Management method and system for PUE value of data center

Abstract

The invention discloses a management method and system for a PUE value of a data center, relates to the technical field of data centers, and solves the problem that related parameters of operation equipment are not effectively adjusted based on energy consumption association change among different operation equipment. According to the energy consumption correlation ratio and the equipment energy consumption change data, whether the energy consumption change of other running equipment is abnormal or not can be quickly and accurately evaluated; corresponding and clear evaluation modes are provided for single-item and multi-item associated equipment sets, and once abnormal energy consumption equipment is determined, operation parameters of the abnormal energy consumption equipment can be adjusted in time, such as voltage and current reduction, so that the energy consumption is recovered to be normal; if the operation parameters are reduced to the lowest value and still cannot reach the standard, whether personnel intervention is needed or not can be determined by re-confirming the PUE value, and the hierarchical processing mode effectively guarantees the stability and reasonability of the energy consumption of the data center, improves the energy utilization efficiency, reduces the operation cost, and guarantees the efficient and stable operation of the data center.

Description

Technical Field

[0001] The present invention relates to the technical field of data centers, and in particular to a management method and system for a PUE value of a data center. Background Art

[0002] A data center is a facility that centrally houses computer systems and related components, designed to store, process, transmit and manage large amounts of data. It is the core infrastructure of modern information technology and plays a key supporting role in the digital operations of various industries. It includes servers, storage devices, network equipment (such as switches, routers, firewalls), etc. Servers are the core computing units of data centers, responsible for running various applications and processing data. Storage devices are used to preserve data for a long time and come in a variety of forms, such as hard disk arrays and tape libraries. Network equipment ensures high-speed, stable transmission and secure access of data between different devices.

[0003] The application with publication number CN115437876A discloses a management method, device, electronic device and storage medium for a data center, the method comprising: obtaining historical monitoring information for multiple electrical devices, and historical environmental information that is associated with the energy consumption of the electrical devices at corresponding moments; predicting the predicted power usage efficiency PUE of the data center within a preset time period based on the historical monitoring information and historical environmental information; when the predicted PUE exceeds the PUE threshold, obtaining the predicted environmental information for the preset time period, and determining the target energy-saving and energy-consuming strategies for multiple electrical devices under the predicted environmental information; in the preset time period, controlling multiple electrical devices according to the target energy-saving and energy-consuming strategies. Through the embodiments of the present invention, when the PUE of the data center may exceed the preset value, each electrical device in the data center is managed and controlled to avoid the PUE of the data center exceeding the preset value; thereby, the energy efficiency of the data center is improved.

[0004] Regarding the specific confirmation of the PUE value related to the data center, the PUE value is confirmed and adjusted based on the changes in the energy consumption values ​​related to different operating equipment. However, in the actual adjustment process, the relevant parameters of the operating equipment are not effectively adjusted based on the correlated changes in energy consumption between different operating equipment, so as to make the PUE value of the corresponding data center meet the standard and improve the overall adjustment effect of its data center. Summary of the invention

[0005] In view of the deficiencies in the prior art, the present invention provides a management method and system for the PUE value of a data center, which solves the problem of not effectively adjusting the relevant parameters of the operating equipment based on the correlated changes in energy consumption between different operating equipment.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: A management method for the PUE value of a data center, comprising the following steps:

[0007] Step 1: Process the relevant historical operation data of different operating equipment in the data center, confirm the energy consumption correlation ratio associated with the corresponding associated equipment based on the correlation between different operating equipment, and record the confirmed energy consumption correlation ratio. The specific sub-steps are:

[0008] S11. Based on the pre-set associations between different operating devices, confirm that there is an associated associated operating device set. If a certain group of operating devices is associated with only one group of operating devices, it is recorded as a single associated operating device set. If a certain group of operating devices is associated with multiple groups of operating devices, it is recorded as a multiple associated operating device set.

[0009] S12. For the confirmed single associated running equipment set, identify the historical energy consumption data of the corresponding running equipment from the set, select energy consumption improvement data from the historical energy consumption data, identify the improvement amount of the corresponding energy consumption data per unit time from the selected energy consumption improvement data, and mark it as Ts i , where i represents different operating equipment, and the associated lifting amount Ts of different operating equipment in different unit time i , perform mean processing, confirm the mean characteristics associated with the corresponding running equipment, perform ratio processing on the mean characteristics of different running equipment in this single associated running equipment set, and confirm the energy consumption correlation ratio of this single associated running equipment set;

[0010] For the confirmed multiple sets of associated running devices, the terminal running devices are preferentially determined, and the terminal running devices belong to the terminal devices, and the terminal devices are associated with other running devices in the multiple sets of associated running devices. The other running devices in the multiple sets of associated running devices except the terminal devices are marked as pending devices, and the historical energy consumption data of several groups of pending devices are determined. The energy consumption improvement data associated with the multiple groups of pending devices in the same period are identified from the historical energy consumption data. From the associated energy consumption improvement data, the mean characteristics associated with the corresponding pending devices are confirmed by using the same processing method as the above-mentioned running devices to confirm the mean characteristics, and then the mean characteristics TZ generated by the terminal running devices in this period are determined;

[0011] The mean characteristics associated with different pending devices are processed by ratio, and the ratio sequences associated with multiple groups of pending devices are confirmed. TZ is evenly divided based on the determined ratio sequence, and the average value associated with a single ratio in the ratio sequence is confirmed. The mean characteristics of the pending devices associated with the corresponding ratios of the ratio sequence and the confirmed average value are determined, and the energy consumption correlation ratio associated with the corresponding pending devices and the terminal operation devices is confirmed by the method of (mean characteristics: average value);

[0012] Step 2: Monitor the energy consumption data associated with different running equipment in the data center, confirm the PUE value associated with the corresponding time in real time, and then confirm the energy consumption abnormality signal based on the specific changes of the PUE value. The specific method is as follows:

[0013] S21. The real-time energy consumption data generated by IT equipment in the data center is calibrated as NH k , where k represents different moments, and the real-time energy consumption data generated by other running equipment in the data center is calibrated as HH k-q , where q represents other different running equipment, and multiple sets of energy consumption data generated by all equipment in the data center at the same time are summed up to confirm the total energy consumption data ZH of this data center;

[0014] S22, use: P k =ZH÷NH k Confirm the PUE value P associated with the corresponding time k , the PUE value P associated with the corresponding time k Verify with the preset parameter Y1, where Y1 is the preset value. k >Y1, it means that the energy consumption of this data center is abnormal, and an energy consumption abnormality signal is generated. If P k ≤Y1, it means that the energy consumption of this data center is normal;

[0015] Step 3: Based on the confirmed energy consumption abnormality signal and the energy consumption correlation ratio confirmed by different operating equipment, and based on the specific energy consumption changes of the operating equipment, analyze the energy consumption data associated with different operating equipment to assess whether other operating equipment has abnormal energy consumption changes. If there are operating equipment with abnormal energy consumption changes, adjust such abnormal energy consumption equipment based on the confirmed energy consumption correlation ratio, and determine whether the PUE value associated with the data center after the adjustment is normal. The specific method is as follows:

[0016] S31. If there is an associated running device belonging to a single associated running device set: based on the confirmed energy consumption abnormality signal, confirm the energy consumption change data NJ generated by the corresponding running device in unit time, and then based on other running devices associated with this running device and the associated energy consumption correlation ratio, confirm the standard energy consumption change data NS associated with other running devices; then directly confirm the actual energy consumption change data JN generated by other associated running devices in this unit time, if NS≤NJ, no processing is performed, if NS>NJ, then this running device is marked as an abnormal energy consumption device;

[0017] If there is an associated running device belonging to a set of multiple associated running devices: based on the confirmed energy consumption abnormality signal, confirm the energy consumption change data generated by different running devices in unit time, and then based on other running devices associated with this running device and the associated energy consumption correlation ratio, confirm the standard energy consumption change data associated with other running devices. Because different running devices can confirm different standard energy consumption change data associated with other running devices after processing, the confirmed multiple groups of different standard energy consumption change data are summed to confirm the total standard energy consumption value HH belonging to other running devices;

[0018] Then confirm the actual energy consumption change data SJ generated by other running equipment in this unit time. If HH≥SJ, no processing is performed. If HH<SJ, other running equipment is marked as abnormal energy consumption equipment.

[0019] Furthermore, in step 3, the specific method of adjusting the abnormal energy consumption equipment is:

[0020] For the calibrated abnormal energy consumption equipment, the operating parameters of such abnormal energy consumption equipment are adjusted to reduce the associated operating parameters until the actual energy consumption change data generated by the corresponding abnormal energy consumption equipment per unit time meets the standard. If the corresponding abnormal energy consumption equipment still cannot meet the standard when the operating parameter is adjusted down to the minimum value, where the minimum value is the preset value, the PUE value associated with the data center is reconfirmed. If the PUE value meets the standard, no processing is performed. If the PUE value does not meet the standard, a personnel intervention signal is generated for display.

[0021] Preferably, a management system for PUE value of a data center includes:

[0022] The energy consumption correlation ratio recording terminal processes the relevant historical operation data of different operating equipment in the data center, confirms the energy consumption correlation ratio associated with the corresponding associated equipment based on the correlation between different operating equipment, and records the confirmed energy consumption correlation ratio;

[0023] The energy consumption abnormality signal confirmation terminal monitors the energy consumption data associated with different operating equipment in the data center, confirms the PUE value associated with the corresponding time in real time, and then confirms the energy consumption abnormality signal based on the specific changes in the PUE value;

[0024] The energy consumption anomaly management end, based on the confirmed energy consumption anomaly signals and the energy consumption correlation ratios confirmed by different operating equipment, and based on the specific energy consumption changes of the operating equipment, analyzes the energy consumption data associated with different operating equipment, and assesses whether other operating equipment has abnormal energy consumption changes. If there are operating equipment with abnormal energy consumption changes, such abnormal energy consumption equipment is adjusted based on the confirmed energy consumption correlation ratio, and it is determined whether the PUE value associated with the data center after the adjustment is normal.

[0025] The present invention provides a method and system for managing the PUE value of a data center. Compared with the prior art, it has the following beneficial effects:

[0026] The present invention processes the historical operation data of different running devices and confirms the energy consumption correlation ratio based on the correlation between devices. This method can deeply explore the internal connection between the energy consumption of devices, and can accurately determine the energy consumption correlation ratio regardless of whether it is a single correlation or a collection of multiple correlated devices; when processing the correlation between heat dissipation devices and multiple groups of heat dissipation devices, a unique mean feature processing and equal distribution method is used to accurately calculate the energy consumption correlation ratio, which provides a reliable basis for subsequent energy consumption analysis and management, and helps to accurately grasp the overall energy consumption structure of the data center;

[0027] Real-time monitoring of energy consumption data of different running equipment, and calculation of PUE value through specific formula; by comparing with preset parameter Y1, it can timely and accurately determine whether the energy consumption of the data center is abnormal; when the PUE value exceeds the preset 1.5, an energy consumption abnormality signal is quickly generated, so that management personnel can detect energy consumption problems at the first time, providing a guarantee for timely measures to avoid cost increases and potential equipment risks caused by excessive energy consumption;

[0028] In the case of abnormal energy consumption, based on the energy consumption correlation ratio and equipment energy consumption change data, it can be quickly and accurately assessed whether the energy consumption changes of other operating equipment are abnormal; there are corresponding clear assessment methods for single and multiple related equipment sets. Once the abnormal energy consumption equipment is determined, its operating parameters can be adjusted in time, such as reducing voltage and current, so that the energy consumption returns to normal; if the operating parameters are lowered to the lowest and still cannot meet the standards, it can be decided whether human intervention is needed by reconfirming the PUE value. This hierarchical processing method effectively ensures the stability and rationality of the data center's energy consumption, improves energy utilization efficiency, reduces operating costs, and ensures the efficient and stable operation of the data center. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 It is a schematic diagram of the process of the present invention;

[0030] Figure 2 It is a schematic diagram of the principle framework of the present invention. DETAILED DESCRIPTION

[0031] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0032] First embodiment

[0033] See also Figure 1 The present application provides a method for managing the PUE value of a data center, comprising the following steps:

[0034] Step 1: Process the relevant historical operation data of different operating equipment in the data center, confirm the energy consumption correlation ratio associated with the corresponding associated equipment based on the correlation between different operating equipment, and record the confirmed energy consumption correlation ratio. Specifically, the correlation between the operating equipment is calibrated in advance by the relevant operators, and is determined based on the operating conditions between the equipment. For example, when the operating load of the IT equipment increases, the corresponding power supply equipment power consumption will increase and the corresponding server processing load will increase. When the load of the IT equipment, power supply equipment and server are all increased, a large amount of heat characteristics will be generated. The corresponding heat dissipation equipment increases the energy consumption load based on the large amount of heat characteristics generated in the data center, performs a large amount of heat dissipation, and processes the heat characteristics generated in the data center. Based on these correlations, the relevant operators calibrate in advance to facilitate the subsequent comprehensive management of the PUE value of the entire data center. The specific sub-steps for confirmation are:

[0035] S11. Based on the pre-set associations between different operating devices, confirm that there is an associated associated operating device set. If a certain group of operating devices is associated with only one group of operating devices, it is recorded as a single associated operating device set. If a certain group of operating devices is associated with multiple groups of operating devices, it is recorded as a multiple associated operating device set. Specifically, there are only two groups of operating devices in the single associated operating device set, that is, the associated operating devices. There are multiple groups of operating devices in the multiple associated operating device set, that is, the corresponding operating device is associated with multiple groups of operating devices, such as the corresponding heat dissipation device, which is associated with multiple groups of related operating devices in the data center that need to be cooled.

[0036] S12. For the confirmed single associated running equipment set, identify the historical energy consumption data of the corresponding running equipment from the set, select energy consumption improvement data from the historical energy consumption data, identify the improvement amount of the corresponding energy consumption data per unit time from the selected energy consumption improvement data, and mark it as Ts i , where i represents different operating equipment, and the associated lifting amount Ts of different operating equipment in different unit time i , perform mean processing, confirm the mean characteristics associated with the corresponding running equipment, perform ratio processing on the mean characteristics of different running equipment in this single associated running equipment set, and confirm the energy consumption correlation ratio of this single associated running equipment set;

[0037] For the confirmed multiple sets of associated running devices, terminal running devices (the terminal running devices are generally heat dissipation devices) are preferentially determined. The terminal running devices belong to terminal devices, and the terminal devices are associated with other running devices in the multiple sets of associated running devices. Other running devices in the multiple sets of associated running devices except the terminal devices are marked as pending devices, and historical energy consumption data of several groups of pending devices are determined. Energy consumption improvement data associated with multiple groups of pending devices in the same period are identified from the historical energy consumption data. From the associated energy consumption improvement data, the mean characteristics associated with the corresponding pending devices are confirmed using the same processing method as the above-mentioned running devices to confirm the mean characteristics, and then the mean characteristics TZ generated by the terminal running devices in this period are determined;

[0038] The mean characteristics associated with different pending devices are processed by ratio, and the ratio sequences associated with multiple groups of pending devices are confirmed. Based on the determined ratio sequence, TZ is evenly divided, and the average value associated with a single ratio in the ratio sequence is confirmed (the proposed ratio sequence is 2:3:5, and the confirmed TZ is 40, then the average value associated with the first group of ratio 2 is 8, the average value associated with the second group of ratio 3 is 12, and the average value associated with the third group of ratio 5 is 20). The mean characteristics of the pending devices associated with the corresponding ratios of the ratio sequence and the confirmed average values ​​are determined, and the energy consumption correlation ratio associated with the corresponding pending devices and the terminal operation devices is confirmed by the method of (mean characteristics: average value);

[0039] Specifically, the energy consumption of the corresponding equipment is correlated during the change process, and the corresponding energy consumption changes are also correlated. However, when the correlated equipment is only associated with a single group, the relevant energy consumption ratio can be quickly determined based on the energy consumption changes of the corresponding single group of associated equipment. For specific equipment with multiple groups of associations, it is necessary to confirm the energy consumption values. Based on the specific changes in the energy consumption values ​​of the corresponding equipment, the overall changes of the corresponding associated equipment can be identified, and then the equalization confirmation is performed to lock the energy consumption correlation ratio associated with the corresponding associated equipment.

[0040] Step 2: Monitor the energy consumption data associated with different running equipment in the data center, confirm the PUE value associated with the corresponding time in real time, and then confirm the energy consumption abnormality signal based on the specific changes of the PUE value. The specific method of confirmation is:

[0041] S21. The real-time energy consumption data generated by IT equipment in the data center is calibrated as NH k , where k represents different moments, and the real-time energy consumption data generated by other running equipment in the data center is calibrated as HH k-q , where q represents other different running equipment, and multiple sets of energy consumption data generated by all equipment in the data center at the same time are summed up to confirm the total energy consumption data ZH of this data center;

[0042] S22, use: P k =ZH÷NH k Confirm the PUE value P associated with the corresponding time k , the PUE value P associated with the corresponding time k Verify with the preset parameter Y1, where Y1 is the preset value, and its specific value is determined by the operator based on experience. k ≤Y1, it means that the energy consumption of this data center is normal. If P k >Y1, it means that the energy consumption of this data center is abnormal, and an energy consumption abnormality signal is generated;

[0043] Among them, Y1 generally takes a value of 1.5. When the confirmed PUE value is lower than 1.5, it means that the overall energy consumption associated with the corresponding data center is good. When it exceeds the corresponding 1.5, it means that the energy consumption data generated by other equipment in the corresponding data center is too large, then there is an abnormal energy consumption situation, and relevant adjustments need to be made.

[0044] Step 3: Based on the confirmed energy consumption abnormality signal and the energy consumption correlation ratio confirmed by different operating equipment, and based on the specific energy consumption changes of the operating equipment, analyze the energy consumption data associated with different operating equipment to assess whether other operating equipment has abnormal energy consumption changes. If there are operating equipment with abnormal energy consumption changes, adjust such abnormal energy consumption equipment based on the confirmed energy consumption correlation ratio, and determine whether the PUE value associated with the data center after the adjustment is normal. The specific method for assessing whether other operating equipment has abnormal energy consumption changes is as follows:

[0045] S31. If there is an associated running device belonging to a single associated running device set: based on the confirmed energy consumption abnormality signal, confirm the energy consumption change data NJ generated by the corresponding running device in unit time (if the energy consumption is increased, the energy consumption change data is a positive value, if the energy consumption is reduced, the energy consumption change data is a negative value, this running device belongs to the former group of devices in the preset association, and the latter group of running devices belongs to the associated running devices), and then based on other running devices associated with this running device and the associated energy consumption association ratio, confirm the standard energy consumption change data NS associated with other running devices; then directly confirm the actual energy consumption change data JN (based on data monitoring) generated by other associated running devices in this unit time. If NS≤NJ, no processing is performed. If NS>NJ, this running device is marked as an abnormal energy consumption device.

[0046] If there is an associated running device belonging to a set of multiple associated running devices: based on the confirmed energy consumption abnormality signal, confirm the energy consumption change data generated by different running devices in unit time, and then based on other running devices associated with this running device and the associated energy consumption correlation ratio, confirm the standard energy consumption change data associated with other running devices. Because different running devices can confirm different standard energy consumption change data associated with other running devices after processing, the confirmed multiple groups of different standard energy consumption change data are summed to confirm the total standard energy consumption value HH belonging to other running devices;

[0047] Then confirm the actual energy consumption change data SJ generated by other running equipment in this unit time. If HH≥SJ, no processing is performed. If HH<SJ, other running equipment is marked as abnormal energy consumption equipment.

[0048] S32. For the calibrated abnormal energy consumption equipment, the operating parameters of such abnormal energy consumption equipment are adjusted (the relevant operating parameters, such as voltage and current, etc., can be appropriately lowered) to reduce the associated operating parameters until the actual energy consumption change data generated by the corresponding abnormal energy consumption equipment per unit time meets the standard. If the corresponding abnormal energy consumption equipment still cannot meet the standard when the operating parameters are adjusted to the lowest value, where the lowest value is a preset value prepared in advance by relevant operating personnel, the PUE value associated with the data center is reconfirmed. If the PUE value meets the standard, no processing is performed. If the PUE value does not meet the standard, a personnel intervention signal is generated for display for external relevant personnel to view, indicating that this data center requires human intervention to adjust the abnormal energy consumption equipment associated with the data center to ensure that the energy consumption data associated with the corresponding abnormal energy consumption equipment can change normally.

[0049] Second embodiment

[0050] Combination Figure 2 , a management system for PUE value of data center, including:

[0051] The energy consumption correlation ratio recording terminal processes the relevant historical operation data of different operating equipment in the data center, confirms the energy consumption correlation ratio associated with the corresponding associated equipment based on the correlation between different operating equipment, and records the confirmed energy consumption correlation ratio;

[0052] The energy consumption abnormality signal confirmation terminal monitors the energy consumption data associated with different operating equipment in the data center, confirms the PUE value associated with the corresponding time in real time, and then confirms the energy consumption abnormality signal based on the specific changes in the PUE value;

[0053] The energy consumption anomaly management end, based on the confirmed energy consumption anomaly signals and the energy consumption correlation ratios confirmed by different operating equipment, and based on the specific energy consumption changes of the operating equipment, analyzes the energy consumption data associated with different operating equipment, and assesses whether other operating equipment has abnormal energy consumption changes. If there are operating equipment with abnormal energy consumption changes, such abnormal energy consumption equipment is adjusted based on the confirmed energy consumption correlation ratio, and it is determined whether the PUE value associated with the data center after the adjustment is normal.

[0054] Some of the data in the above formulas are dimensionless and numerically calculated. Meanwhile, the contents not described in detail in this specification belong to the prior art known to those skilled in the art.

[0055] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A method for managing the PUE value of a data center, characterized in that: The following steps are involved: Step 1: Process the relevant historical operation data of different operating equipment in the data center, confirm the energy consumption correlation ratio associated with the corresponding associated equipment based on the correlation between the different operating equipment, and record the confirmed energy consumption correlation ratio; Step 2: Monitor the energy consumption data associated with different running equipment in the data center, confirm the PUE value associated with the corresponding time in real time, and then confirm the energy consumption abnormality signal based on the specific changes of the PUE value; Step 3: Based on the confirmed energy consumption abnormality signal and the energy consumption correlation ratio confirmed by different operating equipment, and based on the specific energy consumption changes of the operating equipment, analyze the energy consumption data associated with different operating equipment to assess whether other operating equipment has abnormal energy consumption changes. If there are operating equipment with abnormal energy consumption changes, adjust such abnormal energy consumption equipment based on the confirmed energy consumption correlation ratio, and determine whether the PUE value associated with the data center after the adjustment is normal.

2. A method for managing the PUE value of a data center according to claim 1, characterized in that: In the step 1, the specific sub-steps of confirming the energy consumption correlation ratio of the corresponding associated equipment are: S11. Based on the pre-set associations between different operating devices, confirm that there is an associated associated operating device set. If a certain group of operating devices is associated with only one group of operating devices, it is recorded as a single associated operating device set. If a certain group of operating devices is associated with multiple groups of operating devices, it is recorded as a multiple associated operating device set. S12. For the confirmed single associated running equipment set, identify the historical energy consumption data of the corresponding running equipment from the set, select energy consumption improvement data from the historical energy consumption data, identify the improvement amount of the corresponding energy consumption data per unit time from the selected energy consumption improvement data, and mark it as Ts i , where i represents different operating equipment, and the associated lifting amount Ts of different operating equipment in different unit time i , perform mean processing, confirm the mean characteristics associated with the corresponding running equipment, perform ratio processing on the mean characteristics of different running equipment in this single associated running equipment set, and confirm the energy consumption correlation ratio of this single associated running equipment set.

3. A method for managing the PUE value of a data center according to claim 2, characterized in that: In the step S12: For the confirmed multiple sets of associated running devices, the terminal running devices are preferentially determined, and the terminal running devices belong to the terminal devices, and the terminal devices are associated with other running devices in the multiple sets of associated running devices. The other running devices in the multiple sets of associated running devices except the terminal devices are marked as pending devices, and the historical energy consumption data of several groups of pending devices are determined. The energy consumption improvement data associated with the multiple groups of pending devices in the same period are identified from the historical energy consumption data. From the associated energy consumption improvement data, the mean characteristics associated with the corresponding pending devices are confirmed by using the same processing method as the above-mentioned running devices to confirm the mean characteristics, and then the mean characteristics TZ generated by the terminal running devices in this period are determined; The mean characteristics associated with different pending devices are ratio processed to confirm the ratio sequence associated with multiple groups of pending devices. TZ is evenly divided based on the determined ratio sequence to confirm the average value associated with a single ratio in the ratio sequence. The mean characteristics of the pending devices associated with the corresponding ratios of the ratio sequence and the confirmed average value are determined. The energy consumption correlation ratio associated with the corresponding pending device and the terminal operating device is confirmed using the (mean characteristic: average value) method.

4. A method for managing PUE value of a data center according to claim 1, characterized in that: In step 2, the specific method of confirming the abnormal energy consumption signal is: S21. The real-time energy consumption data generated by IT equipment in the data center is calibrated as NH k , where k represents different moments, and the real-time energy consumption data generated by other running equipment in the data center is calibrated as HH k-q , where q represents other different running equipment, and multiple sets of energy consumption data generated by all equipment in the data center at the same time are summed up to confirm the total energy consumption data ZH of this data center; S22, use: P k =ZH÷NH k Confirm the PUE value P associated with the corresponding time k , the PUE value P associated with the corresponding time k Verify with the preset parameter Y1, where Y1 is the preset value. k >Y1, it means that the energy consumption of this data center is abnormal, and an energy consumption abnormality signal is generated.

5. A method for managing the PUE value of a data center according to claim 4, characterized in that: In step S22, if P k ≤Y1, it means that the energy consumption of this data center is normal.

6. A method for managing the PUE value of a data center according to claim 4, characterized in that: In step 3, the specific method for evaluating whether the energy consumption of other running equipment changes abnormally is: S31. If there is an associated running device belonging to a single associated running device set: based on the confirmed energy consumption abnormality signal, confirm the energy consumption change data NJ generated by the corresponding running device in unit time, and then based on other running devices associated with this running device and the associated energy consumption correlation ratio, confirm the standard energy consumption change data NS associated with other running devices; then directly confirm the actual energy consumption change data JN generated by other associated running devices in this unit time, if NS≤NJ, no processing is performed, if NS>NJ, then this running device is marked as an abnormal energy consumption device; If there is an associated running device belonging to a set of multiple associated running devices: based on the confirmed energy consumption abnormality signal, confirm the energy consumption change data generated by different running devices in unit time, and then based on other running devices associated with this running device and the associated energy consumption correlation ratio, confirm the standard energy consumption change data associated with other running devices. Because different running devices can confirm different standard energy consumption change data associated with other running devices after processing, the confirmed multiple groups of different standard energy consumption change data are summed to confirm the total standard energy consumption value HH belonging to other running devices; Then confirm the actual energy consumption change data SJ generated by other running equipment in this unit time. If HH≥SJ, no processing is performed. If HH<SJ, other running equipment is marked as abnormal energy consumption equipment.

7. A method for managing the PUE value of a data center according to claim 6, characterized in that: In step 3, the specific method of adjusting the abnormal energy consumption equipment is: For the calibrated abnormal energy consumption equipment, the operating parameters of such abnormal energy consumption equipment are adjusted to reduce the associated operating parameters until the actual energy consumption change data generated by the corresponding abnormal energy consumption equipment per unit time meets the standard. If the corresponding abnormal energy consumption equipment still cannot meet the standard when the operating parameter is adjusted down to the minimum value, where the minimum value is the preset value, the PUE value associated with the data center is reconfirmed. If the PUE value meets the standard, no processing is performed. If the PUE value does not meet the standard, a personnel intervention signal is generated for display.

8. A management system for PUE value of a data center, the management system is operated based on the management method for PUE value of a data center according to any one of claims 1 to 7, characterized in that: include: The energy consumption correlation ratio recording terminal processes the relevant historical operation data of different operating equipment in the data center, confirms the energy consumption correlation ratio associated with the corresponding associated equipment based on the correlation between different operating equipment, and records the confirmed energy consumption correlation ratio; The energy consumption abnormality signal confirmation terminal monitors the energy consumption data associated with different operating equipment in the data center, confirms the PUE value associated with the corresponding time in real time, and then confirms the energy consumption abnormality signal based on the specific changes in the PUE value; The energy consumption anomaly management end, based on the confirmed energy consumption anomaly signals and the energy consumption correlation ratios confirmed by different operating equipment, and based on the specific energy consumption changes of the operating equipment, analyzes the energy consumption data associated with different operating equipment, and assesses whether other operating equipment has abnormal energy consumption changes. If there are operating equipment with abnormal energy consumption changes, such abnormal energy consumption equipment is adjusted based on the confirmed energy consumption correlation ratio, and it is determined whether the PUE value associated with the data center after the adjustment is normal.

Images