Method, device and medium for evaluating health status of optical module

Abstract

The present disclosure provides a health state evaluation method, device and equipment of an optical module and a medium, and relates to the technical field of communication. The method comprises the following steps: collecting historical running state information of a target terminal in a target port of an optical module at a plurality of historical moments, wherein the target terminal is in a running state; the historical running state information collected at each historical moment comprises a historical transmission rate, a historical packet loss rate and a historical optical power of the target terminal; determining a normal optical power interval of the target terminal according to the historical running state information collected at the plurality of historical moments; obtaining a current optical power of the target terminal at a current moment; and determining that the target terminal is abnormal when the current optical power is outside the normal optical power interval. The method can detect whether the target terminal in the running state is abnormal before the optical module fails, thereby evaluating the health state of the optical module and preventing the optical module from failing.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the field of communication technology, and more particularly, to a health state evaluation method and device of an optical module, an equipment and a medium. BACKGROUND

[0002] An optical module is a core device in an optical fiber communication system and is a carrier for signal transmission between a switch and a device. The optical module includes a sending end and a receiving end. The sending end is configured to convert an electrical signal output by a device where the optical module is located into an optical signal. The receiving end is configured to convert an optical signal sent by an external device into an electrical signal and provide the electrical signal to a device where the receiving end is located.

[0003] Currently, a user can only realize that an optical module is malfunctioning when the optical module cannot work normally. However, the optical module is already in a malfunctioning state and cannot normally perform its functions at this time. Therefore, in order to reduce problems caused by malfunctions of the optical module, how to effectively evaluate the health state of the optical module before the optical module malfunctions to prevent the optical module from malfunctioning becomes a technical problem to be solved. SUMMARY

[0004] An object of the present disclosure is to provide a new technical solution for health state evaluation of an optical module.

[0005] According to a first aspect of the present disclosure, a health state evaluation method of an optical module is provided, comprising:

[0006] For a target terminal in a target port of the optical module in a running state, historical running state information of the target terminal is collected at a plurality of historical time points. Each of the historical running state information collected at the historical time points includes historical transmission rate, historical packet loss rate and historical optical power of the target terminal. The target terminal is a sending end or a receiving end in the target port.

[0007] According to the historical running state information collected at the plurality of historical time points, a normal optical power range of the target terminal is determined.

[0008] A current optical power of the target terminal at a current time point is obtained.

[0009] In a case where the current optical power is located outside the normal optical power range, the target terminal is determined to be abnormal.

[0010] Optionally, the method further comprises:

[0011] inputting the historical running state information of the target terminal collected at the plurality of historical moments into a preset machine learning model to obtain a first optical power interval output by the preset machine learning model;

[0012] determining the normal optical power interval according to the first optical power interval.

[0013] Optionally, the method further comprises:

[0014] obtaining a second optical power interval pre-set by a user;

[0015] taking an intersection of the first optical power interval and the second optical power interval as the normal optical power interval.

[0016] Optionally, the method further comprises:

[0017] obtaining a training sample set, the training sample set comprising a plurality of training samples, one training sample comprising a plurality of groups of training data of a training terminal in a running state, a normal sample optical power interval corresponding to the plurality of groups of training data, one group of training data comprising a sample transmission rate, a sample packet loss rate and a sample optical power, the target terminal and the training terminal being a same sending terminal or a same receiving terminal;

[0018] training the preset machine learning model according to the training sample set.

[0019] Optionally, the method further comprises:

[0020] obtaining a maximum allowable packet loss rate and a minimum transmission rate of the training terminal;

[0021] taking the maximum allowable packet loss rate and the minimum transmission rate as a constraint condition of the preset machine learning model, and training the preset machine learning model according to the training sample set.

[0022] Optionally, the method further comprises:

[0023] periodically performing the steps of collecting the historical running state information of the target terminal at a plurality of historical moments, and determining a normal optical power interval of the target terminal according to the historical running state information, to update the normal optical power interval.

[0024] Optionally, the method further comprises:

[0025] in a case where the target terminal is abnormal, obtaining a static state parameter of the target terminal in a standby state, the static state parameter comprising at least one of actual optical eye diagram information, actual bit error rate and actual static optical power;

[0026] According to the static state parameter, abnormal information of the target terminal is determined.

[0027] According to a second aspect of the present disclosure, a health state evaluation device of an optical module is provided, comprising:

[0028] A collection module is configured to collect historical running state information of a target terminal in a target port of the optical module at a plurality of historical time points, wherein the historical running state information collected at each historical time point comprises historical transmission rate, historical packet loss rate and historical optical power of the target terminal, and the target terminal is a sending terminal or a receiving terminal in the target port.

[0029] A first determination module is configured to determine a normal optical power range of the target terminal according to the historical running state information collected at the plurality of historical time points.

[0030] An acquisition module is configured to acquire current optical power of the target terminal at a current time point.

[0031] A second determination module is configured to determine that the target terminal is abnormal when the current optical power is outside the normal optical power range.

[0032] According to a third aspect of the present disclosure, an electronic device is provided, comprising the health state evaluation device of the optical module according to the second aspect.

[0033] Alternatively, the electronic device comprises a memory and a processor, the memory is configured to store computer instructions, and the processor is configured to call the computer instructions from the memory to execute the method according to any one of the first aspect.

[0034] According to a fourth aspect of the present disclosure, a computer readable storage medium is provided, which stores a computer program, and the computer program is executed by a processor to implement the method according to any one of the first aspect.

[0035] The disclosure provides a health state evaluation method of an optical module, comprising: collecting historical running state information of a target terminal in a target port of the optical module at a plurality of historical time points, the target terminal being in a running state; wherein the historical running state information collected at each historical time point comprises historical transmission rate, historical packet loss rate and historical optical power of the target terminal, the target terminal being a sending terminal or a receiving terminal in the target port; determining a normal optical power range of the target terminal according to the historical running state information collected at the plurality of historical time points; obtaining current optical power of the target terminal at a current time point; and determining that the target terminal is abnormal in a case that the current optical power is located outside the normal optical power range. Based on the method, detection of whether the target terminal in the running state is abnormal before failure of the optical module can be realized, so as to realize evaluation of the health state of the optical module, and further prevent failure of the optical module.

[0036] Other features of the present disclosure, and their advantages, will become apparent from the following detailed description of exemplary embodiments of the present disclosure, with reference to the drawings. BRIEF DESCRIPTION OF DRAWINGS

[0037] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0038] Figure 1 is a flowchart of a health state evaluation method of an optical module provided by the present disclosure;

[0039] Figure 2 is a structural schematic diagram of a health state evaluation device of an optical module provided by the present disclosure;

[0040] Figure 3 is a structural schematic diagram of an electronic device provided by the present disclosure. DETAILED DESCRIPTION

[0041] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. Note that the relative arrangement, numerical expressions, and numerical values of components and steps set forth in these embodiments are not limiting to the scope of the present disclosure unless otherwise specifically stated.

[0042] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way limiting to the scope of the present disclosure and its applications or uses.

[0043] Techniques, methods, and devices known to those of ordinary skill in the relevant art can not be discussed in detail herein, but should be considered as part of the specification, where appropriate.

[0044] In all of the examples shown and discussed herein, any specific values should be interpreted as merely exemplary and not as a limitation. Thus, other examples of the exemplary embodiments can have different values.

[0045] It should be noted that like reference numerals and letters refer to like items throughout the attached drawings, and once an item is defined in one drawing, it is not necessary to discuss it further in subsequent drawings.

[0046] A storage area network (SAN) is a network architecture that provides high-speed data storage services. The SAN can include a plurality of network element devices, for example, including a large number of fiber switches. However, a fiber switch usually includes a plurality of ports, and each port is plugged with an optical module. Each optical module includes a transmitting end and a receiving end, wherein the transmitting end is used to convert an electrical signal output by the device where the optical module is located into an optical signal, and the receiving end is used to receive an optical signal sent by an external device and convert the optical signal into an electrical signal to provide to the device where it is located. In the case of failure of a certain transmitting end and receiving end of an optical module, the optical module fails. Based on the foregoing, there are a large number of optical modules in the SAN. In the case of failure of a transmitting end or a receiving end of one of the optical modules, resulting in failure of the optical module, a large amount of troubleshooting work needs to be performed by maintenance personnel to find the failed transmitting end or receiving end, and at the same time, the optical module cannot normally perform its functions. Therefore, how to effectively evaluate the health status of the optical module before it fails to prevent the failure from occurring is a technical problem to be solved.

[0047] Based on the above problem, the present disclosure provides a health status evaluation method of an optical module, as shown in the following steps S110 to S140. Figure 1

[0048] Step S110, for a target terminal in a target port of the optical module in a running state, collecting historical running state information of the target terminal at a plurality of historical time points.

[0049] Wherein, the historical running state information collected at each historical time point includes a historical transmission rate, a historical packet loss rate, and a historical optical power of the target terminal, and the target terminal is a transmitting end or a receiving end in the target port.

[0050] In this embodiment, the optical module includes two terminals, one receiving end and one transmitting end. The terminal used for health evaluation of the optical module and in a running state is recorded as a target terminal, and the port corresponding to the target terminal is recorded as a target port.

[0051] ​In some embodiments, the running state information of the target terminal in the running state can be collected in a set time period as the historical running state information of the time point after the set time period. In one example, the running state information of the target terminal is collected every hour within each Monday as the historical running state information corresponding to the time point from Tuesday of this week to Monday of next week.

[0052] In some embodiments, for any historical time point, the transmission rate and the packet loss rate of the target terminal at the historical time point can be determined by reading the message statistical information of the optical fiber switch where the optical module is located. The transmission rate of the target terminal at the historical time point is recorded as the historical transmission rate, and the packet loss rate of the target terminal at the historical time point is recorded as the packet loss rate.

[0053] In one example, the message statistical information of the optical fiber switch can be as follows:

[0054] fc1 / 1 is up

[0055] Port description is CH242_010100139056

[0056] Hardware is Fibre Channel, SFP is short wave laser w / o OFC(SN)

[0057] Port WWN is 20:01:8c:60:4f:10:11:60

[0058] Peer port WWN is 50:06:01:62:4a:20:0c:11

[0059] Admin port mode is auto, trunk mode is on

[0060] snmp link state traps are enabled

[0061] Port mode is F, FCID is 0x0b0200

[0062] Port vsan is 1

[0063] Admin Speed is auto

[0064] Operating Speed is 16Gbps

[0065] Rate mode is dedicated

[0066] Port flow-control is R_RDY

[0067] Transmit B2B Credit is 6

[0068] Receive B2B Credit is 64

[0069] B2B State Change:Admin(on),Oper(down)

[0070] Receive data field Size is 2112

[0071] Beacon is turned off

[0072] Logical type is edge

[0073] 5minutes input rate 32bits / sec,4bytes / sec,0frames / sec

[0074] 5minutes output rate 0bits / sec,0bytes / sec,0franes / sec

[0075] 120464frames input,9151676bytes

[0076] 0discards,0errors

[0077] 0invalid CRC / FCS,0unknown class

[0078] 0too long,0too short

[0079] 77957frames output,4677852bytes

[0080] 0discards,0errors

[0081] 1input OLS,1LRR,O NOS,0loop inits

[0082] 1output OLS,O LRR,1NOS,0loop inits

[0083] 64receive B2B credit remaining

[0084] 6 transmit B2B credit remaining

[0085] 6 low priority transmit B2B credit remaining

[0086] Interface last changed at Fri Nov 1 09:55:02 2024

[0087] Last clearing of "show interface counters: never

[0088] And, for any historical moment, the optical power of the target terminal at the historical moment can be determined by reading the Digital Diagnostic Monitoring (DDM) information of the optical fiber switch to which the optical module belongs at the historical moment, and the optical power of the target terminal at the historical moment is recorded as the historical optical power.

[0089] In one example, the above-mentioned digital diagnostic function information can be as follows:

[0090] fc1 / 1sfp is present

[0091] Name is CISCO-AVAGO

[0092] Manufacturer's part number is AFBR-57F5PZ-CS1

[0093] Revision is B2

[0094] Serial number is AVJ1907JNNH

[0095] Nominal bit rate is 14000Mb / s

[0096] Link length supported for 50 / 125um OM2 fiber is 35m

[0097] Link length supported for 62.5 / 125um fiber is 15m

[0098] Link length supported for 50 / 125um OM3 fiber is 100m

[0099] FC Transnitter type is short wave laser w / o OFC(SN)

[0100] FC Transnitter supports short distance link length

[0101] Transnission mediun is multimode laser with 62.5un aperture(M6)

[0102] Supported speeds are-Min speed:4000Mb / s,Max speed:16000Mb / s

[0103] Cisco extended id is unknovn(0x0)

[0104] Cisco part number is 10-2666-01

[0105] Cisco pid is DS-SFP-FC16G-SW

[0106] No tx fault,no rx loss,in sync state,diagnostic monitoring type is0x68

[0107] SFP Diagnostics Information:

[0108]

[0109] Note:++high-alarm:+high-warning.-low-alarm;-low-varning

[0110] Of course, the historical running state information of the target terminal at multiple historical moments can also be collected through other means, and the present disclosure does not make any limitation in this regard.

[0111] It should be noted that the number of historical moments in the above step S110 can be determined according to experience, and the present disclosure does not make any limitation in this regard.

[0112] In step S120, the normal optical power interval of the target terminal is determined according to the historical running state information collected at multiple historical moments.

[0113] The normal optical power interval can be an interval in which the optical power of the target terminal is located in a normal state without failure, that is, the normal optical power interval can be used to represent an optical power interval in which the target terminal meets the preset transmission rate requirement and the packet loss rate requirement. For example, if the optical power of the target terminal exceeds the normal optical power interval, the transmission rate of the target terminal decreases, the packet loss rate increases, and the data transmission quality of the storage area network decreases.

[0114] The historical running state information can reflect the normal optical power interval of the target terminal, and therefore, the normal optical power interval of the target terminal can be determined according to the historical running state information collected at multiple historical moments.

[0115] It can be understood that, due to different usage conditions of different target terminals, the historical running state information collected at multiple historical moments of different target terminals is usually different, and therefore, the normal optical power intervals of different target terminals are also different, that is, the normal optical power intervals of different target terminals determined according to the historical running state information in this step can be different, which is different from the conventional technology in which the same normal optical power interval is set for different terminals.

[0116] In an embodiment of the present disclosure, the step S120 described above can be implemented in a manner of machine learning. In this regard, the step S120 described above is implemented through the following steps S1201 and S1202.

[0117] In the step S1201, the historical running state information collected at multiple historical moments is input into a preset machine learning model to obtain a first optical power interval output by the preset machine learning model.

[0118] The preset machine learning model is pre-trained and can predict a corresponding predicted normal optical power interval according to the historical running state information collected at multiple historical moments. In an embodiment of the present disclosure, the predicted normal optical power interval output by the preset machine learning model is denoted as the first optical power interval.

[0119] In some embodiments, the preset machine learning model of the present disclosure can be exemplarily a machine learning model based on a gradient boosting decision tree (GBDT).

[0120] In some embodiments, the preset machine learning model described above can be trained through the following steps S1201-1 and S1201-2.

[0121] In the step S1201-1, a training sample set is obtained.

[0122] The training sample set includes a plurality of training samples, and each training sample includes a plurality of sets of training data of the training terminal in the running state and a normal sample optical power interval corresponding to the plurality of sets of training data. Each set of training data includes a sample transmission rate, a sample packet loss rate, and a sample optical power. The target terminal and the training terminal are both a sending terminal or a receiving terminal.

[0123] In the embodiments of the present disclosure, when the target terminal is a sending terminal, the training terminal is also a sending terminal. When the target terminal is a receiving terminal, the training terminal is a receiving terminal.

[0124] Taking the target terminal as a sending terminal as an example, for a training sample, in some embodiments, a sending terminal of an optical module of an optical fiber switch is randomly selected as a training terminal, and the training terminal is controlled to be in a running state. On this basis, the acquisition step is performed, which includes: for the same moment, the transmission rate at the moment is acquired as the sample transmission rate, the packet loss rate at the moment is acquired as the sample packet loss rate, and the optical power at the moment is acquired as the sample optical power. The aforementioned acquisition step is repeated to obtain a plurality of sets of training data corresponding to a training sample. The normal optical power interval of the plurality of sets of training data of a training sample can be determined by an expert, for example. Further, the normal optical power interval corresponding to the plurality of sets of training data of a training sample is determined as the normal sample optical power interval of the training sample.

[0125] In step S1201-2, the preset machine learning model is trained according to the training sample set.

[0126] The training sample set obtained based on the above step S1201-1 is input into the preset machine learning model with default parameters, so as to train the preset machine learning model with default parameters, thereby obtaining a trained machine learning model.

[0127] In some embodiments, in order to better train the preset machine learning model, the above step S1201-2 is specifically implemented through the following steps S1201-21 and S1201-22.

[0128] In step S1201-21, the maximum allowed packet loss rate and the minimum transmission rate of the training terminal are obtained.

[0129] In some embodiments, the configuration information corresponding to the training terminal can be read to determine the maximum allowed packet loss rate and the minimum transmission rate of the training terminal.

[0130] In step S1201-22, the maximum allowed packet loss rate and the minimum transmission rate are taken as constraint conditions of the preset machine learning model, and the preset machine learning model is trained according to the training sample set.

[0131] In the embodiment, the preset machine learning model can be trained more accurately through the above steps S1201-22.

[0132] In step S1202, the normal optical power interval is determined according to the first optical power interval.

[0133] In some embodiments, the first optical power interval is directly used as the normal optical power interval.

[0134] In other embodiments, the steps S1202-1 and S1202-2 can be used to determine the normal optical power interval.

[0135] In step S1202-1, the second optical power interval set by the user in advance is obtained.

[0136] In some embodiments, the second optical power interval is set according to the product manual of the optical module where the target terminal is located, for example, the optical power interval specified by the manufacturer of the optical module in the product manual. In other embodiments, the second optical power interval is set according to the experience of experts.

[0137] In step S1202-2, the intersection of the first optical power interval and the second optical power interval is used as the normal optical power interval.

[0138] In one example, if the first optical power interval obtained based on the above step S1201 is [a, b], and the second optical power interval obtained based on the above step S1202-1 is [c, d], where c < a < d < b, then the normal optical power interval is determined to be [a, d].

[0139] Based on the above steps S1202-1 and S1202-2, the first optical power interval obtained based on the preset machine learning model can be combined with the second optical power interval obtained based on the product manual of the optical module where the target terminal is located or the experience of experts, so as to obtain a more accurate normal optical power interval.

[0140] In step S130, the current optical power of the target terminal at the current time is obtained.

[0141] The current optical power of the target terminal at the current time is obtained in the same way as the historical optical power of the target terminal, which will not be described here.

[0142] The current optical power of the target terminal at the current time is a fluctuation value, which is related to the optical fiber switch where the target terminal is located, the optical fiber, and the opposite device.

[0143] For the optical fiber switch, the applicant has found that the optical power of the terminal is a leading indicator of whether the terminal is abnormal through a large number of observations and researches on failed terminals (including sending terminals and receiving terminals). Once the optical power of the terminal deviates from the corresponding normal optical power interval, the transmission rate and the packet loss rate of the terminal will begin to deteriorate, and finally the terminal will be unavailable due to failure. Therefore, on the basis of the above steps S120 and S130, the health status evaluation method of the optical module provided by the present disclosure determines whether the target terminal is abnormal through the following step S140.

[0144] Step S140, in the case that the current optical power is outside the range of the normal optical power interval, it is determined that the target terminal is abnormal.

[0145] In the case that the target terminal is determined to be abnormal based on the above step S140, in some embodiments, alarm information can be output to prompt maintenance personnel to maintain the target terminal. For example, the packaging mode, the adaptation rate and the corresponding optical fiber interface of the target terminal are detected to verify whether the three parameters of center wavelength, transmission distance and transmission rate meet the requirements. Based on this, the failure of the optical module can be prevented.

[0146] Corresponding to the above step S140, in the case that the current optical power is within the range of the normal optical power interval, it is determined that the target terminal is normal.

[0147] In the present disclosure, whether the target terminal is abnormal determined based on the above content is taken as the evaluation result of the health status of the optical module. Maintenance personnel can make a decision to continue to observe the target terminal or maintain the target terminal based on the evaluation result of the health status of the optical module.

[0148] Based on the above content, it can be known that the health status evaluation method of the optical module provided by the present disclosure can detect whether the target terminal in the running state is abnormal before the optical module fails, so as to evaluate the health status of the optical module, and further prevent the optical module from failing.

[0149] The disclosure provides a health state evaluation method of an optical module, comprising: collecting historical running state information of a target terminal in a target port of the optical module at a plurality of historical time points, the target terminal being in a running state; wherein the historical running state information collected at each historical time point comprises a historical transmission rate, a historical packet loss rate and a historical optical power of the target terminal, the target terminal being a sending terminal or a receiving terminal in the target port; determining a normal optical power range of the target terminal according to the historical running state information collected at the plurality of historical time points; obtaining a current optical power of the target terminal at a current time point; and determining that the target terminal is abnormal in a case that the current optical power is located outside the normal optical power range. Based on the method, detection of whether the target terminal in the running state is abnormal before failure of the optical module can be realized, so as to evaluate the health state of the optical module and prevent the optical module from failing.

[0150] In some embodiments, the health state evaluation method of the optical module provided by the disclosure further comprises the following step S150.

[0151] Step S150: periodically performing the steps of collecting the historical running state information of the target terminal at the plurality of historical time points and determining the normal optical power range of the target terminal according to the historical running state information, so as to update the normal optical power range.

[0152] In the embodiments of the disclosure, the duration of the period corresponding to the above-mentioned step S150 is a duration that causes the normal optical power range to change significantly. In one example, the duration of the period corresponding to the above-mentioned step S150 can be 24 hours, that is, the above-mentioned steps S110 and S120 are performed once every other day to obtain a new normal optical power range. Based on this, the latest normal optical power range is used to determine whether the target terminal is abnormal before the next repeated execution of the above-mentioned steps S110 and S120.

[0153] It should be noted that the disclosure does not limit the duration of the period corresponding to the above-mentioned step S150.

[0154] In the embodiments of the disclosure, as the target terminal is used, the normal optical power range of the target terminal will also change. In order to adapt to the change of the normal optical power range of the target terminal, the above-mentioned steps S110 and S120 are repeated to obtain a new and more accurate normal optical power range.

[0155] In some embodiments, in a case that the target terminal is determined to be abnormal based on the above-mentioned step S140, the health state evaluation method of the optical module provided by the disclosure further comprises the following steps S160 and S170.

[0156] Step S160: in a case that the target terminal is abnormal, obtaining a static state parameter of the target terminal in a standby state.

[0157] The static state parameters include at least one of optical eye diagram information, bit error rate and static optical power.

[0158] In some embodiments, the static optical power of the target terminal can be tested by an optical power meter when the target terminal is in the standby state. The static optical power of the target terminal obtained by the optical power meter test is recorded as the actual power and input into the execution subject of the health state evaluation method of the optical module provided by the present disclosure.

[0159] In some embodiments, the optical eye diagram information of the target terminal can be tested by an optical spectrum analyzer when the target terminal is in the standby state. The optical eye diagram information of the target terminal obtained by the optical spectrum analyzer test is recorded as the actual optical eye diagram information and input into the execution subject of the health state evaluation method of the optical module provided by the present disclosure.

[0160] In some embodiments, the bit error rate of the target terminal can be calculated by a bit error tester in a manner of applying a bit error signal to the target terminal and synchronously detecting the bit error when the target terminal is in the standby state. The bit error rate obtained in the foregoing manner is recorded as the actual bit error rate and input into the execution subject of the health state evaluation method of the optical module provided by the present disclosure.

[0161] Step S170, determining the abnormal information of the target terminal according to the static state parameters.

[0162] In some embodiments, when the static state parameters include the actual optical eye diagram information, the specific implementation of the above step S1700 can include: determining the actual extinction ratio, actual jitter, actual crossing point and actual Mask of the target terminal according to the actual optical eye diagram information, comparing the determined actual extinction ratio with the reference extinction ratio of the target terminal, and if the deviation between the two is greater than the allowed extinction ratio deviation, determining that the abnormal information of the target terminal is the extinction ratio abnormality. Similarly, the actual jitter, actual crossing point and actual Mask are also the same.

[0163] In other embodiments, when the static state parameters include the actual bit error rate, the actual bit error rate obtained in the above step S160 is compared with the reference bit error rate of the target terminal, and if the deviation between the two is greater than the allowed bit error rate deviation, it is determined that the abnormal information of the target terminal is the bit error rate abnormality. Similarly, the actual static optical power is also the same.

[0164] The present disclosure also provides a health state evaluation device 200 of an optical module, as shown in Figure 2 including:

[0165] The collection module 210 is configured to collect historical running state information of a target terminal in a target port of the optical module at a plurality of historical time instants, the target terminal being in a running state; the historical running state information collected at each of the plurality of historical time instants includes historical transmission rate, historical packet loss rate and historical optical power of the target terminal, the target terminal being a sending terminal or a receiving terminal in the target port;

[0166] The first determination module 220 is configured to determine a normal optical power range of the target terminal according to the historical running state information collected at the plurality of historical time instants.

[0167] The acquisition module 230 is configured to acquire current optical power of the target terminal at a current time instant.

[0168] The second determination module 240 is configured to determine that the target terminal is abnormal in a case where the current optical power is located outside the normal optical power range.

[0169] In an embodiment of the present disclosure, the first determination module 220 is specifically configured to:

[0170] input the historical running state information collected at the plurality of historical time instants into a preset machine learning model to obtain a first optical power range output by the preset machine learning model;

[0171] determine the normal optical power range according to the first optical power range.

[0172] In an embodiment of the present disclosure, the first determination module 220 is specifically configured to:

[0173] acquire a second optical power range pre-set by a user;

[0174] take an intersection of the first optical power range and the second optical power range as the normal optical power range.

[0175] In an embodiment of the present disclosure, the health state evaluation device 200 of the optical module provided by the present disclosure further includes:

[0176] The training module is configured to acquire a training sample set, the training sample set including a plurality of training samples, one of the training samples including a plurality of groups of training data of a training terminal in a running state, a normal sample optical power range corresponding to the plurality of groups of training data, one group of the training data including sample transmission rate, sample packet loss rate and sample optical power, the target terminal and the training terminal both being a sending terminal or a receiving terminal.

[0177] train the preset machine learning model according to the training sample set.

[0178] In an embodiment of the present disclosure, the training module is specifically configured to:

[0179] obtain the maximum allowable packet loss rate and the minimum transmission rate of the training terminal;

[0180] use the maximum allowable packet loss rate and the minimum transmission rate as constraint conditions of the preset machine learning model, and train the preset machine learning model according to the training sample set.

[0181] In an embodiment of the present disclosure, the health state evaluation device 200 of the optical module provided by the present disclosure further comprises:

[0182] The updating module is configured to periodically perform the steps of collecting the historical running state information of the target terminal at a plurality of historical time points, and determining the normal optical power interval of the target terminal according to the historical running state information, so as to update the normal optical power interval.

[0183] In an embodiment of the present disclosure, the obtaining module 230 is further configured to:

[0184] In the case of abnormality of the target terminal, the static state parameter of the target terminal in the standby state is obtained, and the static state parameter includes at least one of actual optical eye diagram information, actual bit error rate and actual static optical power.

[0185] In an embodiment of the present disclosure, the health state evaluation device 200 of the optical module provided by the present disclosure further comprises:

[0186] The third determining module is configured to determine the abnormal information of the target terminal according to the static state parameter.

[0187] The present disclosure also provides an electronic device, which comprises the health state evaluation device 200 of the optical module provided by any one of the device embodiments described above.

[0188] Alternatively, as shown in the figure, the electronic device 300 comprises a memory 310 and a processor 320, the memory 310 is configured to store computer instructions, and the processor 320 is configured to call the computer instructions from the memory 310 to execute the method according to any one of the method embodiments described above. Figure 3 The present disclosure also provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the method according to any one of the method embodiments described above.

[0189]

[0190] ​The present disclosure can be a system, a method, and / or a computer program product. The computer program product can include a computer readable storage medium (or media) having computer readable program instructions thereon for causing a processor to carry out aspects of the present disclosure.

[0191] The computer readable storage medium can be a tangible device that can retain and store instructions for use by an instruction execution device. The computer readable storage medium can be, for example, but is not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium include the following: a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanically encoded device such as punch-cards or punched tape, a

[0192] The computer readable program instructions described herein can be downloaded to respective computing / processing devices from a computer readable storage medium or to an external computer or external storage device via a network, for example, the Internet, a local area network, a wide area network and / or a wireless network. The network can comprise copper transmission cables, optical transmission fibers, wireless transmission, routers, firewalls, switches, gateway computers and / or edge servers. A network adapter card or network interface in each computing / processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium within the respective computing / processing device.

[0193] Computer readable program instructions for carrying out operations of the present disclosure can be assembler instructions, instruction-set-architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state-setting data, or either source code or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer readable program instructions can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider). In some embodiments, electronic circuitry including, for example, programmable logic circuitry, field-programmable gate array (FPGA), or programmable logic array (PLA) can execute the computer readable program instructions by utilizing state information of the computer readable program instructions to personalize the electronic circuitry, in order to perform aspects of the present disclosure.

[0194] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0195] These computer readable program instructions can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks. These computer readable program instructions can also be stored in a computer readable storage medium that can include random access memory (RAM), read only memory (ROM), electrically erasable programmable read only memory (EEPROM), flash memory or other data storage device. When the computer readable program instructions are loaded into the computer and other programmable data processing apparatus, a series of operational steps are implemented that provide processes such that the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0196] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer, other programmable data processing apparatus, or other device implement the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0197] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer, other programmable data processing apparatus, or other device implement the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0198] Embodiments of the present disclosure have been described above, and the description is intended to be illustrative, and not restrictive, of the disclosed embodiments. Many modifications and variations of the described embodiments are possible, and all such modifications and variations are intended to be within the scope of the described embodiments. The description used herein is intended to best explain the principles of the various embodiments, the practical application, and the best mode of the present disclosure, and to enable others skilled in the art to understand the disclosure, the principles of the various embodiments, and the best mode of the present disclosure, the principles of the various embodiments, and the best mode of the present disclosure. The scope of the present disclosure is defined by the appended claims.

Claims

1. A method of health status assessment of an optical module, characterized by, The method comprises the following steps: collecting historical transmission rates, historical packet loss rates and historical optical powers of a target terminal in a target port of an optical module at a plurality of historical time points, wherein the target terminal is a sending terminal or a receiving terminal in the target port, the optical module is an optical module of a fiber switch in a storage area network providing high-speed data storage services, the historical transmission rates and the historical packet loss rates are determined by reading message statistical information of the fiber switch at the historical time points, and the historical optical powers are determined by reading digital diagnostic function information of the fiber switch at the historical time points; inputting the historical transmission rates, the historical packet loss rates and the historical optical powers into a preset machine learning model to obtain a first optical power interval output by the preset machine learning model, wherein constraint conditions of the preset machine learning model include a maximum allowable packet loss rate and a minimum transmission rate of a training terminal, and the training terminal and the target terminal are both sending terminals or receiving terminals; taking an intersection of a second optical power interval and the first optical power interval as a normal optical power interval, wherein the second optical power interval is preset by a user according to a product manual of the optical module in which the target terminal is located, and the normal optical power interval is used to represent an optical power interval in which the target terminal meets preset transmission rate requirements and packet loss rate requirements; obtaining a current optical power of the target terminal at a current time point; determining that the target terminal is abnormal in a case where the current optical power is located outside the normal optical power interval.

2. The method of claim 1, wherein, The method further comprises the following steps: obtaining a training sample set, wherein the training sample set includes a plurality of training samples, one training sample includes a plurality of groups of training data of a training terminal in an operating state, a normal sample optical power interval corresponding to the plurality of groups of training data, and one group of training data includes a sample transmission rate, a sample packet loss rate and a sample optical power; training the preset machine learning model according to the training sample set.

3. The method of claim 2, wherein, The training of the preset machine learning model according to the training sample set comprises the following steps: obtaining a maximum allowable packet loss rate and a minimum transmission rate of the training terminal; taking the maximum allowable packet loss rate and the minimum transmission rate as constraint conditions of the preset machine learning model, and training the preset machine learning model according to the training sample set.

4. The method of claim 1, wherein, The method further comprises the following steps: periodically performing the steps of collecting the historical transmission rates, the historical packet loss rates and the historical optical powers of the target terminal at the plurality of historical time points to the step of taking the intersection of the second optical power interval and the first optical power interval as the normal optical power interval to update the normal optical power interval.

5. The method of claim 1, wherein, The method further comprises the following steps: in a case where the target terminal is abnormal, obtaining static state parameters of the target terminal in a standby state, wherein the static state parameters include at least one of actual optical eye diagram information, actual bit error rate and actual static optical power; determining abnormal information of the target terminal according to the static state parameters.

6. A health status evaluation device of an optical module, characterized by comprising: The method comprises the following steps: The collection module is configured to collect a historical transmission rate, a historical packet loss rate and a historical optical power of a target terminal in a target port of the optical module at a plurality of historical time points, wherein the target terminal is a sending terminal or a receiving terminal in the target port, the optical module is an optical module of a fiber switch in a storage area network providing high-speed data storage services, the historical transmission rate and the historical packet loss rate are determined by reading message statistical information of the fiber switch at the historical time points, and the historical optical power is determined by reading digital diagnosis function information of the fiber switch at the historical time points. The first determination module is configured to input the historical transmission rate, the historical packet loss rate and the historical optical power into a preset machine learning model to obtain a first optical power interval output by the preset machine learning model, wherein a constraint condition of the preset machine learning model includes a maximum allowed packet loss rate and a minimum transmission rate of a training terminal, the training terminal and the target terminal are both a sending terminal or a receiving terminal, and an intersection of a second optical power interval preset by a user according to a product manual of the optical module in which the target terminal is located and the first optical power interval is taken as a normal optical power interval, wherein the normal optical power interval is used to represent an optical power interval in which the target terminal meets preset transmission rate requirements and packet loss rate requirements. The acquisition module is configured to acquire a current optical power of the target terminal at a current time point. The second determination module is configured to determine that the target terminal is abnormal when the current optical power is located outside the normal optical power interval.

7. An electronic device, comprising: The electronic device includes the health state evaluation device of the optical module. Alternatively, the electronic device includes a memory and a processor, the memory is configured to store computer instructions, and the processor is configured to call the computer instructions from the memory to execute the method in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, A computer program is stored thereon, and the computer program implements the method in any one of claims 1-5 when executed by a processor.

Images