A method and system for analyzing the key business carrying status of power communication optical cable

Abstract

The present invention discloses a method and system for analyzing the key business carrying state of power communication optical cables, including: collecting relevant data of key business carried by power communication optical cables, establishing a list of business attributes such as system level, business level and voltage level; quantifying attribute values ​​and calculating the attribute importance index of optical cables, standardizing data matrices, and constructing analysis data sets; determining the effectiveness index of fuzzy clustering algorithms, cyclically executing fuzzy clustering algorithms, obtaining the best number of clusters and fuzzy set overlap coefficients, thereby determining the optimized fuzzy clustering results, and analyzing the key business carrying state of power communication optical cables accordingly. By using the present invention, power communication operation management personnel can intuitively analyze the business carrying state of optical cables, accurately identify the distribution characteristics of key businesses and overloaded sections, which is conducive to taking effective measures to adjust and optimize optical cable businesses, reduce network operation risks, improve business operation quality, and solve the problem that optical cable loads are difficult to quantify and model.

Description

Technical Field

[0001] The present invention relates to the field of power communication technology, and in particular to a method and system for analyzing the key service bearing status of a power communication optical cable. Background Art

[0002] Power communication optical cable is an important carrier medium for power communication services, and the service carrying status is an important feature of power communication optical cable. Effective analysis and accurate identification of the service carrying status of optical cable will directly affect multiple aspects such as power communication network planning, communication service deployment and service quality assurance. The key services of power communication refer to the two services of line relay protection and safety and stability control. The analysis of the key service carrying status of power communication optical cable is conducive to the accurate identification of key service distribution characteristics and overloaded sections by power communication operation management personnel, and timely taking effective measures to adjust services, further reducing service operation risks and improving the overall operation quality of the communication network.

[0003] Currently, there is no method or system for analyzing the key business carrying status of power communication optical cables based on fuzzy clustering technology. Summary of the invention

[0004] The purpose of the present invention is to provide a method and system for analyzing the key business carrying status of power communication optical cables, which can effectively identify the status of optical cables carrying key businesses such as relay protection and safety and stability control, and solve the problem that optical cable loads are difficult to quantify and model.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A method for analyzing the key service bearing status of a power communication optical cable comprises the following steps:

[0007] S1: Collect relevant data on key services carried by power communication optical cables and establish a list of system-level, service-level and voltage-level service attributes;

[0008] S2: Quantify the attribute values ​​and calculate the attribute importance index I of the optical cable, standardize the data matrix, and construct the analysis data set DS;

[0009] S3: Determine the effectiveness index CVI of the fuzzy clustering algorithm, execute the fuzzy clustering algorithm cyclically, and obtain the optimal number of clusters K and the fuzzy set overlap coefficient m; thereby determine the optimized fuzzy clustering result, and analyze the key business carrying status of the power communication optical cable according to the clustering result;

[0010] S4: Based on the analysis of the key business carrying status of the power communication optical cable in S3, the analysis function of the optical cable business carrying status is completed.

[0011] Furthermore, the quantified attribute values ​​and the calculated attribute importance index I of the optical cable in S2 include:

[0012] S201: The service attributes of the power communication optical cable obtained in S1 include: the level of the optical transmission system, the service level, the service type, the bearing mode, the channel mode, and the service voltage level;

[0013] S202: The optical transmission system is divided into four levels: primary network, secondary network, tertiary network and dedicated optical fiber; the business level is divided into three types: headquarters, branch and provincial company; the business type is divided into two types: protection business and safety and stability control business; the bearing mode is divided into two types: dedicated optical fiber and multiplexing; the channel mode is divided into two types: primary and backup; the business voltage level is divided into five types: AC 1000kV, DC ±800kV, DC ±660kV, AC 500kV and AC 220kV;

[0014] S203: Since different attribute values ​​have different attribute importance indexes I, for power communication optical cable i, its j-th attribute importance index I is expressed as:

[0015]

[0016] Where I(i,j) represents the importance index of the jth service attribute of the i-th optical cable; ω j (l) represents the importance weight of the j-th business attribute and the l-th level; N j (i,l) represents the i-th optical cable, the j-th service attribute, and the number of services of the l-th level; N(i) represents the total number of services of the i-th optical cable; L j Indicates the number of levels of the jth service attribute; the number of services with different attributes and different levels on the same optical cable that meet the condition i=1,2,...,n r ,j=1,2,...,n l ;n r is the total number of optical cables; n l The number of optical cable service attributes.

[0017] Furthermore, the calculation method of the attribute importance index I includes:

[0018] The optical transmission system I is:

[0019] I(i,1)=[0.9×N 1 (i,1)+0.7×N 1 (i,2)+0.5×N 1 (i,3)+0.1×N 1 (i,4)] / N(i)

[0020] Business Level I is:

[0021] I(i,2)=[0.9×N 2 (i,1)+0.7×N 2 (i,2)+0.5×N 2 (i,3)] / N(i)

[0022] Business Type I is:

[0023] I(i,3)=[0.9×N 3 (i,1)+0.7×N 3 (i,2)] / N(i)

[0024] Bearing mode I is:

[0025] I(i,4)=[0.9×N 4 (i,1)+0.7×N 4 (i,2)] / N(i)

[0026] Channel mode I is:

[0027] I(i,5)=[0.9×N 5 (i,1)+0.7×N 5 (i,2)] / N(i)

[0028] Business voltage level I is:

[0029] I(i,6)=[0.9×N 6 (i,1)+0.8×N 6 (i,2)+0.8×N 6 (i,3)+0.7×N 6 (i,4)+0.5×N 6 (i,5)] / N(i).

[0030] Furthermore, the data matrix is ​​standardized in S2, and the analysis data set DS is constructed including:

[0031] Combine the attribute importance and the total number of services carried by the optical cable to form a matrix Assume n l =7, front (n l -1) is listed as attribute importance I, that is, a ij =I(i,j); nth l Listed as the total number of optical cable services, i.e. The standardized expression is:

[0032]

[0033] The normalization result of matrix A is D = {d ij}; The fuzzy clustering analysis data set DS can be constructed by selecting corresponding column data in the matrix D according to different analysis purposes. DS is a subset of D.

[0034] Furthermore, the effectiveness index CVI of the fuzzy clustering algorithm is determined in S3, and the fuzzy clustering algorithm is executed cyclically to obtain the optimal number of clusters K and the fuzzy set overlap coefficient m, including:

[0035] PBMF is selected as the effectiveness index CVI of the fuzzy clustering algorithm, and its expression is:

[0036]

[0037] Among them, K is the number of clusters; m is the fuzzy set overlap coefficient; N is the number of rows in the data set DS, N = n r ;ds i is the i-th data row vector; v is the mean vector of the data set, that is, v k is the kth cluster c k The center vector of ds under the condition of m i Belongs to cluster c k The degree of membership;

[0038] Assume that the value range of K is [2,15], and the value range of m is [1.1,5.0]. Within this range, the fuzzy clustering algorithm is executed cyclically, and the PBMF values ​​under different conditions are calculated using the CVI expression to obtain the CVI array. The optimal parameters of fuzzy clustering satisfy the following formula:

[0039] (K,m)=argmaxCVI(K,m)

[0040] That is, when the clustering validity index CVI takes the maximum value, the corresponding K and m are the optimal fuzzy clustering parameters.

[0041] Furthermore, the cyclic execution of the fuzzy clustering algorithm includes:

[0042] Given the number of clusters K and the fuzzy set overlap coefficient m, and the maximum number of iterations of the algorithm it max =100, minimum step distance of objective function ε=10 -5 ; The fuzzy clustering objective function is:

[0043]

[0044] in,

[0045] Using μ i,k Construct the membership matrix U p , that is U p ={μi,k};

[0046] After successive iterations, the objective function f(N,K,m) gradually becomes smaller; when ||U P+1 -U p ||<ε or the number of iterations reaches the maximum value it max When , the iteration stops and the objective function value is considered to be minimum; at this time, the membership matrix and the center matrix This is the fuzzy clustering result.

[0047] Furthermore, the optimization fuzzy clustering results determined in S3 include:

[0048] When the clustering validity index CVI takes the maximum value, the corresponding K and m are the optimal fuzzy clustering parameters. The optimal fuzzy clustering parameters are used to determine the optimized fuzzy clustering results. and

[0049] Furthermore, based on the clustering results, the key business carrying status analysis of power communication optical cables includes:

[0050] Based on the optimized fuzzy clustering results, The maximum value of each column element divides the key business carrying status of the power communication optical cable into K clusters, and the center of the data point of each cluster is Determine; use data visualization technology to intuitively display the key business carrying status of power communication optical cables, and analyze the importance of the transmission system, business level, business voltage level, and the business status of optical cables with different attribute business quantities

[0051] The present invention provides another technical solution: a power communication optical cable key business carrying state analysis system, including a data acquisition module, a data preprocessing module, a fuzzy clustering algorithm module and a data visualization analysis module; the data acquisition module is used to realize the data information of the key business carried by the power communication optical cable, and the data information comes from a plurality of different data sources such as the network management system, the operation and maintenance system, and the integrated network management system of the power communication operation management department;

[0052] The data preprocessing module preprocesses the multi-source heterogeneous data related to the key business carried by the power communication optical cable obtained by the data acquisition module to obtain a standardized fuzzy clustering data set;

[0053] The fuzzy clustering algorithm module is used to cyclically execute the fuzzy clustering algorithm, optimize and determine the optimal number of clusters K and the fuzzy set overlap coefficient m, and under the premise of the optimal number of clusters K and the fuzzy set overlap coefficient m, the algorithm selects the optimized fuzzy clustering analysis result;

[0054] The data visualization analysis module uses the membership matrix U and the cluster center matrix Center obtained by the fuzzy clustering algorithm module, combined with the clustering data set, to analyze the key business bearing status of the power communication optical cable through data visualization technology.

[0055] Compared with the prior art, the present invention has the following beneficial effects:

[0056] The present invention provides a method and system for analyzing the key business bearing state of a power communication optical cable. The method obtains data information of key business carried by the power communication optical cable through a data acquisition module, and establishes a fuzzy clustering analysis data set DS. Then, PBMF is used as a fuzzy clustering validity index CVI, and the number of clusters K and the fuzzy set overlap coefficient m are optimized by cyclically executing a fuzzy clustering algorithm. The fuzzy clustering algorithm is performed using the optimized K and m parameters to obtain an optimized membership matrix U and a cluster center matrix Center. On this basis, the key business bearing state of the power communication optical cable is analyzed through a data visualization analysis module. By using the present invention, power communication operation management personnel can intuitively analyze the cable business bearing state, accurately identify key business distribution characteristics and overloaded sections, and are conducive to taking effective measures to adjust and optimize the cable business, reduce network operation risks, and improve business operation quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 is a flow chart of the analysis method according to an embodiment of the present invention;

[0058] Figure 2 is a flow chart of a fuzzy clustering algorithm according to an embodiment of the present invention;

[0059] Figure 3 FIG. 4 is a block diagram of the analysis system of the present invention. DETAILED DESCRIPTION

[0060] 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.

[0061] An embodiment of the present invention provides a method for analyzing the key service bearing status of a power communication optical cable, comprising the following steps:

[0062] Step 1: Collect relevant data on key services carried by power communication optical cables and establish a list of system-level, service-level and voltage-level service attributes; details are as follows:

[0063] The embodiment of the present invention collects relevant data from the existing network management system and operation and maintenance management information system to reflect the carrying status of key services in the power communication optical cable; the key service related data is defined as service attributes, including: the level of the optical transmission system, the service level, the service type, the carrying mode, the channel mode, the service voltage level, the total number of services and the like.

[0064] Different business attributes have different value ranges, including:

[0065] The optical transmission system is divided into four levels: primary network, secondary network, tertiary network and dedicated optical fiber; the business level is divided into three levels: headquarters, branch and provincial company; the business type is divided into two types: line relay protection and safety and stability control; the bearing mode is divided into two modes: dedicated optical fiber and multiplexing; the channel mode is divided into two modes: main and backup; the business voltage level is divided into five types: AC 1000kV, DC ±800kV, DC ±660kV, AC 500kV and AC 220kV;

[0066] Step 2: Quantify the attribute values ​​and calculate the attribute importance index I of the optical cable, standardize the data matrix, and construct the analysis data set DS; among them, different attribute values ​​have different attribute importance indexes I for business status analysis m It is expressed as:

[0067]

[0068] Among them, ω j (l) represents the importance weight of the j-th business attribute and the l-th level; N j (i,l) represents the i-th optical cable, the j-th service attribute, and the number of services of the l-th level; N(i) represents the total number of services of the i-th optical cable; L j Indicates the number of levels of the jth service attribute; the number of services that meet the condition

[0069] In the above steps, the importance weight value method based on the service attribute "optical transmission system" is as follows:

[0070] If the optical transmission system is a primary network, then ω 1 (1) = 0.9;

[0071] If the optical transmission system is a secondary network, then ω 1 (2) = 0.7;

[0072] If the optical transmission system is a three-level network, then ω 1 (3) = 0.5;

[0073] If dedicated optical fiber, then ω 1 (4) = 0.1;

[0074] Then the I of the service attribute "optical transmission system" is expressed as:

[0075] I(i,1)=[0.9×N 1 (i,1)+0.7×N 1 (i,2)+0.5×N 1 (i,3)+0.1×N 1 (i,4)] / N(i).

[0076] In the above steps, the importance weight value based on the business attribute "business level" is determined as follows:

[0077] If the business is at the headquarters level, then 2 (1) = 0.9;

[0078] If the business is at the division level, then 2 (2) = 0.7;

[0079] If the business is at the provincial company level, then 2 (3) = 0.5;

[0080] Then the I of the business attribute "business level" is expressed as:

[0081] I(i,2)=[0.9×N 2 (i,1)+0.7×N 2 (i,2)+0.5×N 2 (i,3)] / N(i).

[0082] In the above steps, the importance weight value based on the business attribute "business type" is determined as follows:

[0083] If the service is line relay protection, then ω 3 (1) = 0.9;

[0084] If the business is safe and stable control, then ω 3 (2) = 0.7;

[0085] Then the I of the service attribute "service type" is expressed as:

[0086] I(i,3)=[0.9×N 3 (i,1)+0.7×N 3 (i,2)] / N(i).

[0087] In the above steps, the importance weight value based on the service attribute "service bearing mode" is determined as follows:

[0088] If the service is carried by dedicated optical fiber, then 4 (1) = 0.9;

[0089] If the service is multiplexed bearer mode, then 4 (2) = 0.7;

[0090] Then the I of the service attribute "service bearer mode" is expressed as:

[0091] I(i,4)=[0.9×N 4 (i,1)+0.7×N 4 (i,2)] / N(i).

[0092] In the above steps, the importance weight value based on the service attribute "channel mode" is as follows:

[0093] If the service is in primary channel mode, then ω 5 (1) = 0.9;

[0094] If the service is in standby channel mode, then ω 5 (2) = 0.7;

[0095] Then the I of the service attribute "channel mode" is expressed as:

[0096] I(i,5)=[0.9×N 5 (i,1)+0.7×N 5 (i,2)] / N(i).

[0097] In the above steps, the importance weight value based on the service attribute "voltage level" is determined as follows:

[0098] If the service voltage level is 1000kV AC, then 6 (1) = 0.9;

[0099] If the service voltage level is DC ±800kV or DC ±660kV, then ω 6 (2) = ω 6 (3) = 0.8;

[0100] If the service voltage level is 500kV AC, then 6 (4) = 0.7;

[0101] If the service voltage level is AC 220kV, then ω 6 (5) = 0.5;

[0102] Then the I of the service attribute "voltage level" is expressed as:

[0103] I(i,6)=

[0104] [0.9 × N 6 (i,1)+0.8×N 6 (i,2)+0.8×N 6(i,3)+0.7×N 6 (i,4)+0.5×N 6 (i,5)] / N(i)

[0105] Combine the attribute importance I and the total number of services carried by the optical cable by column to form a matrix The present invention provides l =7, front (n l -1) is listed as I, i.e. a ij =I(i,j); nth l Listed as the total number of optical cable services, i.e.

[0106] The matrix A is expressed as follows

[0107]

[0108] After standardization, the result is D = {d ij The standardized fuzzy clustering analysis data set DS can be constructed by selecting corresponding column data in the matrix D according to different analysis objectives.

[0109] Step 3: Determine the effectiveness index CVI of the fuzzy clustering algorithm, execute the fuzzy clustering algorithm cyclically, and obtain the optimal number of clusters K and the fuzzy set overlap coefficient m; thereby determine the optimized fuzzy clustering results, and analyze the key business carrying status of power communication optical cables based on the clustering results; the specific method is as follows:

[0110] The fuzzy clustering algorithm effectiveness index CVI selects the PBMF index, and its expression is:

[0111]

[0112] Where K is the number of clusters; m is the fuzzy set overlap coefficient; N is the number of rows in the analysis data set DS, N = n r ;ds i is the i-th row element vector of the analysis data set DS; v is the mean vector of the data set, that is, v k is the kth cluster c k The center vector of ds under the condition of m i Belongs to cluster c k The degree of membership;

[0113] Assume the maximum number of iterations of the fuzzy clustering algorithm it max =100, minimum step distance of objective function ε=10 -5 ; Fuzzy clustering is performed with the optimized number of clusters K and the fuzzy set overlap coefficient m as the optimal parameters; the fuzzy clustering result is the membership matrix and the center matrix

[0114] Assume that the value range of K is [2,15], and the value range of m is [1.1,5.0]. Within this range, the fuzzy clustering algorithm is executed cyclically, and the PBMF values ​​under different conditions are calculated using the CVI expression to obtain the CVI array. The optimal parameters of fuzzy clustering satisfy the following formula:

[0115] (K,m)=argmaxCVI(K,m)

[0116] When the clustering validity index CVI takes the maximum value, the corresponding K and m are the optimized fuzzy clustering parameters; moreover, the result corresponding to the optimized fuzzy clustering parameters K and m is the optimized clustering result;

[0117] According to the optimized clustering results, the key business carrying status of power communication optical cables is analyzed, including:

[0118] To optimize the clustering results The maximum value of each column element of U is judged; the maximum value of the U element means the maximum membership; the column number corresponding to the maximum value is the optical cable sequence number, and the row number is the cluster number; in this way, the key business carrying status of the power communication optical cable can be divided into K clusters, and the center position of the data point of each cluster is determined by the cluster center matrix Determine; on this basis, using data visualization technology, the key business carrying status of power communication optical cables can be intuitively displayed, thereby realizing the analysis of key business status of optical cables such as the importance of transmission system, business level, business voltage level, and number of services with different attributes.

[0119] Step 4: Based on the analysis of the key business carrying status of power communication optical cables in S3, the analysis function of the optical cable business carrying status is completed, and a key business carrying status analysis system for power communication optical cables is established, which includes: data acquisition module, data preprocessing module, fuzzy clustering algorithm module and data visualization analysis module; each module is used to realize the key business carrying status analysis of power communication optical cables.

[0120] In order to further better explain the present invention, the following embodiments are described in conjunction with the accompanying drawings:

[0121] See also Figure 1 , a method for analyzing the key service bearing status of a power communication optical cable proposed in an embodiment of the present invention comprises the following steps:

[0122] S1.1: Collect relevant data on key services carried by power communication optical cables; establish a service attribute list L including system level, service level, service type, carrying mode, channel mode, voltage level, service quantity, etc.;

[0123] S1.2: Quantify the attribute values ​​in the attribute list L and calculate the importance index I of the optical cable attribute based on the attribute values m ;

[0124] Optical cable services involve a total of seven attributes, including transmission system level, service level, service type, bearing mode, channel mode, voltage level and service quantity. Among them, the first six attributes are important. For example, the transmission system is divided into four levels: primary, secondary, tertiary and dedicated optical fiber; the business level is divided into three levels: headquarters, branch and provincial company; the service type is divided into two types: line relay protection and safety and stability control; the bearing mode is divided into two types: dedicated optical fiber and multiplexing; the channel mode is divided into two types: main and backup; the voltage level is divided into five types: AC 1000kV, DC ±800kV, DC ±660kV, AC 500kV and AC 220kV.

[0125] Different levels and categories of optical cable attributes have different importance indexes I, which are determined by the importance weight and the proportion of business quantity.

[0126] The importance index I of the optical cable attribute and the total number of optical cable services together constitute the data matrix A. The data matrix A is standardized to obtain the matrix D.

[0127] According to the different purposes of key service bearer status analysis, fuzzy cluster analysis data set DS can be selectively constructed, for example, cluster analysis of transmission system level and service quantity; cluster analysis of service level and service quantity; cluster analysis of service voltage level and service quantity, etc.

[0128] S1.3: Under given DS conditions, determine the effectiveness index CVI (Clustering Validity Index) of the fuzzy clustering algorithm, execute the fuzzy clustering algorithm in a loop, and optimize the optimal number of clusters k and the fuzzy set overlap coefficient m; the fuzzy clustering result corresponding to the optimized parameters is the optimization result; based on the optimized clustering result, analyze the key business carrying status of the power communication optical cable.

[0129] See also Figure 2 , the process of the fuzzy clustering algorithm in the embodiment of the present invention is as follows:

[0130] S2.1: With the fuzzy clustering data set DS, the maximum number of iterations and the iteration step as initial parameters, the algorithm selects PBMF as the clustering validity index CVI, selects 14 sample points at equal intervals in the interval [2, 15] of the number of clusters K, and selects 40 sample points at equal intervals in the interval [1.1, 5.0] of the fuzzy set overlap coefficient m, and obtains the K sample point vectors V respectively. K = {2,3,...,15} and m sample point vector V m={1.1,1.2,...,5.0}, the two types of vector elements are combined to obtain 14×40=560 groups of sample data.

[0131] S2.2: The fuzzy clustering algorithm is iteratively executed to determine whether the accuracy requirement is met; if the result meets the accuracy requirement, the iteration is terminated; otherwise, it is determined whether the maximum number of iterations has been reached; if the number of clustering times has reached the maximum number, the iteration is terminated; otherwise, the fuzzy clustering iterative operation is continued.

[0132] S2.3: After 560 cycles of fuzzy clustering operations, the algorithm obtains 560 CVI values; the largest set of data corresponding to the CVI value is taken as the selected optimal clustering number K and fuzzy set overlap coefficient m; the fuzzy clustering result corresponding to the optimized K and m values ​​is the optimization result.

[0133] Among them, the optimization results of the fuzzy clustering algorithm are the membership matrix U and the cluster center matrix Center. According to the optimized U and Center, the algorithm analyzes the status of optical cable carrying services through data visualization processing: Assume that the total number of power communication optical cables analyzed is n r =732, fuzzy clustering analysis is performed on the "transmission system level" attribute, 14 sample points are selected at equal intervals in the K interval [2, 15], and 40 sample points are selected at equal intervals in the m interval [1.1, 5.0], resulting in a total of 560 sets of K and m sample data. The number of fuzzy clustering algorithm execution cycles is 560, and the maximum number of iterations of each fuzzy clustering is it max =100, minimum step distance of objective function ε=10 -5 , 560 fuzzy clusterings were performed; PBMF (Pakhira, Bandy & Maulik-indexfor Fuzzy C-means Clustering) was selected as the clustering validity index CVI, and 560 CVI values ​​were obtained. The K and m values ​​corresponding to the maximum CVI value were K=6 and m=1.2 respectively, and the membership matrix U and the cluster center matrix Center corresponding to the optimal number of clusters and the optimal fuzzy set overlap coefficient were the optimized fuzzy clustering results.

[0134] Through data visualization technology, combined with the business load of optical cable joints, the analysis results of the key business load status of power communication optical cables based on fuzzy clustering are as follows:

[0135] Cluster 1 (C1): contains 40 optical cables, characterized by "transmission system level" I m The value is medium and the number of businesses is medium to small.

[0136] Cluster 2 (C2): contains 453 optical cables, characterized by "transmission system level" I m The value is low and the number of businesses is small.

[0137] Cluster 3 (C3): contains 9 optical cables, characterized by "transmission system level" I m The lower the value, the more business there is.

[0138] Cluster 4 (C4): contains 158 optical cables, characterized by "transmission system level" I m The value is low and the number of businesses is medium to small.

[0139] Cluster 5 (C5): contains 21 optical cables, characterized by "transmission system level" I m The value is high and the number of businesses is small.

[0140] Cluster 6 (C6): contains 51 cables, characterized by "transmission system level" I m The value is low and the number of businesses is medium.

[0141] The above analysis conclusions can serve as an important basis for power communication operation and maintenance personnel to accurately identify the distribution characteristics of key services and overloaded sections, and take effective measures to adjust and optimize optical cable services to reduce network operation risks.

[0142] See also Figure 3 In the above embodiment, the present invention also provides an analysis system for the key service bearing status of a power communication optical cable, which includes the following contents:

[0143] (1) Data acquisition module, which realizes the data information carried by the key business of power communication optical cables. The data information comes from multiple different data sources such as the network management system of the power communication operation management department, the operation and maintenance system, and the integrated network management system;

[0144] (2) A data preprocessing module, which preprocesses the multi-source heterogeneous data acquired from data collection related to the key business of power communication optical cables to obtain a standardized fuzzy clustering data set;

[0145] (3) Fuzzy clustering algorithm module, which executes the fuzzy clustering algorithm cyclically to optimize and determine the optimal number of clusters K and the fuzzy set overlap coefficient m. Under the premise of the optimal number of clusters K and the fuzzy set overlap coefficient m, the algorithm selects the optimal fuzzy clustering analysis results;

[0146] (4) Data visualization analysis module: This module uses the membership matrix U and cluster center matrix Center obtained by the fuzzy clustering algorithm, combined with the clustering data set, to analyze the key business carrying status of power communication optical cables through data visualization technology.

[0147] Working principle: The present invention provides a method and system for analyzing the key business carrying status of power communication optical cables. The data information of the key business carried by the power communication optical cables is obtained through a data acquisition module, the data information is quantified and processed, the attribute importance index is calculated, the data matrix is ​​standardized, and a fuzzy clustering analysis data set DS is established; then, PBMF is used as the fuzzy clustering effectiveness index CVI, the fuzzy clustering algorithm is cyclically executed, and the number of clusters K and the fuzzy set overlap coefficient m are optimized; the fuzzy clustering algorithm is performed using the optimized K and m parameters to obtain the optimized membership matrix U and cluster center matrix Center; on this basis, the key business carrying status of the power communication optical cable is analyzed through the data visualization analysis module. The power communication operation management personnel can use the present invention to intuitively analyze the cable business carrying status, accurately identify the key business distribution characteristics and overloaded sections, which is conducive to taking effective measures to adjust and optimize the cable business, reduce network operation risks, and improve business operation quality.

[0148] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A method for analyzing the key service bearing status of a power communication optical cable, characterized in that: The following steps are involved: S1: Collect relevant data on key services carried by power communication optical cables and establish a list of system-level, service-level and voltage-level service attributes; S2: Quantify the attribute values ​​and calculate the attribute importance index of the optical cable I , standardize the data matrix and construct the analysis data set DS ; S3: Determine the effectiveness index CVI of the fuzzy clustering algorithm, execute the fuzzy clustering algorithm cyclically, and obtain the optimal number of clusters K and the fuzzy set overlap coefficient m; thereby determine the optimized fuzzy clustering result, and analyze the key business carrying status of the power communication optical cable according to the clustering result; wherein, determine the effectiveness index CVI of the fuzzy clustering algorithm, execute the fuzzy clustering algorithm cyclically, and obtain the optimal number of clusters K and the fuzzy set overlap coefficient m including: PBMF is selected as the effectiveness index CVI of the fuzzy clustering algorithm, and its expression is: ； in, is the number of clusters; is the fuzzy set overlap coefficient; is the number of rows in the data set DS, ; For the i data row vectors; is the mean vector of the data set, that is ; For the Clusters The center vector of for under conditions Belongs to cluster The degree of membership; Assume that the value range of K is [2, 15] and the value range of m is [1.1, 5.0]. Within this range, the fuzzy clustering algorithm is executed cyclically, and the PBMF values ​​under different conditions are calculated using the CVI expression to obtain the CVI array. The optimal parameters of fuzzy clustering satisfy the following formula: ； That is, when the clustering validity index CVI takes the maximum value, the corresponding K and m are the optimal fuzzy clustering parameters; S4: Based on the analysis of the key business carrying status of the power communication optical cable in S3, the analysis function of the optical cable business carrying status is completed.

2. A method for analyzing the key service bearing status of a power communication optical cable according to claim 1, characterized in that: Quantify the attribute values ​​in S2 and calculate the attribute importance index of the optical cable I include: S201: The service attributes of the power communication optical cable obtained in S1 include: the level of the optical transmission system, the service level, the service type, the bearing mode, the channel mode, and the service voltage level; S202: The optical transmission system is divided into four levels: primary network, secondary network, tertiary network and dedicated optical fiber; the business level is divided into three types: headquarters, branch and provincial company; the business type is divided into two types: protection business and safety and stability control business; the bearing mode is divided into two types: dedicated optical fiber and multiplexing; the channel mode is divided into two types: primary and backup; the business voltage level is divided into five types: AC 1000kV, DC ±800kV, DC ±660kV, AC 500kV and AC 220kV; S203: Since different attribute values ​​have different attribute importance indexes I, for power communication optical cables i , its j The attribute importance index I is expressed as: ； in, Indicates i Optical cable No. j Importance index of each business attribute; Indicates j Business attributes l The importance weight of the level; Indicates i Optical cable, j business attributes, l Number of businesses at the level; Indicates i Total number of services of optical cables; Indicates j The number of service attributes and grades of the same optical cable; the number of services with different attributes and grades that meet the conditions ; , ; is the total number of optical cables; Number of optical cable service attributes.

3. A method for analyzing the key service bearing status of a power communication optical cable according to claim 2, characterized in that: The calculation method of attribute importance index I includes: The optical transmission system I is: ； Business Level I is: ； Business Type I is: ； Bearing mode I is: ； Channel mode I is: ； Business voltage level I is: 。 4. A method for analyzing the key service bearing status of a power communication optical cable according to claim 1, characterized in that: In S2, the data matrix is ​​standardized and the analysis data set is constructed DS include: Combine the attribute importance and the total number of services carried by the optical cable to form a matrix ,set up =7, before ( -1) is listed as attribute importance I, that is ;No. Listed as the total number of optical cable services, i.e. ; The standardized expression is: ； matrix A The standardized processing result is ; The fuzzy clustering analysis data set DS is constructed by selecting corresponding column data in the matrix D according to different analysis purposes. DS is a subset of D.

5. A method for analyzing the key service bearing status of a power communication optical cable according to claim 1, characterized in that: The loop execution of the fuzzy clustering algorithm includes: Given the number of clusters K and the fuzzy set overlap coefficient m, and the maximum number of iterations of the algorithm =100, minimum step distance of objective function ; The fuzzy clustering objective function is: ； in, , ; use Constructing the membership matrix ,Right now ={ }; After successive iterations, the objective function gradually becomes smaller; when Or the number of iterations reaches the maximum value When , the iteration stops and the objective function value is considered to be minimum; at this time, the membership matrix and the center matrix This is the fuzzy clustering result.

6. A method for analyzing the key service bearing status of a power communication optical cable according to claim 5, characterized in that: The optimized fuzzy clustering results determined in S3 include: When the clustering validity index CVI takes the maximum value, the corresponding K and m are the optimal fuzzy clustering parameters. The optimal fuzzy clustering parameters are used to determine the optimized fuzzy clustering results. and .

7. A method for analyzing the key service bearing status of a power communication optical cable according to claim 6, characterized in that: According to the clustering results, the key business carrying status analysis of power communication optical cables includes: Based on the optimized fuzzy clustering results, The maximum value of each column element divides the key business carrying status of the power communication optical cable into K clusters, and the center of the data point of each cluster is Determine; use data visualization technology to intuitively display the key business carrying status of power communication optical cables, and analyze the optical cable business status of the importance of the transmission system, business level, business voltage level, and the number of services with different attributes.

8. A power communication optical cable key business bearing status analysis system, characterized in that: It includes a data acquisition module, a data preprocessing module, a fuzzy clustering algorithm module and a data visualization analysis module; the data acquisition module is used to realize the data information carried by the key business of the power communication optical cable, and the data information comes from multiple different data sources such as the network management system, operation and maintenance system, and integrated network management system of the power communication operation management department; The data preprocessing module preprocesses the multi-source heterogeneous data related to the key business carried by the power communication optical cable obtained by the data acquisition module to obtain a standardized fuzzy clustering data set; The fuzzy clustering algorithm module is used to cyclically execute the fuzzy clustering algorithm, optimize and determine the optimal number of clusters K and the fuzzy set overlap coefficient m, and under the premise of the optimal number of clusters K and the fuzzy set overlap coefficient m, the algorithm selects and optimizes the fuzzy clustering analysis results; wherein, determining the effectiveness index CVI of the fuzzy clustering algorithm, cyclically executing the fuzzy clustering algorithm, and obtaining the optimal number of clusters K and the fuzzy set overlap coefficient m includes: PBMF is selected as the effectiveness index CVI of the fuzzy clustering algorithm, and its expression is: ； in, is the number of clusters; is the fuzzy set overlap coefficient; is the number of rows in the data set DS, ; For the i data row vectors; is the mean vector of the data set, that is ; For the Clusters The center vector of for under conditions Belongs to cluster The degree of membership; Assume that the value range of K is [2, 15] and the value range of m is [1.1, 5.0]. Within this range, the fuzzy clustering algorithm is executed cyclically, and the PBMF values ​​under different conditions are calculated using the CVI expression to obtain the CVI array. The optimal parameters of fuzzy clustering satisfy the following formula: ； That is, when the clustering validity index CVI takes the maximum value, the corresponding K and m are the optimal fuzzy clustering parameters; The data visualization analysis module uses the membership matrix U and cluster center matrix obtained by the fuzzy clustering algorithm module ,Combined with clustering data sets, data visualization technology is used to analyze the key business carrying status of power communication optical cables.

Images