Load prediction model establishment method, machine room group control system control method and medium

Abstract

This invention relates to a data center group control system, specifically providing a method for establishing a load forecasting model, a control method for the data center group control system, and a medium, aiming to solve the problem that existing load forecasting is not based on public building condition parameters. To this end, the invention proceeds as follows: S1. Construct a two-dimensional array model and use it as the model to be trained; S2. Obtain public building condition parameters and train the model to be trained based on these parameters, wherein the public building condition parameters include at least public building status parameters and the current cooling capacity value within the public building; S3. Determine whether the model training is complete; S4. If not, repeat steps S2-S4 until model training is complete, generating a load forecasting model. Based on the generated load forecasting model, the public building status parameters are input into the load forecasting model to obtain the predicted load; based on the predicted load, the data center group control system is controlled to perform corresponding temperature control operations.

Description

Technical Field

[0001] This invention relates to a data center group control system, specifically providing a method for establishing a load prediction model, a control method for a data center group control system, and a medium. Background Technology

[0002] Currently, in the group control system of refrigeration plant rooms in public buildings, the cooling load of the refrigeration station is often adjusted based on the feedback of the actual cooling demand at the terminal. This method lacks foresight and only responds passively when the terminal load changes. As a result, it is easy to cause untimely cooling, resulting in a poor user experience at the terminal. It is also easy to cause slow cooling load response of the refrigeration station. In order to compensate for this shortcoming, over-cooling is often caused, resulting in energy waste.

[0003] Existing technologies address the passive response problem of refrigeration plants through load forecasting. However, these technologies rely on historical load curves at the terminal level for load forecasting, without taking into account daily changes in pedestrian traffic and the enthalpy of outdoor air in public buildings. This results in significant load forecasting deviations and fails to achieve the desired temperature control effect.

[0004] Accordingly, there is a need in this field for a new method for establishing load forecasting models to address the aforementioned problems. Summary of the Invention

[0005] The present invention aims to solve the above-mentioned technical problems, namely, to solve the problem that existing load forecasting is not based on parameters of public buildings, resulting in large forecasting deviations and thus reducing the temperature control effect.

[0006] To achieve the above objectives, in a first aspect, the present invention provides a method for establishing a load forecasting model, applied to public buildings, the method comprising:

[0007] S1. Construct a two-dimensional array model and use the two-dimensional array model as the model to be trained;

[0008] S2. Obtain the public building condition parameters, and train the model to be trained based on the public building condition parameters, wherein the public building condition parameters include at least the public building state parameters and the current cooling capacity value inside the public building;

[0009] S3. Determine whether the training of the model to be trained is complete;

[0010] S4. If not completed, repeat steps S2 to S4 until the model training is completed and the load prediction model is generated.

[0011] In the optional technical solutions of the above-mentioned load forecasting model establishment method, the steps of "constructing a two-dimensional array model" include:

[0012] Obtain the threshold for the number of people inside the public building and the threshold for the external enthalpy value of the public building;

[0013] The one-dimensional domain range of the two-dimensional array is determined based on the threshold value of the external enthalpy of the public building;

[0014] The range of the two-dimensional domain of the two-dimensional array is determined based on the threshold number of people in the public building.

[0015] In the optional technical solutions of the above-mentioned load forecasting model establishment method, the step of "training the model to be trained based on the public building condition parameters" includes:

[0016] Set a first parameter j, assign a value to the first parameter j, and update the assigned value of the first parameter j;

[0017] Set a second parameter i, assign a value to the second parameter i, and update the assigned value of the second parameter i;

[0018] After completing the assignment and update of the first parameter j and the second parameter i, determine whether the [j, i] term in the model to be trained is equal to the initial value;

[0019] Based on the judgment result, the [j, i] terms in the model to be trained are updated.

[0020] In the optional technical solution of the above-mentioned load forecasting model establishment method, the public building state parameters include the minimum value of the external enthalpy of the public building, the maximum value of the external enthalpy of the public building, and the current external enthalpy of the public building. The step of "assigning a value to the first parameter j and updating the assignment of the first parameter j" includes:

[0021] S11. Assign the minimum external enthalpy value of the public building to the first parameter j;

[0022] S12. Determine whether the first parameter j is consistent with the current external enthalpy value of the public building;

[0023] S13. If they match, complete the assignment update of the first parameter j; otherwise, update the assignment of the first parameter j.

[0024] S14. Repeat steps S12 to S14 until the value of the first parameter j is greater than the maximum value of the external enthalpy of the public building.

[0025] In the optional technical solution of the above-mentioned load forecasting model establishment method, the public building status parameters include the minimum number of people in the public building, the maximum number of people in the public building, and the current number of people in the public building. The step of "assigning a value to the second parameter i and updating the assignment of the second parameter i" includes:

[0026] S21. Assign the minimum number of people in the public building to the second parameter i;

[0027] S22. Determine whether the second parameter i is consistent with the current number of people in the public building;

[0028] S23. If they match, complete the assignment update of the second parameter i; otherwise, update the assignment of the second parameter i.

[0029] S24. Repeat steps S22 to S24 until the value of the second parameter i is greater than the maximum number of people in the public building.

[0030] In the optional technical solutions of the above-mentioned load forecasting model establishment method, the step of "updating the [j, i] terms in the model to be trained based on the judgment result" includes:

[0031] When the [j, i] term in the model to be trained is equal to the initial value, the current cooling capacity value inside the public building is assigned to the [j, i] term in the model to be trained.

[0032] When the [j, i] term in the model to be trained is not equal to the initial value, the average of the current cooling capacity value in the public building and the [j, i] term in the model to be trained is assigned to the [j, i] term in the model to be trained.

[0033] In the optional technical solutions of the above-mentioned load forecasting model establishment method, the public building state parameters include the minimum external enthalpy value of the public building, the maximum external enthalpy value of the public building, the minimum number of people in the public building, and the maximum number of people in the public building. The step of "determining whether the model training of the model to be trained is completed" includes:

[0034] S31. Set a third parameter m, and assign the minimum external enthalpy value of the public building to the third parameter m; set a fourth parameter n, and assign the minimum number of people in the public building to the fourth parameter n;

[0035] S32. Determine whether the [m, n] term in the model to be trained is equal to the initial value;

[0036] S33. If the [m, n] term in the model to be trained is equal to the initial value, then the loop ends and it is determined that the model training of the training model has not been completed.

[0037] S34. If the value of the third parameter m is equal to the maximum value of the external enthalpy of the public building and the value of the fourth parameter n is equal to the maximum number of people in the public building, and the [m, n] term in the model to be trained is still not equal to the initial value, then the loop ends and it is determined that the model training of the model to be trained is completed.

[0038] S35. Otherwise, update the value of the third parameter m or the fourth parameter n, and repeat steps S32 to S35.

[0039] In a second aspect, the present invention also provides a control method for a data center group control system, the method comprising the following steps:

[0040] Obtain public building status parameters, wherein the public building status parameters include at least the current number of people in the public building and the current external enthalpy value of the public building;

[0041] The public building status parameters are input into the load prediction model to obtain the predicted load.

[0042] Based on the predicted load, the data center group control system is controlled to perform corresponding temperature control operations.

[0043] In a third aspect, the present invention also provides a data center group control system, the data center group control system including a data center group control system body, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the data center group control system control method as described above.

[0044] In a fourth aspect, the present invention also provides a readable storage medium storing a plurality of program codes adapted to be loaded and run by a processor to perform the load forecasting model establishment method or the above-described data center group control system control method as described above.

[0045] Those skilled in the art will understand that in the technical solution of this invention, the process involves: S1, constructing a two-dimensional array model and using it as the model to be trained; S2, acquiring public building condition parameters and training the model to be trained based on these parameters, wherein the public building condition parameters include at least public building status parameters and the current cooling capacity value within the public building; S3, determining whether the model training of the model to be trained is complete; and S4, if not, repeating steps S2 to S4 until model training is complete and a load prediction model is generated. Based on the generated load prediction model, the public building status parameters are input into the load prediction model to obtain the predicted load. Based on the predicted load, the computer room group control system executes corresponding temperature control operations. This setup enables load prediction based on public building condition parameters, reducing load prediction deviations, minimizing energy waste, and improving temperature control effectiveness.

[0046] Furthermore, the steps of "constructing a two-dimensional array model" include: obtaining the threshold for the number of people in the public building and the threshold for the external enthalpy of the public building; determining the one-dimensional domain range of the two-dimensional array based on the threshold for the external enthalpy of the public building; and determining the two-dimensional domain range of the two-dimensional array based on the threshold for the number of people in the public building. This setup enables load forecasting based on the number of people in the public building and the external enthalpy of the public building, expanding the applicability of load forecasting and further improving the user experience. Attached Figure Description

[0047] The disclosure of this invention will become more readily understood with reference to the accompanying drawings. It will be readily understood by those skilled in the art that these drawings are for illustrative purposes only and are not intended to limit the scope of protection of this invention. Furthermore, similar numbers in the drawings are used to denote similar components, wherein:

[0048] Figure 1 This is a schematic diagram of the main steps of a load forecasting model establishment method according to an embodiment of the present invention;

[0049] Figure 2 This is a flowchart illustrating the main steps of constructing a two-dimensional array model according to an embodiment of the present invention;

[0050] Figure 3 This is a schematic diagram of the main steps for training a model based on public building condition parameters according to an embodiment of the present invention.

[0051] Figure 4 This is a schematic diagram of the main steps in determining whether the training of the model to be trained is complete, according to an embodiment of the present invention.

[0052] Figure 5This is a schematic flowchart of the main steps of a data center group control system control method according to an embodiment of the present invention;

[0053] Figure 6 This is a schematic diagram of the module structure of a data center group control system that applies the control method of the data center group control system of the present invention. Detailed Implementation

[0054] Some embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0055] In the description of this invention, ordinal numbers such as "first" and "second" are used only to describe different technical features of the same type, and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature specified with "first" or "second" may explicitly or implicitly include at least one of that feature. Furthermore, the technical solutions or means of the various embodiments of this application can be combined with each other, as long as those skilled in the art can implement them. When the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed by this invention.

[0056] In the description of this invention, "module" and "processor" can include hardware, software, or a combination of both. A module may include hardware circuitry, various suitable sensors, communication ports, memory, and may also include software components, such as program code, or a combination of software and hardware. A processor may be a central processing unit, microprocessor, image processor, digital signal processor, or any other suitable processor. The processor has data and / or signal processing capabilities. The processor may be implemented in software, in hardware, or a combination of both. Non-transitory computer-readable storage media includes any suitable medium capable of storing program code, such as magnetic disks, hard disks, optical disks, flash memory, read-only memory, random access memory, etc. The singular terms "an" and "this" may also include plural forms.

[0057] As described in the background section, existing load forecasting methods do not base their predictions on parameters of public buildings, resulting in significant forecasting errors and reduced temperature control effectiveness. This invention provides a method for establishing a load forecasting model.

[0058] See appendix Figure 1 , Figure 1This is a schematic flowchart illustrating the main steps of a load forecasting model establishment method according to an embodiment of the present invention. The load forecasting model establishment method of the present invention is applied to public buildings, which can be commercial buildings (e.g., shopping malls), transportation buildings (e.g., subways, train stations), or educational, cultural, and health buildings, etc., without specific limitations. Figure 1 As shown, the load forecasting model establishment method of the present invention includes the following steps:

[0059] Step S101: Construct a two-dimensional array model and use the two-dimensional array model as the model to be trained.

[0060] Specifically, a two-dimensional array is essentially an array of arrays, that is, an "array of arrays". A two-dimensional array is also called a matrix, and a matrix with the same number of rows and columns is called a square matrix.

[0061] See appendix Figure 2 , Figure 2 This is a flowchart illustrating the main steps of constructing a two-dimensional array model according to an embodiment of the present invention. In some embodiments, constructing a two-dimensional array model further includes:

[0062] Step S1011: Obtain the threshold for the number of people in the public building and the threshold for the external enthalpy of the public building.

[0063] Step S1012: Determine the one-dimensional domain range of the two-dimensional array based on the threshold value of the external enthalpy of public buildings.

[0064] Step S1013: Determine the range of the two-dimensional domain of the two-dimensional array based on the threshold of the number of people in the public building.

[0065] Specifically, enthalpy refers to the total heat contained in air, usually measured per unit mass of dry air, and is called specific enthalpy. It is obtained by calculating the sum of the enthalpy of one kilogram of dry air and the enthalpy of the corresponding water vapor (contained in 1 kg of dry air). In engineering, we can determine whether air gains or loses heat by observing the change in specific enthalpy during the processing of a certain mass of air. An increase in the specific enthalpy of air indicates that heat has been gained; a decrease in the specific enthalpy of air indicates that heat has been lost.

[0066] Obtaining the threshold value of the external enthalpy of public buildings means obtaining the minimum and maximum values ​​of the external enthalpy of public buildings. The range of the external enthalpy of public buildings that is greater than or equal to the minimum value and less than or equal to the maximum value is used as the one-dimensional domain of the two-dimensional array. Obtaining the threshold value of the number of people in public buildings means obtaining the minimum and maximum values ​​of the number of people in public buildings. The range of the number of people in public buildings that is greater than or equal to the minimum value and less than or equal to the maximum value is used as the two-dimensional domain of the two-dimensional array.

[0067] After determining the range of the one-dimensional and two-dimensional domains, the specific settings for the one-dimensional and two-dimensional domains can be selected according to the actual situation. Taking the two-dimensional domain as an example, the minimum number of people in a public building can be 1, and the maximum number of people in a public building can be 5. Thus, the range of the two-dimensional domain is greater than or equal to 1 and less than or equal to 5. Therefore, the specific settings for the two-dimensional domain can be 1, 2, 3, 4, 5, or 1, 3, 5. The above-described values ​​for the maximum and minimum number of people in a public building and the specific settings for the two-dimensional domain are only illustrative examples; in practical applications, they can be selected according to actual needs.

[0068] It should be noted that although this description refers to determining the one-dimensional domain range of a two-dimensional array based on a threshold for the external enthalpy of a public building, and the two-dimensional domain range based on a threshold for the number of people within the public building, this is not restrictive. Those skilled in the art can also determine the one-dimensional domain range of a two-dimensional array based on a threshold for the number of people within the public building, and the two-dimensional domain range based on a threshold for the external enthalpy of the public building. Adjustments to the one-dimensional and two-dimensional domain ranges of the two-dimensional array do not change the principle of this invention; therefore, the adjusted technical solution will also fall within the protection scope of this invention.

[0069] Step S102: Obtain public building condition parameters and train the model to be trained based on the public building condition parameters, wherein the public building condition parameters include at least the public building status parameters and the current cooling capacity value inside the public building.

[0070] In some embodiments, the public building status parameters include public building personnel parameters and public building external enthalpy parameters, wherein the public building personnel parameters further include the minimum number of public building personnel, the maximum number of public building personnel, and the current number of public building personnel; the public building external enthalpy parameters further include the minimum value of public building external enthalpy, the maximum value of public building external enthalpy, and the current public building external enthalpy.

[0071] Step S103: Determine whether the training of the model to be trained is complete.

[0072] Step S104: If not completed, repeat steps S102 to S104 until model training is completed and a load prediction model is generated.

[0073] Based on the above steps S101 to S104, this invention proceeds as follows: S101: Construct a two-dimensional array model and use it as the model to be trained; S102: Obtain public building condition parameters and train the model to be trained based on these parameters, wherein the public building condition parameters include at least the public building status parameters and the current cooling capacity value within the public building; S103: Determine whether the model training is complete; S104: If not, repeat steps S102 to S104 until model training is complete, generating a load prediction model. This setup enables load prediction based on public building condition parameters, reducing load prediction errors, minimizing energy waste, and improving the user experience.

[0074] The following provides a further explanation of steps S102 and S103.

[0075] See appendix Figure 3 , Figure 3 This is a schematic diagram illustrating the main steps of training a model based on public building condition parameters according to an embodiment of the present invention. Figure 3 As shown, in some embodiments, training the model to be trained based on public building condition parameters further includes:

[0076] Step S1021: Set the first parameter j, assign a value to the first parameter j, and update the assigned value of the first parameter j.

[0077] Step S1022: Set the second parameter i, assign a value to the second parameter i, and update the assigned value of the second parameter i.

[0078] Step S1023: After completing the assignment and update of the first parameter j and the second parameter i, determine whether the [j, i] term in the model to be trained is equal to the initial value.

[0079] Step S1024: Based on the judgment result, update the [j, i] terms in the model to be trained.

[0080] Specifically, the two-dimensional array contains multiple rows and columns, and the [j, i] term in the model to be trained refers to the value corresponding to row j and column i in the two-dimensional array. For example, the initial value can be 0, or other values, such as 99999. The initial values ​​described above are only illustrative examples; in practical applications, they can be selected according to actual needs.

[0081] In some embodiments, the public building status parameters include the minimum external enthalpy of the public building, the maximum external enthalpy of the public building, and the current external enthalpy of the public building. Assigning a value to the first parameter j and updating the value of the first parameter j further includes:

[0082] S10211: Assign the minimum external enthalpy value of the public building to the first parameter j.

[0083] S10212: Determine whether the first parameter j is consistent with the current external enthalpy value of the public building.

[0084] S10213: If they match, complete the assignment and update of the first parameter j; otherwise, update the assignment of the first parameter j.

[0085] S10214: Repeat steps S10212 to S10214 until the value of the first parameter j is greater than the maximum value of the external enthalpy of the public building.

[0086] Specifically, determining whether the first parameter j is consistent with the current external enthalpy value of the public building includes: determining whether the first parameter j is equal to the current external enthalpy value of the public building, or determining whether the difference between the first parameter j and the current external enthalpy value of the public building is less than or equal to a first preset difference, that is, determining whether the absolute value of the difference between the first parameter j and the current external enthalpy value of the public building is less than or equal to the first preset difference.

[0087] Updating the value of the first parameter j involves updating the value of the first parameter j based on the specific settings of the one-dimensional domain in the model to be trained. For example, if the specific settings of the one-dimensional domain in the model to be trained are 1, 2, 3, 4, and 5, then updating the value of the first parameter j means adding 1 to its original value; if the specific settings of the one-dimensional domain in the model to be trained are 1, 3, and 5, then updating the value of the first parameter j means adding 2 to its original value. The specific settings of the one-dimensional domain and the methods for updating the value of the first parameter j described above are merely illustrative examples; in practical applications, they can be set according to actual needs.

[0088] In some embodiments, the public building status parameters include the minimum number of people in the public building, the maximum number of people in the public building, and the current number of people in the public building. Assigning a value to the second parameter i and updating the value of the second parameter i further includes:

[0089] S10221: Assign the minimum number of people in the public building to the second parameter i.

[0090] S10222: Determine whether the second parameter i is consistent with the current number of people in the public building.

[0091] S10223: If they match, complete the assignment and update of the second parameter i; otherwise, update the assignment of the second parameter i.

[0092] S10224: Repeat steps S10222 to S10224 until the value of the second parameter i is greater than the maximum number of people in the public building.

[0093] Specifically, determining whether the second parameter i is consistent with the number of people in the current public building includes: determining whether the second parameter i is equal to the number of people in the current public building, or determining whether the difference between the second parameter i and the number of people in the current public building is less than or equal to a second preset difference, that is, determining whether the absolute value of the difference between the second parameter i minus the number of people in the current public building is less than or equal to the second preset difference.

[0094] Updating the assignment of the second parameter i includes: updating the assignment of the second parameter i based on the specific setting method of the two-dimensional domain in the model to be trained. Exemplarily, if the specific setting of the two-dimensional domain in the model to be trained is, for example, 1, 2, 3, 4, 5, then updating the assignment of the second parameter i is to add 1 to the original assignment of the second parameter i; if the specific setting of the two-dimensional domain in the model to be trained is, for example, 1, 3, 5, then updating the assignment of the second parameter i is to add 2 to the original assignment of the second parameter i. The above specific setting methods of the two-dimensional domain and the method of updating the assignment of the second parameter i are only for illustrative purposes, and can be set according to actual needs in practical applications.

[0095] In some embodiments, further updating the [j, i] term in the model to be trained based on the judgment result includes:

[0096] S10241: When the [j, i] term in the model to be trained is equal to the initial value, assign the cooling value in the current public building to the [j, i] term in the model to be trained.

[0097] S10242: When the [j, i] term in the model to be trained is not equal to the initial value, assign the average value of the cooling value in the current public building and the [j, i] term in the model to be trained to the [j, i] term in the model to be trained.

[0098] It should be noted that although it is described here that when the [j, i] term in the model to be trained is not equal to the initial value, assign the average value of the cooling value in the current public building and the [j, i] term in the model to be trained to the [j, i] term in the model to be trained, this is not restrictive. Those skilled in the art can also assign the [j, i] term in the model to be trained by performing a weighted operation on the cooling value in the current public building and the [j, i] term in the model to be trained, that is, the [j, i] term in the model to be trained = the cooling value in the current public building * a + the [j, i] term in the model to be trained * b, where 0 < a < 1, 0 < b < 1 and a + b = 1. Adjusting the assignment method of the [j, i] term in the model to be trained does not change the principle of the present invention, so the adjusted technical solution will also fall within the protection scope of the present invention.

[0099] In some embodiments, the public building status parameters include the minimum external enthalpy of the public building, the maximum external enthalpy of the public building, the current external enthalpy of the public building, the minimum number of people in the public building, the maximum number of people in the public building, and the current number of people in the public building; steps S1021 to S1024 further include:

[0100] The first for loop starts, iterating from the minimum to the maximum external enthalpy of the public building to the first parameter j, assigning the minimum external enthalpy to j. It then checks if the assigned value of j equals the current external enthalpy of the public building. If it does, the second for loop starts, iterating from the minimum to the maximum number of people in the public building to the second parameter i. If not, the first parameter j is updated. The second for loop then starts, assigning the minimum number of people in the public building to the second parameter i. Finally, it checks if the assigned value of i equals the current number of people in the public building. If the values ​​are equal, then check if the [j, i] term in the model to be trained is equal to the initial value; if not, update the value of the second parameter i; after checking if the [j, i] term in the model to be trained is equal to the initial value, if the [j, i] term in the model to be trained is equal to the initial value, then assign the current cooling capacity value of the public building to the [j, i] term in the model to be trained; if the [j, i] term in the model to be trained is not equal to the initial value, then assign the average value of the current cooling capacity value of the public building and the [j, i] term in the model to the [j, i] term in the model to be trained; end the second for loop; end the first for loop.

[0101] See appendix Figure 4 , Figure 4 This is a schematic diagram illustrating the main steps of determining whether model training of the model to be trained is complete, according to an embodiment of the present invention. Figure 4 As shown, in some embodiments, the public building state parameters include the minimum external enthalpy of the public building, the maximum external enthalpy of the public building, the minimum number of people in the public building, and the maximum number of people in the public building. Determining whether model training of the model to be trained is complete further includes:

[0102] S1031: Set the third parameter m and assign the minimum external enthalpy value of the public building to the third parameter m; set the fourth parameter n and assign the minimum number of people in the public building to the fourth parameter n.

[0103] S1032: Determine whether the [m, n] terms in the model to be trained are equal to the initial values.

[0104] S1033: If the [m, n] terms in the model to be trained are equal to the initial values, then the loop ends and it is determined that the training of the model has not been completed.

[0105] S1034: If the value of the third parameter m is equal to the maximum value of the external enthalpy of the public building and the value of the fourth parameter n is equal to the maximum number of people in the public building, and the [m, n] term in the model to be trained is still not equal to the initial value, then the loop ends and the model training of the model to be trained is determined to be complete.

[0106] S1035: Otherwise, update the assignment of the third parameter m or the fourth parameter n, and repeat steps S1032 to S1035.

[0107] Specifically, the training of the model to be trained is determined by whether all terms in the model to be trained are equal to the initial value. If none of the terms in the model to be trained are equal to the initial value, the training of the model to be trained is considered complete; if at least one term in the model to be trained is equal to the initial value, the training of the model to be trained is considered incomplete.

[0108] In some embodiments, the public building state parameters include the minimum external enthalpy of the public building, the maximum external enthalpy of the public building, the minimum number of people in the public building, and the maximum number of people in the public building. Determining whether model training of the model to be trained is complete further includes:

[0109] Set the bool data type b = true; set the fifth parameter p, and start the third for loop of the fifth parameter p from the minimum value of the external enthalpy of the public building to the maximum value of the external enthalpy of the public building; set the sixth parameter q, and start the fourth for loop of the sixth parameter q from the minimum value of the number of people in the public building to the maximum value of the number of people in the public building. Specifically, the minimum external enthalpy of the public building is assigned to the fifth parameter p, and the minimum number of people inside the public building is assigned to the sixth parameter q. It checks whether the [p, q] term in the model to be trained is equal to the initial value. If it is, the boolean data type a = false; if not, the boolean data type a = true. The boolean data type b = b and a is updated. The fifth parameter p or the sixth parameter q is updated, and the [p, q] term in the model to be trained is checked again to see if it is equal to the initial value. This process is repeated until the fifth parameter p equals the maximum external enthalpy of the public building, at which point the third for loop ends, and the sixth parameter q equals the maximum number of people inside the public building, at which point the fourth for loop ends. After the third and fourth for loops end, the boolean data type b is checked to see if it is true. If it is, the model training is considered complete; otherwise, the model training is considered incomplete.

[0110] See appendix Figure 5 , Figure 5 This is a schematic flowchart illustrating the main steps of a data center group control system control method according to an embodiment of the present invention. Figure 5As shown, the present invention also provides a control method for a data center group control system, the method comprising the following steps:

[0111] S201: Obtain the status parameters of the public building, which include at least the number of people in the current public building and the current external enthalpy value of the public building.

[0112] S202: Input the public building status parameters into the load prediction model described in any one of the above statements to obtain the predicted load.

[0113] S203: Based on the predicted load, control the data center group control system to perform corresponding temperature control operations.

[0114] This setup enables load forecasting based on public building parameters, reducing forecasting errors, minimizing energy waste, and improving temperature control. For example, a people-counting camera can be added to the data center control system to obtain the current number of people inside the public building; alternatively, external temperature and humidity sensors can be added to the system to obtain the external temperature and humidity, and then the external enthalpy value of the public building can be derived from these measurements. The methods for obtaining the number of people inside and the external enthalpy value described above are merely illustrative examples; in practical applications, the appropriate method can be selected based on actual needs.

[0115] It should be noted that although the steps in the above embodiments of the load forecasting model establishment method and the data center group control system control method are described in a specific order, those skilled in the art will understand that in order to achieve the effects of the present invention, different steps do not necessarily have to be executed in such an order. They can be executed simultaneously (in parallel) or in other orders, and these variations are all within the scope of protection of the present invention.

[0116] See appendix Figure 6 , Figure 6 This is a schematic diagram of the module structure of a data center group control system applying the control method of the data center group control system of the present invention. For example... Figure 6 As shown, the present invention also provides a data center group control system. The data center group control system 600 includes a data center group control system body, a memory 601, and a processor 602. The memory 601 stores machine-executable instructions. When the machine-executable instructions are executed by the processor 602, the data center group control system can implement the data center group control system control method described in any of the above method embodiments. For ease of explanation, only the parts related to the embodiments of the present invention are shown. For specific technical details not disclosed, please refer to the method section of the embodiments of the present invention.

[0117] The memory 601 can be an internal storage unit of the data center cluster control system, such as a hard drive or RAM. The memory 601 can also be an external storage device of the data center cluster control system, such as a plug-in hard drive, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card. Furthermore, the memory 601 can include both internal and external storage units. The memory 601 is used to store computer programs and other programs and data required by the data center cluster control system. The memory 601 can also be used to temporarily store data that has been output or will be output.

[0118] The processor 602 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor.

[0119] In some possible implementations, the data center group control system may include multiple memories 601 and multiple processors 602. The program executing the data center group control system control method of the above-described method embodiments can be divided into multiple subroutines. Each subroutine can be loaded and run by a processor 602 to execute different steps of the data center group control system control method of the above-described method embodiments. Specifically, each subroutine can be stored in a different memory 601, and each processor 602 can be configured to execute programs in one or more memories 601 to jointly implement the data center group control system control method of the above-described method embodiments. That is, each processor 602 executes different steps of the data center group control system control method of the above-described method embodiments to jointly implement the data center group control system control method of the above-described method embodiments.

[0120] The aforementioned multiple processors 602 may be processors deployed on the same device, for example, multiple processors 602 may all be processors configured on a data center group control system; in addition, the aforementioned multiple processors 602 may also be processors deployed on different devices, for example, multiple processors 602 may be processors on a data center group control system and processors on a cloud server respectively.

[0121] Furthermore, the present invention also provides a computer-readable storage medium. In one embodiment of the computer-readable storage medium according to the present invention, the computer-readable storage medium can be configured to store a program for executing the load forecasting model establishment method or the data center group control system control method of the above-described method embodiments. This program can be loaded and run by a processor to implement the above-described load forecasting model establishment method or data center group control system control method. For ease of explanation, only the parts related to the embodiments of the present invention are shown; for specific technical details not disclosed, please refer to the method section of the embodiments of the present invention. The computer-readable storage medium can be a storage device comprising various electronic devices. Optionally, in the embodiments of the present invention, the computer-readable storage medium is a non-transitory computer-readable storage medium.

[0122] Furthermore, it should be understood that since the various modules are only provided to illustrate the functional units of the device of the present invention, the physical devices corresponding to these modules may be the processor itself, or a part of the processor's software, hardware, or a combination of software and hardware. Therefore, the number of modules shown in the figures is merely illustrative.

[0123] Those skilled in the art will understand that the various modules in the device can be adaptively split or combined. Such splitting or combining of specific modules will not cause the technical solution to deviate from the principles of the present invention; therefore, the technical solutions after splitting or combining will fall within the protection scope of the present invention.

[0124] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. A method for establishing a load forecasting model, applied to public buildings, characterized in that, The method includes: S1. Construct a two-dimensional array model and use the two-dimensional array model as the model to be trained; S2. Obtain the public building condition parameters, and train the model to be trained based on the public building condition parameters, wherein the public building condition parameters include at least the public building state parameters and the current cooling capacity value inside the public building; S3. Determine whether the training of the model to be trained is complete; S4. If not completed, repeat steps S2 to S4 until the model training is completed and the load prediction model is generated. The steps for "constructing a two-dimensional array model" include: Obtain the threshold for the number of people inside the public building and the threshold for the external enthalpy value of the public building; The one-dimensional domain range of the two-dimensional array is determined based on the threshold value of the external enthalpy of the public building; The range of the two-dimensional domain of the two-dimensional array is determined based on the threshold number of people in the public building; The step of "training the model to be trained based on the parameters of the public building" includes: Set a first parameter j, assign a value to the first parameter j, and update the assigned value of the first parameter j; Set a second parameter i, assign a value to the second parameter i, and update the assigned value of the second parameter i; After completing the assignment and update of the first parameter j and the second parameter i, determine whether the [j, i] term in the model to be trained is equal to the initial value; Based on the judgment result, the [j, i] terms in the model to be trained are updated; The public building state parameters include the minimum and maximum external enthalpy values ​​of the public building, the minimum and maximum number of people inside the public building, and the step of "determining whether the model training of the model to be trained is complete" includes: S31. Set a third parameter m, and assign the minimum external enthalpy value of the public building to the third parameter m; set a fourth parameter n, and assign the minimum number of people in the public building to the fourth parameter n; S32. Determine whether the [m, n] term in the model to be trained is equal to the initial value; S33. If the [m, n] term in the model to be trained is equal to the initial value, then the loop ends and it is determined that the model training of the training model has not been completed. S34. If the value of the third parameter m is equal to the maximum value of the external enthalpy of the public building and the value of the fourth parameter n is equal to the maximum number of people in the public building, and the [m, n] term in the model to be trained is still not equal to the initial value, then the loop ends and it is determined that the model training of the model to be trained is completed. S35. Otherwise, update the value of the third parameter m or the fourth parameter n, and repeat steps S32 to S35.

2. The load forecasting model establishment method according to claim 1, characterized in that, The public building status parameters include the minimum external enthalpy value of the public building, the maximum external enthalpy value of the public building, and the current external enthalpy value of the public building. The step of "assigning a value to the first parameter j and updating the assigned value of the first parameter j" includes: S11. Assign the minimum external enthalpy value of the public building to the first parameter j; S12. Determine whether the first parameter j is consistent with the current external enthalpy value of the public building; S13. If they match, complete the assignment update of the first parameter j; otherwise, update the assignment of the first parameter j. S14. Repeat steps S12 to S14 until the value of the first parameter j is greater than the maximum value of the external enthalpy of the public building.

3. The load forecasting model establishment method according to claim 1, characterized in that, The public building status parameters include the minimum number of people in the public building, the maximum number of people in the public building, and the current number of people in the public building. The step of "assigning a value to the second parameter i and updating the value of the second parameter i" includes: S21. Assign the minimum number of people in the public building to the second parameter i; S22. Determine whether the second parameter i is consistent with the current number of people in the public building; S23. If they match, complete the assignment update of the second parameter i; otherwise, update the assignment of the second parameter i. S24. Repeat steps S22 to S24 until the value of the second parameter i is greater than the maximum number of people in the public building.

4. The load forecasting model establishment method according to claim 1, characterized in that, The step of "updating the [j, i] terms in the model to be trained based on the judgment result" includes: When the [j, i] term in the model to be trained is equal to the initial value, the current cooling capacity value inside the public building is assigned to the [j, i] term in the model to be trained. When the [j, i] term in the model to be trained is not equal to the initial value, the average of the current cooling capacity value in the public building and the [j, i] term in the model to be trained is assigned to the [j, i] term in the model to be trained.

5. A control method for a computer room group control system, characterized in that, The method includes the following steps: Obtain public building status parameters, wherein the public building status parameters include at least the current number of people in the public building and the current external enthalpy value of the public building; The public building status parameters are input into the load prediction model according to any one of claims 1-4 to obtain the predicted load; Based on the predicted load, the data center group control system is controlled to perform corresponding temperature control operations.

6. A data center group control system, comprising a data center group control system body, 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, it implements the control method of the data center group control system as described in claim 5.

7. A readable storage medium storing a plurality of program codes, characterized in that, The program code is adapted to be loaded and run by a processor to perform the load forecasting model establishment method of any one of claims 1-4 or the data center group control system control method of claim 5.

Images