Air conditioner load response optimization method based on multi-dimensional data fusion

Abstract

The invention discloses an air conditioner load response optimization method based on multi-dimensional data fusion, relates to the technical field of air conditioner control, and solves the problem that the number of personnel may suddenly increase or suddenly decrease in an air conditioner refrigeration area. The load capacity predicted only from the air conditioning equipment is difficult to adapt to the complex scene; the accuracy of predicting the load capacity in the future time interval is reduced, and the comfort level of the user is correspondingly reduced. Comprising the following steps: 1, acquiring environment data and image data of each monitoring area; 2, importing the image data into a personnel distribution intelligent model for analysis to obtain a personnel distribution diagram; performing analysis based on the personnel distribution map to obtain a personnel density value used for representing the personnel density of the shopping mall; performing analysis based on the personnel density value and the environment data to obtain a load demand quantity; 3, performing dynamic adjustment based on the load demand quantity to obtain a corresponding optimization adjustment report; and the energy-saving effect of the air conditioner load and the comfort degree of a user are improved.

Description

Technical Field

[0001] This application belongs to the technical field of air-conditioning control, and specifically relates to an air-conditioning load response optimization method based on multi-dimensional data fusion. Background Art

[0002] Multi-dimensional data fusion refers to the process of organically integrating and collaboratively processing heterogeneous data from different dimensions to form information with decision-making value.

[0003] The prior art (CN112113319A) discloses an air-conditioning load adjustment system and an air-conditioning load adjustment method. The air-conditioning load adjustment system is set in a building with air-conditioning equipment and includes: an air-conditioning load prediction unit that calculates the predicted load of the air-conditioning equipment in a future time interval based on data in a past time interval; an indoor temperature and humidity sensing module that senses the temperature and humidity of the building at a first time; a wind speed sensing module that senses the wind speed of the air-conditioning equipment at the first time; a comfort prediction module that calculates the comfort level that the air-conditioning equipment needs to reach at a second time according to the temperature, humidity, and wind speed; and an energy management platform that controls a central monitoring computer to generate a temperature set value and a wind speed set value of the air-conditioning equipment according to the comfort level. The central monitoring computer compares the predicted load with the actual load of the air-conditioning equipment during operation of the air-conditioning equipment and corrects the temperature set value and the wind speed set value according to the comparison result. The present invention can achieve the purpose of energy conservation and reduction of power consumption during peak periods.

[0004] The above-mentioned air-conditioning load adjustment system and air-conditioning load adjustment method predict the load of the air-conditioning equipment in a future time interval, so as to achieve the indoor comfort level. In actual applications, there may be situations where the number of people suddenly increases or decreases in the air-conditioning cooling area, such as the peak passenger flow period in some stores in a shopping mall, or the increase in the number of people inside a meeting room due to a meeting. It is difficult to adapt to the above complex scenarios by simply predicting the load from the air-conditioning equipment, which reduces the accuracy of predicting the load in a future time interval and correspondingly reduces the comfort level of users. Summary of the Invention

[0005] This application aims to solve at least one of the technical problems existing in the prior art. For this purpose, this application proposes an air-conditioning load response optimization method based on multi-dimensional data fusion to solve the technical problems that there may be situations where the number of people suddenly increases or decreases in the air-conditioning cooling area, such as the peak passenger flow period in some stores in a shopping mall, or the increase in the number of people inside a meeting room due to a meeting. It is difficult to adapt to the above complex scenarios by simply predicting the load from the air-conditioning equipment, which reduces the accuracy of predicting the load in a future time interval and correspondingly reduces the comfort level of users.

[0006] To achieve the above object, the first aspect of the present application provides an air-conditioning load response optimization method based on multi-dimensional data fusion, including:

[0007] Step 1: Obtain the environmental data and image data of each monitoring area;

[0008] Step 2: Import the image data into the personnel distribution intelligent model for analysis to obtain a personnel distribution map; analyze based on the personnel distribution map to obtain a personnel density value representing the personnel density in the shopping mall; analyze based on the personnel density value and environmental data to obtain the load demand;

[0009] Step 3: Dynamically adjust based on the load demand to obtain a corresponding optimization adjustment report;

[0010] Further, the personnel distribution intelligent model is obtained through artificial intelligence training, including:

[0011] Obtain a number of image data and personnel distribution maps of the monitoring area from the database; the image data includes the dining area, clothing area, etc.; the personnel distribution map is obtained by experts analyzing a number of image data; specifically, obtain the floor plan of the corresponding monitoring area through the image; mark the positions of the personnel in the monitoring area, draw a scatter plot and obtain the position coordinates corresponding to the personnel positions; integrate the respective position coordinates to obtain the personnel distribution map; integrate a number of image data and the corresponding personnel distribution maps into a number of training data and test data;

[0012] Import a number of training data into the artificial intelligence model for training, and test the trained artificial intelligence model with the test data; specifically, input the image data in the test data into the trained artificial intelligence model and output the personnel distribution map. Compare the personnel distribution map with the personnel distribution map recorded in the test data to determine whether it is within the acceptable range; if so, it means that this group of test data passes the test, and continue to test the next group of test data; if not, the relevant parameters of the artificial intelligence model need to be adjusted, and continue to use this group of test data for testing; until a set proportion of the test data passes the test; finally, obtain an input of image data and personnel distribution map and an output of a personnel distribution intelligent model; where the artificial intelligence model is a BEV model, etc.

[0013] Further, analyzing based on the personnel distribution map to obtain the personnel density value representing the personnel density in the shopping mall includes:

[0014] Obtain the total number of personnel in the monitoring area and the corresponding planar area through the personnel distribution map; the planar area is the surface area corresponding to the top view of the monitoring area; record the ratio of the total number of personnel in the monitoring area to the planar area as the personnel density value;

[0015] Through the formula Calculate the personnel density value RY corresponding to the monitoring area; where RS represents the total number of personnel corresponding to the monitoring area; MJ represents the planar area corresponding to the monitoring area.

[0016] Further, analyze based on the personnel density value and environmental data to obtain the load demand quantity, including:

[0017] Analyze based on the personnel density value to obtain the personnel load demand quantity representing the energy demand of personnel load; analyze based on the environmental data to obtain the environmental load demand quantity representing the energy demand of environmental load;

[0018] Calculate the load demand quantity by summing the personnel load demand quantity and the environmental load demand quantity;

[0019] Further, analyze based on the personnel density value to obtain the personnel load demand quantity representing the energy demand of personnel load, including:

[0020] Sequentially obtain the personnel density values of each time period in the current monitoring area; record the difference between the personnel density value of the previous time period and the personnel density value of the current time period as the personnel density change value, denoted as ΔPY; dynamically convert based on the personnel density change value to obtain the personnel load demand quantity.

[0021] Further, dynamically convert based on the personnel density change value to obtain the personnel load demand quantity, including:

[0022] Obtain the personnel density change value of the monitoring area; record the product of the personnel density change value and the heat released by unit density conversion as the personnel load demand quantity.

[0023] The formula for obtaining the personnel load demand quantity is:

[0024] PF = ΔPY × DWP

[0025] Where PF represents the personnel load demand quantity of the current time period, ΔPY represents the personnel density value of the current time period; DWP represents the heat released by unit density conversion.

[0026] Further, analyze based on the environmental data to obtain the environmental load demand quantity representing the energy demand of environmental change load, including:

[0027] Obtain the current values corresponding to each environmental item in the environmental data of the monitoring area; the environmental items include the temperature difference between indoors and outdoors, humidity, wind speed, etc.; the specific formula for obtaining the environmental load demand quantity is:

[0028]

[0029] Among them, SSD represents the environmental load demand of the current monitoring area, HJi represents the current value corresponding to each environmental item; ZYi represents the optimal value corresponding to each environmental item; HJZNi represents the unit difference corresponding to the environmental item; HGi represents the load energy required for the unit difference corresponding to each item; i represents the number corresponding to each environmental item, i = 1, 2, ……, n; n represents the total number of environmental items; αi1 and αi2 represent proportionality coefficients; specific values are set according to experience.

[0030] Furthermore, based on the load demand, dynamic adjustment is performed to obtain the corresponding optimization adjustment report, including:

[0031] Obtain the load demands for each time period to fit a load change curve based on the load demands for each time period.

[0032] Obtain the load adjustment slope threshold interval corresponding to the monitoring area; the load adjustment slope threshold interval is the gentle slope range corresponding to the load change curve; the gentle slope range is set according to specific experience.

[0033] When the change slope corresponding to the load change curve exceeds the load adjustment slope threshold interval, analyze based on the load demand and the load change curve to obtain the total adjusted load demand; adjust the air conditioner based on the total adjusted load demand.

[0034] When the change slope corresponding to the load change curve does not exceed the load adjustment slope threshold interval, no air conditioner load adjustment is performed.

[0035] Integrate the load change curve of the monitoring area and the load adjustment slope threshold interval into the optimization adjustment report.

[0036] Furthermore, fitting a load change curve based on the load demands for each time period includes:

[0037] Sort the load demands for each time period in the order of their corresponding time periods and fit a load change curve; the fitting methods include interpolation method, etc.

[0038] Furthermore, analyzing based on the load demand and the load change curve to obtain the total adjusted load demand includes:

[0039] Obtain the actual load at the current time period from the database; record the absolute value of the difference between the actual load at the current time period and the load demand as the change demand load at the current time period.

[0040] Record the product of the change demand load and the time required to adjust the unit load as the predicted adjustment time.

[0041] The product of the absolute value of the change slope corresponding to the load change curve and the corresponding predicted adjustment time is denoted as the redundant load amount;

[0042] After that, the change demand load amount and the redundant load amount are summed to calculate the total adjusted load demand;

[0043] Compared with the prior art, the beneficial effects of the present application are as follows:

[0044] 1. In the present application, environmental data and image data of each monitoring area are obtained; the image data is imported into the personnel distribution intelligent model for analysis to obtain a personnel distribution map; based on the personnel distribution map, analysis is performed to obtain a personnel density value representing the personnel density in the shopping mall; based on the personnel density value and environmental data, analysis is performed to obtain the load demand; based on the load demand, dynamic adjustment is performed to obtain a corresponding optimized adjustment report; the air-conditioning load demand in the monitoring area can be predicted for targeted adjustment; thus, the energy-saving effect of the air-conditioning load can be achieved; at the same time, the comfort of users in the monitoring area is greatly improved.

[0045] 2. In the present application, there are two situations where the load change curve is positively correlated and negatively correlated with the time period, and the corresponding situations are also different; when the load change area is positively correlated with the time period, it indicates that the air-conditioning load needs to be increased in the monitoring area; which helps to improve the comfort level in the monitoring area; when the load change area is negatively correlated with the time period; it indicates that the air-conditioning load needs to be reduced in the monitoring area; greatly reducing the power consumption caused by using the air conditioner and achieving the energy-saving effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0047] Figure 1 is a schematic diagram of the principle of the present application;

[0048] Figure 2 is a flowchart of the method of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0049] The following will clearly and completely describe the technical solutions of the present application in conjunction with the embodiments. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0050] Please refer toFigure 1 , an embodiment of the first aspect of the present application provides an air-conditioning load response optimization method based on multi-dimensional data fusion, including:

[0051] Step 1: Obtain environmental data and image data of each monitoring area;

[0052] Step 2: Import the image data into the personnel distribution intelligent model for analysis to obtain a personnel distribution map; analyze based on the personnel distribution map to obtain a personnel density value representing the personnel density in the shopping mall; analyze based on the personnel density value and environmental data to obtain the load demand;

[0053] Step 3: Dynamically adjust based on the load demand to obtain a corresponding optimization adjustment report.

[0054] The monitoring areas include the internal areas of shopping malls, etc.; the environmental data is obtained through temperature sensors, humidity sensors, etc.; the image data is obtained through imaging devices; the imaging devices include cameras, etc.;

[0055] Specifically, the personnel distribution intelligent model is obtained through artificial intelligence training, including:

[0056] Obtain a number of image data and personnel distribution maps of the monitoring area from the database; the image data includes the dining area, clothing area, etc.; the personnel distribution map is obtained by experts analyzing a number of image data; specifically, obtain the floor plan of the corresponding monitoring area through the image; mark the positions of the personnel in the monitoring area, draw a scatter plot and obtain the position coordinates corresponding to the personnel positions; integrate the respective position coordinates to obtain the personnel distribution map; integrate a number of image data and the corresponding personnel distribution maps into a number of training data and test data;

[0057] Import a number of training data into the artificial intelligence model for training, and test the trained artificial intelligence model through the test data; specifically, input the image data in the test data into the trained artificial intelligence model, and output the personnel distribution map. Compare the personnel distribution map with the personnel distribution map recorded in the test data to determine whether it is within the acceptable range; if so, it means that this group of test data passes the test, and continue to test the next group of test data; if not, the relevant parameters of the artificial intelligence model need to be adjusted, and continue to use this group of test data for testing; until a set proportion of the test data passes the test; finally, obtain an input of image data and personnel distribution map, and an output of a personnel distribution intelligent model; where the artificial intelligence model is a BEV model, etc.

[0058] The image data is the image collected for various facilities and personnel flow inside the monitoring area;

[0059] Specifically, analyzing based on the personnel distribution map to obtain the personnel density value representing the personnel density in the shopping mall, including:

[0060] Obtain the total number of personnel and the corresponding planar area of the monitoring area through the personnel distribution map; the planar area is the surface area corresponding to the top view of the monitoring area; record the ratio of the total number of personnel in the monitoring area to the planar area as the personnel density value;

[0061] Through the formula Calculate the personnel density value RY corresponding to the monitoring area; where RS represents the total number of personnel corresponding to the monitoring area; MJ represents the planar area corresponding to the monitoring area;

[0062] In this embodiment, obtaining the personnel density value of the monitoring area through the personnel distribution map, the more users in the monitoring area, the denser the corresponding personnel density, indicating that the increased heat in the monitoring area is greater, providing a basis for obtaining the required load demand in this monitoring area subsequently;

[0063] The personnel distribution map is the personnel quantity distribution map of the monitoring area; the personnel density value is the personnel density in the shopping mall;

[0064] Specifically, analyzing based on the personnel density value and environmental data to obtain the load demand, including:

[0065] Analyze based on the personnel density value to obtain the personnel load demand representing the energy required for personnel load; analyze based on the environmental data to obtain the environmental load demand representing the energy required for environmental load;

[0066] Calculate the load demand by summing the personnel load demand and the environmental load demand.

[0067] In this embodiment, specifically, it should be noted that the load demand is obtained by obtaining the personnel load demand and the environmental load demand and then performing a summation calculation.

[0068] The load demand is the load energy required to maintain the comfort level of the monitoring area; the comfort level specifically refers to that specific environmental parameters such as temperature and humidity can make users comfortable;

[0069] Specifically, analyzing based on the personnel density value to obtain the personnel load demand representing the energy required for personnel load, including:

[0070] Successively obtain the personnel density values of each time period in the current monitoring area; record the difference between the personnel density value of the previous time period and the personnel density value of the current time period as the personnel density change value denoted as ΔPY; perform dynamic conversion based on the personnel density change value to obtain the personnel load demand;

[0071] The personnel load demand is the load demand energy required for the heat released by personnel in the monitoring area;

[0072] Specifically, the personnel load demand is dynamically converted based on the personnel density change value, including:

[0073] Obtain the personnel density change value of the monitoring area; Denote the product of the personnel density change value and the heat released by unit density conversion as the personnel load demand;

[0074] The formula for obtaining the personnel load demand is:

[0075] PF = ΔPY × DWP

[0076] Where, PF represents the personnel load demand in the current time period, ΔPY represents the personnel density value in the current time period; DWP represents the heat released by unit density conversion;

[0077] Specifically, the environmental load demand representing the environmental load demand energy is obtained by analyzing the environmental data, including:

[0078] Obtain the current values corresponding to each environmental item in the environmental data of the monitoring area; The environmental items include the temperature difference between indoor and outdoor, humidity, wind speed, etc.; The specific formula for obtaining the environmental load demand is:

[0079]

[0080] Where, SSD represents the environmental load demand of the current monitoring area, HJi represents the current value corresponding to each environmental item; ZYi represents the optimal value corresponding to each environmental item; HJZNi represents the unit difference corresponding to the environmental item; HGi represents the load energy required for the unit difference corresponding to each item; i represents the number corresponding to each environmental item, i = 1, 2,..., n; n represents the total number of environmental items; αi1 and αi2 represent proportionality coefficients; The specific values are set according to experience;

[0081] In this embodiment, it should be specifically noted that since the current values corresponding to some environmental items have different effects on the environmental comfort level in the monitoring area when they are higher or lower than the optimal values, the proportionality coefficients are also different. The proportionality coefficients corresponding to different environmental items are set in advance according to expert experience; When the current value corresponding to an environmental item is greater than the corresponding optimal value, the environmental comfort level in the monitoring area is adjusted by αi1; When the current value corresponding to an environmental item is less than the corresponding optimal value, the environmental comfort level in the monitoring area is adjusted by αi2;

[0082] In this embodiment, it is illustrated by a formula that the greater the difference between the current value corresponding to the environmental project and its corresponding optimal value is. Specifically, it shows that whether the temperature in the monitoring area is too high or too low, it will affect the environmental comfort level in the monitoring area, and the corresponding air-conditioning load will increase, thus increasing the power consumption. The corresponding environmental impact coefficient will be greater; the environmental load demand is the load required for the monitoring area to maintain a comfortable level due to temperature, humidity, etc.

[0083] Specifically, based on the load demand, dynamic adjustment is performed to obtain the corresponding optimization adjustment report, including:

[0084] Obtain the load demands for each time period, and fit a load change curve based on the load demands for each time period;

[0085] Obtain the threshold interval of the load adjustment slope corresponding to the monitoring area; the threshold interval of the load adjustment slope is the gentle slope range corresponding to the load change curve; the gentle slope range is set according to specific experience;

[0086] When the change slope corresponding to the load change curve exceeds the threshold interval of the load adjustment slope, then analyze based on the load demand and the load change curve to obtain the total adjusted load demand; adjust the air conditioner based on the total adjusted load demand;

[0087] When the change slope corresponding to the load change curve does not exceed the threshold interval of the load adjustment slope, no air-conditioning load adjustment is performed;

[0088] Integrate the load change curve of the monitoring area and the threshold interval of the load adjustment slope into an optimization adjustment report.

[0089] In this embodiment, specifically, it should be noted that when the change slope corresponding to the load change curve is within the threshold interval of the load adjustment slope, it indicates that the load required to maintain the user's comfort level in the monitoring area is less, and the corresponding load demand is also less, indicating that no air-conditioning load adjustment is required for the current time period, reducing power consumption and making the air conditioner more energy-efficient; the optimization adjustment report is the result of the air-conditioning load adjustment required in the shopping mall; the load change curve is a quantitative curve of the demand load changing dynamically with time; the total adjusted load demand is the total energy required for air-conditioning load adjustment in the monitoring area.

[0090] Specifically, analyzing based on the load demand and the load change curve to obtain the total adjusted load demand includes:

[0091] Obtain the actual load for the current time period from the database; record the absolute value of the difference between the actual load for the current time period and the load demand as the changing demand load for the current time period;

[0092] Denote the product of the changing demand load and the time required to adjust the unit load as the predicted adjustment time;

[0093] Denote the product of the absolute value of the changing slope corresponding to the load change curve and the corresponding predicted adjustment time as the redundant load;

[0094] After that, sum the changing demand load and the redundant load to calculate the total adjusted load demand;

[0095] In this embodiment, it should be specifically noted that since the load change curve has two cases of being positively correlated and negatively correlated with the time period, the corresponding situations are also different; when the load change area is positively correlated with the time period, it means that the air-conditioning load needs to be increased in the monitored area; which helps to improve the comfort level of the monitored area; when the load change area is negatively correlated with the time period; it means that the air-conditioning load needs to be reduced in the monitored area; which greatly reduces the power consumption caused by using the air conditioner; and can also improve the comfort of users in the monitored area;

[0096] In this embodiment, it should be specifically noted that when adjusting the changing demand load to obtain the predicted adjustment time, a redundant load will be generated according to the predicted adjustment time, that is, both the changing demand load and the redundant load are adjusted; therefore, it can not only predict the air-conditioning load demand in the monitored area for targeted adjustment, but also improve the comfort of users in the monitored area; the predicted adjustment time is the time required to adjust the changing demand load; the redundant load is the load required during the predicted adjustment time;

[0097] Please refer to Figure 2 , the second aspect embodiment of this application provides a method flow chart of an air-conditioning load response optimization method based on multi-dimensional data fusion;

[0098] Some of the data in the above formula are calculated by removing the dimension and taking their numerical values. The formula is obtained by software simulation of a large amount of collected data to get a formula closest to the real situation; the preset parameters and preset thresholds in the formula are set by those skilled in the art according to the actual situation or obtained through simulation of a large amount of data.

[0099] The working principle of this application: Obtain the environmental data and image data of each monitored area; Import the image data into the personnel distribution intelligent model for analysis to obtain the personnel distribution map; Analyze based on the personnel distribution map to obtain the personnel density value representing the personnel density in the shopping mall; Analyze based on the personnel density value and environmental data to obtain the load demand; Dynamically adjust based on the load demand to obtain the corresponding optimization adjustment report; It can predict the air-conditioning load demand in the monitored area for targeted adjustment; thereby achieving the energy-saving effect of the air-conditioning load; At the same time, greatly improve the comfort of users in the monitored area;

[0100] The above embodiments are only used to illustrate the technical solutions of the present application and not to limit them. Although the present application has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present application can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present application.

Claims

1. An air conditioning load response optimization method based on multi-dimensional data fusion, characterized in that: Step 1: Obtain environmental data and image data of each monitoring area; Step 2: Import the image data into the intelligent model of personnel distribution for analysis to obtain a personnel distribution map; analyze the personnel distribution map to obtain a personnel density value used to represent the density of personnel in the shopping mall; The load demand is obtained by analyzing the population density value and environmental data; Step 3: Perform dynamic adjustments based on load demand to obtain the corresponding optimization adjustment report.

2. The air conditioning load response optimization method based on multi-dimensional data fusion according to claim 1 is characterized in that: The personnel distribution intelligent model is obtained through artificial intelligence training, including: Acquire a number of image data and a personnel distribution map of the monitoring area from the database; the personnel distribution map is obtained by analyzing the number of image data by experts; integrate the number of image data and the corresponding personnel distribution map into a number of training data and test data; Import several training data into the artificial intelligence model for training, and test the trained artificial intelligence model through test data; finally, the input is image data and personnel and object distribution map, and the output is personnel distribution intelligent model.

3. The air conditioning load response optimization method based on multi-dimensional data fusion according to claim 1 is characterized in that: The personnel density value used to represent the density of personnel in the shopping mall is obtained by analyzing the personnel distribution map, including: The total number of personnel in the monitoring area and the corresponding plane area are obtained through the personnel distribution map; the plane area is the surface area corresponding to the top view of the monitoring area; the ratio of the total number of personnel in the monitoring area to the plane area is recorded as the personnel density value.

4. The air conditioning load response optimization method based on multi-dimensional data fusion according to claim 1 is characterized in that: The load demand is obtained by analyzing the population density value and environmental data, including: Based on the personnel density value, the personnel load demand is obtained to represent the personnel load demand energy; based on the environmental data, the environmental load demand is obtained to represent the environmental load demand energy; The load demand is calculated by summing the personnel load demand and the environmental load demand.

5. The air conditioning load response optimization method based on multi-dimensional data fusion according to claim 4 is characterized in that: The personnel load demand for indicating the personnel load demand energy is obtained by analyzing based on the personnel density value, including: Obtain the population density value of each time period in the current monitoring area in turn; record the difference between the population density value of the previous time period and the population density value of the current time period as the population density change value; and obtain the personnel load demand by performing dynamic conversion based on the population density change value.

6. The air conditioning load response optimization method based on multi-dimensional data fusion according to claim 5 is characterized in that: The dynamic conversion based on the change value of the personnel density to obtain the personnel load demand includes: Obtain the change value of the personnel density in the monitoring area; record the product of the change value of the personnel density and the heat released by the set unit density conversion as the personnel load demand.

7. The air conditioning load response optimization method based on multi-dimensional data fusion according to claim 4 is characterized in that: The environmental load demand for indicating the environmental change load demand energy is obtained by analyzing the environmental data, including: Obtain the current values ​​corresponding to each environmental item in the environmental data of the monitoring area; the specific formula for obtaining the environmental load demand is: Among them, SSD represents the environmental load demand of the current monitoring area, HJi represents the current value corresponding to each environmental item; ZYi represents the optimal value corresponding to each environmental item; HJZNi represents the unit difference corresponding to the environmental item; HGi represents the load energy required for the unit difference corresponding to each item; i represents the number corresponding to each environmental item, i=1, 2,..., n; n represents the total number of environmental items; αi1 and αi2 represent the proportional coefficients.

8. The air conditioning load response optimization method based on multi-dimensional data fusion according to claim 1 is characterized in that: The corresponding optimization adjustment report is obtained by dynamically adjusting the load demand, including: Obtain each load demand in each time period, and fit the load change curve based on each load demand; Obtaining a load adjustment slope threshold interval corresponding to the monitoring area; the load adjustment slope threshold interval is a gentle slope range corresponding to the load change curve; When the change slope corresponding to the load change curve exceeds the load adjustment slope threshold range, the total load demand is analyzed based on the load demand and the load change curve to obtain the adjustment; the air conditioner is adjusted based on the adjustment total load demand; When the change slope corresponding to the load change curve does not exceed the load adjustment slope threshold range, the air conditioning load is not adjusted; The load change curve and load regulation slope threshold range of the monitoring area are integrated into an optimization adjustment report.

9. The air conditioning load response optimization method based on multi-dimensional data fusion according to claim 8, characterized in that: The load variation curve is fitted based on each load demand, including: The load demands are sorted in the order of their corresponding time periods and fitted into a load change curve.

10. The air conditioning load response optimization method based on multi-dimensional data fusion according to claim 8, characterized in that: The total load demand is obtained by analyzing the load demand and the load variation curve, including: Obtain the actual load of the current time period from the database; record the absolute value of the difference between the actual load of the current time period and the load demand as the change demand load of the current time period; The product of the change demand load and the set unit load adjustment time is recorded as the predicted adjustment time; The product of the absolute value of the change slope corresponding to the load change curve and the corresponding predicted adjustment time is recorded as the redundant load; The total load demand is calculated by adding the variable demand load and the redundant load.

Images