaction.

[0096] For example, for air conditioning setting condition B1 (users are located in sub-area A1, number of people is 0-3), there are walls on two sides and open space on two sides. According to preset standards, six fourth air conditioning operation modes are generated as follows: a1. Set the target temperature of the air conditioning equipment corresponding to sub-area A1 to 24℃; a2. Set the target temperature of the air conditioning equipment corresponding to sub-area A1 to 26℃; a3. Cycle the target temperature of the air conditioning equipment corresponding to sub-area A1 to 24℃ and 26℃ according to a preset cycle; a4. Set the target temperature of the air conditioning equipment corresponding to sub-area A1 to 25℃ and the target temperature of the air conditioning equipment corresponding to sub-area A2 to 26℃; a5. Set the target temperature of the air conditioning equipment corresponding to sub-area A1 to 25℃ and the target temperature of the air conditioning equipment corresponding to sub-area A3 to 26℃; a6. Set the target temperature of the air conditioning equipment corresponding to sub-area A1 to 26℃, the target temperature of the air conditioning equipment corresponding to sub-area A2 to 27℃, and the target temperature of the air conditioning equipment corresponding to sub-area A3 to 27℃. Alternatively, the target temperature of each air conditioning unit in A4, A5, and A6 can be set dynamically in a periodic cycle; the fan speed can also be set at the same time as the target temperature is set.

[0097] The formula for calculating the energy consumption reduction rate R corresponding to the i-th type of fourth air conditioning operation mode is:

[0098] ,

[0099] Among them, E t E represents the total energy consumption under the baseline control mode. i Let be the energy consumption under the i-th fourth air conditioning operation mode.

[0100] For example, the above-mentioned baseline control mode is that all air conditioning equipment in the temperature control area operates according to the preset target temperature and preset fan speed.

[0101] For example, there are two air conditioning setting conditions B2 and B3. The result of sorting all the fourth air conditioning operation modes corresponding to air conditioning setting condition B2 is (c1, c2, c3), and the result of sorting all the fourth air conditioning operation modes corresponding to air conditioning setting condition B3 is (d1, d2, d3). If c1 and d1 are grouped together (labeled as E1), c2 and d2 are grouped together (labeled as E2), and c3 and d3 are grouped together (labeled as E3), then there are 3 temperature control modes. The first temperature control mode E1 corresponds to the air conditioning operation modes c1 and d1, the second temperature control mode E2 corresponds to the air conditioning operation modes c2 and d2, and the third temperature control mode E3 corresponds to the air conditioning operation modes c3 and d3.

[0102] Energy efficiency and comfort are inversely related; higher energy efficiency generally leads to lower comfort, and vice versa. By sorting all fourth-order air conditioning operation modes according to their energy reduction rate from highest to lowest, users can understand the energy efficiency of various operation modes and choose the appropriate mode based on their needs. Grouping air conditioning operation modes with the same serial number simplifies temperature control strategy management because the operation modes within each group have similar energy consumption characteristics and temperature control effects. This helps to unify temperature control strategies under different air conditioning settings, making the temperature control of the entire building more coordinated and consistent. Assigning identifiers to the grouped air conditioning operation modes helps to standardize temperature control mode management, ensuring that each mode can be uniquely identified and invoked, increasing flexibility, and allowing users to select the most suitable mode for temperature control according to their actual needs.

[0103] When generating a second air conditioning operation mode for any temperature control area based on user information and the first temperature control mode, the user information includes the number of users and user location information. By analyzing the user information, the corresponding air conditioning setting conditions can be obtained. Each air conditioning setting condition corresponds to multiple fourth air conditioning operation modes. The second air conditioning operation mode can be selected based on the first temperature control mode.

[0104] Preferably, user information may also include user activities (such as sitting still or exercising).

[0105] Specifically, before step 5, the administrator sets the first temperature control mode for any temperature control area, or dynamically sets the first temperature control mode for any temperature control area according to the time period.

[0106] Each temperature-controlled zone manager is responsible for that zone. Each zone manager can select a suitable temperature control mode based on their needs (prioritizing energy conservation or comfort). Different temperature control modes are set for each zone based on its function, purpose, or the importance of the user, enabling precise control of the air conditioning equipment within each zone.

[0107] The temperature control mode can also be dynamically set according to time period. For example, during non-working hours, when there are fewer people working, a temperature control mode with a high energy consumption reduction rate can be selected, while during working hours, when there are more people working, a temperature control mode with a low energy consumption reduction rate can be selected.

[0108] According to the technical solution of the present invention, personalized temperature control modes can be generated, energy consumption can be controlled more precisely, and energy use can be optimized.

[0109] Step 6: Periodically check whether user feedback information has been received. If yes, proceed to step 7. If no, store the current air conditioning operation mode in the historical operation data table corresponding to the first control reference sequence.

[0110] Specifically, the current air conditioning operation mode mentioned above is either the first air conditioning operation mode or the second air conditioning operation mode.

[0111] For example, user feedback may include whether the ambient temperature feels high, low, or comfortable. A user's perception of ambient temperature may change over time or due to variations in clothing thickness. If user feedback is received, the air conditioning operating mode needs to be adjusted based on the user's actual situation.

[0112] Step 7: Generate a third air conditioning operation mode for any temperature control zone based on the feedback information, generate a third temperature control command based on the third air conditioning operation mode, and send it to the corresponding air conditioning equipment. Then, store the third air conditioning operation mode in the historical operation data table in correspondence with the first control reference sequence.

[0113] Specifically, user information includes user identifiers, and step 7 includes:

[0114] Step 71: Define the user who sends feedback information as the first user, and calculate the somatosensory parameter value of any first user based on the personal information and environmental information of any first user.

[0115] Step 72: Based on the user identifier of any first user, obtain the first somatosensory value distribution table of any first user from the historical somatosensory data table.

[0116] Step 73: Based on the feedback information and somatosensory parameter values ​​of any first user, determine whether a specific somatosensory interval in the first somatosensory value distribution table has changed. If so, update the first somatosensory value distribution table based on the feedback information and somatosensory parameter values.

[0117] Step 74: After traversing all first users, extract the distribution table of the body temperature values ​​of all users in any temperature control area, and cluster all users based on a specific body temperature interval to form multiple user groups.

[0118] Step 75: Extract any user group, calculate the first average of the lower limit of the specific somatosensory interval and the second average of the upper limit of the specific somatosensory interval for all users in the user group, and generate the specific somatosensory interval for the group based on the first average and the second average.

[0119] Step 76: After traversing all user groups, generate a specific sensory interval for the region based on the specific sensory interval of the group.

[0120] Step 77: Based on the specific regional somatosensory range, learn the current air conditioning operation mode to generate a third air conditioning operation mode, so that the somatosensory parameter values ​​of all users fall within the specific regional somatosensory range.

[0121] The aforementioned specific somatosensory range refers to the range of somatosensory parameters within which users feel the ambient temperature is comfortable.

[0122] The perceived thermal comfort parameter value is based on the principle of human thermal balance, comprehensively considering factors such as air temperature, average radiant temperature, relative humidity, air velocity, human activity level, and clothing, and is used to predict the average thermal comfort experience of the human body in a specific environment. For example, it is based on an empirical function. Calculate the human body parameter values, where x1 is the human metabolic rate, x2 is the thermal resistance of clothing, x3 is the air temperature, x4 is the average radiant temperature, x5 is the relative humidity, and x6 is the air velocity.

[0123] Metabolic rate can be estimated by using wearable devices or sensors to monitor a user's physiological parameters, such as heart rate and skin temperature. Alternatively, it can be determined by analyzing the user's movement patterns (e.g., through accelerometer data) to assess activity levels and adjust the metabolic rate accordingly. Clothing thermal resistance can be estimated based on sensor data of ambient temperature and user activity levels. It can also be estimated by acquiring the type of clothing worn by the user (image recognition or user input) and using the system to determine the thermal resistance. Additionally, preset default values ​​can be used, which are set based on average data from the general population. For example, the metabolic rate in a sedentary state is typically set to 1.1 metabolic units (met), while the thermal resistance of typical indoor clothing might be set to 0.6 clo (clo units).

[0124] The distribution table of users' somatosensory values ​​in the historical somatosensory data table is generated based on the users' historical somatosensory parameter values ​​and historical feedback information. For example, for user Y1, the distribution table of his somatosensory values ​​is [(-3, z1), low ambient temperature; (z1, z2), suitable ambient temperature; (z2, 3), high ambient temperature], and for user Y2, the distribution table of his somatosensory values ​​is [(-3, z3), low ambient temperature; (z3, z4), suitable ambient temperature; (z4, 3), high ambient temperature].

[0125] If a user's perceived ambient temperature changes (e.g., a user previously reported "comfortable ambient temperature" at a certain PMV value, but now reports "high ambient temperature"), the newly calculated perceived temperature parameter value is compared with historical data to redefine the boundary values ​​between different perceived ambient temperatures (e.g., "cold," "comfortable," and "hot"). Suppose user Y3 feels "comfortable ambient temperature" in a morning environment with a temperature of 22°C and 50% humidity, and the calculated perceived temperature parameter value at that time is 0.5. This perceived temperature parameter value and the user's feeling are stored in the historical perceived temperature data table. In the afternoon, in an environment with a temperature of 22°C and 50% humidity, the user reports feeling "high ambient temperature," and the recalculated perceived temperature parameter value remains 0.5. However, because user Y3's comfort preference has changed, it is necessary to adjust the boundary values ​​between different perceived ambient temperatures. For example, the comfortable ambient temperature range in the morning is [-0.6, 0.6], and the comfortable ambient temperature range in the afternoon is adjusted to [-0.9, 0.4].

[0126] After updating the distribution table of perceived comfort values ​​for all users within the temperature-controlled area, all users are clustered into multiple user groups based on specific perceived comfort intervals to identify user groups with similar perceived comfort needs. Subsequently, specific perceived comfort intervals for each group are generated to determine the shared perceived comfort needs of each user group. Then, specific perceived comfort intervals for the entire region are generated based on the specific perceived comfort intervals for each group to obtain the shared perceived comfort needs of all users in the entire temperature-controlled area. Finally, based on these shared perceived comfort needs and reinforcement learning of the current air conditioning operation mode, the environmental conditions are changed to a range that everyone feels comfortable in.

[0127] According to the technical solution of the present invention, personalized temperature control services can be provided for different user groups, improving user satisfaction. Furthermore, by dynamically adjusting the boundary values ​​of the user's ambient temperature perception range to optimize the perceived temperature range, unnecessary energy consumption can be reduced while ensuring user comfort.

[0128] Specifically, step 76 includes:

[0129] Determine if there is any overlap in the specific sensory intervals of all groups. If there is, use the overlapping area as the specific sensory interval of the region. If not, obtain the number of users in each user group, set the weight parameter for each user group based on the number of users, and perform a weighted average of the upper and lower limits of the specific sensory interval of the group based on the weight parameter to generate the specific sensory interval of the region.

[0130] The overlapping areas of specific sensory ranges for different user groups represent the common needs of different user groups. If there are no overlapping areas, generating specific sensory ranges for different user groups by obtaining the number of users in each user group and setting weight parameters based on the number of users can make the final sensory range more representative of the needs and preferences of most users, better balance the needs of different user groups, achieve a fairer allocation of resources among different user groups, and help improve the efficiency and user satisfaction of the entire building temperature control system.

[0131] As a preferred technical solution of the present invention, in step 6 or step 7, when storing the air conditioner operation mode and the first control reference sequence in the historical operation data table, the average value of each parameter value of the original control parameter sequence and the first control reference sequence corresponding to the air conditioner operation mode is calculated, and the control parameter sequence obtained after averaging is stored in correspondence with the air conditioner operation mode.

[0132] Based on this, while reducing the amount of data stored, the stored control parameter sequence can be made more stable and reliable, improving the quality of historical operating data and enhancing robustness in the face of environmental changes and changes in user behavior.

[0133] Figure 2 The diagram shown is a structural schematic of an embodiment of the distributed control load control system based on user random behavior provided by the present invention. Figure 2 As shown, the system includes: a region division module 10, a data acquisition module 20, an information judgment module 30, a first control module 40, a second control module 50, an adjustment judgment module 60, and a control adjustment module 70.

[0134] The zone division module 10 is used to obtain detailed floor plans of the building and divide the building into multiple temperature-controlled zones based on the building's physical structure.

[0135] The data acquisition module 20 is used to extract any temperature control zone, acquire user information and environmental information of any temperature control zone, and generate a first control reference sequence based on the user information and environmental information.

[0136] The information judgment module 30 is used to traverse the historical operation data table according to the first control reference sequence and determine whether there is a control reference sequence in the historical operation data table that has a similarity greater than the first preset value to the first control reference sequence. If yes, it enters the first control module 40; otherwise, it enters the second control module 50.

[0137] The first control module 40 is used to define the control reference sequence corresponding to the maximum similarity as the second control reference sequence, take the air conditioning operation mode corresponding to the second control reference sequence as the first air conditioning operation mode of any temperature control area, generate a first temperature control command based on the first air conditioning operation mode, and send the first temperature control command to the corresponding air conditioning equipment.

[0138] The second control module 50 is used to obtain the first temperature control mode corresponding to any temperature control zone according to the identification information of any temperature control zone, generate the second air conditioning operation mode of any temperature control zone based on user information and the first temperature control mode, generate the second temperature control command based on the second air conditioning operation mode, and send the second temperature control command to the corresponding air conditioning equipment.

[0139] The adjustment judgment module 60 is used to periodically determine whether user feedback information has been received. If not, the current air conditioning operation mode is stored in the historical operation data table corresponding to the first control reference sequence. If yes, the control adjustment module 70 is entered, where the current air conditioning operation mode is either the first air conditioning operation mode or the second air conditioning operation mode.

[0140] The control adjustment module 70 is used to generate a third air conditioning operation mode for any temperature control zone based on feedback information, generate a third temperature control command based on the third air conditioning operation mode, send the third temperature control command to the corresponding air conditioning equipment, and then store the third air conditioning operation mode in the historical operation data table in correspondence with the first control reference sequence.

[0141] It should be understood that although the steps in the flowcharts of the various embodiments of the present invention are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the various embodiments may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least a portion of the sub-steps or stages of other steps.

[0142] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0143] The above-described embodiments merely illustrate preferred embodiments of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention.

Claims

1. A distributed control method for control load based on user random behavior, characterized in that, Includes the following steps: Step 1: Divide the building into multiple temperature-controlled zones based on its physical structure; Step 2: Obtain user information and environmental information for any temperature control zone, and generate a first control reference sequence based on the user information and the environmental information; Step 3: Determine whether there is a control reference sequence in the historical operation data table that has a similarity greater than the first preset value to the first control reference sequence. If yes, proceed to step 4; otherwise, proceed to step 5. Step 4: Define the control reference sequence corresponding to the maximum similarity as the second control reference sequence, take the air conditioning operation mode corresponding to the second control reference sequence as the first air conditioning operation mode of any temperature control area, generate a first temperature control command based on the first air conditioning operation mode, and send it to the corresponding air conditioning equipment. Step 5: Obtain the corresponding first temperature control mode based on the identification information of any of the temperature control zones; generate a second air conditioning operation mode based on the user information and the first temperature control mode; generate a second temperature control command based on the second air conditioning operation mode; and send it to the corresponding air conditioning equipment. Step 6: Periodically determine whether user feedback information has been received. If yes, proceed to step 7. If no, store the current air conditioning operation mode in the historical operation data table corresponding to the first control reference sequence. Step 7: Generate a third air conditioning operation mode for any of the temperature control zones based on the feedback information, generate a third temperature control command based on the third air conditioning operation mode, and send it to the corresponding air conditioning equipment. Then, store the third air conditioning operation mode in the historical operation data table in correspondence with the first control reference sequence. Step 7 includes: Step 71: Define the user who sent the feedback information as the first user, and calculate the somatosensory parameter value of any first user based on the personal information of any first user and the environmental information; Step 72: Based on the user identifier of any first user, obtain the first somatosensory value distribution table of any first user from the historical somatosensory data table; Step 73: Based on the feedback information and the somatosensory parameter value of any of the first users, determine whether a specific somatosensory interval in the first somatosensory value distribution table has changed. If so, update the first somatosensory value distribution table based on the feedback information and the somatosensory parameter value. Step 74: After traversing all first users, extract the distribution table of the body sensation values ​​of all users in any of the temperature control areas, and cluster all users based on the specific body sensation interval to divide them into multiple user groups; Step 75: Extract any user group, calculate the first average of the lower limit of the specific somatosensory interval and the second average of the upper limit of the specific somatosensory interval for all users in the user group, and generate the specific somatosensory interval for the group based on the first average and the second average. Step 76: After traversing all user groups, generate a specific somatosensory interval for the region based on the specific somatosensory interval of the group. Step 77: Based on the specific sensory range of the region, learn the current air conditioning operation mode to generate the third air conditioning operation mode, so that the sensory parameter values ​​of all users fall within the specific sensory range of the region.

2. The method according to claim 1, characterized in that, First environmental information is collected through a data acquisition device, and the method for acquiring the environmental information is as follows: Obtain the device identifier of the data acquisition device, and extract the calibration function corresponding to the data acquisition device from the calibration function table based on the device identifier; Obtain the first environmental value and acquisition time from the first environmental information, calculate the calibration value based on the calibration function, the first environmental value and the acquisition time, and use the sum of the calibration value and the first environmental value as the second environmental value of the data acquisition device; The environmental information is generated based on the device identifier, the second environmental value, and the collection time.

3. The method according to claim 2, characterized in that, The calibration function is generated as follows: Step 21: Perform calibration tests on the data acquisition device at preset time intervals, obtain test results, and store the test results in a calibration information table corresponding to the device identifier. The test results include actual values, measured values, and calibration time. Step 22: When the test result is received, determine whether the number of all test results corresponding to the device identifier in the calibration information table is 1. If so, calculate the initial calibration value based on the test result, assign the initial calibration value to the calibration function, and store the calibration function and the device identifier in the calibration function table accordingly. If not, proceed to step 23. Step 23: Extract all the test results corresponding to the device identifier from the calibration information table, perform machine learning on all the test results to generate a new calibration function, and update the calibration function table based on the new calibration function.

4. The method according to claim 1, characterized in that, Step 2 includes: obtaining air conditioning equipment information for any of the temperature control zones, and dividing any of the temperature control zones into multiple sub-zones based on the air conditioning equipment information.

5. The method according to claim 4, characterized in that, The user information includes the number of users and user location information. The method for generating the temperature control mode is as follows: Step 511: Extract any of the temperature control zones, and divide the air conditioning setting conditions of any of the temperature control zones into N types based on the user information; Step 512: Extract any air conditioning setting condition and obtain the building structure information corresponding to any of the air conditioning setting conditions. Based on any of the air conditioning setting conditions and the building structure information, generate M fourth air conditioning operation modes according to preset standards. The fourth air conditioning operation mode includes the temperature setting and fan speed setting of the air conditioning equipment related to the sub-area corresponding to any of the air conditioning setting conditions. Step 513: Calculate the energy consumption reduction rate corresponding to any fourth air conditioning operation mode; Step 514: After traversing all the fourth air conditioning operation modes, sort all the fourth air conditioning operation modes in descending order of energy consumption reduction rate; Step 515: After traversing all air conditioning settings, group the fourth air conditioning operating modes with the same serial number in different air conditioning settings into one group. Step 516: Assign identifiers to all the fourth air conditioning operation modes after grouping and processing, and then generate K temperature control modes based on the air conditioning operation modes after assigning identifiers.

6. The method according to claim 1, characterized in that, Before step 5, the administrator sets the first temperature control mode of any of the temperature control zones, or dynamically sets the first temperature control mode of any of the temperature control zones according to a time period.

7. The method according to claim 1, characterized in that, Step 76 includes: Determine whether there is an overlapping area among the specific sensory intervals of all groups. If there is, the overlapping area is taken as the specific sensory interval of the region. If not, obtain the number of users in each user group, set the weight parameter for each user group based on the number of users, and perform a weighted average of the upper and lower limits of the specific sensory interval of the group based on the weight parameter to generate the specific sensory interval of the region.

8. A distributed control system for control load based on user random behavior, used to implement the method as described in any one of claims 1 to 7, characterized in that, include: The module includes a region division module, a data acquisition module, an information judgment module, a first control module, a second control module, an adjustment judgment module, and a control adjustment module. The area division module is used to obtain a detailed floor plan of the building and divide the building into multiple temperature control zones based on the building's physical structure. The data acquisition module is used to extract any temperature control zone, acquire user information and environmental information of any temperature control zone, and generate a first control reference sequence based on the user information and the environmental information. The information judgment module is used to traverse the historical operation data table according to the first control reference sequence, and determine whether there is a control reference sequence in the historical operation data table that has a similarity greater than a first preset value to the first control reference sequence. If yes, then proceed to the first control module; otherwise, proceed to the second control module. The first control module is configured to define the control reference sequence corresponding to the maximum similarity as the second control reference sequence, take the air conditioning operation mode corresponding to the second control reference sequence as the first air conditioning operation mode of any temperature control area, generate a first temperature control command based on the first air conditioning operation mode, and send the first temperature control command to the corresponding air conditioning equipment. The second control module is used to obtain the first temperature control mode corresponding to any temperature control zone according to the identification information of any temperature control zone, generate a second air conditioning operation mode for any temperature control zone based on the user information and the first temperature control mode, generate a second temperature control command based on the second air conditioning operation mode, and send the second temperature control command to the corresponding air conditioning equipment. The adjustment judgment module is used to periodically determine whether user feedback information has been received. If not, the current air conditioner operation mode is stored in the historical operation data table corresponding to the first control reference sequence. If yes, the control adjustment module is entered, wherein the current air conditioner operation mode is the first air conditioner operation mode or the second air conditioner operation mode. The control adjustment module is used to generate a third air conditioning operation mode for any of the temperature control zones based on the feedback information, generate a third temperature control command based on the third air conditioning operation mode, send the third temperature control command to the corresponding air conditioning equipment, and then store the third air conditioning operation mode in the historical operation data table in correspondence with the first control reference sequence.

Images