Data center pipeline optimization management method and system

Abstract

The present invention provides a data center pipeline optimization management method and system, which belongs to the field of optimization management technology, and specifically includes: when it is determined that the optimization processing of the matching optical cable line is not needed based on the overlap between the distribution data of the harmonic monitoring abnormal period and the data processing busy period of the corresponding server, based on the distribution data of the harmonic monitoring abnormal period, the abnormal situation of the data processing result of the corresponding server in the harmonic monitoring abnormal period is determined, and based on the abnormal situation, the interference risk server in the server is determined, and the optimization management method of the matching optical cable line is determined based on the interference risk server data in different harmonic monitoring abnormal periods and the data processing busy periods of different interference risk servers, thereby improving the reliability of the server operation and reducing the risk of electromagnetic interference.

Description

Technical Field

[0001] The present invention belongs to the technical field of optimization management, and in particular relates to a data center pipeline optimization management method and system. Background Art

[0002] Data center pipelines often involve multiple types of cables, such as network / fiber optic cables, cooling water pipes, and power lines. Therefore, there is a certain risk of interference between different pipeline systems. For example, cooling water pipes may cause short circuits in power lines, and power lines may also have a certain degree of impact on the signals of fiber optic cables. This makes optimizing data center pipelines to reduce risks a technical problem that needs to be solved urgently.

[0003] To solve the above technical problems, existing technical solutions often use IoT monitoring devices to monitor different types of pipeline systems, such as vibration sensors, temperature sensors, or infrared sensors. However, these technical solutions have the following technical drawbacks:

[0004] At the beginning of the design of the pipeline system in the data center, since the data flow of different servers is often difficult to accurately assess, the horizontal spacing between the network / fiber optic cables and the power lines is often required to be ≥30cm and the vertical crossing angle is ≥60° in accordance with national standards to avoid electromagnetic interference. However, after it is put into use, on the one hand, the data processing flow of different servers will change, which in turn causes the data flow of the fiber optic cables to change. On the other hand, the harmonic state of the power lines that may cause electromagnetic interference may also be abnormal, which may make it difficult to meet the electromagnetic interference risk requirements for the servers. This makes it difficult to determine how to optimize the electromagnetic interference treatment of the power lines based on the spacing between the network / fiber optic cables and the power lines, as well as the data flow of the fiber optic cables, to reduce the risk of electromagnetic interference and ensure the reliability of server operation. This has become a technical problem that needs to be solved urgently.

[0005] To solve the above technical problems, the present application provides a data center pipeline optimization management method and system. Summary of the Invention

[0006] To achieve the purpose of the present invention, the present invention adopts the following technical solutions:

[0007] Specifically, this application provides a data center pipeline optimization management method, which specifically includes:

[0008] S1 uses the interval data detection results of different pipeline systems in the data center to determine the risk interference location in the pipeline system. Based on the server data corresponding to different risk interference locations, it determines the harmonic monitoring line in the power line and the matching optical cable line.

[0009] S2 determines the overlap between the distribution data of the abnormal harmonic monitoring period and the busy data processing period of the corresponding server based on the harmonic monitoring data of the harmonic monitoring line, and proceeds to the next step when it is determined based on the overlap that the optimization processing of the matching optical cable line is not required;

[0010] S3: determining, based on the distribution data of the harmonic monitoring abnormal period, an abnormality of the data processing result of the corresponding server in the harmonic monitoring abnormal period, and determining an interference risk server among the servers based on the abnormality;

[0011] S4 uses different harmonics to monitor the interference risk server data during abnormal periods and the data processing busy periods of different interference risk servers to determine the optimal management method for matching optical cable lines.

[0012] The beneficial effects of the present invention are:

[0013] According to the abnormal situation of the data processing results of the server during the abnormal harmonic monitoring period, the interference risk server in the server is determined, which enables accurate assessment of the electromagnetic interference risk of the server during the abnormal harmonic monitoring period from the abnormal state of the data processing results during the abnormal harmonic monitoring period. It also lays the foundation for further determining the optimal management method of matching the optical cable line with the number of servers with higher interference risks, and also improves the reliability of data processing.

[0014] The interference risk server data in different harmonic monitoring abnormality periods and the data processing busy periods of different interference risk servers are used to determine the optimal management method for matching optical cable lines, thereby realizing the determination of the optimal management method for matching optical cable lines from two perspectives: the number of harmonic monitoring abnormality periods of interference risk servers and the changes in data processing busy periods. Not only the difference in the number of interference risk servers with a large number of harmonic monitoring abnormality periods is taken into account, but also the risk of overlap with harmonic monitoring abnormality periods due to changes in data processing busy periods is taken into account, thereby realizing the determination of differentiated optimal management methods for matching optical cable lines, which reduces the difficulty of optimization processing and improves the operating stability of the server.

[0015] Furthermore, the risk interference position is a position where the horizontal spacing between the optical fiber cable and the power line is less than 30 cm or the vertical intersection angle is less than 60°.

[0016] Furthermore, the server data corresponding to the risk interference location is based on the server connected by the optical fiber cable at the risk interference location.

[0017] Furthermore, the method for determining the harmonic monitoring line in the power line is:

[0018] Determine the risk interference location in the optical fiber cable based on the spacing between the optical fiber cable and the power line;

[0019] Determine the number of risk interference locations corresponding to different servers based on server data corresponding to different risk interference locations;

[0020] Based on the number of risk interference locations corresponding to different servers, it is determined whether the power line is a harmonic monitoring line.

[0021] Furthermore, the method for determining the optimization management method of the matching optical cable line is:

[0022] Determine the composition of the interference risk servers in the different harmonic monitoring abnormality periods using the interference risk server data in the different harmonic monitoring abnormality periods; and based on the composition of the interference risk servers, determine the period in which the interference risk servers have data processing abnormalities in the harmonic monitoring abnormality periods, and use it as the abnormal overlap period;

[0023] Determine the changes in the data processing busy periods of different interference risk servers based on the data processing busy period data of different interference risk servers;

[0024] Based on the changes and the number of abnormal overlap periods of different interference risk servers, an optimized management method for matching optical cable lines is determined.

[0025] In a second aspect, the present invention provides a computer system comprising: a memory and a processor in communication connection, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the above-mentioned data center pipeline optimization management method when running the computer program.

[0026] Other features and advantages will be described in the following description. The objectives and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description and drawings.

[0027] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The above and other features and advantages of the present invention will become more apparent by describing in detail example embodiments thereof with reference to the accompanying drawings;

[0029] Figure 1 It is a flow chart of a data center pipeline optimization management method;

[0030] Figure 2is a flow chart of a method for determining a harmonic monitoring line in a power line;

[0031] Figure 3 is a flow chart of a method for determining an interference risk server in a server;

[0032] Figure 4 is a flow chart of a method for determining an optimized management method for matching optical cable lines;

[0033] Figure 5 It is a framework diagram of a computer system. DETAILED DESCRIPTION

[0034] To help those skilled in the art better understand the technical solutions in this specification, the following will provide a clear and complete description of the technical solutions in the embodiments of this specification, in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of this specification, not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this specification without creative work should fall within the scope of protection of this specification.

[0035] In the present application, based on the abnormal processing of the server using the optical cable line during the harmonic abnormal period of the power line that causes electromagnetic interference risk to the optical cable line, the server with suspected interference risk is determined, and the changes in the busy period of data processing of the server with suspected interference risk are used to determine the optimal management method of the optical cable line from the perspective of the abnormal risk of coincidence with the harmonic abnormal period, that is, whether to carry out layout modification or monitor and process electromagnetic interference through monitoring equipment, thereby improving the reliability of the server operation.

[0036] Example 1

[0037] like Figure 1 As shown, the present application provides a data center pipeline optimization management method, which specifically includes:

[0038] S1 uses the interval data detection results of different pipeline systems in the data center to determine the risk interference location in the pipeline system. Based on the server data corresponding to different risk interference locations, it determines the harmonic monitoring line in the power line and the matching optical cable line.

[0039] Furthermore, the risk interference position is a position where the horizontal spacing between the optical fiber cable and the power line is less than 30 cm or the vertical intersection angle is less than 60°.

[0040] Furthermore, the server data corresponding to the risk interference location is determined based on the server connected to the optical fiber cable at the risk interference location.

[0041] Specifically, such as Figure 2 As shown, the method for determining the harmonic monitoring line in the power line is:

[0042] Determine the risk interference location in the optical fiber cable based on the spacing between the optical fiber cable and the power line;

[0043] Determine the number of risk interference locations corresponding to different servers based on server data corresponding to different risk interference locations;

[0044] Based on the number of risk interference locations corresponding to different servers, it is determined whether the power line is a harmonic monitoring line.

[0045] It can be understood that when there is a server where the number of risk interference locations does not meet the requirements, the power line is determined to be a harmonic monitoring line, and the optical fiber cable interfered by the harmonic monitoring line is used as a matching optical cable line, that is, the number of risk interference locations caused by the harmonic monitoring line does not meet the requirements of the optical fiber cable.

[0046] In a possible embodiment, when there are servers with risk interference locations of more than 8, the power line is determined to be a harmonic monitoring line.

[0047] Optionally, the method for determining the harmonic monitoring line in the power line is:

[0048] Determine the risk interference location in the optical fiber cable based on the spacing between the optical fiber cable and the power line;

[0049] Determine the number of risk interference locations corresponding to different servers based on server data corresponding to different risk interference locations;

[0050] According to the server at the risk interference location, it is determined whether the power line is a harmonic monitoring line.

[0051] It is understandable that when the number of servers at risk interference locations does not meet the requirement, the power line is determined to be a harmonic monitoring line.

[0052] S2 determines the overlap between the distribution data of the abnormal harmonic monitoring period and the busy data processing period of the corresponding server based on the harmonic monitoring data of the harmonic monitoring line, and proceeds to the next step when it is determined based on the overlap that the optimization processing of the matching optical cable line is not required;

[0053] During the busy data processing period in the history, servers that were included in the harmonic monitoring abnormal period will be inserted and used as overlapping servers. When the number of overlapping servers is greater than the number threshold, the matching optical cable lines will be optimized, and the layout between the optical fiber cables connected to the servers and the power lines will be optimized to ensure that different locations can exceed the national standard requirements, that is, the horizontal spacing between the power lines is greater than 35 cm or the vertical crossing angle is greater than 63°.

[0054] Furthermore, the abnormal harmonic monitoring period is a period in which the number of moments when the harmonic content does not meet the requirements does not meet the requirements, wherein the unit time length of the period ranges from 5 minutes to 15 minutes. Specifically, the period in which the total harmonic distortion rate is greater than 2% accounts for more than 0.3 of the moments is regarded as an abnormal harmonic monitoring period. It can be understood that the proportion of the number of moments is determined based on the ratio of the number of moments when the total harmonic distortion rate is greater than 2% to the number of moments for harmonic collection.

[0055] Furthermore, the corresponding server is the server connected to the optical fiber cable, that is, the server connected to the optical fiber cable corresponding to the harmonic monitoring line.

[0056] Furthermore, the data processing busy period is a period in which the data processing amount of the server is greater than the average of the data processing amounts of different periods.

[0057] Specifically, determining that the matching optical cable line does not need to be optimized includes:

[0058] Based on the overlap between the distribution data of the harmonic monitoring abnormal period and the data processing busy period of the corresponding server, determine the server that was included in the harmonic monitoring abnormal period during the data processing busy period in history, and use it as the overlapping server;

[0059] According to the coincidence server, it is determined whether optimization processing of the matching optical cable line is required.

[0060] It can be understood that when the number of overlapping servers is large, that is, greater than the preset overlapping server number threshold, in a possible embodiment, when it is greater than 5, under the harmonic abnormality at this time, the degree of electromagnetic interference to the server's data processing is relatively high. Therefore, in order to ensure the operational reliability of the server, it is necessary to optimize the matching optical cable line, that is, optimize the layout between the optical fiber cable connected to the server and the power line to ensure that different positions can exceed the national standard requirements, that is, the horizontal spacing between the power line is greater than 35 cm or the vertical intersection angle is greater than 63°.

[0061] Optionally, determining that the matching optical cable line optimization process is not required specifically includes:

[0062] Based on the overlap between the distribution data of the harmonic monitoring abnormal period and the data processing busy period of the corresponding server, determine the servers whose data processing busy period in the history is entered in the harmonic monitoring abnormal period, and use them as the overlapping servers, and determine the number of servers whose data processing busy period is entered in the harmonic monitoring abnormal period;

[0063] Optionally, in the above steps, it is necessary to determine whether the number of overlapping servers meets the requirements. It is understandable that when the number of overlapping servers is large, that is, greater than the preset overlapping server number threshold, under the current harmonic abnormality, the degree of electromagnetic interference to the server's data processing is high. Therefore, in order to ensure the operational reliability of the server, it is necessary to optimize the matching optical cable line, that is, optimize the layout between the optical fiber cable and the power line to ensure that different positions can exceed the national standard requirements, that is, the horizontal spacing between the power line is greater than 35 cm or the vertical intersection angle is greater than 63°.

[0064] It should also be noted that if the number of overlapping servers meets the requirements, it is necessary to further determine the number of overlapping servers that enter the harmonic monitoring abnormal period when the data processing is busy. When there are overlapping servers whose number enters the harmonic monitoring abnormal period when the data processing is busy does not meet the requirements, that is, the number of overlapping servers whose number enters the harmonic monitoring abnormal period when the data processing is busy is greater than the preset threshold, the layout between the optical fiber cable and the power line is optimized;

[0065] Furthermore, even if there are no overlapping servers whose number during the busy data processing period input into the harmonic monitoring abnormal period does not meet the requirement, it is necessary to further determine the ratio of the number of the busy data processing period input into the harmonic monitoring abnormal period to the number of the harmonic monitoring abnormal period to determine the interference value. When the number of overlapping servers whose interference value is greater than a preset interference threshold does not meet the requirement, that is, when it is greater than the threshold, the layout between the optical fiber cable and the power line is optimized.

[0066] Based on the number of servers belonging to the data processing busy period in different harmonic monitoring abnormality periods, determining the number of overlapping servers in different harmonic monitoring abnormality periods and the number of harmonic monitoring abnormality periods in which overlapping servers exist;

[0067] It can be understood that in the above steps, if the number of harmonic monitoring abnormal periods of the overlapping servers does not meet the requirements, that is, the number of harmonic monitoring abnormal periods of the overlapping servers is greater than the preset abnormal period number threshold, then the layout between the optical fiber cable and the power line is optimized;

[0068] Furthermore, if the number of harmonic monitoring abnormality periods of overlapping servers meets the requirements, it is necessary to further determine the number of overlapping servers in different harmonic monitoring abnormality periods. When the number of harmonic monitoring abnormality periods in which the number of overlapping servers does not meet the requirements is large, that is, the number of harmonic monitoring abnormality periods in which the number of overlapping servers is more than 3 is greater than the preset threshold, the layout between the optical fiber cable and the power line is optimized;

[0069] Determine whether optimization processing of the matching optical cable line is required based on the number of coincidence servers input into the harmonic monitoring abnormality period during the busy data processing period of the coincidence server, the number of coincidence servers in different harmonic monitoring abnormality periods, and the number of harmonic monitoring abnormality periods in which coincidence servers exist.

[0070] In one possible embodiment, a function is constructed based on the number of overlapping servers entering the harmonic monitoring abnormality period during busy data processing hours, the number of overlapping servers in different harmonic monitoring abnormality periods, and the number of harmonic monitoring abnormality periods with overlapping servers to determine the interference risk value, wherein the greater the number of overlapping servers entering the harmonic monitoring abnormality period during busy data processing hours, the greater the number of overlapping servers in different harmonic monitoring abnormality periods, and the greater the number of harmonic monitoring abnormality periods with overlapping servers, the greater the interference risk value. In a possible embodiment, the determination is made through expert scoring or neural network.

[0071] S3: determining, based on the distribution data of the harmonic monitoring abnormal period, an abnormality of the data processing result of the corresponding server in the harmonic monitoring abnormal period, and determining an interference risk server among the servers based on the abnormality;

[0072] An interference risk server is a server whose data processing results are abnormal during the harmonic abnormality period.

[0073] Furthermore, the abnormality of the data processing results of the server during the harmonic monitoring abnormal period is determined based on whether there is an abnormality in the data processing results of the server during the harmonic monitoring abnormal period, specifically including a surge in verification errors, comparison of data hash values ​​(such as MD5 / SHA-256), if the verification failure rate before and after transmission is greater than 0.1%, message loss / disorder: TCP retransmission rate suddenly increases (such as greater than 5%) or UDP packet loss rate is greater than 1%, and calculation logic errors.

[0074] Specifically, such as Figure 3 As shown, the method for determining the interference risk server among the servers is:

[0075] Based on the abnormality of the data processing result of the server in the abnormal harmonic monitoring period, determining a period in which the server has data processing abnormality in the abnormal harmonic monitoring period, and using it as the abnormal coincidence period;

[0076] According to the distribution of the abnormal overlapping time periods, it is determined whether the server is an interference risk server.

[0077] It can be understood that when the proportion of the server's abnormal overlap period in the harmonic monitoring abnormal period does not meet the requirements, or the periods with data processing abnormalities are all in the abnormal overlap period, the server is determined to be an interference risk server. In a possible embodiment, when the proportion of the server's abnormal overlap period in the harmonic monitoring abnormal period is greater than 0.35, it is determined that the proportion of the server's abnormal overlap period in the harmonic monitoring abnormal period does not meet the requirements.

[0078] S4 uses different harmonics to monitor the interference risk server data during abnormal periods and the data processing busy periods of different interference risk servers to determine the optimal management method for matching optical cable lines.

[0079] Specifically, such as Figure 4 As shown, the method for determining the optimization management method of the matching optical cable line is:

[0080] Determine the composition of the interference risk servers in the different harmonic monitoring abnormality periods using the interference risk server data in the different harmonic monitoring abnormality periods; and based on the composition of the interference risk servers, determine the period in which the interference risk servers have data processing abnormalities in the harmonic monitoring abnormality periods, and use it as the abnormal overlap period;

[0081] Determine the changes in the data processing busy periods of different interference risk servers based on the data processing busy period data of different interference risk servers;

[0082] Based on the changes and the number of abnormal overlap periods of different interference risk servers, an optimized management method for matching optical cable lines is determined.

[0083] It is understandable that when the number of interference risk servers does not meet the requirements, that is, the number of interference risk servers is greater than the preset interference risk server number threshold or the proportion of interference risk servers in the servers connected to the optical fiber cable is greater than 0.2, then the number of interference risk servers at this time is large, so it is necessary to optimize the layout between the optical fiber cable and the power line.

[0084] It should also be noted that when the number of interference risk servers meets the requirements, the proportion of the number of abnormal overlapping time periods of different interference risk servers in the harmonic monitoring abnormal time period is used as the interference weight value of the different interference risk servers. According to the changes in the data processing busy time periods of different interference risk servers, the similarity of the data processing busy time periods of different interference risk servers on different dates is determined. When the data processing busy time periods on different dates are inconsistent, that is, the time period belongs to the data processing busy time period on a certain date but does not belong to the data processing busy time period on other dates, then the interference risk server is determined to be a variable server;

[0085] When the interference weight value of the variable server does not meet the requirements, and when there is a variable server with an interference weight value greater than 0.4, the fluctuation during the busy data processing period is more serious, and there is a greater risk of overlap with the abnormal harmonic monitoring period in the later period. Therefore, on this basis, it is determined that the layout between the optical fiber cable and the power line needs to be optimized.

[0086] However, if there is no variable server with an interference weight value greater than 0.4, the interference risk of different variable servers is relatively small. Therefore, on this basis, electromagnetic interference monitoring equipment is set at the risk interference position between the optical fiber cable and the power line, and the monitoring data of the electromagnetic interference monitoring equipment is used to determine whether it is necessary to optimize the layout between the optical fiber cable and the power line.

[0087] Furthermore, when there is an electromagnetic interference risk at any one of the different risk interference locations, and the monitoring data of the electromagnetic interference monitoring device does not meet the requirements, that is, when there is a battery interference risk under the monitoring data, it is determined that the layout between the optical fiber cable and the power line needs to be optimized. When there is no electromagnetic interference risk at the different risk interference locations, it is determined that the layout between the optical fiber cable and the power line needs to be optimized. In a possible embodiment, when the electromagnetic field monitoring data at the risk interference location is not within the qualified range pre-set by the monitoring device, it is determined that there is an electromagnetic interference risk at the risk interference location.

[0088] Optionally, the method for determining the optimized management method for matching optical cable lines is:

[0089] S41 determines the composition of the interference risk servers in the different harmonic monitoring abnormality periods using the interference risk server data in the different harmonic monitoring abnormality periods. Based on the composition of the interference risk servers, determines the periods in which the interference risk servers have data processing abnormalities in the harmonic monitoring abnormality periods, and uses them as abnormal overlap periods. Determine interference weight values ​​for the different interference risk servers according to the number of abnormal overlap periods of the different interference risk servers.

[0090] Optionally, in the above steps, if there is interference risk to the server in different harmonic monitoring abnormal periods, the impact of electromagnetic interference on the server is relatively large. Therefore, on this basis, in order to ensure the operating stability of the server, it is determined that the layout between the optical fiber cable and the power line needs to be optimized to ensure that different positions can exceed the national standard requirements, that is, the horizontal spacing between the power line is greater than 35 cm or the vertical intersection angle is greater than 63°.

[0091] Furthermore, in the above steps, if interference risk servers do not exist uniformly in different harmonic monitoring abnormality periods, it is also necessary to determine whether the number of interference risk servers meets the requirements. When the number of interference risk servers is large, that is, greater than the preset threshold, it is determined that the layout between the optical fiber cable and the power line needs to be optimized to ensure that different positions can exceed the national standard requirements, that is, the horizontal spacing between the power line is greater than 35 cm or the vertical intersection angle is greater than 63°.

[0092] In another possible embodiment, when the number of the interference risk servers is not greater than a threshold, it is necessary to further determine whether the sum of the interference weight values ​​of different interference risk servers meets the requirements. When the sum of the interference weight values ​​of different interference risk servers does not meet the requirements, it is determined that the layout between the optical fiber cable and the power line needs to be optimized to ensure that different positions can exceed the national standard requirements, that is, the horizontal spacing between the power line is greater than 35 cm or the vertical intersection angle is greater than 63°.

[0093] S42: determining changes in the data processing busy periods of the different interference risk servers based on the data processing busy period data of the different interference risk servers, and determining a change value of the data processing busy period of the interference risk servers based on the proportion of the number of dates belonging to the data processing busy period in the different periods;

[0094] Optionally, the change value of the busy period of data processing of the interference risk server is determined according to the difference between a preset value and the maximum proportion of the number of dates belonging to the busy period of data processing of the interference risk server, and its value range is between 0 and 1.

[0095] It can be understood that in the above steps, based on the changes in the data processing busy periods of different interference risk servers, the similarities of the data processing busy periods of different interference risk servers on different dates are determined. When the data processing busy periods on different dates are not consistent, the interference risk server is determined to be a variable server. Specifically, when the number of variable servers does not meet the requirements, it is determined that the layout between the optical fiber cable and the power line needs to be optimized.

[0096] It is also understandable that when the number of variable servers meets the requirements, if the interference weight value of the variable server does not meet the requirements, when there is a variable server with an interference weight value greater than 0.4, the changes in the busy data processing period are more serious, and there is a greater risk of overlap with the abnormal harmonic monitoring period in the later period. Therefore, on this basis, it is determined that the layout between the optical fiber cable and the power line needs to be optimized.

[0097] Furthermore, if the interference weight values ​​of the variable servers all meet the requirements, it is also necessary to determine the variable values ​​of the data processing busy periods of different interference risk servers. When the number of interference risk servers with variable values ​​greater than the preset variable threshold does not meet the requirements, since the changes in the data processing busy period are more serious, there is a greater risk of overlap with the harmonic monitoring abnormal period in the later stage. Therefore, on this basis, it is determined that the layout between the optical fiber cable and the power line needs to be optimized.

[0098] S43 determines an optimized management method for matching optical cable lines based on the interference weight values ​​of different interference risk servers and the change value during the data processing busy period.

[0099] In a possible embodiment, based on the interference weight values ​​of different interference risk servers and the variation values ​​during busy data processing periods, the sum of the products of the variation values ​​of different interference risk servers and the interference weight values ​​is determined and used as the line interference risk value. When the line interference risk value is greater than a preset risk threshold, it is determined that the layout between the optical fiber cable and the power line needs to be optimized. In other cases, electromagnetic interference monitoring equipment is set at the risk interference position between the optical fiber cable and the power line on this basis, and the monitoring data of the electromagnetic interference monitoring equipment is used to determine whether the layout between the optical fiber cable and the power line needs to be optimized.

[0100] Example 2

[0101] Second, as Figure 5 As shown, the present invention provides a computer system, comprising: a memory and a processor that are communicatively connected, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the above-mentioned data center pipeline optimization management method when running the computer program.

[0102] The various embodiments in this specification are described in a progressive manner. Similar portions between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from the other embodiments. In particular, the device, apparatus, and non-volatile computer storage medium embodiments are generally similar to the method embodiments, so their descriptions are relatively simplified. For relevant details, refer to the descriptions of the method embodiments.

[0103] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0104] The foregoing description is merely one or more embodiments of this specification and is not intended to limit this specification. It will be apparent to those skilled in the art that various modifications and variations may be made to one or more embodiments of this specification. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of one or more embodiments of this specification are intended to be within the scope of the claims of this specification.

Claims

1. A data center pipeline optimization management method, characterized in that: Specifically include: Using the interval data detection results of different pipeline systems in the data center, we can determine the risk interference locations in the pipeline system. Based on the server data corresponding to different risk interference locations, we can determine the harmonic monitoring lines in the power lines and the matching optical cable lines. Using the harmonic monitoring data of the harmonic monitoring line, determining the overlap between the distribution data of the harmonic monitoring abnormal period and the data processing busy period of the corresponding server, and when it is determined based on the overlap that the optimization processing of the matching optical cable line is not required, proceeding to the next step; Determining, based on the distribution data of the harmonic monitoring abnormal period, an abnormality of the data processing result of the corresponding server in the harmonic monitoring abnormal period, and determining an interference risk server among the servers based on the abnormality; The interference risk server data in different harmonic monitoring abnormal periods and the data processing busy periods of different interference risk servers are used to determine the optimal management method for matching optical cable lines.

2. The data center pipeline optimization management method according to claim 1, characterized in that: The risk interference position is a position where the horizontal distance between the optical fiber cable and the power line is less than 30 cm or the vertical intersection angle is less than 60°.

3. The data center pipeline optimization management method according to claim 1, characterized in that: The server data corresponding to the risk interference location is determined according to the server connected by the optical fiber cable at the risk interference location.

4. The data center pipeline optimization management method according to claim 1, characterized in that: The method for determining the harmonic monitoring line in the power line is: Determine the risk interference location in the optical fiber cable based on the spacing between the optical fiber cable and the power line; Determine the number of risk interference locations corresponding to different servers based on server data corresponding to different risk interference locations; Based on the number of risk interference locations corresponding to different servers, it is determined whether the power line is a harmonic monitoring line.

5. The data center pipeline optimization management method according to claim 1, characterized in that: The abnormal harmonic monitoring period is a period in which the number of moments when the harmonic content does not meet the requirements does not meet the requirements.

6. The data center pipeline optimization management method according to claim 1, characterized in that: Determining that the matching optical cable line does not need to be optimized specifically includes: Based on the overlap between the distribution data of the harmonic monitoring abnormal period and the data processing busy period of the corresponding server, determine the server that was included in the harmonic monitoring abnormal period during the data processing busy period in history, and use it as the overlapping server; According to the coincidence server, it is determined whether optimization processing of the matching optical cable line is required.

7. The data center pipeline optimization management method according to claim 1, characterized in that: The method for determining the interference risk server among the servers is: Based on the abnormality of the data processing result of the server in the abnormal harmonic monitoring period, determining a period in which the server has data processing abnormality in the abnormal harmonic monitoring period, and using it as the abnormal coincidence period; According to the distribution of the abnormal overlapping time periods, it is determined whether the server is an interference risk server.

8. The data center pipeline optimization management method according to claim 7, characterized in that: When the proportion of the abnormal overlap period of the server in the harmonic monitoring abnormal period does not meet the requirements, or the periods with data processing abnormalities are all in the abnormal overlap period, the server is determined to be an interference risk server.

9. The data center pipeline optimization management method according to claim 1, characterized in that: The method for determining the optimization management method of the matching optical cable line is: Determine the composition of the interference risk servers in the different harmonic monitoring abnormality periods using the interference risk server data in the different harmonic monitoring abnormality periods; and based on the composition of the interference risk servers, determine the period in which the interference risk servers have data processing abnormalities in the harmonic monitoring abnormality periods, and use it as the abnormal overlap period; Determine the changes in the data processing busy periods of different interference risk servers based on the data processing busy period data of different interference risk servers; Based on the changes and the number of abnormal overlap periods of different interference risk servers, an optimized management method for matching optical cable lines is determined.

10. A computer system comprising: A memory and a processor in communication connection, and a computer program stored in the memory and capable of running on the processor, characterized in that when the processor runs the computer program, it executes a data center pipeline optimization management method as described in any one of claims 1-9.

Images