A test method for power supply and distribution system of shielded machine room

By analyzing the load test data of the power supply and distribution system of the computer room, the stability assessment vector is constructed, which solves the problem of low stability analysis accuracy in traditional testing methods, and realizes a more accurate system stability judgment under load conditions.

CN118940071BActive Publication Date: 2024-12-06SHENYANG SHITENG TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411412208.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-10-11
Publication Date
2024-12-06
Estimated Expiration
2044-10-11

AI Technical Summary

Technical Problem

The traditional computer room power supply and distribution system testing method is under the influence of load changes and power disturbances, resulting in low accuracy of stability analysis, and it is impossible to accurately judge the system stability under different load conditions.

Method used

By obtaining electrical parameter test data under different loads, analyzing the relative difference value and error value of load test, building a test data deviation vector and weight, combining the difference in load-test data characteristics, building a stability assessment vector, and conducting comprehensive load judgment.

Benefits of technology

The accuracy of the test stability analysis of the computer room power supply and distribution system under different load conditions is improved, the impact of load changes and power disturbances on the test results is reduced, and accurate operation test results are obtained.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118940071B_ABST
    Figure CN118940071B_ABST
Patent Text Reader

Abstract

The present application relates to the field of electrical testing technology, and specifically to a method for testing a power supply and distribution system in a shielded computer room, the method comprising: obtaining test data of various electrical parameters under different loads during the operation of the power supply and distribution system in the shielded computer room; analyzing the differences between the same test data sequences under different loads to determine the relative difference values ​​of the load tests of the same test data sequences under various loads; constructing power supply and distribution error values ​​under various loads, and then constructing test data deviation vectors of various test data sequences; analyzing the similarities between the test data deviation vectors of various test data sequences, and determining the power supply and distribution test weights of various test data sequences; constructing a stability evaluation vector through the power supply and distribution test weights and test data deviation vectors of the test data sequences of all electrical parameters, and testing the power supply and distribution system in the computer room. The present application can obtain accurate test results of the operation of the power supply and distribution system in the shielded computer room.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of electrical testing technology, and in particular to a method for testing a power supply and distribution system in a shielded machine room. Background Art

[0002] The power supply and distribution system in the computer room is the key to ensure the stable operation of the data center and other key facilities. Regular testing can ensure the reliability and safety of the power supply and distribution system and prevent equipment damage or data loss due to power problems. With the rapid development of information construction, the design of the power supply and distribution system in the computer room is becoming more and more complex, involving multiple aspects such as mains power supply, lightning protection grounding, anti-static, UPS uninterruptible power supply, diesel generators, etc.

[0003] At present, UPS power supply and distribution system has become the main power supply mode of the computer room of the data center. Although the design and construction of the power supply and distribution system of the computer room have made certain progress, there are still some problems, such as the capacity configuration of the power supply and distribution system, power quality, harmonic interference, grounding and lightning protection system design, etc. Therefore, it is necessary to test the operation of the power supply and distribution system of the computer room to ensure the stable operation of the power supply and distribution system of the computer room. The test of the traditional power supply and distribution system is mainly carried out through the monitoring of short circuit, overload and short circuit. Due to the existence of load changes and power supply disturbances during the load test of the power supply and distribution system of the computer room, the stability analysis of the test under a single load condition and the relative analysis under multiple load conditions have large errors, which makes the accuracy of the test data analysis of the power supply and distribution system of the computer room generally low, affecting the judgment of the stability of the power supply and distribution system of the computer room under different load conditions. Summary of the invention

[0004] In order to solve the above technical problems, the present application provides a method for testing a power supply and distribution system in a shielded computer room to solve the existing problems.

[0005] A shielded room power supply and distribution system testing method of the present application adopts the following technical solution:

[0006] An embodiment of the present application provides a method for testing a power supply and distribution system in a shielded equipment room, the method comprising the following steps:

[0007] Acquire test data of various electrical parameters under different loads during the operation of the power supply and distribution system of the shielded equipment room, and form various test data sequences under different loads, wherein one electrical parameter corresponds to one test data sequence;

[0008] Analyze the differences between the same test data sequences under different loads to determine the relative difference values ​​of the load tests of the same test data sequence under each load;

[0009] Analyze the difference between the relative difference values ​​of load tests of the same test data sequence under various loads, and construct the power supply and distribution error value under various loads;

[0010] Constructing test data deviation vectors of various test data sequences based on the power supply and distribution error values ​​of the same test data sequence under all loads, wherein the mean of all the power supply and distribution error values ​​obtained under each load in each cluster is recorded as the first error mean under each load in each cluster, the average of the first error means under the same load in all clusters is taken as the second error mean under the same load, and the vector composed of the second error means obtained under all loads arranged in ascending order of load is taken as the test data deviation vector of the test data sequence under different load conditions during the test process;

[0011] Analyze the similarity between the test data deviation vectors of various test data sequences and determine the power supply and distribution test weights of various test data sequences;

[0012] A stability evaluation vector is constructed through the power supply and distribution test weights and test data deviation vectors of the test data sequences of all electrical parameters, wherein the measurement data deviation vectors of various test data sequences are used as rows to form a load comprehensive judgment matrix, and the product of the power supply and distribution test weight vector and the load comprehensive judgment matrix is ​​used as the stability evaluation vector to test the power supply and distribution system of the computer room.

[0013] Furthermore, the process of acquiring the load test relative difference value is: taking the average of the differences between each load and the same test data sequence under all other loads as the load test relative difference value of the same test data sequence under each load.

[0014] Furthermore, the method for constructing the power supply and distribution error value under each load is:

[0015] Clustering the same test data sequences under all loads, obtaining probability distribution curves of all the same test data sequences under the same load in each cluster, and recording them as probability distribution curves under each load in each cluster;

[0016] The difference between the probability distribution curve under each load in each cluster and the probability distribution curve under the same load in other clusters is taken as the power supply and distribution error value under each load.

[0017] Furthermore, the power supply and distribution test weights of the various test data sequences are the averages of the similarities between the test deviation vectors of the various test data sequences and all other test data sequences.

[0018] Furthermore, the power supply and distribution test weights of all test data sequences are combined into a one-dimensional vector, which is recorded as a power supply and distribution test weight vector.

[0019] Furthermore, the testing of the power supply and distribution system in the computer room includes: normalizing all elements in the stability evaluation vector and then calculating the average, which is recorded as the load test result. When the load test result is within a preset qualified range, the load test of the power supply and distribution system in the computer room is qualified.

[0020] This application has at least the following beneficial effects:

[0021] The present application considers that in the traditional load test process of the power supply and distribution in the computer room, only a single parameter analysis is performed on the difference in system stability under different loads, thereby ignoring the relative characteristics of the stability differences under different loads caused by load changes and power supply disturbances, thereby affecting the accuracy of the test stability analysis of the power supply and distribution system under different load conditions. Therefore, the load-test data feature differences at different test times are introduced into the load test process of the power supply and distribution system, specifically including the differences in load-voltage features, load-current features and load-power features, wherein the load-test data features represent the test data change features under different load conditions at each test time, and the test data is divided according to the load-test data feature differences, so as to perform relative difference analysis of the data, and obtain the analysis results of the stability of the power supply and distribution system test under different load conditions for all types of test data. The beneficial effect lies in combining the load-test data feature differences at different test times, reducing the influence of the stability differences under different loads caused by load changes and power supply disturbances on the load test stability results, and obtaining accurate shielded computer room power supply and distribution system operation test results. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 A flowchart of the steps of a method for testing a power supply and distribution system in a shielded equipment room provided in this application;

[0024] Figure 2 A schematic diagram of a flow chart for constructing power supply and distribution error values ​​under various loads provided in this application;

[0025] Figure 3 A schematic diagram of the test data deviation vector construction process provided for this application;

[0026] Figure 4 Schematic diagram of the evaluation curve for the load test of the power supply and distribution system in the computer room provided for this application. DETAILED DESCRIPTION

[0027] In order to further explain the technical means and effects adopted by the present application to achieve the predetermined invention purpose, the following is a detailed description of the specific implementation method, structure, features and effects of a shielded room power supply and distribution system testing method proposed in the present application in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0028] Unless otherwise defined, terms such as "comprises", "comprising" or any other variants thereof are intended to cover non-exclusive inclusion, so that a circuit structure, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such articles or devices. In the absence of further restrictions, an element defined by the statement "comprising a ..." does not exclude the presence of other identical elements in the article or device comprising the element. In addition, the term "and\or" used herein includes any and all combinations of one or more related listed items. All technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present application belongs.

[0029] The specific scheme of the shielded machine room power supply and distribution system testing method provided by the present application is described in detail below with reference to the accompanying drawings.

[0030] An embodiment of the present application provides a method for testing a power supply and distribution system in a shielded equipment room. For details, please refer to Figure 1 , the method comprises the following steps:

[0031] Step 1: Obtain test data during the operation test of the power supply and distribution system in the shielded equipment room.

[0032] The test data of various electrical parameters under different loads during the operation of the shielded computer room power supply and distribution system are obtained to form various test data sequences under different loads, wherein one electrical parameter corresponds to one test data sequence. Generally, the test of the computer room power supply and distribution system mainly includes voltage or current overload test, load test, grounding test, power value test and safety test, wherein the load test of the computer room power supply and distribution system is mainly carried out by monitoring and analyzing the stability characteristics of the power supply and distribution system under different loads. Therefore, this embodiment collects the test data of the electrical parameters of the computer room power supply and distribution system under different loads, wherein the electrical parameters include the output voltage, current and power data of the power supply and distribution equipment, and the voltage, current and power data collected under each load are respectively used as the voltage data sequence, current data sequence and power data sequence in ascending time order, wherein the voltage data sequence, current data sequence and power data sequence obtained under each load are all the test data sequences of the computer room power supply and distribution system operation test under each load.

[0033] Furthermore, during the above-mentioned power supply and distribution system operation test process, test data under different loads are collected through voltage sensors, current sensors and power sensors. The specific sensor models can be determined by the implementer according to the actual test environment; the test data sequence of the computer room power supply and distribution system operation test under each load condition is used as input, and the median filtering algorithm is used for noise reduction processing. In other embodiments, the implementer can use other noise reduction methods in the prior art to perform noise reduction processing on the collected data.

[0034] So far, the test data sequences under different loads during the operation test of the power supply and distribution system have been obtained.

[0035] Step 2: Analyze the differences between the same test data sequences under different loads to determine the relative difference values ​​of the load tests of the same test data sequence under each load.

[0036] Normally, during the load test of the power supply and distribution system, the gradual increase in load may cause disturbances in the parameters of the power supply and distribution system within the set range. During the operation test of the power supply and distribution system, due to the influence of factors such as equipment parameters and power supply disturbances, the stability of the test data of the power supply and distribution system under different load conditions is judged only by analyzing the test data of the power supply and distribution system under a single load condition, ignoring the randomness and short-term trend of the data stability differences under different load conditions, resulting in the analysis results of the power supply and distribution system test data under different load conditions cannot accurately reflect the load test conditions of the power supply and distribution system.

[0037] In view of the above situation, when the power supply and distribution system is load tested, the power supply and distribution test data under different load conditions are relatively analyzed, and the deviation characteristics of the power supply and distribution system operation test under different load conditions are accurately obtained based on the analysis results, so as to obtain accurate stability judgment results of the operation test under different load conditions during the power supply and distribution system test, thereby improving the accuracy of the power supply and distribution system operation test analysis.

[0038] Furthermore, a test weight matrix is ​​obtained based on the relative characteristics of the test data changes under different loads in the power supply and distribution system. The test weight matrix reflects the relative characteristics of different types of test data under different loads, that is, the load-test data characteristics of different data at different test times are combined to obtain accurate stability difference results of the power supply and distribution system operation test. The specific analysis process is as follows:

[0039] For the test data sequence obtained under each load condition during the operation test of the power supply and distribution system, the voltage data sequence in the test data sequence is taken as an example for analysis, and the difference between the voltage data sequence under each load and all other loads is fused as the load test relative difference value of the voltage data sequence under each load.

[0040] It should be noted that the fusion can be an additive relationship, a multiplicative relationship, a mean or other positive correlation relationship, and the difference between the sequences can also be expressed by Euclidean distance, Manhattan distance, etc., which can be selected by the implementer. Preferably, in this embodiment, for the convenience of expression, the Manhattan distance between the voltage data sequence under each load and other loads is used as the first characteristic difference, and the mean of the first characteristic difference between each load and all other loads is used as the load test relative difference value of the voltage data sequence under each load, that is, the mean of the Manhattan distance between the voltage data sequence of each load and all other loads is used as the load test relative difference value of the voltage data sequence under each load.

[0041] It should be understood that the larger the relative difference value of the load test is, the more significant the relative deviation of the voltage data sequence under the current load is from that under other loads during the operation test of the power supply and distribution system.

[0042] Step 3: Analyze the difference between the relative difference values ​​of the load tests of the same test data sequence under each load, and construct the power supply and distribution error value under each load.

[0043] Taking the voltage data sequence in the test data sequence as an example, for the convenience of analysis, in this embodiment, the voltage data sequences under all loads are taken as a load test set, and the density peak clustering algorithm is used to obtain the division results of all sequences in the load test set. The relative difference values ​​of the load tests of all sequences in each cluster in the division result are taken as a sequence composed of the corresponding acquisition time in ascending order as a load interference data sequence. By analyzing the similar load-voltage change characteristics at different times divided in each cluster, the deviation state distribution characteristics of each sequence in the cluster relative to the overall sequence are obtained;

[0044] It should be noted that the density peak clustering algorithm used above is used to obtain the division results of all sequences in the load test set. The density peak clustering algorithm is only one of the implementation methods for dividing the sequences in the load test set in this embodiment. On the basis of achieving the purpose of dividing the sequences in the load test set, other existing technologies can be used in other embodiments.

[0045] Normally, when the random characteristics and short-term relative change characteristics of stability deviation disturbances under different load test conditions during the operation test of the power supply and distribution system are also small, the load-voltage characteristics at different test times are less different. However, due to the influence of factors such as load changes and power supply disturbances on the power supply and distribution system during the actual operation test, the deviation characteristics of stability are quite different, and the differences between load voltage characteristics at different test times are large. According to the above clustering results based on load-voltage characteristics, the voltage data under the same load conditions are analyzed. The specific analysis process is as follows:

[0046] Based on the degree of difference between the relative difference values ​​of the load tests of the same test data sequence under each load, the power supply and distribution error value under each load is constructed. The same test data sequence under all loads is clustered, and the probability distribution curves of all the same test data sequences under each load in each cluster cluster are obtained; the difference between the probability distribution curve under each load in each cluster cluster and the probability distribution curves under the same load in other cluster clusters is used as the power supply and distribution error value under each load.

[0047] Preferably, in this embodiment, the probability distribution curve of the elements in all test data sequences under the same load in each cluster is obtained; for the probability distribution curve under each load condition in each cluster, in this embodiment, the KL divergence value between the probability distribution curves under the same load in all clusters is used as the power supply and distribution error value under each load.

[0048] It should be understood that the larger the power supply and distribution error value is, the greater the relative change difference in the load-voltage data of the power supply and distribution system operation test at different test times is based on the load-voltage characteristic division at different test times.

[0049] Specifically, the schematic diagram of the power supply and distribution error value construction process under each load is as follows: Figure 2 shown.

[0050] Step 4: Construct test data deviation vectors of various test data sequences based on the power supply and distribution error values ​​of the same test data sequence under all loads.

[0051] The above process is an analysis process taking the voltage data sequence under different load conditions during the operation test of the power supply and distribution system as an example. Therefore, the same as the above calculation and analysis process, the test data deviation vectors of the current data sequence and the power data sequence under different load conditions can be obtained respectively, and the power supply and distribution test weight of each test data sequence is calculated according to the test data deviation vectors of different test data sequences. The specific calculation and analysis process is as follows:

[0052] The mean of all power supply and distribution error values ​​corresponding to each load condition in each cluster after clustering is taken as the first error mean under each load condition in each cluster, and the mean of the first error means under the same load condition in all clusters is taken as the second error mean.

[0053] A vector composed of the second error means obtained under all load conditions in order from small to large according to the corresponding loads is used as the test data deviation vector of the voltage data sequence under different load conditions during the test process. The test data deviation vector represents the relative difference in the voltage data performance under each load condition after comparing and dividing the load-voltage characteristics under different test times, and accurately characterizes the degree of test stability difference under each load condition.

[0054] Specifically, the test data deviation vector construction process diagram is as follows Figure 3 shown.

[0055] Step 5: Analyze the similarities between the test data deviation vectors of various test data sequences, and determine the power supply and distribution test weights of various test data sequences.

[0056] The power supply and distribution test weights of various test data sequences are the mean of the similarities between the test deviation vectors of various test data sequences and all other test data sequences. It should be noted that there are many methods for calculating the similarity between vectors. This embodiment uses cosine similarity, and there is no special limitation on this.

[0057] Preferably, in this embodiment, for the test data deviation vector of each test data sequence, the cosine similarity between the test data deviation vector and the test deviation vector of each other test data sequence, and the average of all cosine similarities corresponding to each test data sequence are used as the power supply and distribution test weight.

[0058] It should be understood that the larger the weight of the power supply and distribution test, the smaller the relative change difference in the stability of the current test data sequence based on the load-test data feature analysis under different load conditions.

[0059] The power supply and distribution test weights of all test data sequences are formed into a one-dimensional vector, which is recorded as the power supply and distribution test weight vector. Preferably, in this embodiment, the power supply and distribution test weights of the test data sequences of all types of electrical parameters are formed into a one-dimensional vector in the order of voltage, current and power, which is recorded as the power supply and distribution test weight vector A.

[0060] At this point, the power supply and distribution test weight vector in the power supply and distribution system test process of the computer room is obtained.

[0061] Step 6: Construct a stability evaluation vector through the power supply and distribution test weights and test data deviation vectors of the test data sequences of all electrical parameters to test the power supply and distribution system of the computer room.

[0062] The measured data deviation vector of each test data sequence is used as a row element in the matrix, and the matrix composed of the measured data deviation vectors of all test data sequences is used as the load comprehensive judgment matrix. Preferably, in this embodiment, the measured data deviation vector of each test data sequence obtained during the operation test of the power supply and distribution system in the computer room is used as a row element in the matrix, and the matrix composed of the measured data deviation vectors of all electrical parameter test data sequences in the order of voltage, current and power from top to bottom is used as the load comprehensive judgment matrix B.

[0063] Furthermore, according to the test weight matrix of the power supply and distribution system and the load comprehensive judgment matrix, a stability evaluation vector representing the difference in stability characteristics of the power supply and distribution system under different load conditions is obtained. , the specific calculation relationship is: It should be noted that the final stability evaluation vector is a one-dimensional row vector, and the stability evaluation vector represents the comprehensive judgment result of the stability characteristics under different load conditions.

[0064] To facilitate analysis, in this embodiment, the stability evaluation vector obtained during the operation test of the computer room power supply and distribution system is used as input, and the Z-score normalization algorithm is used to obtain the normalized results of all elements in the stability evaluation vector, and the average of the normalized results of each element in the stability evaluation vector is calculated, which is recorded as the load test result of the computer room power supply and distribution system; the elements of the stability evaluation vector are mapped to a two-dimensional rectangular coordinate system, and the curve formed by all data points in the two-dimensional rectangular coordinate system is used as the evaluation curve of the load test of the computer room power supply and distribution system, wherein the horizontal axis is the load and the vertical axis is the element in the stability evaluation vector. Specifically, the evaluation curve of the load test of the computer room power supply and distribution system is as follows: Figure 4As shown in the figure, the evaluation curve can be used to obtain the visualization results of the stability change characteristics of the power supply and distribution system in the computer room under different loads.

[0065] Furthermore, in this embodiment, the qualified range of the load test of the power supply and distribution system in the computer room is set to If the load test result is within the qualified range, the load test of the power supply and distribution system in the computer room is qualified.

[0066] It is understood that references to "one embodiment" or "some embodiments" etc. described in the specification of the present application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, if "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. appear in different places in this specification, they do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0067] It should be noted that the sequence of the above-mentioned embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-tasking and parallel processing are also possible or may be advantageous. At the same time, the size of the sequence number of each step in the embodiment does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments in this specification.

[0068] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for testing a power supply and distribution system in a shielded machine room, characterized in that: The method comprises the following steps: Acquire test data of various electrical parameters under different loads during the operation of the power supply and distribution system of the shielded equipment room, and form various test data sequences under different loads, wherein one electrical parameter corresponds to one test data sequence; Analyze the differences between the same test data sequences under different loads to determine the relative difference values ​​of the load tests of the same test data sequences under each load; Analyze the difference between the relative difference values ​​of load tests of the same test data sequence under various loads, and construct the power supply and distribution error value under various loads; Constructing test data deviation vectors of various test data sequences based on the power supply and distribution error values ​​of the same test data sequence under all loads, wherein the mean of all the power supply and distribution error values ​​obtained under each load in each cluster is recorded as the first error mean under each load in each cluster, the average of the first error means under the same load in all clusters is taken as the second error mean under the same load, and the vector composed of the second error means obtained under all loads arranged in ascending order of load is taken as the test data deviation vector of the test data sequence under different load conditions during the test process; Analyze the similarity between the test data deviation vectors of various test data sequences and determine the power supply and distribution test weights of various test data sequences; A stability evaluation vector is constructed through the power supply and distribution test weights and test data deviation vectors of the test data sequences of all electrical parameters, wherein the measurement data deviation vectors of various test data sequences are used as rows to form a load comprehensive judgment matrix, and the product of the power supply and distribution test weight vector and the load comprehensive judgment matrix is ​​used as the stability evaluation vector to test the power supply and distribution system of the computer room.

2. A method for testing a power supply and distribution system in a shielded machine room as claimed in claim 1, characterized in that: The process of obtaining the load test relative difference value is as follows: taking the average of the differences between each load and the same test data sequence under all other loads as the load test relative difference value of the same test data sequence under each load.

3. A method for testing a power supply and distribution system in a shielded machine room as claimed in claim 1, characterized in that: The method for constructing the power supply and distribution error value under each load is: Clustering the same test data sequences under all loads, obtaining probability distribution curves of all the same test data sequences under the same load in each cluster, and recording them as probability distribution curves under each load in each cluster; The difference between the probability distribution curve under each load in each cluster and the probability distribution curve under the same load in other clusters is taken as the power supply and distribution error value under each load.

4. A method for testing a power supply and distribution system in a shielded machine room as claimed in claim 1, characterized in that: The power supply and distribution test weights of the various test data sequences are the averages of the similarities between the test deviation vectors of the various test data sequences and all other test data sequences.

5. A method for testing a power supply and distribution system in a shielded machine room as claimed in claim 1, characterized in that: The power supply and distribution test weights of all test data sequences are formed into a one-dimensional vector, which is recorded as the power supply and distribution test weight vector.

6. A method for testing a power supply and distribution system in a shielded machine room as claimed in claim 1, characterized in that: The testing of the power supply and distribution system in the computer room includes: normalizing all elements in the stability evaluation vector and then calculating the average value, which is recorded as the load test result. When the load test result is within a preset qualified range, the load test of the power supply and distribution system in the computer room is qualified.