Network topology restoration method, device, equipment and readable storage medium

Abstract

The present invention provides a network topology restoration method, apparatus, device, and readable storage medium. The method comprises: calculating a first similarity and a second similarity between two ONUs in a pairwise ONU combination under the same PON port in an unknown network topology and each ONU in an ONU set; calculating a third similarity between the two ONUs in the pairwise ONU combination; wherein the pairwise ONU combination is removed from all ONUs connected to the PON port, and the ONU set is composed of the remaining ONUs; determining whether the two ONUs belong to the same optical splitter based on the first similarity, the second similarity, and the third similarity; and obtaining the optical splitter affiliation relationship of all pairwise ONU combinations in a similar manner; and restoring the unknown network topology based on the optical splitter affiliation relationship of all pairwise ONU combinations. The present invention achieves automatic restoration of the topological structure of a PON network.

Description

Technical Field

[0001] The present invention relates to the field of network operation and maintenance technology, and in particular to a network topology restoration method, apparatus, device, and readable storage medium. Background Art

[0002] In a PON (passive optical network) network, the optical splitter is a passive device, and its operating parameters cannot be obtained. In addition, in the operator's existing asset management system, the optical splitter information above the ONU is incomplete, making it impossible to restore the PON network topology. Summary of the Invention

[0003] The main purpose of the present invention is to provide a network topology restoration method, device, equipment and readable storage medium, aiming to solve the technical problem in the prior art that the topology structure of the PON network cannot be restored.

[0004] In a first aspect, the present invention provides a network topology restoration method, the network topology restoration method comprising:

[0005] Select two ONU combinations that have not been selected before under the same PON port in an unknown network topology;

[0006] Calculating a first similarity between an ONU in the pairwise ONU combination and each ONU in the ONU set, calculating a second similarity between another ONU in the pairwise ONU combination and each ONU in the ONU set, and calculating a third similarity between the two ONUs in the pairwise ONU combination, wherein the pairwise ONU combination is removed from all ONUs connected to the PON port, and the remaining ONUs are used to form the ONU set;

[0007] Calculate the probability that any two ONU combinations belong to the same optical splitter based on the first similarity, the second similarity, and the third similarity;

[0008] If the probability that any two ONU combinations belong to the same optical splitter is greater than a preset threshold, the optical splitter affiliation relationship of the two ONU combinations is determined to be a first affiliation relationship; if the probability that any two ONU combinations belong to the same optical splitter is not greater than the preset threshold, the optical splitter affiliation relationship of the two ONU combinations is determined to be a second affiliation relationship;

[0009] If there is an unselected pairwise ONU combination, returning to the step of selecting an unselected pairwise ONU combination under the same PON port in the unknown network topology;

[0010] The unknown network topology is restored according to the optical splitter ownership relationship of all pairwise ONU combinations.

[0011] Optionally, after the step of selecting unselected pairs of ONU combinations under the same PON port in the unknown network topology, the method further includes:

[0012] Matching the first characteristic data of one ONU in the two-by-two ONU combination, the second characteristic data of the other ONU in the two-by-two ONU combination, and the third characteristic data of the PON port with the topology rules in the rule knowledge base;

[0013] If the match is successful, the splitter ownership relationship of the two ONU combinations is determined according to the matched topology rule. If there is an unselected two ONU combination, the process returns to the step of selecting the unselected two ONU combinations under the same PON port in the unknown network topology;

[0014] If the matching fails, the steps of calculating the first similarity between one ONU in the pairwise ONU combination and each ONU in the ONU set, calculating the second similarity between another ONU in the pairwise ONU combination and each ONU in the ONU set, and calculating the third similarity between the two ONUs in the pairwise ONU combination are performed.

[0015] Optionally, before the step of selecting the unselected pairwise ONU combinations under the same PON port in the unknown network topology, the method further includes:

[0016] The characteristic data of a PON port in a known network topology, the characteristic data of two ONUs under the PON port, and the splitter ownership relationship of the two ONUs are used as a topology rule. If the two ONUs belong to the same splitter, the splitter ownership relationship is the first ownership relationship; if the two ONUs belong to different splitters, the splitter ownership relationship is the second ownership relationship.

[0017] The rule knowledge base is composed of a plurality of topological rules.

[0018] Optionally, after the step of determining that the optical splitter affiliation relationship of the two ONU combinations is the first affiliation relationship if the probability that the two ONU combinations belong to the same optical splitter is greater than a preset threshold, the method further includes:

[0019] The first characteristic data, the second characteristic data, the third characteristic data and the first attribution relationship are added to a rule knowledge base as a new topology rule.

[0020] Optionally, after the step of adding the first characteristic data, the second characteristic data, the third characteristic data, and the first attribution relationship as a new topology rule to a rule knowledge base, the method further includes:

[0021] When it is calculated that the new probability that any two ONU combinations belong to the same optical splitter is not greater than a preset threshold, the new topology rule is deleted from the rule knowledge base.

[0022] Optionally, the step of calculating a first similarity between an ONU in the pairwise ONU combination and each ONU in the ONU set, and calculating a second similarity between another ONU in the pairwise ONU combination and each ONU in the ONU set includes:

[0023] The first similarity between an ONU in the pairwise ONU combination and each ONU in the ONU set is calculated according to the first calculation formula, and the second similarity between another ONU in the pairwise ONU combination and each ONU in the ONU set is calculated according to the second calculation formula. The first calculation formula is:

[0024]

[0025] The second calculation formula is:

[0026]

[0027] Among them, a i is the first similarity between an ONU and the i-th ONU in the ONU set, i ranges from 1 to n, n is the number of ONUs in the ONU set, p is the order, x ak is the characteristic data of the kth dimension of an ONU, x ik is the feature data of the kth dimension of the i-th ONU in the ONU set, m is the number of dimensions of the feature data, a′ i is the second similarity between another ONU and the i-th ONU in the ONU set, x bk is the feature data of the kth dimension of another ONU.

[0028] Optionally, the step of calculating the probability that any two ONU combinations belong to the same optical splitter according to the first similarity, the second similarity, and the third similarity includes:

[0029] Substituting the first similarity and the second similarity into the third calculation formula to obtain the overall similarity of any two ONU combinations, the third calculation formula is:

[0030]

[0031] Among them, S2 is the overall similarity of the two ONU combinations, min(a i , a′ i ) means from a i and a′ i Select the minimum value, max(a i , a′ i ) means from a i and a′ i Select the maximum value among them; if a i and a′ iare all zero, then we have

[0032] Multiplying the overall similarity by the third similarity, and taking the product as the probability that any two ONU combinations belong to the same optical splitter;

[0033] Alternatively, the overall similarity and the third similarity are weightedly summed, and the result of the weighted sum is used as the probability that any two ONU combinations belong to the same optical splitter.

[0034] In a second aspect, the present invention further provides a network topology restoration device, the network topology restoration device comprising:

[0035] A selection module is used to select two ONU combinations that have not been selected under the same PON port in an unknown network topology;

[0036] A first calculation module is configured to calculate a first similarity between an ONU in a pairwise ONU combination and each ONU in an ONU set, calculate a second similarity between another ONU in the pairwise ONU combination and each ONU in the ONU set, and calculate a third similarity between two ONUs in the pairwise ONU combination, wherein the pairwise ONU combination is removed from all ONUs connected to the PON port, and the remaining ONUs are used to form the ONU set;

[0037] A second calculation module is configured to calculate the probability that any two ONU combinations belong to the same optical splitter based on the first similarity, the second similarity, and the third similarity;

[0038] An ownership relationship determination module is configured to determine that the ownership relationship of the optical splitters of the two ONU combinations is a first ownership relationship if the probability that the two ONU combinations belong to the same optical splitter is greater than a preset threshold; and to determine that the ownership relationship of the optical splitters of the two ONU combinations is a second ownership relationship if the probability that the two ONU combinations belong to the same optical splitter is not greater than the preset threshold;

[0039] A loop module is configured to return to the step of selecting unselected pairwise ONU combinations under the same PON port in the unknown network topology if there are any unselected pairwise ONU combinations;

[0040] The restoration module is used to restore the unknown network topology according to the optical splitter ownership relationship of all two ONU combinations.

[0041] In a third aspect, the present invention also provides a network topology restoration device, which includes a processor, a memory, and a network topology restoration program stored on the memory and executable by the processor, wherein when the network topology restoration program is executed by the processor, the steps of the network topology restoration method described above are implemented.

[0042] In a fourth aspect, the present invention further provides a readable storage medium, on which a network topology restoration program is stored, wherein when the network topology restoration program is executed by a processor, the steps of the network topology restoration method described above are implemented.

[0043] In the present invention, a pairwise ONU combination that has not been selected under the same PON port in an unknown network topology is selected; a first similarity between an ONU in the pairwise ONU combination and each ONU in the ONU set is calculated, a second similarity between another ONU in the pairwise ONU combination and each ONU in the ONU set is calculated, and a third similarity between the two ONUs in the pairwise ONU combination is calculated, wherein the pairwise ONU combination is removed from all ONUs connected to the PON port, and the remaining ONUs are used to form the ONU set; and a pairwise ONU combination is obtained based on the first similarity, the second similarity, and the third similarity. The probability of belonging to the same optical splitter; if the probability of the two ONU combinations belonging to the same optical splitter is greater than a preset threshold, the optical splitter belonging relationship of the two ONU combinations is determined to be a first belonging relationship; if the probability of the two ONU combinations belonging to the same optical splitter is not greater than the preset threshold, the optical splitter belonging relationship of the two ONU combinations is determined to be a second belonging relationship; if there are unselected two ONU combinations, the step of selecting unselected two ONU combinations under the same PON port in the unknown network topology is returned to; the unknown network topology is restored according to the optical splitter belonging relationships of all two ONU combinations. Through the present invention, the topological structure of the PON network is automatically restored, and when determining whether two ONUs belong to the same optical splitter, it relies on the individual similarity of the two ONUs and the overall similarity of the two ONUs and the ONU set, ensuring the high accuracy of the restored network topology. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 This is a flow chart of a first embodiment of a network topology restoration method according to the present invention;

[0045] Figure 2 This is a flow chart of a second embodiment of the network topology restoration method of the present invention;

[0046] Figure 3 This is a schematic diagram of the functional modules of an embodiment of a network topology restoration device of the present invention;

[0047] Figure 4 The figure is a schematic diagram of the hardware structure of the network topology restoration device involved in the embodiment of the present invention.

[0048] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0049] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0050] In a first aspect, an embodiment of the present invention provides a method for restoring a network topology.

[0051] In one embodiment, referring to Figure 1 , Figure 1 FIG. 1 is a flow chart of the first embodiment of the network topology restoration method of the present invention. Figure 1 As shown, the network topology restoration method includes:

[0052] Step S10, selecting two ONU combinations that have not been selected under the same PON port in the unknown network topology;

[0053] In this embodiment, it is assumed that the ONUs connected to the same PON port in the unknown network topology include ONU1 to ONU5. Then:

[0054] ONU1 and ONU2 are combined into two ONUs, ONU1 and ONU3 are combined into two ONUs, ONU1 and ONU4 are combined into two ONUs, ONU1 and ONU5 are combined into two ONUs, ONU2 and ONU3 are combined into two ONUs, ONU2 and ONU4 are combined into two ONUs, ONU2 and ONU5 are combined into two ONUs, ONU3 and ONU4 are combined into two ONUs, ONU3 and ONU5 are combined into two ONUs, and ONU4 and ONU5 are combined into two ONUs.

[0055] Step S20, calculating a first similarity between an ONU in the pairwise ONU combination and each ONU in the ONU set, calculating a second similarity between another ONU in the pairwise ONU combination and each ONU in the ONU set, and calculating a third similarity between the two ONUs in the pairwise ONU combination, wherein the pairwise ONU combination is removed from all ONUs connected to the PON port, and the remaining ONUs are used to form the ONU set;

[0056] In this embodiment, taking a pairwise ONU combination including ONU1 and ONU2 as an example, the first similarity between ONU1 and ONU3, ONU4 and ONU5 is calculated respectively, the second similarity between ONU2 and ONU3, ONU4 and ONU5 is calculated respectively, and the third similarity between ONU1 and ONU2 is calculated.

[0057] The similarity is calculated based on ONU feature data, including ONU received optical power, ONU jittered received optical power, ONU transmitted optical power, ONU downstream optical attenuation, ONU upstream optical attenuation, ONU ranging value, and ONU power / fiber break alarms. You can select one, multiple, or all of the feature data when calculating the similarity.

[0058] Step S30, calculating the probability that any two ONU combinations belong to the same optical splitter based on the first similarity, the second similarity, and the third similarity;

[0059] In this embodiment, a preset operation is performed on the first similarity, the second similarity, and the third similarity to obtain the probability that any two ONU combinations belong to the same optical splitter.

[0060] It should be noted that the first and second similarities represent the overall similarity of the two ONUs in a pairwise ONU combination relative to all ONUs connected to the same PON port, while the third similarity represents the individual similarity of the two ONUs. In other words, the probability is determined based on a combination of overall and individual similarities, eliminating the error caused by relying solely on individual similarities. This makes the calculated probability more consistent with objective facts, thereby ensuring the accuracy of the restored network topology.

[0061] Step S40: If the probability that any two ONU combinations belong to the same optical splitter is greater than a preset threshold, the optical splitter affiliation relationship of the any two ONU combinations is determined to be a first affiliation relationship; if the probability that any two ONU combinations belong to the same optical splitter is not greater than the preset threshold, the optical splitter affiliation relationship of the any two ONU combinations is determined to be a second affiliation relationship;

[0062] In this embodiment, the preset threshold is set according to actual needs and is not limited here. If the probability that two ONU combinations belong to the same optical splitter is greater than the preset threshold, the optical splitter affiliation relationship of the two ONU combinations is determined to be a first affiliation relationship, that is, the two ONU combinations are determined to belong to the same optical splitter; if the probability that two ONU combinations belong to the same optical splitter is not greater than the preset threshold, the optical splitter affiliation relationship of the two ONU combinations is determined to be a second affiliation relationship, that is, the two ONU combinations are determined to belong to different optical splitters.

[0063] If there are any two ONU combinations that have not been selected, return to step S10;

[0064] In this embodiment, if there are any unselected pairwise ONU combinations, the process returns to step S10, i.e., a new pairwise ONU combination is selected, and the optical splitter affiliation relationship of the new pairwise ONU combination is obtained according to steps S20 to S40. Similarly, if there are no unselected pairwise ONU combinations, the optical splitter affiliation relationships of all pairwise ONU combinations are obtained.

[0065] Step S50: restoring the unknown network topology according to the optical splitter ownership relationship of all two ONU combinations.

[0066] In this embodiment, logical deduction is performed based on the splitter ownership relationship of all two-by-two ONU combinations to determine the number of optical splitters and the connection relationship between the optical splitters and the ONUs, that is, to obtain the network topology.

[0067] Specifically, the pairwise ONU combinations with the first splitter affiliation and their probabilities are put into the first set as elements, and the pairwise ONU combinations with the second splitter affiliation and their probabilities are put into the second set as elements.

[0068] Each element is extracted from the first set in descending order of probability. If both ONUs corresponding to the extracted element do not have a tag, the two ONUs are assigned the same new tag. If only one of the two ONUs has a tag, the other ONU is assigned the same tag using the existing tag. If the two ONUs have different tags, the tags of the two ONUs are unified to one of the two different tags.

[0069] After processing the elements of the first set in the above manner, if all ONUs are labeled, the number of labels is the number of splitters, and ONUs with the same label are connected to the same splitter, thus obtaining the network topology.

[0070] For example, a total of ONU1 to ONU4 are involved, but the first set only involves ONU1, ONU2, and ONU3. After processing the elements of the first set, ONU4 still exists without a mark.

[0071] If there is still an ONU without a tag, then extract an element containing the ONU without a tag from the second set. If the two ONUs corresponding to the extracted element are both tagged and the tags are different, and the number of determined tags is greater than a preset value and the similarity corresponding to the extracted element is greater than a first threshold, then unify the tags of the two ONUs into any one of the two different tags;

[0072] If only one of the two ONUs corresponding to the extracted elements has a tag and the similarity corresponding to the extracted elements is greater than the second threshold, the existing tag is used to assign a tag to the other ONU;

[0073] If only one of the two ONUs corresponding to the extracted elements has a tag and the similarity corresponding to the extracted elements is not greater than the second threshold, a new tag is assigned to the other ONU;

[0074] If both ONUs corresponding to the extracted elements have no tags and the similarity corresponding to the extracted elements is greater than the third threshold, the same new tag is assigned to the two ONUs;

[0075] If both of the two ONUs corresponding to the extracted elements have no tags and the similarity corresponding to the extracted elements is not greater than a third threshold, different new tags are assigned to the two ONUs.

[0076] At this point, all ONUs are labeled. The number of labels is the number of splitters. ONUs with the same label are connected to the same splitter, and the network topology can be obtained.

[0077] The first threshold value, the second threshold value, and the third threshold value are all smaller than a preset threshold value.

[0078] In this embodiment, a pairwise ONU combination that has not been selected under the same PON port in an unknown network topology is selected; a first similarity between an ONU in the pairwise ONU combination and each ONU in the ONU set is calculated, a second similarity between another ONU in the pairwise ONU combination and each ONU in the ONU set is calculated, and a third similarity between the two ONUs in the pairwise ONU combination is calculated, wherein the pairwise ONU combination is removed from all ONUs connected to the PON port, and the remaining ONUs are used to form the ONU set; the pairwise ONU combination is obtained based on the first similarity, the second similarity, and the third similarity. The probability of belonging to the same optical splitter; if the probability of the two ONU combinations belonging to the same optical splitter is greater than the preset threshold, the optical splitter belonging relationship of the two ONU combinations is determined to be the first belonging relationship; if the probability of the two ONU combinations belonging to the same optical splitter is not greater than the preset threshold, the optical splitter belonging relationship of the two ONU combinations is determined to be the second belonging relationship; if there are two ONU combinations that have not been selected, return to the step of selecting the two ONU combinations that have not been selected under the same PON port in the unknown network topology; restore the unknown network topology according to the optical splitter belonging relationships of all two ONU combinations. Through this embodiment, the topological structure of the PON network is automatically restored, and when determining whether two ONUs belong to the same optical splitter, it relies on the individual similarity of the two ONUs and the overall similarity of the two ONUs and the ONU set, ensuring the high accuracy of the restored network topology.

[0079] Furthermore, in one embodiment, referring to Figure 2 , Figure 2 FIG. 1 is a flow chart of the second embodiment of the network topology restoration method of the present invention. Figure 2 As shown, after step S10, the following steps are further included:

[0080] Step S60, matching the first characteristic data of one ONU in the two-by-two ONU combination, the second characteristic data of the other ONU in the two-by-two ONU combination, and the third characteristic data of the PON port with the topology rules in the rule knowledge base;

[0081] Step S70: If the match is successful, the splitter ownership relationship of the two ONU combinations is determined according to the matched topology rule. If there are any two ONU combinations that have not been selected, the process returns to the step of selecting two ONU combinations that have not been selected under the same PON port in the unknown network topology.

[0082] If the matching fails, step S20 is executed.

[0083] Furthermore, in one embodiment, before step S10, the method further includes:

[0084] The characteristic data of a PON port in a known network topology, the characteristic data of two ONUs under the PON port, and the splitter ownership relationship of the two ONUs are used as a topology rule. If the two ONUs belong to the same splitter, the splitter ownership relationship is the first ownership relationship; if the two ONUs belong to different splitters, the splitter ownership relationship is the second ownership relationship.

[0085] The rule knowledge base is composed of a plurality of topological rules.

[0086] In this embodiment, characteristic data of a PON port in a known network topology is collected, such as the PON port transmit optical power (g1) and the PON port receive optical power (g2); characteristic data of the ONU combination of two pairs belonging to the PON port is collected, such as ONU1 receive optical power (g3), ONU1 jitter receive optical power (g4), ONU1 transmit optical power (g5), ONU1 downstream optical attenuation (g6), ONU1 upstream optical attenuation (g7), ONU1 ranging value (g8), ONU1 power off / fiber break alarm (g9), ONU2 identification information, ONU 2 received optical power (g10), ONU2 jitter received optical power (g11), ONU2 transmitted optical power (g12), ONU2 downstream optical attenuation (g13), ONU2 upstream optical attenuation (g14), ONU2 ranging value (g15), ONU2 power off / fiber break alarm (g16) and other data are then pre-processed as feature vector X. It should be noted that when selecting features, one, multiple, or all features can be selected to construct a feature vector. For example, feature vector X can be constructed using all feature data or only from power off / fiber break alarms. In one embodiment, there are:

[0087] X={g1,g2,g3,g4,g5,g6,g7,g8,g9,g10,g11,g12,g13,g14,g15,g16}.

[0088] If two ONUs are connected to the same optical splitter, the label Y is 1 (ie, it represents a first affiliation relationship); if two ONUs are connected to different optical splitters, the label Y is 0 (ie, it represents a second affiliation relationship).

[0089] Taking X and Y as a rule, a rule knowledge base can be formed with multiple topological rules.

[0090] After obtaining the first, second, and third feature data, an X' is generated that matches the dimension of X. X' is then matched against each X in the rule knowledge base. Specifically, the similarity between X' and each X in the rule knowledge base is calculated. Pearson correlation coefficient, Gaussian distance, cosine similarity, and other metrics can be used. If at least one X' has a similarity greater than a preset value, the match is considered successful. The rule corresponding to the X with the greatest similarity to X' is used as the matched rule, and the label corresponding to the matched rule is used as the splitter affiliation for the current pairwise ONU combination. If no X' has a similarity greater than the preset value, the match fails.

[0091] Furthermore, in one embodiment, after the step of determining that the optical splitter affiliation of the two ONU combinations is the first affiliation if the probability that the two ONU combinations belong to the same optical splitter is greater than a preset threshold, the method further includes:

[0092] The first characteristic data, the second characteristic data, the third characteristic data and the first attribution relationship are added to a rule knowledge base as a new topology rule.

[0093] In this embodiment, if no rule can be matched in the rule knowledge base based on the first characteristic data, the second characteristic data, and the third characteristic data, the splitter affiliation relationship of the two ONU combinations will be determined according to steps S20 to S40. If the splitter affiliation relationship of the two ONU combinations is determined to be the first affiliation relationship, the first characteristic data, the second characteristic data, the third characteristic data, and the first affiliation relationship will be used as a new topology rule and added to the rule knowledge base.

[0094] Furthermore, in one embodiment, after the step of adding the first feature data, the second feature data, the third feature data, and the first attribution relationship as a new topology rule to the rule knowledge base, the method further includes:

[0095] When it is calculated that the new probability that any two ONU combinations belong to the same optical splitter is not greater than a preset threshold, the new topology rule is deleted from the rule knowledge base.

[0096] In this embodiment, since the probability that any two ONU combinations belong to the same splitter is obtained based on the overall similarity and individual similarity, the change of the ONU cluster will cause the overall similarity to change, thereby causing the probability that any two ONU combinations belong to the same splitter to change. When the new probability that any two ONU combinations belong to the same splitter is not greater than the preset threshold, the corresponding topology rule is deleted from the rule knowledge base.

[0097] Furthermore, in one embodiment, the steps of calculating the first similarity between an ONU in the pairwise ONU combination and each ONU in the ONU set, and calculating the second similarity between another ONU in the pairwise ONU combination and each ONU in the ONU set include:

[0098] The first similarity between an ONU in the pairwise ONU combination and each ONU in the ONU set is calculated according to the first calculation formula, and the second similarity between another ONU in the pairwise ONU combination and each ONU in the ONU set is calculated according to the second calculation formula. The first calculation formula is:

[0099]

[0100] The second calculation formula is:

[0101]

[0102] Among them, a i is the first similarity between an ONU and the i-th ONU in the ONU set, i ranges from 1 to n, n is the number of ONUs in the ONU set, p is the order, x ak is the characteristic data of the kth dimension of an ONU, x ik is the feature data of the kth dimension of the i-th ONU in the ONU set, m is the number of dimensions of the feature data, a′ i is the second similarity between another ONU and the i-th ONU in the ONU set, x bk is the feature data of the kth dimension of another ONU.

[0103] In this embodiment, the similarity between the two ONUs in the pairwise ONU combination and each ONU in the ONU set can be obtained according to the above method.

[0104] Furthermore, in one embodiment, step S30 includes:

[0105] Substituting the first similarity and the second similarity into the third calculation formula to obtain the overall similarity of any two ONU combinations, the third calculation formula is:

[0106]

[0107] Among them, S2 is the overall similarity of the two ONU combinations, min(a i , a′ i ) means from a i and a′ i Select the minimum value, max(a i , a′ i ) means from a i and a′ i Select the maximum value; if ai and a′ i are all zero, then we have

[0108] Multiplying the overall similarity by the third similarity, and taking the product as the probability that any two ONU combinations belong to the same optical splitter;

[0109] Alternatively, the overall similarity and the third similarity are weightedly summed, and the result of the weighted sum is used as the probability that any two ONU combinations belong to the same optical splitter.

[0110] In this embodiment, the third similarity may be calculated by calculating the Pearson correlation coefficient, Gaussian distance, or cosine similarity.

[0111] The overall similarity is used as the weight of the third similarity, the overall similarity is multiplied by the third similarity, and the product is used as the probability that any two ONU combinations belong to the same optical splitter.

[0112] Alternatively, the overall similarity and the third similarity are weighted and summed, and the weighted sum is used as the probability that any two ONU combinations belong to the same optical splitter. The weights of the overall similarity and the third similarity are fixed, or different weights are selected according to the third similarity.

[0113] Furthermore, in one embodiment, 100 OLTPON ports are selected, and the types of optical splitters and ONU information hanging below them are confirmed as the benchmark for judging the performance of the topology restoration method. Two topology restoration methods are used for simulation, namely the clustering method (taking the maximum silhouette coefficient as the number of clusters) and the classification rules constructed by individual and overall combination similarity (i.e., the present application scheme), and then the performance is compared. The results show that compared with other methods, the present application scheme has better topology restoration performance. The performance calculation rules are as follows:

[0114] The accuracy of the number of secondary optical splitters at PON ports = the number of accurate secondary optical splitters PON ports / the number of all PON ports. The accurate secondary optical splitters PON ports means that the number of identified secondary optical splitters is exactly the same as the actual number.

[0115] Deviation rate of the number of secondary optical splitters on a single PON port = absolute value of the difference between the actual number of secondary optical splitters and the restored number of secondary optical splitters / actual number of secondary optical splitters.

[0116] Deviation rate of the number of secondary optical splitters at a PON port = sum of deviation rates of the number of secondary optical splitters at a single PON port / number of all PON ports.

[0117] The accuracy of a single PON port = the number of accurate secondary optical splitters / the number of secondary optical splitters on the PON port. The accurate number of secondary optical splitters means that the identified ONUs under the splitter are exactly the same as the actual ones.

[0118] PON port accuracy = sum of all PON port accuracy / number of all PON ports.

[0119] The calculation results are shown in the following table:

[0120]

[0121]

[0122] In a second aspect, an embodiment of the present invention further provides a network topology restoration device.

[0123] In one embodiment, referring to Figure 3 , Figure 3 FIG. 1 is a functional module diagram of an embodiment of a network topology restoration device of the present invention. Figure 3 As shown, the network topology restoration device includes:

[0124] A selection module 10 is used to select two ONU combinations that have not been selected under the same PON port in an unknown network topology;

[0125] A first calculation module 20 is configured to calculate a first similarity between an ONU in a pairwise ONU combination and each ONU in an ONU set, calculate a second similarity between another ONU in a pairwise ONU combination and each ONU in an ONU set, and calculate a third similarity between two ONUs in a pairwise ONU combination, wherein the pairwise ONU combination is removed from all ONUs connected to the PON port, and the remaining ONUs are used to form the ONU set;

[0126] A second calculation module 30 is configured to calculate the probability that any two ONU combinations belong to the same optical splitter based on the first similarity, the second similarity, and the third similarity;

[0127] The belonging relationship determining module 40 is configured to determine that the optical splitter belonging relationship of the two ONU combinations is a first belonging relationship if the probability that the two ONU combinations belong to the same optical splitter is greater than a preset threshold, and to determine that the optical splitter belonging relationship of the two ONU combinations is a second belonging relationship if the probability that the two ONU combinations belong to the same optical splitter is not greater than the preset threshold;

[0128] A loop module 50 is configured to return to the step of selecting unselected pairwise ONU combinations under the same PON port in the unknown network topology if there are any unselected pairwise ONU combinations;

[0129] The restoration module 60 is configured to restore the unknown network topology according to the optical splitter ownership relationship of all two ONU combinations.

[0130] Furthermore, in one embodiment, the network topology restoration device further includes a matching module, configured to:

[0131] Matching the first characteristic data of one ONU in the two-by-two ONU combination, the second characteristic data of the other ONU in the two-by-two ONU combination, and the third characteristic data of the PON port with the topology rules in the rule knowledge base;

[0132] If the match is successful, the splitter ownership relationship of the two ONU combinations is determined according to the matched topology rule. If there is an unselected two ONU combination, the process returns to the step of selecting the unselected two ONU combinations under the same PON port in the unknown network topology;

[0133] If the matching fails, the steps of calculating the first similarity between one ONU in the pairwise ONU combination and each ONU in the ONU set, calculating the second similarity between another ONU in the pairwise ONU combination and each ONU in the ONU set, and calculating the third similarity between the two ONUs in the pairwise ONU combination are performed.

[0134] Furthermore, in one embodiment, the network topology restoration device further includes a knowledge base generation module, which is used to:

[0135] The characteristic data of a PON port in a known network topology, the characteristic data of two ONUs under the PON port, and the splitter ownership relationship of the two ONUs are used as a topology rule. If the two ONUs belong to the same splitter, the splitter ownership relationship is the first ownership relationship; if the two ONUs belong to different splitters, the splitter ownership relationship is the second ownership relationship.

[0136] The rule knowledge base is composed of a plurality of topological rules.

[0137] Furthermore, in one embodiment, the network topology restoration device further includes a knowledge base updating module configured to:

[0138] The first characteristic data, the second characteristic data, the third characteristic data and the first attribution relationship are added to a rule knowledge base as a new topology rule.

[0139] Furthermore, in one embodiment, the knowledge base updating module is further configured to:

[0140] When it is calculated that the new probability that any two ONU combinations belong to the same optical splitter is not greater than a preset threshold, the new topology rule is deleted from the rule knowledge base.

[0141] Furthermore, in one embodiment, the first calculation module 20 is configured to:

[0142] The first similarity between an ONU in the pairwise ONU combination and each ONU in the ONU set is calculated according to the first calculation formula, and the second similarity between another ONU in the pairwise ONU combination and each ONU in the ONU set is calculated according to the second calculation formula. The first calculation formula is:

[0143]

[0144] The second calculation formula is:

[0145]

[0146] Among them, a i is the first similarity between an ONU and the i-th ONU in the ONU set, i ranges from 1 to n, n is the number of ONUs in the ONU set, p is the order, x ak is the characteristic data of the kth dimension of an ONU, x ik is the feature data of the kth dimension of the i-th ONU in the ONU set, m is the number of dimensions of the feature data, a′ i is the second similarity between another ONU and the i-th ONU in the ONU set, x bk is the feature data of the kth dimension of another ONU.

[0147] Furthermore, in one embodiment, the second calculation module 30 is configured to:

[0148] Substituting the first similarity and the second similarity into the third calculation formula to obtain the overall similarity of any two ONU combinations, the third calculation formula is:

[0149]

[0150] Among them, S2 is the overall similarity of the two ONU combinations, min(a i , a′ i ) means from a i and a′ i Select the minimum value, max(a i , a′ i ) means from a i and a′ i Select the maximum value among them; if a i and a′ i are all zero, then we have

[0151] Multiplying the overall similarity by the third similarity, and taking the product as the probability that any two ONU combinations belong to the same optical splitter;

[0152] Alternatively, the overall similarity and the third similarity are weightedly summed, and the result of the weighted sum is used as the probability that any two ONU combinations belong to the same optical splitter.

[0153] Among them, the functional implementation of each module in the above-mentioned network topology restoration device corresponds to the various steps in the above-mentioned network topology restoration method embodiment, and their functions and implementation processes are no longer repeated here.

[0154] In a third aspect, an embodiment of the present invention provides a network topology restoration device, which may be a device with data processing capabilities, such as a personal computer (PC), a laptop computer, or a server.

[0155] Reference Figure 4 , Figure 4 This is a hardware structure diagram of the network topology restoration device involved in the embodiment of the present invention. In the embodiment of the present invention, the network topology restoration device may include a processor 1001 (such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components; the user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard); the network interface 1004 may optionally include a standard wired interface, a wireless interface (such as a wireless fidelity WIreless-FIdelity, WI-FI interface); the memory 1005 may be a high-speed random access memory (RAM), or a stable memory (non-volatile memory), such as a disk memory. The memory 1005 may optionally be a storage device independent of the aforementioned processor 1001. Those skilled in the art will understand that Figure 4 The hardware structure shown in the figure does not constitute a limitation of the present invention, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0156] Continue to refer to Figure 4 , Figure 4 The memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and a network topology restoration program. The processor 1001 may call the network topology restoration program stored in the memory 1005 and execute the network topology restoration method provided in the embodiment of the present invention.

[0157] In a fourth aspect, an embodiment of the present invention further provides a readable storage medium.

[0158] The readable storage medium of the present invention stores a network topology restoration program, wherein when the network topology restoration program is executed by a processor, the steps of the network topology restoration method described above are implemented.

[0159] The method implemented when the network topology restoration program is executed can refer to the various embodiments of the network topology restoration method of the present invention, and will not be described in detail here.

[0160] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or system comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or system. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or system comprising the element.

[0161] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0162] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, or of course by hardware, but in many cases the former is a better embodiment. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes a number of instructions for enabling a terminal device to execute the methods described in various embodiments of the present invention.

[0163] The above are only preferred embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A network topology restoration method, characterized in that: The network topology restoration method comprises: Select two ONU combinations that have not been selected before under the same PON port in an unknown network topology; Calculating a first similarity between an ONU in the pairwise ONU combination and each ONU in the ONU set, calculating a second similarity between another ONU in the pairwise ONU combination and each ONU in the ONU set, and calculating a third similarity between the two ONUs in the pairwise ONU combination, wherein the pairwise ONU combination is removed from all ONUs connected to the PON port, and the remaining ONUs are used to form the ONU set; Calculate the probability that any two ONU combinations belong to the same optical splitter based on the first similarity, the second similarity, and the third similarity; If the probability that any two ONU combinations belong to the same optical splitter is greater than a preset threshold, the optical splitter affiliation relationship of the two ONU combinations is determined to be a first affiliation relationship; if the probability that any two ONU combinations belong to the same optical splitter is not greater than the preset threshold, the optical splitter affiliation relationship of the two ONU combinations is determined to be a second affiliation relationship; If there is an unselected pairwise ONU combination, returning to the step of selecting an unselected pairwise ONU combination under the same PON port in the unknown network topology; The unknown network topology is restored according to the optical splitter ownership relationship of all pairwise ONU combinations.

2. The network topology restoration method according to claim 1, wherein: After the step of selecting the unselected pairwise ONU combinations under the same PON port in the unknown network topology, the method further includes: Matching the first characteristic data of one ONU in the two-by-two ONU combination, the second characteristic data of the other ONU in the two-by-two ONU combination, and the third characteristic data of the PON port with the topology rules in the rule knowledge base; If the match is successful, the splitter ownership relationship of the two ONU combinations is determined according to the matched topology rule. If there is an unselected two ONU combination, the process returns to the step of selecting the unselected two ONU combinations under the same PON port in the unknown network topology; If the matching fails, the steps of calculating the first similarity between one ONU in the pairwise ONU combination and each ONU in the ONU set, calculating the second similarity between another ONU in the pairwise ONU combination and each ONU in the ONU set, and calculating the third similarity between the two ONUs in the pairwise ONU combination are performed.

3. The network topology restoration method according to claim 2, wherein: Before the step of selecting the unselected pairwise ONU combinations under the same PON port in the unknown network topology, the method further includes: The characteristic data of a PON port in a known network topology, the characteristic data of two ONUs under the PON port, and the splitter ownership relationship of the two ONUs are used as a topology rule. If the two ONUs belong to the same splitter, the splitter ownership relationship is the first ownership relationship; if the two ONUs belong to different splitters, the splitter ownership relationship is the second ownership relationship. The rule knowledge base is composed of a plurality of topological rules.

4. The network topology restoration method according to claim 3, wherein: After the step of determining that the optical splitter affiliation of the two ONU combinations is the first affiliation if the probability that the two ONU combinations belong to the same optical splitter is greater than a preset threshold, the method further includes: The first characteristic data, the second characteristic data, the third characteristic data and the first attribution relationship are added to a rule knowledge base as a new topology rule.

5. The network topology restoration method according to claim 4, wherein: After the step of adding the first characteristic data, the second characteristic data, the third characteristic data, and the first attribution relationship as a new topology rule to the rule knowledge base, the method further includes: When it is calculated that the new probability that any two ONU combinations belong to the same optical splitter is not greater than a preset threshold, the new topology rule is deleted from the rule knowledge base.

6. The network topology restoration method according to claim 1, wherein: The steps of calculating a first similarity between an ONU in each ONU combination and each ONU in the ONU set, and calculating a second similarity between another ONU in each ONU combination and each ONU in the ONU set include: The first similarity between an ONU in the pairwise ONU combination and each ONU in the ONU set is calculated according to the first calculation formula, and the second similarity between another ONU in the pairwise ONU combination and each ONU in the ONU set is calculated according to the second calculation formula. The first calculation formula is: The second calculation formula is: Among them, a i is the first similarity between an ONU and the i-th ONU in the ONU set, i ranges from 1 to n, n is the number of ONUs in the ONU set, p is the order, x ak is the characteristic data of the kth dimension of an ONU, x ik is the feature data of the kth dimension of the i-th ONU in the ONU set, m is the number of dimensions of the feature data, a' i is the second similarity between another ONU and the i-th ONU in the ONU set, x bk is the feature data of the kth dimension of another ONU.

7. The network topology restoration method according to claim 6, wherein: The step of calculating the probability that any two ONU combinations belong to the same optical splitter according to the first similarity, the second similarity, and the third similarity includes: Substituting the first similarity and the second similarity into the third calculation formula to obtain the overall similarity of any two ONU combinations, the third calculation formula is: Among them, S2 is the overall similarity of the two ONU combinations, min(a i , a' i ) means from a i and a' i Select the minimum value, max(a i , a' i ) means from a i and a' i Select the maximum value; if a i and a' i are all zero, then we have Multiplying the overall similarity by the third similarity, and taking the product as the probability that any two ONU combinations belong to the same optical splitter; Alternatively, the overall similarity and the third similarity are weightedly summed, and the result of the weighted sum is used as the probability that any two ONU combinations belong to the same optical splitter.

8. A network topology restoration device, characterized in that: The network topology restoration device includes: A selection module is used to select two ONU combinations that have not been selected under the same PON port in an unknown network topology; A first calculation module is configured to calculate a first similarity between an ONU in a pairwise ONU combination and each ONU in an ONU set, calculate a second similarity between another ONU in the pairwise ONU combination and each ONU in the ONU set, and calculate a third similarity between two ONUs in the pairwise ONU combination, wherein the pairwise ONU combination is removed from all ONUs connected to the PON port, and the remaining ONUs are used to form the ONU set; A second calculation module is configured to calculate the probability that any two ONU combinations belong to the same optical splitter based on the first similarity, the second similarity, and the third similarity; An ownership relationship determination module is configured to determine that the ownership relationship of the optical splitters of the two ONU combinations is a first ownership relationship if the probability that the two ONU combinations belong to the same optical splitter is greater than a preset threshold; and to determine that the ownership relationship of the optical splitters of the two ONU combinations is a second ownership relationship if the probability that the two ONU combinations belong to the same optical splitter is not greater than the preset threshold; A loop module is configured to return to the step of selecting unselected pairwise ONU combinations under the same PON port in the unknown network topology if there are any unselected pairwise ONU combinations; The restoration module is used to restore the unknown network topology according to the optical splitter ownership relationship of all two ONU combinations.

9. A network topology restoration device, characterized in that: The network topology restoration device includes a processor, a memory, and a network topology restoration program stored in the memory and executable by the processor, wherein when the network topology restoration program is executed by the processor, the steps of the network topology restoration method according to any one of claims 1 to 7 are implemented.

10. A readable storage medium, characterized in that: The readable storage medium stores a network topology restoration program, wherein when the network topology restoration program is executed by a processor, the steps of the network topology restoration method according to any one of claims 1 to 7 are implemented.

Images