A method for evaluating energy efficiency of split air conditioners in computer rooms based on quantile regression

Abstract

The present invention provides a method for evaluating the energy efficiency of a split-type air conditioner in a computer room based on quantile regression. According to the quantile regression model constructed by the target indicator and the currently collected target indicator data, the regression coefficient of the independent variable of the air conditioner energy efficiency is obtained, and the air conditioner optimization control strategy is obtained according to the regression coefficient, so as to control the air conditioner more finely, and achieve the effects of high efficiency, good timeliness, low energy consumption, and energy saving and emission reduction by automatically collecting indicators remotely and calculating automatically without manual on-site judgment. The present invention also discloses a computer device and a readable storage medium for evaluating the energy efficiency of a split-type air conditioner in a computer room based on quantile regression.

Description

Technical Field

[0001] The present invention relates to the technical field of power systems, and in particular to a method for evaluating the energy efficiency of a split-type air conditioner in a computer room based on quantile regression, a computer device and a readable storage medium. Background Art

[0002] Due to the large number of IT equipment and line systems in the internal structure of the computer room, a large amount of heat will be generated during the operation of the equipment, causing the temperature to rise. In order to ensure the normal operation of the equipment and avoid the failure of electronic equipment and power supply machinery due to high temperature, cooling equipment needs to be installed in the computer room. The main cooling equipment used in the computer room is basically household air conditioners, and only a few use precision air conditioners. The performance of ordinary household air conditioners is average, and long-term operation is prone to failure. The air conditioners in some computer rooms have not cooled or have poor cooling capacity but still consume electricity. The energy efficiency is low and the energy consumption is high, so the computer room needs to be inspected and maintained. Small computer rooms generally use one or more split air conditioners. Computer rooms have the characteristics of variable heat load demand and complex air conditioning control. They are different under different areas, different outdoor temperatures, different wall materials, and different IT equipment heating conditions, which puts forward certain requirements for the refined control of computer room air conditioners.

[0003] The existing small computer rooms do not have long-term maintenance personnel stationed in the computer rooms. People are required to regularly or irregularly inspect and observe the temperature changes in the computer rooms, and then decide whether to turn on or off the air conditioner or whether the equipment in the computer room is faulty based on manual judgment.

[0004] The existing manual maintenance method of the computer room has low management efficiency, poor timeliness, high energy consumption, and cannot achieve fine control of air conditioning. Summary of the invention

[0005] In view of the deficiencies in the prior art, the present invention provides a method for evaluating the energy efficiency of split-type air conditioners in computer rooms based on quantile regression, which solves the problems in the prior art of low manual maintenance efficiency, poor timeliness, high energy consumption, and inability to achieve fine-grained control of air conditioners.

[0006] According to an embodiment of the present invention, a method for evaluating the energy efficiency of a split-type air conditioner in a computer room based on quantile regression is provided, which comprises the following steps: constructing a quantile regression model according to target indicators; wherein the target indicators include outdoor temperature, indoor temperature, accumulated air conditioner operating time and equipment power; obtaining a regression coefficient of an air conditioner energy efficiency independent variable according to the quantile regression model and currently collected target indicator data; wherein the air conditioner energy efficiency independent variable is the target indicator; and obtaining an air conditioner optimization control strategy according to the regression coefficient.

[0007] Optionally, the formula expression for constructing a quantile regression model based on the target indicator is:

[0008] y=a 0 +a 1 x 1 +a 2 x 2 +a 3 x 3 +a 4 x 4 +u, where, a 0 ,a 1 , a 2 , a 3 , a 4 is the coefficient of the variable to be estimated, y is the expectation about x, x 1 is the outdoor temperature, x 2 is the indoor temperature, x 3 is the accumulated running time of the air conditioner, x 4 is the equipment power, and u is the residual.

[0009] Optionally, before obtaining the regression coefficient of the air conditioning energy efficiency independent variable according to the quantile regression model and the currently collected target indicator data, the method also includes: preprocessing the currently collected initial indicator data to obtain the target indicator data; wherein, when the initial indicator data has missing values, the average value of the initial indicator data is used to fill in and obtain the target indicator data.

[0010] Optionally, according to the quantile regression model and the currently collected target indicator data, the regression coefficient of the air conditioner energy efficiency independent variable is obtained, including: according to the currently collected target indicator data, the minimum weighted absolute deviation is estimated by a linear programming method to obtain the regression coefficient of the air conditioner energy efficiency independent variable, which can be expressed as follows:

[0011] min Eρ τ (ya 0 -a 1 x 1 -a 2 x 2 -...-a k x k ), and further obtain Among them, ρ τ (t)=t(τ-I(t<0)),τ∈(0,1), E is the expectation, τ is the quantile, is the mean of the random variable, is the regression coefficient of the air conditioning energy efficiency independent variable, x 1 ,x 2 ,...,x k The target indicator data currently being collected.

[0012] Optionally, based on the regression coefficient, an air conditioning optimization control strategy is obtained, including: when the absolute value of the regression coefficient is greater than 0.01, it can be considered that the air conditioning energy efficiency independent variable corresponding to the regression coefficient has an impact on the air conditioning energy efficiency; based on the air conditioning energy efficiency independent variable that affects the air conditioning energy efficiency, the air conditioning optimization control strategy is obtained.

[0013] Optionally, based on the air conditioning energy efficiency independent variable affecting the air conditioning energy efficiency, an air conditioning optimization control strategy is obtained, including: when the air conditioning energy efficiency independent variable is the indoor temperature or the outdoor temperature, the air conditioner can be turned off when the outdoor temperature is lower than the indoor temperature, and the air conditioner is restored to the on state when the indoor temperature is greater than or equal to the outdoor temperature.

[0014] Optionally, based on the air conditioning energy efficiency independent variable that affects the air conditioning energy efficiency, an air conditioning optimization control strategy is obtained, including: when the air conditioning energy efficiency independent variable is the accumulated running time of the air conditioner, the air conditioner with energy efficiency lower than the standard energy efficiency can be turned off, and the missing cooling load can be compensated by other air conditioners in the computer room.

[0015] Optionally, an air conditioning optimization control strategy is obtained according to the air conditioning energy efficiency independent variable affecting the air conditioning energy efficiency, including: when the air conditioning energy efficiency independent variable is equipment power, the air conditioning can be automatically adjusted according to the equipment power.

[0016] According to an embodiment of the present invention, a computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.

[0017] According to an embodiment of the present invention, a readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0018] The technical principle of the present invention is: according to the quantile regression model constructed by the target indicator and the currently collected target indicator data, the regression coefficient of the air conditioning energy efficiency independent variable is obtained, wherein the air conditioning energy efficiency independent variable is the target indicator, and the air conditioning optimization control strategy is obtained according to the regression coefficient to control the air conditioning more finely.

[0019] Compared with the prior art, the present invention has the following beneficial effects: by adopting the quantile regression model, because the quantile regression does not make any assumptions about the distribution of the random error terms in the model, all quantiles can be modeled and analyzed, and can resist outliers in the data, and can more comprehensively characterize the characteristics of the distribution, thereby obtaining a comprehensive analysis, which is more robust than the ordinary linear mean regression. The influence of the air conditioning energy efficiency independent variable on the air conditioning energy efficiency is reflected more accurately according to the regression coefficient of the established quantile regression model, and the air conditioning optimization control strategy is obtained according to the regression coefficient, which can screen out some indicators that have almost no effect on the air conditioning energy efficiency, and control the air conditioning according to the indicators that have the main influence on the air conditioning energy efficiency and the actual operating energy efficiency of the split air conditioner in the machine room, so as to realize the refined control of the air conditioning, and achieve the effects of high efficiency, good timeliness, low energy consumption, and energy saving and emission reduction by automatically collecting indicators remotely and calculating them automatically without manual on-site judgment. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 A schematic diagram of a method for evaluating energy efficiency of a split-type air conditioner in a computer room based on quantile regression provided by an embodiment of the present invention;

[0021] Figure 2 A schematic diagram of another method for evaluating energy efficiency of a split-type air conditioner in a computer room based on quantile regression provided by the present invention. DETAILED DESCRIPTION

[0022] The technical solution of the present invention is further described below in conjunction with the accompanying drawings and embodiments.

[0023] like Figure 1 As shown, the embodiment of the present invention proposes a method for evaluating the energy efficiency of a split-type air conditioner in a computer room based on quantile regression, which includes the following steps:

[0024] S101, constructing a quantile regression model according to target indicators; wherein the target indicators include outdoor temperature, indoor temperature, accumulated air conditioner operating time and equipment power.

[0025] S102, obtaining a regression coefficient of an air-conditioning energy efficiency independent variable according to a quantile regression model and currently collected target indicator data; wherein the air-conditioning energy efficiency independent variable is a target indicator.

[0026] S103, obtaining an air conditioning optimization control strategy according to the regression coefficient.

[0027] The detailed working process of this embodiment is to obtain the regression coefficient of the air conditioning energy efficiency independent variable according to the quantile regression model constructed according to the target indicator and the currently collected target indicator data, wherein the air conditioning energy efficiency independent variable is the target indicator, and the air conditioning optimization control strategy is obtained according to the regression coefficient, so as to control the air conditioning more finely. Since the influence of the air conditioning energy efficiency independent variable on the air conditioning energy efficiency is reflected more accurately according to the regression coefficient of the established quantile regression model, the air conditioning optimization control strategy is obtained according to the regression coefficient, and some indicators that have almost no effect on the air conditioning energy efficiency can be screened out, and the air conditioning can be controlled according to the indicators that have the main influence on the air conditioning energy efficiency and the actual operating energy efficiency of the split air conditioner in the computer room, so as to realize fine control of the air conditioning, and achieve high efficiency, good timeliness, low energy consumption, and energy saving and emission reduction effects by automatically collecting indicators remotely and calculating automatically without manual on-site judgment.

[0028] Optionally, the formula expression for constructing a quantile regression model based on the target indicator is:

[0029] y=a 0 +a 1 x 1 +a 2 x 2 +a 3 x 3 +a 4 x 4 +u, where, a 0 ,a 1 , a 2 , a 3 , a 4 is the coefficient of the variable to be estimated, y is the expectation about x, x 1 is the outdoor temperature, x 2 is the indoor temperature, x 3 is the accumulated running time of the air conditioner, x 4 is the equipment power, and u is the residual. Quantile regression is a modeling method that estimates the linear relationship between a set of regression variables X and the quantiles of the explained variable Y. Quantile regression is different from conventional linear regression. Conventional linear regression uses the least squares method to calculate the mean of the conditional probability between different eigenvalues, and quantile regression estimates the median of the conditional probability. Quantile regression is an extension of the least squares method based on the classical conditional mean model, using multiple quantile functions to estimate the overall model. Median regression is a special case of quantile regression, which uses symmetric weights to solve the residual minimization problem, while other conditional quantile regressions use asymmetric weights to solve the residual minimization problem. In this way, by adopting the quantile regression model, because quantile regression does not make any assumptions about the distribution of random error terms in the model, all quantiles can be modeled and analyzed, which can resist outliers in the data and more comprehensively characterize the characteristics of the distribution, thereby obtaining a comprehensive analysis. It is more robust than ordinary linear mean regression.

[0030] In some embodiments, since the air conditioner in the computer room runs 24 hours a day, the energy efficiency performance of the split air conditioner may change during this operation period. There are many factors that cause this change, which are mainly divided into three categories: computer room data, split air conditioner operation data, and IT equipment operation data. Among them, the computer room data includes: outdoor temperature and indoor temperature, etc.; the split air conditioner operation data includes: outlet temperature, inlet temperature, set temperature, set air supply gear number, cumulative operation time and actual energy efficiency ratio, etc.; IT equipment operation data includes: equipment power, etc. When selecting indicators, indicators can be selected from them. Outdoor temperature, indoor temperature, cumulative operation time and equipment power are the main factors affecting air conditioning. These indicators can be selected through the construction of quantile models to further see what the main factors affecting air conditioning under different conditions are, because different conditions and environments may affect the energy efficiency of air conditioning. For example, in computer rooms where seasonal changes are more obvious and the temperature difference between morning and evening is relatively large, since the equipment power is basically unchanged and the state of the air conditioner is relatively stable, the outdoor temperature may be the main factor affecting the air conditioning energy efficiency ratio. The explanation of air conditioning energy efficiency ratio is as follows: within a certain evaluation time T, the split air conditioning operation state is divided into n typical operating conditions and corresponding time T i . Operation analysis and field measurement are performed for each typical operating condition. Assume that the actual cooling capacity and total energy consumption under the i-th typical operating condition are Q i and N i , then the operating energy consumption of the split air conditioner can be calculated as follows: Among them, Eff is the operating energy efficiency of the split air conditioner, τ i is the time length of the i-th operating condition. After obtaining the operating energy efficiency of the split air conditioner, the difference between the actual operating energy efficiency of the split air conditioner and the standard energy efficiency can be determined. The calculation formula for the cooling capacity Q is: Q = 3.6CρVΔt, where C is the specific heat capacity of air at average temperature, in J / kg·K; ρ is the air density at average temperature, in kg / m 3 ; V is the circulating air volume, unit is m 3 / h; Δt is the temperature difference between the inlet and outlet air of the evaporator, in °C; 3.6 is the conversion factor.

[0031] Optionally, according to the quantile regression model and the currently collected target indicator data, the regression coefficient of the air conditioner energy efficiency independent variable is obtained, including: according to the currently collected target indicator data, the linear programming method is used to estimate the minimum weighted absolute deviation, and the regression coefficient of the air conditioner energy efficiency independent variable is obtained, which can be expressed as follows: min Eρ τ (ya 0 -a 1 x 1 -a 2 x 2 -...-ak x k ), and further obtain Among them, ρ τ (t)=t(τ-I(t<0)),τ∈(0,1), E is the expectation, τ is the quantile, is the mean of the random variable, is the regression coefficient of the air conditioning energy efficiency independent variable, x 1 ,x 2 ,...,x k is the target indicator data currently collected. In this way, by estimating the weighted absolute deviation through the linear programming method, the regression coefficient of the independent variable of air conditioning energy efficiency can be obtained more accurately.

[0032] In some embodiments, when collecting target data, air conditioners of different brands, different powers and different years of use can be selected in different computer rooms, and corresponding collection equipment can be installed in the test room for collection. This can ensure data diversity and increase the accuracy of model prediction.

[0033] Optionally, based on the regression coefficient, an air conditioning optimization control strategy is obtained, including: when the absolute value of the regression coefficient is greater than 0.01, it can be considered that the air conditioning energy efficiency independent variable corresponding to the regression coefficient has an impact on the air conditioning energy efficiency; based on the air conditioning energy efficiency independent variable that affects the air conditioning energy efficiency, the air conditioning optimization control strategy is obtained. In this way, by obtaining the air conditioning optimization control strategy based on the regression coefficient, some indicators that have almost no impact on the air conditioning energy efficiency can be screened out, and the air conditioning can be controlled based on the indicators that have a major impact on the air conditioning energy efficiency and the actual operating energy efficiency of the split air conditioner in the computer room, so as to achieve refined control of the air conditioning, and achieve high efficiency, good timeliness, low energy consumption, and energy saving and emission reduction effects by automatically collecting indicators remotely and calculating automatically without manual on-site judgment.

[0034] Optionally, based on the air conditioning energy efficiency independent variable that affects the air conditioning energy efficiency, an air conditioning optimization control strategy is obtained, including: when the air conditioning energy efficiency independent variable is the indoor temperature or the outdoor temperature, the air conditioning can be turned off when the outdoor temperature is lower than the indoor temperature, and the air conditioning can be restored to the on state when the indoor temperature is greater than or equal to the outdoor temperature. In this way, when it is determined that the outdoor temperature and the indoor temperature are the main factors affecting the air conditioning energy efficiency, the state of the air conditioning can be controlled according to different temperature conditions, unnecessary energy waste can be reduced, and the air conditioning can be controlled more finely, rather than being extensively controlled without knowing where to start.

[0035] In some embodiments, if the outdoor temperature is very high, such as in summer, a space as closed as possible can be created for the computer room to avoid a reduction in the energy efficiency of the air conditioner due to excessively high outdoor temperature.

[0036] Optionally, based on the air conditioner energy efficiency independent variable that affects the air conditioner energy efficiency, an air conditioner optimization control strategy is obtained, including: when the air conditioner energy efficiency independent variable is the accumulated running time of the air conditioner, the air conditioner with energy efficiency lower than the standard energy efficiency can be turned off, and the missing cooling load can be compensated by other air conditioners in the computer room. In this way, when the running time is the main factor affecting the air conditioner energy efficiency, the air conditioner is likely to have a fault due to long-term operation. Through the actual energy efficiency of each air conditioner in the computer room, the air conditioner with abnormal and low energy efficiency is found, and the air conditioner is turned off. The cooling load of the faulty air conditioner is compensated by other air conditioners with normal operating energy efficiency, which can reduce the energy waste caused by the failure of the air conditioner with low cooling capacity and high energy consumption, and achieve the purpose of energy saving.

[0037] In some embodiments, for the shut down air conditioner, personnel can be arranged to perform on-site repair and replacement, which improves the efficiency of manual maintenance and optimizes the air conditioner maintenance plan.

[0038] Optionally, based on the air conditioning energy efficiency independent variable that affects the air conditioning energy efficiency, an air conditioning optimization control strategy is obtained, including: when the air conditioning energy efficiency independent variable is the equipment power, the air conditioning can be automatically adjusted according to the equipment power. In this way, when the main factor that should modify the air conditioning energy efficiency is the equipment power, the parameters of the air conditioning are automatically controlled according to the equipment power, the main factors affecting the air conditioning energy efficiency can be discovered in time, avoiding complicated manual maintenance and finely managing the air conditioning control plan.

[0039] In some embodiments, measured data of a certain computer room is selected, for example, data selected from November 1, 2020 to October 31, 2021 is taken as an example, a regression model is constructed and the regression coefficient is solved for the preprocessed data set, and the regression coefficient of the air conditioning energy efficiency independent variable is obtained as listed in the following table:

[0040]

[0041] Const is a constant, R 2For the degree of fit, if the value of the regression coefficient is positive, it means that the corresponding variable has a positive correlation with the air conditioning energy efficiency. If it is negative, it means that the corresponding variable has a negative correlation with the air conditioning energy efficiency. The larger the absolute value of the regression coefficient, the greater the impact on the air conditioning energy consumption. When the regression coefficient is close to 0, it has almost no impact on the air conditioning energy efficiency. From the above table, it can be seen that overall, the changes in the indoor and outdoor temperatures of the computer room have a significant impact on the energy efficiency of the air conditioner. Since the power of the equipment in a small computer room does not change much over a period of time, the impact on the energy efficiency of the computer room air conditioner is small. The cumulative running time of the computer room air conditioner has a certain impact on the energy efficiency of the air conditioner. In order to make more efficient use of the computer room split air conditioner, it should be mainly based on the perspective of the indoor and outdoor temperatures of the computer room. When the outdoor temperature is low, such as in winter, on the premise of meeting the indoor temperature safety requirements of the small computer room, some or all air conditioners can be dormant or shut down to reduce the energy consumption of the computer room. Computer room inspection personnel should regularly or irregularly inspect and maintain air conditioners that have been running for a long time. Air conditioners that have been in use for a long time in some computer rooms and have very low actual operating efficiency should be repaired or replaced in a timely manner.

[0042] like Figure 2 As shown, the embodiment of the present invention provides another method for evaluating the energy efficiency of a split-type air conditioner in a computer room based on quantile regression, which comprises the following steps:

[0043] S201, constructing a quantile regression model according to target indicators; wherein the target indicators include outdoor temperature, indoor temperature, accumulated air conditioning operation time and equipment power.

[0044] S202, preprocessing the currently collected initial indicator data to obtain target indicator data; wherein, when the initial indicator data has missing values, the average value of the initial indicator data is used to fill in the missing values ​​to obtain the target indicator data.

[0045] S203, obtaining a regression coefficient of an air-conditioning energy efficiency independent variable according to the quantile regression model and the currently collected target indicator data, wherein the air-conditioning energy efficiency independent variable is the target indicator.

[0046] S204: Obtain an air conditioning optimization control strategy based on the regression coefficient.

[0047] The detailed working process of this embodiment is to construct a quantile regression model according to the target indicator, pre-process the initial indicator data currently collected to obtain the target indicator data, wherein when there are missing values ​​in the initial indicator data, fill them with the average value of the initial indicator data to obtain the target indicator data, and obtain the regression coefficient of the air conditioning energy efficiency independent variable according to the quantile regression model and the target indicator data, wherein the air conditioning energy efficiency independent variable is the target indicator, and obtain the air conditioning optimization control strategy according to the regression coefficient. Based on the above further improvement, since the initial indicator data currently collected is pre-processed to obtain the target indicator data, the pre-processed target data is also generated to make up for the missing values ​​so that the quantile regression coefficient can be solved more accurately.

[0048] In some embodiments, data preprocessing is to remove invalid data, irregular data, and erroneous data collected. One is the case of missing values, and there are also cases where duplicate values ​​appear. For example, if two rows of data are exactly the same, one row can be deleted. Another is the case of duplicate data in the same column. In this case, it is necessary to consider whether the field allows duplicate values. If not, delete the redundant duplicate values. In addition, box plots can be used to identify whether there are singular values. Singular values ​​refer to values ​​that far exceed the normal range of the data. If so, the singular values ​​are deleted.

[0049] An embodiment of the present invention provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above method are implemented.

[0050] An embodiment of the present invention provides a readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the above method are implemented.

[0051] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the purpose and scope of the technical solution of the present invention, which should be included in the scope of the claims of the present invention.

Claims

1. A method for evaluating the energy efficiency of split-type air conditioners in computer rooms based on quantile regression, characterized in that: Constructing a quantile regression model based on target indicators; wherein the target indicators include outdoor temperature, indoor temperature, accumulated air conditioning operation time and equipment power; According to the quantile regression model and the currently collected target indicator data, a regression coefficient of the air conditioning energy efficiency independent variable is obtained; wherein the air conditioning energy efficiency independent variable is the target indicator; According to the regression coefficient, an air conditioning optimization control strategy is obtained.

2. The method for evaluating energy efficiency of a split-type air conditioner in a computer room based on quantile regression according to claim 1, characterized in that: The formula for constructing a quantile regression model based on the target indicator is: y=a0+a1 x1+a2 x2+a3 x3+a4 x4+u, where a0, a1, a2, a3, and a4 are the coefficients of the variables to be estimated, y is the expectation about x, x1 is the outdoor temperature, x2 is the indoor temperature, x3 is the accumulated running time of the air conditioner, x4 is the equipment power, and u is the residual.

3. The method for evaluating energy efficiency of a split-type air conditioner in a computer room based on quantile regression according to claim 1, characterized in that: Before obtaining the regression coefficient of the air conditioner energy efficiency independent variable according to the quantile regression model and the currently collected target indicator data, the method further includes: Preprocess the currently collected initial indicator data to obtain the target indicator data; When there are missing values ​​in the initial indicator data, the missing values ​​are filled with the average value of the initial indicator data to obtain the target indicator data.

4. The method for evaluating energy efficiency of a split-type air conditioner in a computer room based on quantile regression according to claim 1, characterized in that: According to the quantile regression model and the currently collected target indicator data, the regression coefficient of the air conditioning energy efficiency independent variable is obtained, including: According to the currently collected target indicator data, the linear programming method is used to estimate its minimum weighted absolute deviation, and the regression coefficient of the air conditioning energy efficiency independent variable is obtained, which can be expressed as follows: min Eρ τ (y-a0-a1x1-a2x2-...-a k x k ), and further obtain Among them, ρ τ (t)=t(τ-I(t<0)),τ∈(0,1), E is the expectation, τ is the quantile, is the mean of the random variable, is the regression coefficient of the air conditioning energy efficiency independent variable, x1, x2, ..., x k The target indicator data currently being collected.

5. The method for evaluating energy efficiency of a split-type air conditioner in a computer room based on quantile regression according to claim 1, characterized in that: According to the regression coefficient, the air conditioning optimization control strategy is obtained, including: When the absolute value of the regression coefficient is greater than 0.01, it can be considered that the air conditioning energy efficiency independent variable corresponding to the regression coefficient has an impact on the air conditioning energy efficiency; According to the air conditioning energy efficiency independent variable affecting the air conditioning energy efficiency, an air conditioning optimization control strategy is obtained.

6. A method for evaluating energy efficiency of a split-type air conditioner in a computer room based on quantile regression as claimed in claim 5, characterized in that: According to the air conditioning energy efficiency independent variable affecting the air conditioning energy efficiency, an air conditioning optimization control strategy is obtained, including: When the air conditioning energy efficiency independent variable is the indoor temperature or the outdoor temperature, the air conditioning may be turned off when the outdoor temperature is lower than the indoor temperature, and the air conditioning may be restored to the on state when the indoor temperature is greater than or equal to the outdoor temperature.

7. The method for evaluating energy efficiency of a split-type air conditioner in a computer room based on quantile regression according to claim 5, characterized in that: According to the air conditioning energy efficiency independent variable affecting the air conditioning energy efficiency, an air conditioning optimization control strategy is obtained, including: When the air conditioner energy efficiency independent variable is the accumulated running time of the air conditioner, the air conditioner with energy efficiency lower than the standard energy efficiency may be turned off, and the missing cooling load may be compensated by other air conditioners in the computer room.

8. The method for evaluating energy efficiency of a split-type air conditioner in a computer room based on quantile regression according to claim 5, characterized in that: According to the air conditioning energy efficiency independent variable affecting the air conditioning energy efficiency, an air conditioning optimization control strategy is obtained, including: When the air conditioner energy efficiency independent variable is equipment power, the air conditioner can be automatically adjusted according to the equipment power.

9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

10. A readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of any one of the methods of claims 1 to 8 are implemented.

Images