Data Center Energy Saving Control Method, System and Storage Medium

Abstract

The present invention provides a data center energy-saving control method, system, and storage medium, belonging to the technical field of data centers. Specifically, it includes: using the time distribution data of divided time periods in different similar time period groups to determine the reference time period group in the similar time period group of the server. Based on the time of the divided time periods in different reference time period groups, the divided time periods are divided into different time periods. According to the change data of the temperature monitoring data of the server between different time periods in each reference time period group, the heat dissipation abnormal servers in the server are determined. When it is determined that there are no heat dissipation abnormal servers with fluctuating data processing amounts based on the change situation of the data processing amounts of the heat dissipation abnormal servers in the data center on different dates, the temperature control strategy of the temperature control device in the data center is determined based on the data processing amounts of the heat dissipation abnormal servers on different dates, reducing the energy consumption of temperature control.

Description

Technical Field

[0001] The present invention belongs to the technical field of data centers, and in particular, relates to an energy-saving control method, system, and storage medium for a data center. Background Art

[0002] In order to achieve energy-saving control of a data center and reduce the energy consumption of the data center, in the patent application for invention CN118981618A "An Energy-Saving Control Method and System for a Data Center", when the real-time energy consumption is not within the range of historical energy consumption data, the thermal management system determines the interval where the operating temperature value of the main equipment is located and decides the operations to be performed, which can solve the problem of the lag in updating control parameters caused by the inability to update the data of the energy-saving system of the existing data center in a timely manner due to changes in equipment status. However, there are the following technical problems:

[0003] During the process of controlling the energy consumption of a data center, since the energy consumption data of the data center is related to the data processing volume of different servers in the data center, this leads to the determination of the temperature control strategy by using the real-time energy consumption. Once the data processing volume changes, it will inevitably cause a delay in temperature control, making it difficult to meet the requirements of reliable operation of the server.

[0004] In view of the above technical problems, specifically, the present application provides an energy-saving control method, system, and storage medium for a data center. Summary of the Invention

[0005] To achieve the object of the present invention, the present invention adopts the following technical solutions:

[0006] According to one aspect of the present invention, an energy-saving control method for a data center is provided.

[0007] An energy-saving control method for a data center specifically includes:

[0008] S1 Obtain the historical monitoring data of the servers in the data center, use the historical monitoring data to determine the deviation of the data processing volume between different divided time periods, and divide the divided time periods into different similar time period groups based on the deviation;

[0009] S2 Use the time distribution data of the divided time periods in different similar time period groups to determine the reference time period group in the similar time period group of the server. Based on the time of the divided time periods in different reference time period groups, divide the divided time periods into different time periods. When determining the change data of the temperature monitoring data of the server between different time periods in each reference time period group and there is a server with abnormal heat dissipation in the server, proceed to the next step;

[0010] S3 determines the variation of the data processing volume of the heat dissipation abnormal servers in the data center on different dates, and when it is determined that there are no heat dissipation abnormal servers with fluctuating data processing volume by using the variation, the temperature control strategy of the temperature control device in the data center is determined based on the data processing volume of the heat dissipation abnormal servers on different dates.

[0011] The beneficial effects of the present invention are as follows:

[0012] According to the variation data of the temperature monitoring data of the servers between different time periods in each reference time period group, it is determined whether there are heat dissipation abnormal servers in the servers, thereby realizing the variation of the temperature monitoring data of the servers between different time periods in each reference time period group, realizing the screening of the servers with poor heat dissipation volume variation, and also laying a foundation for determining the differential temperature control strategy according to whether there are servers with poor heat dissipation volume in the data center and the distribution data of the servers with poor heat dissipation volume.

[0013] The temperature control strategy of the temperature control device in the data center is determined based on the data processing volume of the heat dissipation abnormal servers on different dates, so that both the distribution data of the heat dissipation abnormal servers in the data center and the probability of temperature abnormality caused by the size of the data processing volume of the heat dissipation abnormal servers in the data center are considered, realizing the determination of the temperature control strategy from multiple perspectives, ensuring the reliability of temperature control and reducing the energy consumption of temperature control.

[0014] A further technical solution is that the historical monitoring data of the server includes the data processing volume of the server in different divided time periods.

[0015] A further technical solution is that the divided time period is 30 minutes or 1 hour.

[0016] A further technical solution is that the deviation situation of the data processing volume between the divided time periods is determined according to the deviation amount of the data processing volume between the divided time periods.

[0017] A further technical solution is that dividing the divided time periods into different similar time period groups specifically includes:

[0018] Based on the data processing volume between different divided time periods, the divided time periods located within the same data processing volume interval are divided into the same similar time period group.

[0019] A further technical solution is that the time distribution data of the divided time periods includes the distribution data of the divided time periods on different dates.

[0020] A further technical solution lies in that the method for determining the reference time period group in the similar time period groups is as follows:

[0021] Based on the time of the divided time periods in different similar time period groups, with a preset interval time period as the basis, divide the divided time periods into different time periods;

[0022] Determine the effective time periods in the time periods according to the number of divided time periods in different time periods;

[0023] Determine whether the similar time period group is a reference time period group according to the number of effective time periods.

[0024] A further technical solution lies in that the effective time period is the time period in which the number of divided time periods is greater than the preset number of divided time periods.

[0025] A further technical solution lies in that the method for determining the temperature control strategy of the temperature control device in the data center is as follows:

[0026] Based on the data processing volume of the heat dissipation abnormal server on different dates, determine the dates on which the data processing volume in the heat dissipation abnormal server is greater than the preset data processing volume, and use them as high-load dates;

[0027] Determine the high-load proportion factors of different heat dissipation abnormal servers according to the proportion of the number of high-load dates of different heat dissipation abnormal servers;

[0028] Based on the sum of the high-load proportion factors of different heat dissipation abnormal servers, determine the load abnormal factor of the data center, and use the load abnormal factor to determine the temperature control strategy of the temperature control device in the data center.

[0029] A further technical solution lies in that using the load abnormal factor to determine the temperature control strategy of the temperature control device in the data center specifically includes:

[0030] When the load abnormal factor is greater than the preset abnormal factor threshold, use the set temperature threshold to adjust the temperature of the temperature control device;

[0031] When the load abnormal factor is not greater than the preset abnormal factor threshold, based on the load abnormal factor, determine the temperature control threshold of the temperature control device according to the preset mapping function, and use the temperature control threshold to adjust the temperature of the temperature control device.

[0032] In a second aspect, the present invention provides a computer system, including: a memory and a processor communicatively connected, and a computer program stored on the memory and capable of running on the processor, wherein when the processor runs the computer program, it executes the above-described data center energy-saving control method.

[0033] In a third aspect, the present invention provides a computer storage medium, on which a computer program is stored, and when the computer program is executed in a computer, it causes the computer to execute the above-described data center energy-saving control method.

[0034] Other features and advantages will be described in the following specification, and the objectives and other advantages of the present invention are achieved and obtained by the structures specifically pointed out in the specification and the drawings.

[0035] To make the above objectives, features, and advantages of the present invention more obvious and understandable, the following specifically enumerates preferred embodiments and, in conjunction with the accompanying drawings, makes a detailed description as follows. Description of the Drawings

[0036] By referring to the drawings and describing its exemplary embodiments in detail, the above and other features and advantages of the present invention will become more obvious.

[0037] Figure 1 is a flowchart of a data center energy-saving control method;

[0038] Figure 2 is a flowchart of a method for determining a reference time period group in a similar time period group;

[0039] Figure 3 is a flowchart of a method for determining a heat dissipation abnormal server in a server;

[0040] Figure 4 is a flowchart of a method for determining a heat dissipation abnormal server with fluctuating data processing volume;

[0041] Figure 5 is a flowchart of a method for determining a temperature control strategy of a temperature control device in a data center;

[0042] Figure 6 is a framework diagram of a computer system. Detailed Embodiments

[0043] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of this specification, rather than all of the embodiments. Based on the embodiments of this specification, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of this specification.

[0044] If the temperature control strategy is determined by using the real-time energy consumption method, once the data processing volume changes, it will inevitably lead to a delay in temperature control, making it difficult to meet the requirements for the reliable operation of the server.

[0045] Similar time period group: Based on the data processing volumes between different divided time periods, the divided time periods within the same data processing volume range are divided into the same similar time period group.

[0046] Reference time period group: The divided time periods in the similar time period group are divided into different time periods. According to the number of divided time periods in different time periods, the effective time periods in the time periods are determined. The time periods with more than 10 divided time periods are used as effective time periods, and the similar time period groups with more than 15 effective time periods are used as reference time period groups.

[0047] Overheating abnormal server: Based on the change amount of the temperature monitoring data of the server between different time periods in each reference time period group, the temperature change amount between the current time period and other time periods is determined. The reference time period group with an average temperature change amount greater than 3 degrees Celsius compared to other time periods is used as the temperature change abnormal group. When the proportion of the temperature change abnormal group in the reference time period group is greater than 0.7, the server is determined to be an overheating abnormal server.

[0048] Overheating abnormal server with fluctuating data processing volume: Based on the data processing volumes of the overheating abnormal servers in the data center on different dates, the average value of the data processing volumes on different dates is determined and used as the reference data volume. According to the deviation amount between the data processing volume on different dates and the reference data volume, the deviation dates in the dates are determined. When the proportion of the number of deviation dates is greater than 0.2, the server is determined to be an overheating abnormal server with fluctuating data processing volume.

[0049] Temperature control strategy: The date when the data processing volume in the server with abnormal heat dissipation is greater than the preset data processing volume is used as the high-load date. The high-load proportion factor of different servers with abnormal heat dissipation is determined according to the proportion of the number of high-load dates of different servers with abnormal heat dissipation. The load anomaly factor of the data center is determined based on the sum of the high-load proportion factors of different servers with abnormal heat dissipation. When the load anomaly factor is greater than the preset anomaly factor threshold, the temperature of the temperature control device is adjusted using the set temperature threshold. When the load anomaly factor is not greater than the preset anomaly factor threshold, based on the load anomaly factor, the temperature control threshold of the temperature control device is determined according to the preset mapping function, and the temperature of the temperature control device is adjusted using the temperature control threshold.

[0050] Embodiment 1 To solve the above problems, according to one aspect of the present invention, as Figure 1 shown, a data center energy-saving control method is provided, which specifically includes:

[0051] S1 Obtain the historical monitoring data of the servers in the data center, use the historical monitoring data to determine the deviation of the data processing volume between different divided time periods, and divide the divided time periods into different similar time period groups based on the deviation;

[0052] Furthermore, the historical monitoring data of the servers includes the data processing volume of the servers in different divided time periods.

[0053] Specifically, the divided time period is 30 minutes or 1 hour.

[0054] It should be noted that the deviation of the data processing volume between the divided time periods is determined according to the deviation amount of the data processing volume between the divided time periods.

[0055] It can be understood that dividing the divided time periods into different similar time period groups specifically includes:

[0056] Based on the data processing volume between different divided time periods, the divided time periods within the same data processing volume interval are divided into the same similar time period group.

[0057] S2 Use the time distribution data of the divided time periods in different similar time period groups to determine the reference time period group in the similar time period group of the server. Based on the time of the divided time periods in different reference time period groups, the divided time periods are divided into different time periods. According to the change data of the temperature monitoring data of the servers between different time periods in each reference time period group, when it is determined that there is a server with abnormal heat dissipation in the server, proceed to the next step;

[0058] Specifically, the time distribution data of the divided time periods includes the distribution data of the divided time periods on different dates.

[0059] It can be understood that, as Figure 2 shown, the method for determining the reference time period group in the similar time period group is as follows:

[0060] Based on the time of the divided time periods in different similar time period groups, with a preset interval time period as the basis, divide the divided time periods into different time periods;

[0061] Determine the effective time periods in the time periods according to the number of divided time periods in different time periods;

[0062] Determine whether the similar time period group is a reference time period group according to the number of effective time periods.

[0063] Further, the effective time period is the time period in which the number of divided time periods is greater than the preset number of divided time periods.

[0064] In addition, it should be noted that when the number of effective time periods in the similar time period group is within the preset range of the number of effective time periods, then determine that the similar time period group is a reference time period group.

[0065] In another embodiment, the method for determining the reference time period group in the similar time period group is as follows:

[0066] Based on the time of the divided time periods in different similar time period groups, with a preset interval time period as the basis, divide the divided time periods into different time periods;

[0067] Based on the number of divided time periods in different time periods, determine the average value of the number of divided time periods in different time periods and use it as the average value of the number;

[0068] Determine whether the similar time period group is a reference time period group according to the average value of the number.

[0069] In another embodiment, the method for determining the reference time period group in the similar time period group is as follows:

[0070] S11 Based on the time of the divided time periods in the similar time period group, with a preset interval time period as the basis, divide the divided time periods into different time periods, determine the effective time periods in the time periods based on the number of divided time periods in different time periods, and determine the reference value coefficients of different effective time periods based on the number of time periods in different effective time periods;

[0071] S12 determines the interval duration between different adjacent valid time periods based on the distribution data of different valid time periods, and determines the distribution dispersion coefficient of the valid time periods by using the average value of the interval durations between different adjacent valid time periods.

[0072] S13 determines the reference coefficient evaluation quantity of the similar time period group according to the product of the average value of the reference value coefficients of different valid time periods and the distribution dispersion coefficient of the valid time periods, and determines whether it is a reference time period group by using the reference coefficient evaluation quantity.

[0073] Further, the reference value coefficient is determined according to the ratio of the number of time periods in the valid time period to the preset number of time periods.

[0074] In addition, it should be noted that the distribution dispersion coefficient of the valid time periods is determined according to the product of the average value of the interval durations between different adjacent valid time periods and a preset scale factor.

[0075] Further, dividing the divided time periods into different time intervals specifically includes:

[0076] Based on a preset interval time period, determine the preset interval time period corresponding to the divided time period, and divide the preset interval time period corresponding to the divided time period into the corresponding time intervals.

[0077] Specifically, as Figure 3 shown, the method for determining the heat dissipation abnormal server in the server is:

[0078] Based on the change data of the temperature monitoring data of the server between different time periods in each reference time period group, determine the change amount of the temperature monitoring data of the server between different time periods.

[0079] According to the change amount of the temperature monitoring data of the server between different time periods, determine the temperature change amount between the current time period and other time periods, and use the temperature change amount to determine the temperature change abnormal group in the reference time period group.

[0080] Determine whether the server is a heat dissipation abnormal server according to the number of the temperature change abnormal groups.

[0081] Further, the current time period is the time period closest to the current moment.

[0082] It should be noted that the temperature change abnormal group is a reference time period group in which the average value of the temperature change amount between the current time period and other time periods is greater than the preset change amount.

[0083] Optionally, the method for determining the heat dissipation abnormal server in the server is:

[0084] Determine the change amount of the temperature monitoring data of the server between different time periods based on the change data of the temperature monitoring data of the server between different time periods in each reference time period group;

[0085] Determine the temperature change amount between the current time period and other time periods based on the change amount of the temperature monitoring data of the server between different time periods, and determine the temperature change abnormal coefficient of the reference time group in combination with the interval duration between the current time period and other time periods;

[0086] Determine whether the server is a server with abnormal heat dissipation based on the average value of the temperature change abnormal coefficients of different reference time groups.

[0087] Further, when the average value of the temperature change abnormal coefficients of the server in different reference time groups is greater than the preset change coefficient threshold, it is determined that the server is a server with abnormal heat dissipation.

[0088] Optionally, the method for determining the server with abnormal heat dissipation in the server is as follows:

[0089] S21 Determine the change amount of the temperature monitoring data of the server between different time periods based on the change data of the temperature monitoring data of the server between different time periods in each reference time period group;

[0090] S22 Determine the temperature change amount between the current time period and other time periods based on the change amount of the temperature monitoring data of the server between different time periods, and determine the temperature change abnormal coefficient of the reference time group in combination with the interval duration between the current time period and other time periods;

[0091] Optionally, the following content is included in step S22:

[0092] S221 Determine the temperature change amount between the current time period and other time periods based on the change amount of the temperature monitoring data of the server between different time periods. When the temperature change amounts in different reference time groups are all within the preset change amount interval, it is determined that the server does not belong to the server with abnormal heat dissipation. When there is a reference time group in which the temperature change amount is not within the preset change amount interval, go to step S222;

[0093] S222 Determine the temperature change abnormal coefficient of the reference time group based on the temperature change amount between the current time period and other time periods and the interval duration between the current time period and other time periods. When the temperature change abnormal coefficients of different reference time groups are all within the preset abnormal coefficient interval, it is determined that the server does not belong to the server with abnormal heat dissipation. When there is a reference time group in which the temperature change abnormal coefficient is not within the preset abnormal coefficient interval, go to step S223;

[0094] S223 takes the reference time groups with abnormal temperature change coefficients not within the preset abnormal coefficient range as the temperature change abnormal groups. When the number of the temperature change abnormal groups is greater than the preset abnormal group number, it is determined that the server belongs to a server with abnormal heat dissipation. When the number of the temperature change abnormal groups is not greater than the preset abnormal group number, it proceeds to step S23.

[0095] S23 determines the weight coefficients of different reference time groups according to the number of time periods of different reference time groups, and combines the temperature change abnormal coefficients of different reference time groups to determine the temperature change evaluation amount of the server. The temperature change evaluation amount of the server is used to determine whether the server is a server with abnormal heat dissipation.

[0096] Optionally, the above step S23 includes the following content:

[0097] S231 determines the weight coefficients of different reference time groups according to the number of time periods of different reference time groups. When the sum of the weight coefficients of the temperature change abnormal groups is greater than the preset weight coefficient, it is determined that the server belongs to a server with abnormal heat dissipation. When the sum of the weight coefficients of the temperature change abnormal groups is not greater than the preset weight coefficient, it proceeds to step S232;

[0098] S232 When there is no temperature change abnormal group with a weight coefficient greater than the preset weight coefficient threshold, it proceeds to step S233. When there is a temperature change abnormal group with a weight coefficient greater than the preset weight coefficient threshold, it proceeds to step S234;

[0099] S233 obtains the number of temperature change abnormal groups. When the number of temperature change abnormal groups is less than the preset group number threshold, it is determined that the server does not belong to a server with abnormal heat dissipation. When the number of temperature change abnormal groups is not less than the preset group number threshold, it proceeds to step S234;

[0100] S234 determines the weight coefficients of different reference time groups according to the number of time periods of different reference time groups, and combines the temperature change abnormal coefficients of different reference time groups to determine the temperature change evaluation amount of the server. The temperature change evaluation amount of the server is used to determine whether the server is a server with abnormal heat dissipation.

[0101] Furthermore, when there is no server with abnormal heat dissipation in the server, the temperature of the temperature control device in the data center is controlled by using a preset temperature control strategy. Specifically, the temperature adjustment threshold of the temperature control device is determined according to the preset temperature threshold corresponding to the total daily energy consumption of different servers in the data center, and the temperature of the temperature control device is adjusted by using the temperature adjustment threshold.

[0102] In addition, it should be noted that the preset temperature threshold is determined according to the preset corresponding relationship between the total daily energy consumption and the temperature threshold.

[0103] S3 Determine the variation of the data processing volume of the heat dissipation abnormal servers in the data center on different dates, and when it is determined that there is no heat dissipation abnormal server with fluctuating data processing volume by using the variation, determine the temperature control strategy of the temperature control device in the data center based on the data processing volume of the heat dissipation abnormal servers on different dates.

[0104] Specifically, as Figure 4 shown, the method for determining the heat dissipation abnormal server with fluctuating data processing volume is:

[0105] Based on the data processing volume of the heat dissipation abnormal servers in the data center on different dates, determine the average value of the data processing volume on different dates and use it as the reference data volume;

[0106] Determine the deviation dates in the dates according to the deviation amount between the data processing volume on different dates and the reference data volume;

[0107] Based on the proportion of the number of the deviation dates, determine whether the server is a heat dissipation abnormal server with fluctuating data processing volume.

[0108] Further, when the proportion of the number of the deviation dates is greater than the preset proportion of the number of dates, determine that the server is a heat dissipation abnormal server with fluctuating data processing volume.

[0109] It can be understood that when there is a heat dissipation abnormal server with fluctuating data processing, the temperature of the temperature control device is adjusted by using the set temperature threshold.

[0110] Specifically, as Figure 5 shown, the method for determining the temperature control strategy of the temperature control device in the data center is:

[0111] Based on the data processing volume of the heat dissipation abnormal servers on different dates, determine the dates when the data processing volume in the heat dissipation abnormal servers is greater than the preset data processing volume and use them as high-load dates;

[0112] Determine the high-load proportion factors of different heat dissipation abnormal servers according to the proportion of the number of high-load dates of different heat dissipation abnormal servers;

[0113] Based on the sum of the high-load proportion factors of different heat dissipation abnormal servers, determine the load abnormal factor of the data center, and use the load abnormal factor to determine the temperature control strategy of the temperature control device in the data center.

[0114] Further, a temperature control strategy for the temperature control device of the data center is determined by using the load anomaly factor, specifically including:

[0115] When the load anomaly factor is greater than a preset anomaly factor threshold, the temperature of the temperature control device is adjusted by using the set temperature threshold;

[0116] When the load anomaly factor is not greater than the preset anomaly factor threshold, based on the load anomaly factor, a temperature control threshold of the temperature control device is determined according to a preset mapping function, and the temperature of the temperature control device is adjusted by using the temperature control threshold.

[0117] Embodiment 2 In the second aspect, as Figure 6 shown, the present invention provides a computer system, including: a memory and a processor connected by communication, and a computer program stored on the memory and capable of running on the processor, and when the processor runs the computer program, it executes the above-mentioned energy-saving control method for a data center.

[0118] Optionally, the above step S11 includes the following content:

[0119] S111 Based on the number of divided time periods in the similar time period group, when the number of divided time periods in the similar time period group is less than a preset number threshold, it is determined that the similar time period group does not belong to the reference time period group, and when the number of divided time periods in the similar time period group is not less than the preset number threshold, step S112 is entered;

[0120] S112 Based on the number of divided time periods in different time periods, when it is determined that there is no valid time period in the time period, it is determined that the similar time period group does not belong to the reference time period group, and when it is determined that there is a valid time period in the time period, step S113 is entered;

[0121] S113 The total number of time periods of different valid time periods is determined by using the number of time periods of different valid time periods. When the total number of time periods is less than a preset total number threshold, it is determined that the similar time period group belongs to the reference time period group, and when the total number of time periods is not less than the preset total number threshold, step S114 is entered;

[0122] S114 The reference value coefficients of different valid time periods are determined based on the number of time periods in different valid time periods. When the sum of the reference value coefficients of different valid time periods is less than a preset value coefficient threshold, it is determined that the similar time period group does not belong to the reference time period group, and when the sum of the reference value coefficients of different valid time periods is not less than the preset value coefficient threshold, step S12 is entered.

[0123] Optionally, the above step S12 includes the following content:

[0124] S121: When determining, based on the distribution data of different effective time periods, that the maximum value of the interval duration between effective time periods is within the preset interval duration range, it is determined that the similar time period group does not belong to the reference time period group; when the maximum value of the interval duration between effective time periods is not within the preset interval duration range, proceed to step S122;

[0125] S122: Obtain the effective time periods with an interval duration greater than the preset interval duration and use them as interval time periods. When the number of interval time periods is greater than the set value of the number of time periods, proceed to step S123; when the number of interval time periods is not greater than the set value of the number of time periods, it is determined that the similar time period group does not belong to the reference time period group;

[0126] S123: Use the average value of the interval durations between different adjacent effective time periods to determine the distribution dispersion coefficient of the effective time periods. When the distribution dispersion coefficient of the effective time periods is less than the preset dispersion coefficient threshold, it is determined that the similar time period group belongs to the reference time period group; when the distribution dispersion coefficient of the effective time periods is not less than the preset dispersion coefficient threshold, proceed to step S12.

[0127] Embodiment 3. In a third aspect, the present invention provides a computer storage medium, on which a computer program is stored. When the computer program is executed on a computer, the computer is made to execute the above data center energy-saving control method.

[0128] Optionally, the method for determining the heat dissipation abnormal server with fluctuating data processing volume is as follows:

[0129] Based on the data processing volumes of the heat dissipation abnormal servers in the data center on different dates, determine the median of the data processing volumes on different dates and use it as the reference data volume;

[0130] When the deviation amounts between the data processing volumes on different dates and the reference data volume are all within the preset deviation amount range, it is determined that the server does not belong to the heat dissipation abnormal server with fluctuating data processing volume;

[0131] When there are dates where the deviation amount between the data processing volume and the reference data volume is not within the preset deviation amount range:

[0132] Take the dates where the deviation amount between the data processing volume and the reference data volume is not within the preset deviation amount range as the deviation dates among the dates. When the number of deviation dates is greater than the preset deviation date number threshold, it is determined that the server belongs to the heat dissipation abnormal server with fluctuating data processing volume;

[0133] When the number of the deviation dates is not greater than a preset deviation date quantity threshold:

[0134] Based on the deviation amounts between the data processing amounts of different deviation dates and the reference data amount, determine the deviation coefficients of different deviation dates. When the sum of the deviation coefficients of different deviation dates is greater than a preset deviation coefficient, it is determined that the server belongs to a heat dissipation abnormal server with fluctuating data processing amount;

[0135] When the sum of the deviation coefficients of different deviation dates is not greater than a preset deviation coefficient:

[0136] When the sum of the deviation coefficients of different deviation dates is not within a preset deviation coefficient interval:

[0137] It is determined that the server does not belong to a heat dissipation abnormal server with fluctuating data processing amount;

[0138] When the sum of the deviation coefficients of different deviation dates is within a preset deviation coefficient interval:

[0139] Determine the server deviation coefficient based on the quantity proportion of the deviation dates and the average value of the deviation coefficients of different deviation dates, and use the server deviation coefficient to determine whether the server is a heat dissipation abnormal server with fluctuating data processing amount.

[0140] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the embodiments of the device, equipment, and non - volatile computer storage medium, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiments.

[0141] The above describes specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be executed in a different order from that in the embodiments and still achieve the desired results. Additionally, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0142] The above is only one or more embodiments of this specification and is not used to limit this specification. For those skilled in the art, one or more embodiments of this specification can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of this specification shall be included within the scope of the claims of this specification.

Claims

1. A data center energy-saving control method, characterized in that, Specifically include: Obtain the historical monitoring data of the servers in the data center, use the historical monitoring data to determine the deviation of the data processing volume between different divided time periods, and divide the divided time periods into different similar time period groups based on the deviation; Use the time distribution data of the divided time periods in different similar time period groups to determine the reference time period group in the similar time period group of the server. Based on the time of the divided time periods in different reference time period groups, divide the divided time periods into different time periods. When determining that there is a heat dissipation abnormal server in the server according to the change data of the temperature monitoring data of the server between different time periods in each reference time period group, proceed to the next step; Determine the change of the data processing volume of the heat dissipation abnormal server in the data center on different dates, and use the change to determine the temperature control strategy of the temperature control device in the data center when there is no heat dissipation abnormal server with fluctuating data processing volume; The method for determining the heat dissipation abnormal server in the server is: Based on the change data of the temperature monitoring data of the server between different time periods in each reference time period group, determine the change amount of the temperature monitoring data of the server between different time periods; According to the change amount of the temperature monitoring data of the server between different time periods, determine the temperature change amount between the current time period and other time periods, and use the temperature change amount to determine the temperature change abnormal group in the reference time period group; Determine whether the server is a heat dissipation abnormal server based on the number of the temperature change abnormal groups. The temperature change abnormal group is a reference time period group in which the average value of the temperature change amount between the current time period and other time periods is greater than the preset change amount; The method for determining the heat dissipation abnormal server with fluctuating data processing volume is: Based on the data processing volume of the heat dissipation abnormal server in the data center on different dates, determine the average value of the data processing volume on different dates and use it as the reference data volume; Determine the deviation date in the date according to the deviation amount between the data processing volume on different dates and the reference data volume; Determine whether the server is a heat dissipation abnormal server with fluctuating data processing volume based on the proportion of the number of the deviation dates; When there is a heat dissipation abnormal server with fluctuating data processing, use the set temperature threshold to adjust the temperature of the temperature control device; Based on the data processing volume of the heat dissipation abnormal server on different dates, determine the date when the data processing volume in the heat dissipation abnormal server is greater than the preset data processing volume and use it as the high-load date; Determine the high-load proportion factor of different heat dissipation abnormal servers according to the proportion of the number of high-load dates of different heat dissipation abnormal servers; Determine the load anomaly factor of the data center based on the sum of the high-load proportionality factors of different heat dissipation abnormal servers. When the load anomaly factor is greater than the preset anomaly factor threshold, use the set temperature threshold to adjust the temperature of the temperature control device; When the load anomaly factor is not greater than the preset anomaly factor threshold, based on the load anomaly factor, determine the temperature control threshold of the temperature control device according to the preset mapping function, and use the temperature control threshold to adjust the temperature of the temperature control device.

2. The energy-saving control method for a data center according to claim 1, wherein, The historical monitoring data of the server includes the data processing volume of the server in different divided time periods.

3. The energy-saving control method for a data center according to claim 2, wherein The divided time period is 30 minutes or 1 hour.

4. The energy-saving control method for a data center according to claim 1, wherein, The deviation situation of the data processing volume between the divided time periods is determined according to the deviation amount of the data processing volume between the divided time periods.

5. The energy-saving control method for a data center according to claim 4, wherein Dividing the divided time periods into different similar time period groups specifically includes: Based on the data processing volume between different divided time periods, divide the divided time periods within the same data processing volume interval into the same similar time period group.

6. The energy-saving control method for a data center according to claim 1, characterized in that The method for determining the reference time period group in the similar time period group is: Based on the time of the divided time periods in different similar time period groups, divide the divided time periods into different time periods based on the preset interval time period; Determine the effective time period in the time period according to the number of divided time periods in different time periods; Determine whether the similar time period group is a reference time period group according to the number of effective time periods.

7. The energy-saving control method for a data center according to claim 6, characterized in that, The effective time period is the time period in which the number of divided time periods is greater than the preset number of divided time periods.

8. A computer system, comprising: A memory and a processor in communication connection, and a computer program stored on the memory and capable of running on the processor. When the processor runs the computer program, it executes a data center energy-saving control method according to any one of claims 1-7.

9. A computer storage medium having a computer program stored thereon, and when the computer program is executed on a computer, it is characterized in that, Cause a computer to execute a data center energy-saving control method according to any one of claims 1-7.

Images