Large-scale server monitoring system

Abstract

The invention is suitable for the technical field of computer heat dissipation, and provides a large-scale server monitoring system, which comprises a central control module, a temperature monitoring module and a storage module, and is characterized in that the central control module calculates, stores and uploads a server heat plane and different heat level data to a cloud memory, the server is divided into different areas through the central control module, and the server heat level data is stored through the temperature monitoring module. The method comprises the following steps of: establishing a server heat plane according to a region, dividing a heat level, establishing a model according to a relationship between the heat level and the power consumption of the server, and realizing an evaluation standard of the energy consumption of the server and the current heat level, thereby establishing a prediction model through the power consumption data of the server, predicting and monitoring the power consumption of the server; and the corresponding heat dissipation state can be regulated and controlled in real time according to the heat level of the current server while the power supply stability and accuracy of the large-scale server are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of computer heat dissipation, and in particular to a large server monitoring system. Background Art

[0002] A server is a computer hardware or software system that provides various services and resources to other computers or devices. Servers are usually used to store, manage and process large amounts of data, files and network requests, and will generate a lot of heat during operation. In order to ensure the overall stability and reliability of the data center, an effective cooling system is required to keep the servers in the data center working at normal temperatures. When building air-cooled equipment, the cooling system usually uses air conditioning systems, fans, heat sinks and other equipment to increase the heat dissipation rate of the server to ensure that the server operates within an appropriate temperature range. In order to ensure the working status of the cooling system, the status of the server needs to be monitored.

[0003] At the same time, during the operation of the server, ensuring the stable power supply status of the server is the key. In view of the problems in related technologies such as low control efficiency of server cooling equipment and unstable power operation status, no effective solutions have been proposed. A large-scale server monitoring system is proposed to address the above problems. Summary of the invention

[0004] In view of the above-mentioned defects, the purpose of the present invention is to provide a large-scale server monitoring system, which establishes a server thermal plane and divides thermal levels according to the temperature status of the server, evaluates the status and power consumption of the server according to the thermal level, and provides a large-scale server monitoring system.

[0005] In order to achieve the above object, the present invention provides a large server monitoring system, comprising: The temperature monitoring module uses several temperature sensors to measure the temperature of different areas of the server and upload the temperature data.

[0006] The central control module receives and transmits module data connected to the central control module, and executes and calculates the data.

[0007] The storage module includes a local storage and a cloud storage, and is used to store data in the central control module and transmit it to the cloud storage.

[0008] The cooling module includes several air cooling devices for lowering the temperature of the server, which are used for normal cooling of the server group and regional cooling of a server.

[0009] The operation steps of the server monitoring system are as follows: S1. The temperature detection module monitors the temperature of the server group in different areas, and numbers several servers through the central control module, counts the temperature data of the servers, and integrates the collected temperature data into several server heat planes parallel to the horizontal plane. .

[0010] S2. The server heat plane The heat level is set according to the temperature. The central control module uses the server heat plane Adjust the status of the air cooling device corresponding to the server.

[0011] S3. The central control module collects the power consumption data of the server group, establishes a corresponding power consumption prediction model according to the thermal level fitting, and predicts the power consumption data of the server group according to the real-time data of the server group.

[0012] The server group is composed of a plurality of servers.

[0013] According to a large server monitoring system of the present invention, the average temperature in the area is measured by a temperature sensor arranged on the server, and the average temperature in the area is obtained. The average temperature of the area is , the height difference between two adjacent areas is .

[0014] According to the number of server group regions Divide the server heat plane into two adjacent and The interface of the area is the server heat plane , specifies the server in the server heat plane The heat level per unit space is , is the initial value of the heat level, and .

[0015] According to a large server monitoring system described in the present invention, the server heat plane The coordinates of the center point of the unit space are , with the unit space of the current server as the center and spreading outward, the heat level of the unit space that overlaps with the unit space of the current server on at least one side is defined as , so as to adjust the server heat plane The heat level of the unit space on the server is calculated by decreasing the heat level by one level, until the heat level of the corresponding unit space is reduced to 0. The server group is on the server heat plane. The heat level inside is the superposition of several heat levels within the unit space.

[0016] According to a large server monitoring system of the present invention, the heat level distribution plan of the entire server group is composed of several The server is composed of a rectangular shape of a certain size, and the center of the unit space of the server corresponds one-to-one to the center of the rectangle.

[0017] According to a large server monitoring system described in the present invention, the unit space is The rectangular space.

[0018] in, is the height per unit space and , and are the length and width of the unit space respectively, , , the current server thermal plane is affected by the thermal levels in the upper and lower adjacent server thermal planes.

[0019] According to a large server monitoring system of the present invention, the power consumption of the server group , is the correction coefficient, is the power consumption coefficient corresponding to the server group, Indicates the current number is The server is in Thermal levels in the thermal plane.

[0020] According to a large server monitoring system described in the present invention, For the number Total heat level of the server .

[0021] According to a large server monitoring system of the present invention, the unit time The power consumption within is ,in , according to several observation sequences , a time series model is established based on the observation sequence.

[0022] Establish a time series model based on the observation sequence.

[0023] in express The power consumption data predicted at all times, Indicates the length value of the predicted sequence selection Indicated in The actual power consumption data at all times, Indicated in The actual power consumption data at all times, Indicated in The actual power consumption data at all times, express The power consumption data predicted at any moment.

[0024] According to a large server monitoring system described in the present invention, The power consumption data predicted at all times, , Standard error of the predicted value for, .

[0025] The present invention provides a large server monitoring system, which has the following beneficial effects: The present invention divides the server into different areas, establishes a server thermal plane according to the area, divides the thermal level, and establishes a model based on the relationship between the thermal level and the power consumption, thereby realizing an evaluation standard for the server energy consumption and the current thermal level; a prediction model is established through the power consumption data of the server to predict and monitor the power consumption of the server, thereby realizing the stability and accuracy of the power supply at the large server and adjusting the corresponding heat dissipation state in real time according to the current thermal level of the server. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 Process diagram for establishing a server thermal plane for the present invention; Figure 2 It is a schematic diagram of the system structure of the present invention. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0028] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0029] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0030] See also Figure 1~Figure 2 The present invention provides a large-scale server monitoring system, comprising: The temperature monitoring module uses several temperature sensors to measure the temperature of different areas of the server and upload the temperature data.

[0031] The central control module receives and transmits module data connected to the central control module, and executes and calculates the data.

[0032] The storage module includes a local storage and a cloud storage, and is used to store the temperature data in the central control module and transmit it to the cloud storage.

[0033] The cooling module includes several air cooling devices for lowering the temperature of the server, which are used for normal cooling of the server group and regional cooling of a server.

[0034] S1. Use temperature sensors to monitor the temperature of servers in different areas, and use the central control module to number the server groups, count the temperature data of the servers, and integrate the collected temperature data into several server heat planes parallel to the horizontal plane. ; S2. Based on the server heat plane The state of the air cooling equipment of the corresponding server is adjusted according to different heat levels, that is, the temperature of the corresponding server is reduced by adjusting the refrigeration equipment at a higher heat level; The power consumption of the server is calculated based on the corresponding power consumption of the server, and the monitored data is transmitted to the cloud server for storage.

[0035] S3. Collect the power consumption data of the server, establish a corresponding power consumption prediction model according to the thermal level fitting, and predict the corresponding server power consumption data according to the real-time data of the server.

[0036] Divide the servers into The average temperature of each area is measured by the temperature sensor set on the server. In this embodiment, the number of regions , the height difference between two adjacent areas is .

[0037] in, Indicates that the current number is Servers, Indicates the current number is The server is in The average temperature of the area. Several servers in the server group are numbered in a plan view, starting with the server in the upper left corner and sorted counterclockwise.

[0038] Preferably, the height difference between the two regions is It can be a single constant value, or an arithmetic progression or linear function can be selected to divide the server heights.

[0039] Encode the location information of each server in the server group, and the center position of the server rectangular frame The server's position is relative to the coordinate origin The length of the server group is proportional to the length and width of the server. Suppose the length of a single server is , width is , the length and width of the cold pool (equal to the length and width of the server group) are and , defines the information about a single server based on the number of servers surrounding it Location coordinates .

[0040] The corresponding coordinates of the servers at the four corners of the server group are arranged counterclockwise as follows: ,in, and Respectively represent the number of servers represented by the server group horizontally and vertically.

[0041] in , Furthermore, the total number of servers in the server group .

[0042] In this embodiment, construct The server group of the unit, that is, the number of horizontal servers is 4, the number of vertical servers is 10, and the number of servers required to form a server group is 24. Among them, the coordinates of the servers located at the four corners of the server group are arranged counterclockwise from the upper left corner. .

[0043] According to the number of divided areas Establish server heat planes of different heights for the server group, with two adjacent and The interface of the area is the server heat plane ,in .

[0044] Using the average temperature of each area as Heat plane with servers The heat level per unit space is Perform linear conversion. is the initial value of the heat level, and .

[0045] Furthermore, the current server is specified Zones in the server thermal plane The heat level per unit space is , the coordinates of the center point of the unit space are , with the unit space of the current server as the center and spreading outward, the heat level of the unit space that overlaps with the unit space of the current server on at least one side is defined as , so as to adjust the server heat plane The heat level of the unit space on the server is calculated by decreasing the heat level by one level in sequence until the heat level of the current corresponding unit space decreases to 0, and the server group is obtained on the server heat plane. Different heat levels within the server The heat levels in different areas are superimposed to obtain the heat level distribution plan of the entire server group.

[0046] A server group is formed by interconnecting several servers and surrounding a rectangular frame. A plurality of air cooling devices are arranged at the center of the rectangular frame formed by the servers. The air cooling devices are cooling devices such as cold air blowers or air conditioners. The refrigeration equipment guides cold air to the servers through a cold pool arranged on the ground and cools the servers. The cold pool is a cold channel arranged at the center of the rectangular frame of the server. Arranging a cold pool in a large server is a conventional technical means for those skilled in the art and will not be repeated here.

[0047] Furthermore, according to the heat level distribution plan of the server group, the central control module adjusts the air cooling device to adopt different cooling effects on the server according to the heat level, and can adjust the air volume or cooling temperature of the air cooling device to achieve the reduction of the temperature of the server group.

[0048] The heat distribution plan of the entire server group is divided into several The server is composed of a rectangular shape of a certain size, and the center of the unit space of the server corresponds one-to-one to the center of the rectangle.

[0049] Furthermore, the unit space is The cuboid space is ,in, is the height per unit space and , and are the length and width of the unit space respectively. The length of the unit space is slightly larger than the length and width of the server. , , so that the current server heat plane is affected by the heat level in the upper and lower adjacent server heat planes.

[0050] Furthermore, in this embodiment, , , is the scale factor of the unit space, where .

[0051] Furthermore, the power consumption of the servers is estimated using the heat level distribution plan of the entire server group.

[0052] Power consumption of server group , is the correction coefficient, is the power consumption coefficient corresponding to the server group, Indicates the current number is The server is in Thermal levels in the thermal plane.

[0053] Among them, the correction coefficient The value is obtained through multiple calculations. It is positively correlated with the number of servers.

[0054] Preferably, , by calculating the heat level of a single server to determine the heat level of the current server, For the number The total heat level of the server.

[0055] Furthermore, the cooling frequency of the cooling equipment corresponding to the single server is called according to the number of unit spaces of different heat levels of the single server, thereby achieving targeted control of the heat distribution of the server group and improving the stability of the server during operation.

[0056] Furthermore, the past power consumption data of the server group is used to fit the corresponding correction coefficient. Power consumption coefficient corresponding to the server group , and based on the average temperature of the server Establish the corresponding power consumption data set and use the fitted correction coefficient Power consumption coefficient corresponding to the server group Calculated power consumption of the server group Compare with the power consumption dataset to ensure the power consumption of the server group The error falling into the corresponding power consumption data set does not exceed the set error value, avoiding the power consumption of the server group Overfitting.

[0057] Specifies the current server The power consumption generated by the read and write frequency in the area is , ,in Indicates the current server The corresponding power consumption coefficient is Indicates the rated power of the server and Proportional to power consumption, Indicates the current The average read and write frequency at the moment, Indicates the rated frequency of the current server.

[0058] Furthermore, the power consumption of the server group , To optimize the correction factor, To optimize the power consumption factor, Corresponds to the power consumption generated by the air-cooled device group.

[0059] Unit time The power consumption within is ,in , according to several observation sequences , a time series model is established based on the observation sequence to predict the upcoming moments in the future, so as to estimate the future power consumption of the current server group based on the predicted energy consumption, so as to maintain a stable power supply at the server group, and infer whether the cooling temperature in the space where the server group is currently located meets the operating standards of the server group through the energy consumption generated by the server group, thereby improving the stability of the server group's operation process and saving the energy used by the air cooling equipment.

[0060] Establish a time series model based on the observation sequence.

[0061] in express The power consumption data predicted at all times, Indicates the length value of the prediction sequence selection and In this embodiment, select , unit time selection , Indicated in The actual power consumption data at all times, Indicated in The actual power consumption data at all times, Indicated in The actual power consumption data at all times, express The power consumption data predicted at any time is used to predict the future power consumption data based on the actual measured power consumption data. Predict power consumption data at all times and build a prediction model.

[0062] , in express The power consumption data predicted at all times, The standard error of the predicted values ​​is as follows,

[0063] Get the corresponding future The predicted power consumption at time .

[0064] The present invention provides a large-scale server monitoring system, including a central control module, which is used to calculate temperature data in the system and control the operation of storage and temperature monitoring modules; the temperature monitoring module is used to monitor the temperature in the server in real time, including several temperature monitoring sensors; the storage module is used to monitor the heat plane of the server The data of different thermal levels are stored and connected to the cloud storage, and the data is uploaded to the cloud storage to realize the backup and networking of the data; the server is divided into different areas, and the server thermal plane is established according to the area, the thermal level is divided, and a model is established based on the relationship between the thermal level and the power consumption to realize the evaluation standard of the server energy consumption and the current thermal level; a prediction model is established through the power consumption data of the server to predict and monitor the power consumption of the server, so as to realize the stability and accuracy of the power supply at the large server and adjust the corresponding heat dissipation status in real time according to the current thermal level of the server.

[0065] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0066] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0067] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0068] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0069] The above contents are only for explaining the technical idea of ​​the present invention and cannot be used to limit the protection scope of the present invention. Any changes made on the basis of the technical solution in accordance with the technical idea proposed by the present invention shall fall within the protection scope of the claims of the present invention.

Claims

1. A large server monitoring system, characterized in that: include: The temperature monitoring module uses several temperature sensors to measure the temperature of different areas of the server and upload the temperature data; The central control module receives and transmits data from the modules connected to the central control module, and executes and calculates the data; The storage module includes a local storage and a cloud storage, which is used to store and transmit the data in the central control module to the cloud storage; The cooling module includes several air cooling devices for lowering the temperature of the server, which are used for normal cooling of the server group and regional cooling of a server; The operation steps of the server monitoring system are as follows: S1. The temperature detection module monitors the temperature of the server group in different areas, and numbers several servers through the central control module, counts the temperature data of the servers, and integrates the collected temperature data into several server heat planes parallel to the horizontal plane. ; S2. The server heat plane The heat level is set according to the temperature. The central control module uses the server heat plane Adjust the status of air cooling equipment; S3. The central control module collects the power consumption data of the server group, establishes the corresponding power consumption prediction model according to the heat level fitting, and predicts the power consumption data of the server group according to the data of the server group; The server group is composed of a plurality of servers.

2. A large server monitoring system according to claim 1, characterized in that: The average temperature in the area is measured by the temperature sensor set on the server and obtained respectively. The average temperature of the area is , the height difference between two adjacent areas is ; According to the number of server group regions Divide the server heat plane into two adjacent and The interface of the area is the server heat plane , specifies the server in the server heat plane The heat level per unit space is , is the initial value of the heat level, and .

3. A large server monitoring system according to claim 2, characterized in that: The server heat plane The coordinates of the center point of the unit space are , with the server unit space as the center and spreading outward, the heat level of the unit space that overlaps with the server unit space on at least one side is defined as , so as to adjust the server heat plane The heat level of the unit space on the server is calculated by decreasing the heat level by one level, until the heat level of the corresponding unit space is reduced to 0. The server group is on the server heat plane. The heat level inside is the superposition of several heat levels within the unit space.

4. A large server monitoring system according to claim 3, characterized in that: The heat level distribution plan of the server group consists of several The server is composed of a rectangular shape of a certain size, and the center of the unit space of the server corresponds one-to-one to the center of the rectangle.

5. A large server monitoring system according to claim 3, characterized in that: The unit space is The rectangular space of in, is the height per unit space and , and are the length and width of the unit space respectively, , , the current server thermal plane is affected by the thermal levels in the upper and lower adjacent server thermal planes.

6. According to a large server monitoring system as claimed in claim 5, the power consumption of the server group , is the correction coefficient, is the power consumption coefficient corresponding to the server group, Indicates the current number is The server is in Thermal levels in the thermal plane.

7. A large server monitoring system according to claim 6, characterized in that: Said For the number Total heat level of the server .

8. A large server monitoring system according to claim 7, characterized in that: The unit time The power consumption within is ,in , according to several observation sequences , establish a time series model based on the observation sequence; Establish a time series model based on the observation sequence. in, express The power consumption data predicted at all times, Indicates the length value of the predicted sequence selection Indicated in The actual power consumption data at all times, Indicated in The actual power consumption data at all times, Indicated in The actual power consumption data at all times, express The power consumption data predicted at any moment.

Images