A method for predicting air conditioning cooling load based on IoT big data and AI

Through IoT big data and AI technology, combined with energy balance principle and cosine function modeling, the problem of poor prediction effect of existing air conditioner cooling load prediction methods in multi-factor models is solved, and the refined prediction of air conditioner load is achieved. Reduces energy waste and operating costs.

CN118705730BActive Publication Date: 2024-11-12NANJING DEEPCTRLS TECHNOLOGIES CO LTD
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
CN202411195485.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-29
Publication Date
2024-11-12
Estimated Expiration
2044-08-29

AI Technical Summary

Technical Problem

The existing air conditioner cooling load prediction method has poor prediction effect when dealing with models of multiple influencing factors, and it is difficult to effectively deal with external weather changes and fluctuations in internal activity patterns, resulting in energy waste and operational cost control problems.

Method used

Using a method based on IoT big data and AI, the energy balance equation of air conditioning load is constructed by obtaining the internal and external heat transfer, thermal conductivity and heating speed of the building, combined with the principle of energy balance, and using cosine function to model outdoor temperature and number of people changes , predict air conditioning load demand.

Benefits of technology

It improves the refinement and accuracy of air conditioning load prediction, helps to automatically adjust the operating strategies of air conditioning systems, reduces energy waste, and achieves the dual goals of energy conservation and emission reduction and operational cost control.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118705730B_ABST
    Figure CN118705730B_ABST
Patent Text Reader

Abstract

A method for predicting air conditioning cooling load based on IoT big data and AI, the method comprising: calculating the heat conduction rate of the target building based on the heat transferred between the inside and outside of the target building in unit time, and calculating the heat generation rate in the target building. According to the energy balance principle, the energy balance equation for the air conditioning load is established in combination with the heat conduction rate and the heat generation rate. The number of people in the target building at different times is obtained to construct a functional relationship of the indoor number of people over time, the outdoor temperature at different times is obtained, and the cosine function is used to construct a functional relationship of the outdoor temperature over time. Based on the functional relationship of the indoor number of people over time and the functional relationship of the outdoor temperature over time, the functional relationship of the air conditioning load over time is constructed in combination with the energy balance equation. The functional relationship of the air conditioning load over time is called to calculate and predict the air conditioning load in the target building corresponding to the indoor number of people and the outdoor temperature at any time.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of artificial intelligence and air conditioning data prediction, and more specifically, relates to an air conditioning cooling load prediction method based on Internet of Things big data and AI. Background Art

[0002] With changes in external weather conditions (such as high temperatures in summer) and fluctuations in activity patterns within buildings (differences in traffic between weekdays and weekends, mornings and evenings), the energy demand of the air conditioning system will fluctuate significantly. Predicting the air conditioning load helps to automatically adjust the air conditioning system operation strategy, such as pre-adjusting to energy-saving mode during expected low-load periods, or pre-cooling and storing cold capacity before high demand, thereby effectively avoiding energy waste and achieving the dual goals of energy conservation and emission reduction and operating cost control.

[0003] The air conditioning system can be composed of one or more air conditioners. The objects in the building space can be divided into two categories, one is fixed objects, such as walls, floors, tables and chairs, etc.; the other is mobile objects, mainly people. Applicable environments include home environments, shopping malls, companies, schools and other scenes. At present, in the prediction methods of air conditioning cooling load, most of them are based on algorithms. Most algorithms have high requirements on the regularity of original data, and the prediction effect is poor when processing models with multiple influencing factors or models with too large data samples. In this regard, the present invention proposes a method for predicting air conditioning cooling load based on Internet of Things big data and AI. By integrating multi-source information such as building physical characteristics, real-time meteorological data, changes in the number of people inside, and using physical modeling and energy balance principles, the real-time and future load requirements of air conditioning are refined and predicted, thereby improving the effect of air conditioning load prediction in buildings. Summary of the invention

[0004] In order to solve the deficiencies in the prior art, the purpose of the present invention is to solve the above-mentioned defects and further propose an air conditioning cooling load prediction method based on Internet of Things big data and AI.

[0005] The present invention adopts the following technical solution.

[0006] The first aspect of the present invention discloses a method for predicting air conditioning cooling load based on Internet of Things big data and AI, the method comprising:

[0007] Acquire the amount of heat transferred between the inside and outside of a target building within a unit time, and calculate the heat conduction rate of the target building based on the amount of heat transferred between the inside and outside of the target building within the unit time, and calculate the heat generation rate within the target building;

[0008] According to the energy balance principle, combining the heat conduction speed and the heat generation speed, an energy balance equation for the air conditioning load is established;

[0009] Obtaining the number of people in the target building at different times to construct a functional relationship of the indoor number of people changing with time, and obtaining the outdoor temperature at different times, and using a cosine function to construct a functional relationship of the outdoor temperature changing with time;

[0010] Based on the functional relationship of the indoor number of people changing over time and the functional relationship of the outdoor temperature changing over time, combined with the energy balance equation, construct a functional relationship of the air conditioning load changing over time;

[0011] Calling the functional relationship of the air conditioning load changing over time to calculate and predict the air conditioning load in the target building corresponding to the number of people indoors and the outdoor temperature at any time;

[0012] Among them, the heat transferred between the inside and outside of the target building includes the heat transferred from the inside to the outside of the target building and the heat transferred from the outside to the inside of the target building. The heating rate includes the heating rate of the human body and the heating rate of the equipment. The equipment heating rate is the heating rate of the electrical equipment. The energy balance equation is the ratio between the absolute value of the sum of the heat conduction rate and the heating rate and the air conditioning energy efficiency ratio.

[0013] Furthermore, the step of obtaining the amount of heat transferred between the inside and outside of the target building within a unit time, and calculating the heat conduction rate of the target building based on the amount of heat transferred between the inside and outside of the target building within the unit time, and calculating the heat generation rate within the target building, includes:

[0014] When the outdoor temperature of the target building is higher than the indoor temperature of the target building, obtaining the amount of heat transferred from the outside to the inside of the target building per unit time, and calculating the heat transfer rate based on the amount of heat transferred from the outside to the inside of the target building per unit time; and

[0015] When the indoor temperature of the target building is higher than the outdoor temperature of the target building, obtaining the amount of heat transferred from the inside to the outside of the target building in a unit time, and calculating the heat transfer rate based on the amount of heat transferred from the inside to the outside of the target building in the unit time;

[0016] Wherein, the calculation formula of the heat conduction rate is:

[0017] ;

[0018] In the formula, is the outdoor temperature, is the indoor temperature, is the heat conduction rate of the target building, is a thermal conductivity factor, which depends on the material and door and window structure of the target building;

[0019] The thermal conductivity factor The calculation formula is:

[0020] ;

[0021] In the formula, is the thermal conductivity of the wall of the target building, is the surface area of ​​the wall, is the thermal conductivity of the door and window structure, It is the area of ​​the door and window structure.

[0022] Furthermore, the step of obtaining the amount of heat transferred between the inside and outside of a target building within a unit time, and calculating the heat conduction rate of the target building based on the amount of heat transferred between the inside and outside of the target building within the unit time, and calculating the heat generation rate within the target building, further includes:

[0023] According to the ASHRAE standard, the human body heating rate of each person is obtained and the human body heating rate is calculated. The calculation formula of the human body heating rate is:

[0024] ;

[0025] In the formula, is the heating rate of each person in the ASHRAE standard. is the number of people in the target building, is the heating speed of the human body;

[0026] The power consumption of each electrical device in the target building and the heat dissipation index of each electrical device are obtained, and the heating speed of the device is calculated based on the power consumption and the heat dissipation index of the electrical device. The calculation formula of the heating speed of the device is:

[0027] ;

[0028] In the formula, is the power consumption of each electrical device in the target building, is the heat dissipation index of each electrical equipment, The speed at which the device generates heat.

[0029] Furthermore, the method further comprises:

[0030] Obtaining heat dissipation indexes, air conditioning energy efficiency ratios, and actual air conditioning power consumption of multiple electrical equipment in the target building, and constructing a sample data set based on the heat dissipation indexes, air conditioning energy efficiency ratios, and actual air conditioning power consumption;

[0031] Based on the sample data set, the heat dissipation index and the air conditioner energy efficiency ratio are used as the input of the long short-term memory network model, and the actual power consumption of the air conditioner is used as the output of the long short-term memory network model, and the long short-term memory network model is trained. The trained long short-term memory network model is used to determine the heat dissipation index of each electrical equipment in the target building.

[0032] Furthermore, according to the energy balance principle, in combination with the heat conduction rate and the heat generation rate, an energy balance equation for the air conditioning load is established, including:

[0033] Based on the heat conduction rate of the target building and the heating rate of the human body and the heating rate of the equipment in the target building, an energy balance equation for the air conditioning load is constructed, and the energy balance equation is:

[0034] ;

[0035] In the formula, is the air conditioning energy efficiency ratio, which is the ratio between the heat transported by the air conditioning equipment per unit time and the amount of electricity consumed, is the heat conduction rate of the target building, is the human body heating rate, Indicates the heating rate of the device. It is the absolute value of the sum of the heat conduction rate, the human body heating rate and the equipment heating rate.

[0036] Furthermore, the obtaining of the number of people in the target building at different times to construct a functional relationship of the number of people indoors changing with time, and the obtaining of the outdoor temperature at different times, and the use of a cosine function to construct a functional relationship of the outdoor temperature changing with time, include:

[0037] Based on the number of people in the target building at different times, a function of the number of people indoors changing with time is constructed. The function expression of the number of people indoors changing with time is:

[0038] ;

[0039] In the formula, is the number of people in the room, t is any moment, is the number of people indoors at time t;

[0040] A cosine function is used to construct a function of the outdoor temperature changing with time during the day according to the outdoor temperature at different times. The function expression of the outdoor temperature changing with time is:

[0041] ;

[0042] In the formula, is the outdoor temperature, Any time of the day, in hours. is the outdoor temperature corresponding to time t, is the highest outdoor temperature of the day, The lowest outdoor temperature of the day.

[0043] Furthermore, the functional relationship of the indoor number of people changing over time and the functional relationship of the outdoor temperature changing over time, combined with the energy balance equation, constructs the functional relationship of the air conditioning load changing over time, including:

[0044] Based on the energy balance equation, the number of people in the human body heating rate calculation formula in the energy balance equation is replaced by a function of the number of people in the room changing over time; and

[0045] Replacing the outdoor temperature in the heat transfer rate in the energy balance equation with a function of the outdoor temperature changing with time, to obtain a function of the air conditioning load changing with time;

[0046] The function expression of the air conditioning load changing with time is:

[0047] ;

[0048] In the formula, is the air conditioning load, t is any time of the day, is the air conditioning load corresponding to time t, is the thermal conductivity factor of the target building, is the outdoor temperature corresponding to time t, is the indoor temperature, is the number of people indoors at time t, is the heating rate of each person in the ASHRAE standard. Indicates the heating speed of the device. is the energy efficiency ratio of air conditioning.

[0049] The second aspect of the present invention discloses an air conditioning cooling load prediction device based on Internet of Things big data and AI, the device comprising:

[0050] A heating rate calculation module, used to obtain the amount of heat transferred between the inside and outside of a target building in a unit time, and calculate the heat conduction rate of the target building based on the amount of heat transferred between the inside and outside of the target building in the unit time, and calculate the heating rate in the target building;

[0051] An energy balance equation establishment module is used to establish an energy balance equation for air conditioning load according to the energy balance principle and in combination with the heat conduction speed and the heat generation speed;

[0052] A functional relationship building module is used to obtain the number of people in the target building at different times to build a functional relationship of the indoor number of people changing with time, and to obtain the outdoor temperature at different times and use a cosine function to build a functional relationship of the outdoor temperature changing with time;

[0053] An air conditioning load function construction module, used to construct a functional relationship of the air conditioning load changing over time based on the functional relationship of the indoor number of people changing over time and the functional relationship of the outdoor temperature changing over time, combined with the energy balance equation;

[0054] An air conditioning load prediction module, used to call the functional relationship of the air conditioning load changing over time to calculate and predict the air conditioning load in the target building corresponding to the number of people indoors and the outdoor temperature at any time;

[0055] Among them, the heat transferred between the inside and outside of the target building includes the heat transferred from the inside to the outside of the target building and the heat transferred from the outside to the inside of the target building. The heating rate includes the heating rate of the human body and the heating rate of the equipment. The equipment heating rate is the heating rate of the electrical equipment. The energy balance equation is the ratio between the absolute value of the sum of the heat conduction rate and the heating rate and the air conditioning energy efficiency ratio.

[0056] The third aspect of the present invention discloses a terminal, including a processor and a storage medium; the characteristics are:

[0057] The storage medium is used to store instructions;

[0058] The processor is used to operate according to the instructions to execute the steps of the method described in the first aspect.

[0059] The fourth aspect of the present invention discloses a computer-readable storage medium having a computer program stored thereon, characterized in that when the program is executed by a processor, the steps of the method described in the first aspect are implemented.

[0060] The beneficial effects of the present invention are that, compared with the prior art, the present invention has the following advantages:

[0061] By obtaining the heat transferred between the inside and outside of the target building in unit time, the heat conduction speed of the target building is calculated based on the heat transferred between the inside and outside of the target building in unit time, and the heat generation speed in the target building is calculated. Then, according to the energy balance principle, combined with the pre-calculated heat conduction speed and heat generation speed, the energy balance equation for the air conditioning load is established. Subsequently, the number of people in the target building at different times is obtained to construct the functional relationship of the indoor number of people changing with time, and the outdoor temperature at different times is obtained, and the cosine function is used to construct the functional relationship of the outdoor temperature changing with time. Finally, based on the functional relationship of the indoor number of people changing with time and the functional relationship of the outdoor temperature changing with time, combined with the energy balance equation, the functional relationship of the air conditioning load changing with time is constructed, and the functional relationship of the air conditioning load changing with time can be called to calculate and predict the air conditioning load in the target building corresponding to the indoor number of people and the outdoor temperature at any time. This method integrates multi-source information such as building physical characteristics, real-time meteorological data, and internal number changes, and uses physical modeling and energy balance principles to finely predict the real-time and future load requirements of air conditioning, thereby improving the effect of building air conditioning load prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 It is a flow chart of an air conditioning cooling load prediction method based on IoT big data and AI. DETAILED DESCRIPTION

[0063] The present application is further described below in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and cannot be used to limit the protection scope of the present application.

[0064] like Figure 1 As shown, in one embodiment, a method for predicting air conditioning cooling load based on IoT big data and AI comprises the following steps:

[0065] Step S110, obtaining the amount of heat transferred between the inside and outside of the target building in unit time, and calculating the heat conduction rate of the target building based on the amount of heat transferred between the inside and outside of the target building in unit time, and calculating the heat generation rate in the target building.

[0066] Among them, the heat transferred between the inside and outside of the target building includes the heat transferred from the inside to the outside of the target building and the heat transferred from the outside to the inside of the target building. The heating rate includes the heating rate of the human body and the heating rate of the equipment. The equipment heating rate is the heating rate of the electrical equipment.

[0067] In some embodiments, the air conditioning cooling load prediction method based on IoT big data and AI provided by the present invention obtains the heat transferred between the inside and outside of the target building per unit time, and calculates the heat conduction speed of the target building based on the heat transferred between the inside and outside of the target building per unit time, and calculates the heat generation speed in the target building, specifically including the following steps:

[0068] Step S111, when the outdoor temperature of the target building is higher than the indoor temperature of the target building, the heat transferred from the outside to the inside of the target building per unit time is obtained, and the heat transfer rate is calculated based on the heat transferred from the outside to the inside of the target building per unit time.

[0069] Step S112, when the indoor temperature of the target building is higher than the outdoor temperature of the target building, the heat transferred from the inside to the outside of the target building in unit time is obtained, and the heat transfer rate is calculated based on the heat transferred from the inside to the outside of the target building in unit time.

[0070] The calculation formula of heat conduction rate is:

[0071] .

[0072] In the formula, is the outdoor temperature, is the indoor temperature, is the heat conduction rate of the target building, is the thermal conductivity factor, which depends on the material and door and window structure of the target building.

[0073] Thermal conductivity factor The calculation formula is:

[0074] .

[0075] In the formula, is the thermal conductivity of the target building’s wall, is the surface area of ​​the wall, is the thermal conductivity of the door and window structure, It is the area of ​​the door and window structure.

[0076] In some embodiments, the air conditioning cooling load prediction method based on IoT big data and AI provided by the present invention obtains the heat transferred between the inside and outside of the target building per unit time, and calculates the heat conduction rate of the target building based on the heat transferred between the inside and outside of the target building per unit time, and calculates the heat generation rate in the target building, and specifically also includes the following steps:

[0077] Step S113, obtaining the human body heating rate of each person according to the ASHRAE standard, and calculating the human body heating rate. The calculation formula of the human body heating rate is:

[0078] .

[0079] In the formula, is the heating rate of each person in the ASHRAE standard. is the number of people in the target building, The rate at which the human body generates heat.

[0080] Step S114, obtaining the power consumption of each electrical device in the target building and the heat dissipation index of each electrical device, and calculating the heating speed of the device based on the power consumption and heat dissipation index of the electrical device. The calculation formula of the heating speed of the device is:

[0081] .

[0082] In the formula, is the power consumption of each electrical device in the target building, is the heat dissipation index of each electrical equipment, The heating speed of the device.

[0083] In some embodiments, the air conditioning cooling load prediction method based on IoT big data and AI provided by the present invention further includes the following steps:

[0084] Step S210, obtaining heat dissipation index, air conditioning energy efficiency ratio and actual air conditioning power consumption of multiple electrical equipment in the target building, and constructing a sample data set based on the heat dissipation index, air conditioning energy efficiency ratio and actual air conditioning power consumption.

[0085] Step S220, based on the sample data set, the heat dissipation index and the air conditioner energy efficiency ratio are used as the input of the long short-term memory network model, and the actual power consumption of the air conditioner is used as the output of the long short-term memory network model, and the long short-term memory network model is trained. The trained long short-term memory network model is used to determine the heat dissipation index of each electrical equipment in the target building.

[0086] Step S120: According to the energy balance principle, an energy balance equation for the air conditioning load is established by combining the heat conduction speed and the heat generation speed.

[0087] Among them, the energy balance equation is the ratio between the absolute value of the sum of the heat conduction rate and the heat generation rate and the air conditioning energy efficiency ratio.

[0088] In some embodiments, the air conditioning cooling load prediction method based on IoT big data and AI provided by the present invention establishes an energy balance equation for the air conditioning load based on the energy balance principle and in combination with the heat conduction rate and the heat generation rate, specifically including the following steps:

[0089] Step S121, based on the heat conduction rate of the target building and the heating rate of the human body and the heating rate of the equipment in the target building, an energy balance equation for the air conditioning load is constructed. The energy balance equation is:

[0090] .

[0091] In the formula, The air conditioning energy efficiency ratio is the ratio between the heat transported by the air conditioning equipment per unit time and the amount of electricity consumed. is the heat conduction rate of the target building, The rate at which the human body heats up. Indicates the heating speed of the device. It is the absolute value of the sum of the heat conduction rate, the human body heating rate and the equipment heating rate.

[0092] Step S130, obtaining the number of people in the target building at different times to construct a functional relationship of the indoor number of people changing with time, and obtaining the outdoor temperature at different times, and using a cosine function to construct a functional relationship of the outdoor temperature changing with time.

[0093] In some embodiments, the air conditioning cooling load prediction method based on IoT big data and AI provided by the present invention obtains the number of people in the target building at different times to construct a functional relationship between the number of people indoors and time, and obtains the outdoor temperature at different times, and uses a cosine function to construct a functional relationship between the outdoor temperature and time, specifically including the following steps:

[0094] Step S131, based on the number of people in the target building at different times, construct a function of the number of people indoors changing with time, and the function expression of the number of people indoors changing with time is:

[0095] .

[0096] In the formula, is the number of people in the room, t is any moment, is the number of people indoors at time t.

[0097] Step S132, using the cosine function to construct a function of the outdoor temperature changing with time during the day according to the outdoor temperature at different times, the function expression of the outdoor temperature changing with time is:

[0098] .

[0099] In the formula, is the outdoor temperature, Any time of the day, in hours. is the outdoor temperature corresponding to time t, is the highest outdoor temperature of the day, The lowest outdoor temperature of the day.

[0100] Step S140, based on the functional relationship of the indoor number of people changing with time and the functional relationship of the outdoor temperature changing with time, combined with the energy balance equation, construct a functional relationship of the air conditioning load changing with time.

[0101] In some embodiments, the air conditioning cooling load prediction method based on IoT big data and AI provided by the present invention is based on the functional relationship between the number of people indoors and the time and the functional relationship between the outdoor temperature and the time, combined with the energy balance equation, to construct the functional relationship between the air conditioning load and the time, specifically including the following steps:

[0102] Step S141, based on the energy balance equation, the number of people in the human body heating rate calculation formula in the energy balance equation is replaced by a function of the number of people in the room changing with time.

[0103] Step S142, replacing the outdoor temperature in the heat transfer rate in the energy balance equation with a function of the outdoor temperature changing with time, to obtain a function of the air conditioning load changing with time.

[0104] Among them, the function expression of air conditioning load changing with time is:

[0105] .

[0106] In the formula, is the air conditioning load, t is any time of the day, is the air conditioning load corresponding to time t, is the thermal conductivity factor of the target building, is the outdoor temperature corresponding to time t, is the indoor temperature, is the number of people indoors at time t, is the heating rate of each person in the ASHRAE standard. Indicates the heating speed of the device. is the energy efficiency ratio of air conditioning.

[0107] Step S150, calling the functional relationship of the air conditioning load changing with time to calculate and predict the air conditioning load in the target building corresponding to the number of people indoors and the outdoor temperature at any time.

[0108] The above-mentioned air conditioning cooling load prediction method based on IoT big data and AI obtains the heat transferred between the inside and outside of the target building in unit time, and calculates the heat conduction speed of the target building based on the heat transferred between the inside and outside of the target building in unit time, as well as the heat generation speed in the target building. Then, according to the energy balance principle, combined with the pre-calculated heat conduction speed and heat generation speed, an energy balance equation for the air conditioning load is established. Subsequently, the number of people in the target building at different times is obtained to construct a functional relationship of the indoor number of people changing with time, and the outdoor temperature at different times is obtained, and the cosine function is used to construct a functional relationship of the outdoor temperature changing with time. Finally, based on the functional relationship of the indoor number of people changing with time and the functional relationship of the outdoor temperature changing with time, combined with the energy balance equation, the functional relationship of the air conditioning load changing with time is constructed, and the functional relationship of the air conditioning load changing with time can be called to calculate and predict the air conditioning load in the target building corresponding to the indoor number of people and the outdoor temperature at any time. This method integrates multi-source information such as building physical characteristics, real-time meteorological data, and internal number changes, and uses physical modeling and energy balance principles to finely predict the real-time and future load requirements of air conditioning, thereby improving the effect of building air conditioning load prediction.

[0109] In a specific embodiment, the present invention provides an air conditioning cooling load prediction method based on IoT big data and AI. With the changes in external weather conditions (such as high temperature periods in summer) and fluctuations in activity patterns inside buildings (differences in traffic between weekdays and weekends, mornings and evenings), the energy demand of the air conditioning system will fluctuate significantly. Predicting the air conditioning load helps to automatically adjust the air conditioning system operation strategy, such as pre-adjusting to energy-saving mode during expected low-load periods, or pre-refrigerating and storing cold capacity before high demand, thereby effectively avoiding energy waste and achieving the dual goals of energy conservation and emission reduction and operating cost control. In addition, the method can also assist facility managers in making long-term equipment upgrade and expansion decisions to ensure the long-term and efficient operation of the air conditioning system and meet green building certification requirements.

[0110] In this embodiment, two technologies are used to predict the air conditioning cooling load. One is the Energy Balance Model, which means that the heat generation and loss in the building should be equal while ensuring the constant temperature in the building. The other technology is a physical model based on thermodynamics, which describes the heat generation and transfer process. The input of the air conditioning cooling load prediction includes: (1) the temperature outside the building; (2) the target temperature in the building; (3) the building material; (4) the number of people; (5) the air conditioning energy efficiency ratio. The output is: theoretical load.

[0111] In this embodiment, physical environment modeling is first required. The purpose of physical environment modeling is to quantify the heat transfer process in a building. The model includes three parts. The first part is the heat conduction rate between the inside and outside of the building, the second part is the heat generation rate in the building, and the third part is to establish an energy balance equation.

[0112] Calculate the heat conduction rate of a building: The heat conduction rate refers to the amount of heat transferred from the inside of a building to the outside per unit time, measured in watts. In summer, the outdoor temperature is higher than the indoor temperature, and heat is transferred from the outside to the inside; in winter, the outdoor temperature is lower than the indoor temperature, and heat is transferred from the inside to the outside. Assuming that the outdoor temperature is To and the indoor temperature is Ti, both the outdoor temperature and the indoor temperature can be obtained through temperature sensors installed inside and outside the building. The heat conduction rate of the building is represented by P1, and the expression of P1 is:

[0113] .

[0114] In the formula, is the outdoor temperature, is the indoor temperature, is the heat conduction rate of the target building, is the thermal conductivity factor, which is determined by the following factors: the material of the building, the size of the windows, and the materials of the floor and ceiling. It can be calculated by the following formula:

[0115] .

[0116] In the formula, is the thermal conductivity of the wall. If the wall is a brick wall, the value is 0.8 W / K / m^2. If it is a concrete wall, the value is 2.0 W / K / m^2. If the wall is coated with an insulation layer, the value is 0.4 W / K / m^2. S1 is the surface area of ​​the wall, which is obtained by actual measurement. is the thermal conductivity of doors and windows, and its value is 1.0 W / K / m^2; S2 is the area of ​​doors and windows, which is obtained by actual measurement.

[0117] Calculate the heating rate in a building: The heating rate in a building consists of two parts. The first part is the heating rate of the human body, and the second part is the heating rate of the equipment.

[0118] First, the human body heat dissipation rate is calculated according to the ASHRAE standard. The average heat dissipation rate of each person is 100 W. Assuming that the number of people in the building is N, the human body heat dissipation rate P2 can be calculated by the following formula:

[0119] .

[0120] In the formula, is the heating rate of each person in the ASHRAE standard. is the number of people in the target building, The rate at which the human body generates heat.

[0121] The equipment heat dissipation rate P3 is calculated by the following formula:

[0122] .

[0123] In the formula, They are the power consumption of each electrical appliance in the building, and the sum of these items is the same as the number of electrical devices there are. Indicates the heat dissipation index of each electrical appliance, which is determined by the functional attributes, volume, aging degree and other factors of each device. It is the heating rate of the overall equipment.

[0124] It should be noted that are unknown quantities, so it is necessary to combine LSTM network (Long Short-Term Memory Network Model) for learning to determine these unknown quantities. Among them, the input of sample data in LSTM network is: and , the output is: . Refers to the energy efficiency ratio of the air conditioner. Refers to the actual power consumption of the air conditioner.

[0125] ,

[0126] .

[0127] In the formula, , Index indicating the degree of aging of various electrical equipment and other indexes.

[0128] Establish energy balance equation: According to the energy balance principle, assuming that the air conditioning load is P, the following equation can be established:

[0129] .

[0130] In the formula, It is the air conditioning energy efficiency ratio, which indicates the ratio between the heat carried by the air conditioner per unit time and the amount of electricity consumed. Generally, it can be 3.5 in summer and 3.0 in winter. It is the absolute value of the sum of the heat conduction rate, the human body heating rate and the equipment heating rate.

[0131] In this embodiment, the second is the real-time calculation and prediction of the air conditioning cooling load. In the above content, a physical model has been established to calculate the air conditioning load, but in actual application scenarios, the scenario is constantly changing. For example, the number of people in the building will change, and then the air conditioning cooling load will change; the outdoor temperature is also constantly changing, and the air conditioning cooling load will also change accordingly.

[0132] Therefore, it is necessary to model the changes in the number of people and outdoor temperature over time to calculate the changes in the air conditioning cooling load over time. After calculating the changes in the air conditioning cooling load over time, two important functions can be obtained: one is to predict the future air conditioning cooling load, and the other is to calculate the average value of the air conditioning cooling load within a period of time.

[0133] First, we need to obtain the relationship between the number of people in the building and time. For example, in a home environment, there are five people living in the home. During the day, two people go to work, two people go to school, and one person is at home. At night, everyone is at home. Then, the number of people N is a function of time, which can be expressed as:

[0134] .

[0135] In the formula, is the number of people in the room, t is any moment, is the number of people indoors at time t.

[0136] In addition, the outdoor temperature To also changes with time. The cosine function can be used to represent the change of outdoor temperature during the day. The outdoor temperature at any time of the day is The expression is:

[0137] .

[0138] In the formula, is the outdoor temperature, is the outdoor temperature corresponding to time t, is the highest outdoor temperature of the day, is the lowest outdoor temperature of the day; Any time of the day in hours, for example, 00:00 corresponds to t = 0, and 07:00 corresponds to t = 7.

[0139] Except for the number of people and the outdoor temperature, other parameters can be considered as constants. Therefore, after obtaining the changes of the number of people and the outdoor temperature over time, the relationship between the change of the air conditioning load over time can be obtained, that is, the heat dissipation rate of the human body The number of people N in the figure is replaced by the number of people N(t) in the room corresponding to time t, and the heat conduction rate of the building is The outdoor temperature To in is replaced by the outdoor temperature To(t) function corresponding to time t, and the function of the air conditioning load P changing with time can be obtained. The function of the air conditioning load P changing with time is used to complete the real-time calculation and prediction of the air conditioning load. The function expression is:

[0140] .

[0141] In the formula, is the air conditioning load, t is any time of the day, is the air conditioning load corresponding to time t, is the thermal conductivity factor of the target building, is the outdoor temperature corresponding to time t, is the indoor temperature, is the number of people indoors at time t, is the heating rate of each person in the ASHRAE standard. Indicates the heating speed of the device. is the energy efficiency ratio of air conditioning.

[0142] In summary, since the materials and equipment of the building itself remain basically unchanged, the change of air conditioning load is mainly affected by the number of people and outdoor temperature. Therefore, the function of air conditioning load P changing with time has typical periodic characteristics. There are two types of cycles. One is a daily cycle, which is mainly affected by personnel changes and day and night temperature differences; the other is a yearly cycle, which is mainly affected by the temperature difference between the four seasons. This method can assist air conditioning equipment managers in making long-term equipment upgrade and expansion decisions, ensuring the long-term and efficient operation of the air conditioning system and meeting the requirements of green building certification.

[0143] The air conditioning cooling load prediction device based on the Internet of Things big data and AI provided by the present invention is described below. The air conditioning cooling load prediction device based on the Internet of Things big data and AI described below and the air conditioning cooling load prediction method based on the Internet of Things big data and AI described above can be referenced to each other.

[0144] In one embodiment, an air conditioning cooling load prediction device based on IoT big data and AI includes a heating rate calculation module, an energy balance equation establishment module, a function relationship construction module, an air conditioning load function construction module, and an air conditioning load prediction module.

[0145] The heating rate calculation module is used to obtain the heat transferred between the inside and outside of the target building per unit time, and calculate the heat conduction rate of the target building based on the heat transferred between the inside and outside of the target building per unit time, as well as the heating rate in the target building.

[0146] The energy balance equation establishment module is used to establish the energy balance equation for the air conditioning load based on the energy balance principle and in combination with the heat conduction rate and the heat generation rate.

[0147] The functional relationship construction module is used to obtain the number of people in the target building at different times to construct the functional relationship of the indoor number of people changing with time, and to obtain the outdoor temperature at different times and use the cosine function to construct the functional relationship of the outdoor temperature changing with time.

[0148] The air conditioning load function construction module is used to construct the functional relationship of the air conditioning load changing over time based on the functional relationship of the indoor number of people changing over time and the functional relationship of the outdoor temperature changing over time, combined with the energy balance equation.

[0149] The air conditioning load prediction module is used to call the functional relationship of the air conditioning load changing over time to calculate and predict the air conditioning load in the target building corresponding to the number of people indoors and the outdoor temperature at any time.

[0150] Among them, the heat transferred between the inside and outside of the target building includes the heat transferred from the inside to the outside of the target building and the heat transferred from the outside to the inside of the target building. The heating rate includes the heating rate of the human body and the heating rate of the equipment. The equipment heating rate is the heating rate of the electrical equipment. The energy balance equation is the ratio between the absolute value of the sum of the heat conduction rate and the heating rate and the air conditioning energy efficiency ratio.

[0151] In this embodiment, the air conditioning cooling load prediction device based on IoT big data and AI provided by the present invention, the heating speed calculation module is specifically used for:

[0152] When the outdoor temperature of the target building is higher than the indoor temperature of the target building, the amount of heat transferred from the outside to the inside of the target building per unit time is obtained, and the heat transfer rate is calculated based on the amount of heat transferred from the outside to the inside of the target building per unit time.

[0153] When the indoor temperature of the target building is higher than the outdoor temperature of the target building, the amount of heat transferred from the inside to the outside of the target building per unit time is obtained, and the heat conduction rate is calculated based on the amount of heat transferred from the inside to the outside of the target building per unit time.

[0154] The calculation formula of heat conduction rate is:

[0155] .

[0156] In the formula, is the outdoor temperature, is the indoor temperature, is the heat conduction rate of the target building, is the thermal conductivity factor, which depends on the material and door and window structure of the target building.

[0157] Thermal conductivity factor The calculation formula is:

[0158] .

[0159] In the formula, is the thermal conductivity of the target building’s wall, is the surface area of ​​the wall, is the thermal conductivity of the door and window structure, It is the area of ​​the door and window structure.

[0160] In this embodiment, the air conditioning cooling load prediction device based on IoT big data and AI provided by the present invention, the heating speed calculation module is specifically used for:

[0161] According to the ASHRAE standard, the human body heating rate of each person is obtained and calculated. The calculation formula of the human body heating rate is:

[0162] .

[0163] In the formula, is the heating rate of each person in the ASHRAE standard. is the number of people in the target building, The rate at which the human body generates heat.

[0164] The power consumption of each electrical device in the target building and the heat dissipation index of each electrical device are obtained, and the heating speed of the device is calculated based on the power consumption and heat dissipation index of the electrical device. The calculation formula for the heating speed of the device is:

[0165] .

[0166] In the formula, is the power consumption of each electrical device in the target building, is the heat dissipation index of each electrical equipment, The heating speed of the device.

[0167] In this embodiment, the air conditioning cooling load prediction device based on IoT big data and AI provided by the present invention further includes a model training module for:

[0168] The heat dissipation index, air conditioning energy efficiency ratio and actual air conditioning power consumption of multiple electrical equipment in the target building are obtained, and a sample data set is constructed based on the heat dissipation index, air conditioning energy efficiency ratio and actual air conditioning power consumption.

[0169] Based on the sample data set, the heat dissipation index and air conditioner energy efficiency ratio are used as the input of the long short-term memory network model, and the actual power consumption of the air conditioner is used as the output of the long short-term memory network model. The long short-term memory network model is trained. The trained long short-term memory network model is used to determine the heat dissipation index of each electrical equipment in the target building.

[0170] In this embodiment, the air conditioning cooling load prediction device based on IoT big data and AI provided by the present invention, the energy balance equation establishment module is specifically used for:

[0171] Based on the heat conduction rate of the target building and the heating rate of the human body and equipment in the target building, an energy balance equation for the air conditioning load is constructed. The energy balance equation is:

[0172] .

[0173] In the formula, The air conditioning energy efficiency ratio is the ratio between the heat transported by the air conditioning equipment per unit time and the amount of electricity consumed. is the heat conduction rate of the target building, The rate at which the human body heats up. Indicates the heating speed of the device. It is the absolute value of the sum of the heat conduction rate, the human body heating rate and the equipment heating rate.

[0174] In this embodiment, the air conditioning cooling load prediction device based on IoT big data and AI provided by the present invention, the function relationship construction module is specifically used for:

[0175] Based on the number of people in the target building at different times, a function of the number of people indoors changing over time is constructed. The function expression of the number of people indoors changing over time is:

[0176] .

[0177] In the formula, is the number of people in the room, t is any moment, is the number of people indoors at time t.

[0178] Use the cosine function to construct a function of the outdoor temperature changing with time during the day based on the outdoor temperature at different times. The function expression of the outdoor temperature changing with time is:

[0179] .

[0180] In the formula, is the outdoor temperature, Any time of the day, in hours. is the outdoor temperature corresponding to time t, is the highest outdoor temperature of the day, The lowest outdoor temperature of the day.

[0181] In this embodiment, the air conditioning cooling load prediction device based on IoT big data and AI provided by the present invention, the air conditioning load function construction module is specifically used for:

[0182] Based on the energy balance equation, the number of people in the human body heating rate calculation formula in the energy balance equation is replaced by a function of the number of people in the room changing over time.

[0183] The outdoor temperature in the heat transfer rate in the energy balance equation is replaced by the function of the outdoor temperature changing with time, and the function of the air conditioning load changing with time is obtained.

[0184] Among them, the function expression of air conditioning load changing with time is:

[0185] .

[0186] In the formula, is the air conditioning load, t is any time of the day, is the air conditioning load corresponding to time t, is the thermal conductivity factor of the target building, is the outdoor temperature corresponding to time t, is the indoor temperature, is the number of people indoors at time t, is the heating rate of each person in the ASHRAE standard. Indicates the heating speed of the device. is the energy efficiency ratio of air conditioning.

[0187] The applicant of the present invention has made a detailed explanation and description of the implementation examples of the present invention in conjunction with the drawings in the specification. However, those skilled in the art should understand that the above implementation examples are only preferred implementation schemes of the present invention, and the detailed description is only to help readers better understand the spirit of the present invention, but not to limit the scope of protection of the present invention. On the contrary, any improvements or modifications based on the inventive spirit of the present invention should fall within the scope of protection of the present invention.

Claims

1. A method for predicting air conditioning cooling load based on IoT big data and AI, characterized in that: The method comprises: Acquire the amount of heat transferred between the inside and outside of a target building within a unit time, and calculate the heat conduction rate of the target building based on the amount of heat transferred between the inside and outside of the target building within the unit time, and calculate the heat generation rate within the target building; According to the energy balance principle, combining the heat conduction speed and the heat generation speed, an energy balance equation for the air conditioning load is established; Obtaining the number of people in the target building at different times to construct a functional relationship of the indoor number of people changing with time, and obtaining the outdoor temperature at different times, and using a cosine function to construct a functional relationship of the outdoor temperature changing with time; Based on the functional relationship of the indoor number of people changing over time and the functional relationship of the outdoor temperature changing over time, combined with the energy balance equation, construct a functional relationship of the air conditioning load changing over time; Calling the functional relationship of the air conditioning load changing over time to calculate and predict the air conditioning load in the target building corresponding to the number of people indoors and the outdoor temperature at any time; The heat transferred between the inside and outside of the target building includes the heat transferred from the inside of the target building to the outside and the heat transferred from the outside of the target building to the inside. The heating rate includes the heating rate of the human body and the heating rate of the equipment. The heating rate of the equipment is the heating rate of the electrical equipment. The energy balance equation is the ratio between the absolute value of the sum of the heat conduction rate and the heating rate and the air conditioning energy efficiency ratio. The step of obtaining the amount of heat transferred between the inside and outside of a target building within a unit time, calculating the heat conduction rate of the target building based on the amount of heat transferred between the inside and outside of the target building within the unit time, and calculating the heat generation rate within the target building includes: When the outdoor temperature of the target building is higher than the indoor temperature of the target building, obtaining the amount of heat transferred from the outside to the inside of the target building per unit time, and calculating the heat transfer rate based on the amount of heat transferred from the outside to the inside of the target building per unit time; and When the indoor temperature of the target building is higher than the outdoor temperature of the target building, obtaining the amount of heat transferred from the inside to the outside of the target building in a unit time, and calculating the heat transfer rate based on the amount of heat transferred from the inside to the outside of the target building in the unit time; Wherein, the calculation formula of the heat conduction rate is: ; In the formula, is the outdoor temperature, is the indoor temperature, is the heat conduction rate of the target building, is a thermal conductivity factor, which depends on the material and door and window structure of the target building; The thermal conductivity factor The calculation formula is: ; In the formula, is the thermal conductivity of the wall of the target building, is the surface area of ​​the wall, is the thermal conductivity of the door and window structure, is the area of ​​the door and window structure; The step of obtaining the amount of heat transferred between the inside and outside of a target building within a unit time, and calculating the heat conduction rate of the target building based on the amount of heat transferred between the inside and outside of the target building within the unit time, and calculating the heat generation rate within the target building, further includes: According to the ASHRAE standard, the human body heating rate of each person is obtained and the human body heating rate is calculated. The calculation formula of the human body heating rate is: ; In the formula, is the heating rate of each person in the ASHRAE standard. is the number of people in the target building, is the heating speed of the human body; The power consumption of each electrical device in the target building and the heat dissipation index of each electrical device are obtained, and the heating speed of the device is calculated based on the power consumption and the heat dissipation index of the electrical device. The calculation formula of the heating speed of the device is: ; In the formula, is the power consumption of each electrical device in the target building, is the heat dissipation index of each electrical equipment, The heating speed of the device; The method of obtaining the number of people in the target building at different times to construct a functional relationship of the number of people indoors changing with time, and obtaining the outdoor temperature at different times and using a cosine function to construct a functional relationship of the outdoor temperature changing with time includes: Based on the number of people in the target building at different times, a function of the number of people indoors changing with time is constructed. The function expression of the number of people indoors changing with time is: ; In the formula, is the number of people in the room, t is any moment, is the number of people indoors at time t; A cosine function is used to construct a function of the outdoor temperature changing with time during the day according to the outdoor temperature at different times. The function expression of the outdoor temperature changing with time is: ; In the formula, is the outdoor temperature, Any time of the day, in hours. is the outdoor temperature corresponding to time t, is the highest outdoor temperature of the day, is the lowest outdoor temperature of the day; The functional relationship of the indoor number of people changing over time and the functional relationship of the outdoor temperature changing over time, combined with the energy balance equation, is used to construct a functional relationship of the air conditioning load changing over time, including: Based on the energy balance equation, the number of people in the human body heating rate calculation formula in the energy balance equation is replaced by a function of the number of people in the room changing over time; and Replacing the outdoor temperature in the heat transfer rate in the energy balance equation with a function of the outdoor temperature changing with time, to obtain a function of the air conditioning load changing with time; The function expression of the air conditioning load changing with time is: ; In the formula, is the air conditioning load, t is any time of the day, is the air conditioning load corresponding to time t, is the thermal conductivity factor of the target building, is the outdoor temperature corresponding to time t, is the indoor temperature, is the number of people indoors at time t, is the heating rate of each person in the ASHRAE standard. Indicates the heating speed of the device. is the energy efficiency ratio of air conditioning.

2. The air conditioning cooling load prediction method based on Internet of Things big data and AI according to claim 1 is characterized in that: The method further comprises: Obtaining heat dissipation indexes, air conditioning energy efficiency ratios, and actual air conditioning power consumption of multiple electrical equipment in the target building, and constructing a sample data set based on the heat dissipation indexes, air conditioning energy efficiency ratios, and actual air conditioning power consumption; Based on the sample data set, the heat dissipation index and the air conditioner energy efficiency ratio are used as the input of the long short-term memory network model, and the actual power consumption of the air conditioner is used as the output of the long short-term memory network model, and the long short-term memory network model is trained. The trained long short-term memory network model is used to determine the heat dissipation index of each electrical equipment in the target building.

3. The air conditioning cooling load prediction method based on Internet of Things big data and AI according to claim 1 is characterized in that: According to the energy balance principle, in combination with the heat conduction rate and the heat generation rate, an energy balance equation for the air conditioning load is established, including: Based on the heat conduction rate of the target building and the heating rate of the human body and the heating rate of the equipment in the target building, an energy balance equation for the air conditioning load is constructed, and the energy balance equation is: ; In the formula, is the air conditioning energy efficiency ratio, which is the ratio between the heat transported by the air conditioning equipment per unit time and the amount of electricity consumed, is the heat conduction rate of the target building, is the human body heating rate, Indicates the heating rate of the device. It is the absolute value of the sum of the heat conduction rate, the human body heating rate and the equipment heating rate.

4. An air conditioning cooling load prediction device based on Internet of Things big data and AI, applied to any method described in claims 1-3, characterized in that: The device comprises: A heating rate calculation module, used to obtain the amount of heat transferred between the inside and outside of a target building in a unit time, and calculate the heat conduction rate of the target building based on the amount of heat transferred between the inside and outside of the target building in the unit time, and calculate the heating rate in the target building; An energy balance equation establishment module is used to establish an energy balance equation for air conditioning load according to the energy balance principle and in combination with the heat conduction speed and the heat generation speed; A functional relationship building module is used to obtain the number of people in the target building at different times to build a functional relationship of the indoor number of people changing with time, and to obtain the outdoor temperature at different times and use a cosine function to build a functional relationship of the outdoor temperature changing with time; An air conditioning load function construction module, used to construct a functional relationship of the air conditioning load changing over time based on the functional relationship of the indoor number of people changing over time and the functional relationship of the outdoor temperature changing over time, combined with the energy balance equation; An air conditioning load prediction module, used to call the functional relationship of the air conditioning load changing over time to calculate and predict the air conditioning load in the target building corresponding to the number of people indoors and the outdoor temperature at any time; Among them, the heat transferred between the inside and outside of the target building includes the heat transferred from the inside to the outside of the target building and the heat transferred from the outside to the inside of the target building. The heating rate includes the heating rate of the human body and the heating rate of the equipment. The equipment heating rate is the heating rate of the electrical equipment. The energy balance equation is the ratio between the absolute value of the sum of the heat conduction rate and the heating rate and the air conditioning energy efficiency ratio.

5. A terminal comprising a processor and a storage medium; characterized in that: The storage medium is used to store instructions; The processor is configured to operate according to the instructions to execute the steps of the method according to any one of claims 1-3.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 3 are implemented.

Citation Information

Patent Citations

  • Air-conditioning load prediction method and system based on big data

    CN107220514A

  • Method for quantifying participation demand response capability of central air conditioner by considering user will

    CN116255729A

  • Central air conditioner control method and system based on digital twinning and electronic equipment

    CN117989679A

  • Load regulation and control method, device and equipment for air conditioning system

    CN118049737A

  • Building energy management system intra-day optimization scheduling method and related device

    CN118052380A