Matrix optical switch array switching method based on fuzzy control algorithm

The matrix optical switch control model is constructed through the fuzzy control algorithm, and the working path is analyzed and the switching strategy is optimized, which solves the problem of difficulty in optimizing the matrix optical switch switching path and improves control efficiency.

CN116382091BActive Publication Date: 2024-11-12HC OPTICAL SCI & TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202310492053.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-05-04
Publication Date
2024-11-12
Estimated Expiration
2043-05-04

AI Technical Summary

Technical Problem

The switching path optimization of existing matrix optical switches is difficult, resulting in inefficient matrix optical switch control.

Method used

The matrix optical switch array switching method based on fuzzy control algorithm is adopted. By obtaining the working path of the matrix optical switch, building a control model, analyzing the path, generating multiple sets of switching strategies, and optimizing the preset switching evaluation model, the optimal switching strategy is obtained. .

Benefits of technology

Improve the switching path optimization capability of matrix optical switches and improve control efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116382091B_ABST
    Figure CN116382091B_ABST
Patent Text Reader

Abstract

The present invention discloses a matrix optical switch array switching method based on a fuzzy control algorithm, which belongs to the field of optical communication technology and solves the problem that the switching path optimization of the existing matrix optical switch is difficult, thereby bringing burden to the matrix optical switch operation and reducing the control efficiency of the matrix optical switch. The switching method specifically includes: obtaining the matrix optical switch working path, constructing a matrix optical switch control model through a fuzzy control algorithm, parsing the matrix optical switch working path, taking the matrix optical switch working path as input, executing the matrix optical switch control model, and obtaining multiple groups of matrix optical switch array switching strategies; obtaining multiple groups of matrix optical switch array switching strategies; the present application constructs a matrix optical switch control model through a fuzzy control algorithm, parses the matrix optical switch working path, and then obtains the optimal matrix optical switch array switching strategy, thereby fully optimizing the switching path of the matrix optical switch and improving the control efficiency of the matrix optical switch.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention belongs to the technical field of optical communication, and in particular relates to a matrix optical switch array switching method based on a fuzzy control algorithm. Background Art

[0002] At present, optical switches with various switching principles and implementation technologies are widely proposed in optical transmission networks. Optical switches with different principles and technologies have different characteristics and are suitable for different occasions. According to different optical switch principles, optical switches can be divided into: mechanical optical switches, thermal optical switches, electro-optical switches and acousto-optic switches. According to the switching medium of optical switches, optical switches can be divided into: free space switching optical switches and waveguide switching optical switches.

[0003] Mechanical optical switches have been developed to a relatively mature stage and can be divided into mobile optical fibers, mobile sleeves, mobile collimators, mobile reflectors, mobile prisms and mobile couplers. Traditional mechanical optical switches have low insertion loss (≤1.5dB); high isolation (>45dB); and are not affected by polarization and wavelength. Its drawback is that the switching time is relatively long, generally in the order of milliseconds. Thermo-optic, electro-optic, and acousto-optic effect optical switches achieve the purpose of switching by changing the waveguide refractive index of the exchange medium.

[0004] At present, the commonly used optical switches are as follows: MEMS optical switch, inkjet bubble optical switch, thermo-optical effect optical switch, liquid crystal optical switch, holographic optical switch, acousto-optic switch, liquid grating optical switch, SOA optical switch, etc. With the development of new technologies, more types of optical switches will appear; however, the switching path optimization of the existing matrix optical switch is difficult, which brings a burden to the work of the matrix optical switch and reduces the control efficiency of the matrix optical switch. Based on this, we propose a matrix optical switch array switching method based on fuzzy control algorithm. Summary of the invention

[0005] The purpose of the present invention is to address the deficiencies of the prior art and provide a matrix optical switch array switching method based on a fuzzy control algorithm, thereby solving the problem that the switching path optimization of the existing matrix optical switch is difficult, thereby bringing a burden to the operation of the matrix optical switch and reducing the control efficiency of the matrix optical switch.

[0006] At present, the commonly used optical switches are as follows: MEMS optical switch, inkjet bubble optical switch, thermo-optical effect optical switch, liquid crystal optical switch, holographic optical switch, acousto-optic switch, liquid grating optical switch, SOA optical switch, etc. With the development of new technologies, more types of optical switches will appear; however, the switching path of the existing matrix optical switch is difficult to optimize, which brings a burden to the matrix optical switch and reduces the control efficiency of the matrix optical switch. Based on this, we propose a matrix optical switch array switching method based on a fuzzy control algorithm, and the switching method includes: obtaining the working path of the matrix optical switch; constructing a matrix optical switch control model through a fuzzy control algorithm, parsing the working path of the matrix optical switch, taking the working path of the matrix optical switch as input, executing the matrix optical switch control model, and obtaining multiple groups of matrix optical switch array switching strategies; obtaining multiple groups of matrix optical switch array switching strategies, and obtaining the optimal matrix optical switch array switching strategy. The present application constructs a matrix optical switch control model through a fuzzy control algorithm, analyzes the working path of the matrix optical switch, and then evaluates multiple groups of matrix optical switch array switching strategies with a preset switching evaluation model to obtain the optimal matrix optical switch array switching strategy, thereby fully optimizing the switching path of the matrix optical switch and improving the control efficiency of the matrix optical switch.

[0007] The present invention is implemented in this way: a matrix optical switch array switching method based on a fuzzy control algorithm comprises:

[0008] Obtain the working path of the matrix optical switch;

[0009] A matrix optical switch control model is constructed by a fuzzy control algorithm, a matrix optical switch working path is analyzed, and the matrix optical switch control model is executed with the matrix optical switch working path as input to obtain multiple groups of matrix optical switch array switching strategies;

[0010] A plurality of matrix optical switch array switching strategies are obtained, and the plurality of matrix optical switch array switching strategies are evaluated using a preset switching evaluation model to obtain an optimal matrix optical switch array switching strategy.

[0011] Preferably, it also includes:

[0012] The optimal matrix optical switch array switching strategy is obtained, the optimal matrix optical switch array switching strategy is executed, a program control instruction for controlling the matrix optical switch is generated, the program control instruction is compiled in real time, and a matrix optical switch operation control electrical signal is obtained.

[0013] Preferably, the method for obtaining the working path of the matrix optical switch specifically includes:

[0014] In response to the power-on instruction, the matrix optical switch is powered on;

[0015] The matrix optical switch generates TCP / IP network instructions and collects the voltage at the BK terminal of the amplifier output terminal at high speed through ADC+DMA.

[0016] Preferably, the method for obtaining a matrix optical switch working path further comprises:

[0017] The switch compilation path and control path are collected separately through TCP / IP.

[0018] Preferably, the construction of the matrix optical switch control model by using a fuzzy control algorithm specifically includes:

[0019] Acquire a preset matrix optical switch data set, wherein the preset matrix optical switch data set includes a matrix code set, a switching response time corresponding to each switch unit in each matrix code set, a switching error rate corresponding to each switch unit in each matrix code set, and a transmission delay corresponding to every two switch units in each matrix code set;

[0020] The matrix optical switch data set is processed to form a fuzzy control rule; specifically, based on the domain conversion relationship, a comprehensive membership of the fuzzy control is formed according to the switching response time of each switch unit corresponding to each matrix code set, the switching error rate of each switch unit corresponding to each matrix code set, and the downward transmission delay of each switch unit corresponding to each matrix code set, and the comprehensive membership is used to characterize the fuzziness of the optical switch array switching strategy;

[0021] The comprehensive membership calculation formula is: U = [(T1 + T2) × (1-e)] - (T 1min +T 2min +T 1max +T 2max -4m) / 2×2n / (T 1max +T 2max +T 1min +T 2min ), where T1 is the switching response time of the switch unit, T2 is the transmission delay of the switch unit to the lower level, e is the switching error rate, T 1min is the minimum switching response time of the switch unit, T 1max is the maximum switching response time of the switch unit, T 2min is the minimum transmission delay of the switch unit to the next level, T 2max is the maximum transmission delay of the switch unit to the lower level, m is the average time consumption, and n is the domain range.

[0022] Step S203, obtaining a matrix optical switch control model according to the comprehensive membership degree calculation formula.

[0023] Preferably, the method for constructing the preset switching evaluation model specifically includes:

[0024] Import the virtual evaluation model template;

[0025] Calling multiple sets of virtual evaluation model plug-ins, reading the multiple sets of virtual evaluation model plug-ins, and converting the virtual evaluation model plug-ins into execution programs to create standard virtual evaluation models;

[0026] The standard virtual evaluation model is adjusted, and the standard data is used as input to perform multiple standard virtual evaluation model trainings. After multiple trainings, a switching evaluation model is obtained.

[0027] Preferably, the training method of the switching evaluation model specifically includes:

[0028] Obtain test result sample data and normalize the test results;

[0029] Extract the path element in the sample data, and determine whether the light variable corresponding to the extracted path element is greater than a preset threshold. If the light variable is greater than the preset threshold, retain the test result sample data; if not, determine that the path element is an invalid path element.

[0030] Preferably, the training method of the switching evaluation model further includes:

[0031] Fusing the path elements and the associated quantities of the valid test result sample data to obtain a first fused element set;

[0032] The noise data of the path elements and the associated quantities are removed to obtain a second fusion element set, and the weight values ​​of the path elements in the first fusion element and the second fusion element are determined respectively to obtain a weight value database.

[0033] Preferably, the training method of the switching evaluation model further includes:

[0034] Taking a single data in the weight value database as input, the switching evaluation model to be trained is trained multiple times to obtain a mature switching evaluation model.

[0035] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0036] The present application constructs a matrix optical switch control model through a fuzzy control algorithm, analyzes the working path of the matrix optical switch, and then evaluates multiple groups of matrix optical switch array switching strategies with a preset switching evaluation model to obtain the optimal matrix optical switch array switching strategy, thereby fully optimizing the switching path of the matrix optical switch and improving the control efficiency of the matrix optical switch. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1It is a schematic diagram of the implementation flow of the matrix optical switch array switching method based on the fuzzy control algorithm provided by the present invention.

[0038] Figure 2 A schematic diagram of the implementation flow of a method for obtaining a working path of a matrix optical switch is shown.

[0039] Figure 3 The schematic diagram of the implementation process of the method of constructing a matrix optical switch control model through a fuzzy control algorithm is shown.

[0040] Figure 4 A schematic diagram of the implementation flow of a preset switching evaluation model construction method is shown.

[0041] Figure 5 A schematic diagram of the implementation process of the switching evaluation model training method is shown.

[0042] Figure 6 The schematic diagram of the structure of the matrix optical switch array switching system based on the fuzzy control algorithm is shown. DETAILED DESCRIPTION

[0043] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of this application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of this application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0044] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0045] At present, the commonly used optical switches are as follows: MEMS optical switch, inkjet bubble optical switch, thermo-optical effect optical switch, liquid crystal optical switch, holographic optical switch, acousto-optic switch, liquid grating optical switch, SOA optical switch, etc. With the development of new technologies, more types of optical switches will appear; however, the switching path of the existing matrix optical switch is difficult to optimize, which brings a burden to the matrix optical switch and reduces the control efficiency of the matrix optical switch. Based on this, we propose a matrix optical switch array switching method based on a fuzzy control algorithm, and the switching method includes: obtaining the working path of the matrix optical switch; constructing a matrix optical switch control model through a fuzzy control algorithm, parsing the working path of the matrix optical switch, taking the working path of the matrix optical switch as input, executing the matrix optical switch control model, and obtaining multiple groups of matrix optical switch array switching strategies; obtaining multiple groups of matrix optical switch array switching strategies, and obtaining the optimal matrix optical switch array switching strategy. The present application constructs a matrix optical switch control model through a fuzzy control algorithm, analyzes the working path of the matrix optical switch, and then evaluates multiple groups of matrix optical switch array switching strategies with a preset switching evaluation model to obtain the optimal matrix optical switch array switching strategy, thereby fully optimizing the switching path of the matrix optical switch and improving the control efficiency of the matrix optical switch.

[0046] The embodiment of the present invention provides a matrix optical switch array switching method based on a fuzzy control algorithm, such as Figure 1 As shown, a schematic diagram of the implementation process of a matrix optical switch array switching method based on a fuzzy control algorithm is shown. The matrix optical switch array switching method based on a fuzzy control algorithm specifically includes:

[0047] Step S10, obtaining a matrix optical switch working path;

[0048] Step S20, constructing a matrix optical switch control model through a fuzzy control algorithm, parsing the matrix optical switch working path, taking the matrix optical switch working path as input, executing the matrix optical switch control model, and obtaining multiple sets of matrix optical switch array switching strategies;

[0049] Step S30, obtaining multiple sets of matrix optical switch array switching strategies, evaluating the multiple sets of matrix optical switch array switching strategies using a preset switching evaluation model, and obtaining an optimal matrix optical switch array switching strategy.

[0050] Step S40, obtaining an optimal matrix optical switch array switching strategy, executing the optimal matrix optical switch array switching strategy, generating program control instructions for controlling the matrix optical switch, and compiling the program control instructions in real time to obtain matrix optical switch operation control electrical signals.

[0051] In this embodiment, the present application constructs a matrix optical switch control model through a fuzzy control algorithm, analyzes the working path of the matrix optical switch, and then evaluates multiple groups of matrix optical switch array switching strategies with a preset switching evaluation model to obtain the optimal matrix optical switch array switching strategy, thereby fully optimizing the switching path of the matrix optical switch and improving the control efficiency of the matrix optical switch.

[0052] The embodiment of the present invention provides a method for obtaining a working path of a matrix optical switch, such as Figure 2 As shown, a schematic diagram of the implementation process of the method for obtaining the working path of the matrix optical switch is shown, and the method for obtaining the working path of the matrix optical switch specifically includes:

[0053] Step S101, in response to a power-on instruction, the matrix optical switch is powered on;

[0054] Step S102, the matrix optical switch generates a TCP / IP network instruction, and collects the voltage of the amplifier output terminal BK at high speed through ADC+DMA;

[0055] Step S103: collecting the switch compilation path and the control path respectively through TCP / IP.

[0056] In this embodiment, the control information chip used by the matrix optical switch is the STM32F103ZET6 chip. The STM32F103ZET6 chip is provided with a cloud interface, and the matrix optical switch supports the LoRaWAN protocol. The module communicates in transparent transmission mode. The user does not need encoding and control, and a UART interface is provided.

[0057] The embodiment of the present invention provides a method for constructing a matrix optical switch control model by using a fuzzy control algorithm, such as Figure 3 As shown, a schematic diagram of the implementation process of a method for constructing a matrix optical switch control model by a fuzzy control algorithm is shown. The method for constructing a matrix optical switch control model by a fuzzy control algorithm specifically includes:

[0058] Step S201, obtaining a preset matrix optical switch data set, wherein the preset matrix optical switch data set includes a matrix code set, a switching response time corresponding to each switch unit in each matrix code set, a switching error rate corresponding to each switch unit in each matrix code set, and a transmission delay corresponding to every two switch units in each matrix code set;

[0059] Step S202, processing the matrix optical switch data set to form a fuzzy control rule; specifically, based on the domain conversion relationship, according to the switching response time of each switch unit corresponding to each matrix code set, the switching error rate of each switch unit corresponding to each matrix code set, and the downward transmission delay of each switch unit corresponding to each matrix code set, a comprehensive membership of the fuzzy control is formed, and the comprehensive membership is used to characterize the deviation of the optical switch array switching strategy;

[0060] The comprehensive membership calculation formula is: U = [(T1 + T2) × (1-e)] - (T 1min +T 2min +T 1max +T 2max -4m) / 2×2n / (T 1max +T 2max +T 1min +T 2min ), where T1 is the switching response time of the switch unit, T2 is the transmission delay of the switch unit to the lower level, e is the switching error rate, T 1min is the minimum switching response time of the switch unit, T 1max is the maximum switching response time of the switch unit, T 2min is the minimum transmission delay of the switch unit to the next level, T 2max is the maximum transmission delay of the switch unit to the lower level, m is the average time consumption, and n is the domain range.

[0061] Step S203, obtaining a matrix optical switch control model according to the comprehensive membership degree calculation formula.

[0062] The embodiment of the present invention provides a method for constructing a preset switching evaluation model, such as Figure 4 As shown, a schematic diagram of the implementation process of a preset switching evaluation model construction method is shown, and the preset switching evaluation model construction method specifically includes:

[0063] Step S301, importing a virtual evaluation model template;

[0064] Step S302, calling multiple sets of virtual evaluation model plug-ins, reading the multiple sets of virtual evaluation model plug-ins, and converting the virtual evaluation model plug-ins into execution programs to create standard virtual evaluation models;

[0065] Step S303, adjusting the standard virtual evaluation model, taking the standard data as input, executing multiple standard virtual evaluation model trainings, and obtaining a switching evaluation model after multiple trainings.

[0066] The embodiment of the present invention provides a training method for switching evaluation models, such as Figure 5As shown, a schematic diagram of the implementation process of the switching evaluation model training method is shown, and the switching evaluation model training method specifically includes:

[0067] Step S401, obtaining test result sample data and normalizing the test results;

[0068] Step S402, extracting the path element in the sample data, and determining whether the light variable corresponding to the extracted path element is greater than a preset threshold value, if the light variable is greater than the preset threshold value, retaining the test result sample data, if not, determining that the path element is an invalid path element;

[0069] Step S403, fusing the path elements and associated quantities of the valid test result sample data to obtain a first fused element set;

[0070] Step S404, removing the noise data of the path elements and the associated quantities to obtain a second fused element set, and determining the weight values ​​of the path elements in the first fused element and the second fused element respectively to obtain a weight value database;

[0071] Step S405 , taking a single data in the weight value database as input, training the handover evaluation model to be trained multiple times to obtain a handover evaluation model that has been trained to perfection.

[0072] In this embodiment, the switching evaluation model is trained with consideration of the background containing more noise. Excessive noise will blur the boundaries between targets, resulting in increased missed detection rate and false alarm rate. Therefore, the present invention adds a supervised attention structure, which includes two modules, a channel attention module and a supervised data set attention module. The structure effectively reduces noise information and enhances the switching evaluation model.

[0073] The embodiment of the present invention provides a matrix optical switch array switching system based on a fuzzy control algorithm, such as Figure 6 FIG. 1 shows a schematic diagram of the structure of a matrix optical switch array switching system based on a fuzzy control algorithm. The matrix optical switch array switching system based on a fuzzy control algorithm specifically includes:

[0074] A working path acquisition module 100 is used to acquire a working path of a matrix optical switch;

[0075] The switching strategy acquisition module 200 constructs a matrix optical switch control model through a fuzzy control algorithm, analyzes the matrix optical switch working path, takes the matrix optical switch working path as input, executes the matrix optical switch control model, and obtains multiple sets of matrix optical switch array switching strategies;

[0076] A strategy evaluation module 300 is used to obtain multiple sets of matrix optical switch array switching strategies, evaluate the multiple sets of matrix optical switch array switching strategies using a preset switching evaluation model, and obtain an optimal matrix optical switch array switching strategy;

[0077] The program control instruction generation module 400 is used to obtain the optimal matrix optical switch array switching strategy, execute the optimal matrix optical switch array switching strategy, generate program control instructions for controlling the matrix optical switch, and compile the program control instructions in real time to obtain the matrix optical switch operation control electrical signal.

[0078] In this embodiment, the present application constructs a matrix optical switch control model through a fuzzy control algorithm, analyzes the working path of the matrix optical switch, and then evaluates multiple groups of matrix optical switch array switching strategies with a preset switching evaluation model to obtain the optimal matrix optical switch array switching strategy, thereby fully optimizing the switching path of the matrix optical switch and improving the control efficiency of the matrix optical switch.

[0079] Another aspect of the embodiments of the present invention further provides a computer-readable storage medium, which stores computer program instructions, and the computer program instructions can be executed by a processor. When the computer program instructions are executed, the method of any of the above embodiments is implemented:

[0080] Obtain the working path of the matrix optical switch;

[0081] A matrix optical switch control model is constructed by a fuzzy control algorithm, a matrix optical switch working path is analyzed, and the matrix optical switch control model is executed with the matrix optical switch working path as input to obtain multiple groups of matrix optical switch array switching strategies;

[0082] Acquire multiple groups of matrix optical switch array switching strategies, evaluate the multiple groups of matrix optical switch array switching strategies using a preset switching evaluation model, and obtain an optimal matrix optical switch array switching strategy;

[0083] The optimal matrix optical switch array switching strategy is obtained, the optimal matrix optical switch array switching strategy is executed, a program control instruction for controlling the matrix optical switch is generated, the program control instruction is compiled in real time, and a matrix optical switch operation control electrical signal is obtained.

[0084] Another aspect of an embodiment of the present invention provides a computer device, including a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the method of any one of the above embodiments is implemented.

[0085] As a non-volatile computer-readable storage medium, the memory can be used to store non-volatile software programs, non-volatile computer executable programs and modules, such as the program instructions / modules corresponding to the matrix optical switch array switching method based on the fuzzy control algorithm in the embodiment of the present application. The memory may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required by at least one function; the data storage area may store data created by the use of the resource monitoring method, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the local module via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0086] Finally, it should be noted that the computer-readable storage medium (e.g., memory) herein may be a volatile memory or a nonvolatile memory, or may include both a volatile memory and a nonvolatile memory. As an example and not by way of limitation, a nonvolatile memory may include a read-only memory (ROM), a programmable ROM (PROM), an electrically programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), or a flash memory. A volatile memory may include a random access memory (RAM), which may act as an external cache memory. As an example and not by way of limitation, RAM may be obtained in a variety of forms, such as synchronous RAM (DRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct Rambus RAM (DRRAM). The storage devices of the disclosed aspects are intended to include, but are not limited to, these and other suitable types of memory.

[0087] In summary, the present invention provides a matrix optical switch array switching method based on a fuzzy control algorithm. The present application constructs a matrix optical switch control model through a fuzzy control algorithm, analyzes the working path of the matrix optical switch, and then evaluates multiple groups of matrix optical switch array switching strategies with a preset switching evaluation model to obtain the optimal matrix optical switch array switching strategy, thereby fully optimizing the switching path of the matrix optical switch and improving the control efficiency of the matrix optical switch.

[0088] It should be noted that, for the above-mentioned embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described order of actions, because according to the present invention, some steps may be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0089] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the above-mentioned units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be in the form of telecommunication or other forms.

[0090] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0091] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the scope of protection of the invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on these embodiments, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in this field can still combine, add, delete or make other adjustments to the features in the various embodiments of the present invention according to the circumstances without conflict, without making creative work, so as to obtain different other technical solutions that do not deviate from the concept of the present invention in essence, and these technical solutions also belong to the scope of protection of the present invention.

Claims

1. A matrix optical switch array switching method based on fuzzy control algorithm, characterized in that: include: Obtain the working path of the matrix optical switch; A matrix optical switch control model is constructed by a fuzzy control algorithm, a matrix optical switch working path is analyzed, and the matrix optical switch control model is executed with the matrix optical switch working path as input to obtain multiple groups of matrix optical switch array switching strategies; Acquire multiple groups of matrix optical switch array switching strategies, evaluate the multiple groups of matrix optical switch array switching strategies using a preset switching evaluation model, and obtain an optimal matrix optical switch array switching strategy; The matrix optical switch control model is constructed by using a fuzzy control algorithm, specifically including: Acquire a preset matrix optical switch data set, wherein the preset matrix optical switch data set includes a matrix code set, a switching response time corresponding to each switch unit in each matrix code set, a switching error rate corresponding to each switch unit in each matrix code set, and a transmission delay corresponding to every two switch units in each matrix code set; The matrix optical switch data set is processed to form a fuzzy control rule; specifically, based on the domain conversion relationship, a comprehensive membership of the fuzzy control is formed according to the switching response time of each switch unit corresponding to each matrix code set, the switching error rate of each switch unit corresponding to each matrix code set, and the downward transmission delay of each switch unit corresponding to each matrix code set, and the comprehensive membership is used to characterize the fuzziness of the optical switch array switching strategy; The comprehensive membership calculation formula is: U = [(T1 + T2) × (1-e)] - (T 1min +T 2min +T 1max +T 2max -4m) / 2×2n / (T 1max +T 2max +T 1min +T 2min ), where T1 is the switching response time of the switch unit, T2 is the transmission delay of the switch unit to the lower level, e is the switching error rate, T 1min is the minimum switching response time of the switch unit, T 1max is the maximum switching response time of the switch unit, T 2min is the minimum transmission delay of the switch unit to the next level, T 2max is the maximum transmission delay of the switch unit to the lower level, m is the average time consumption, and n is the domain range; Step S203, obtaining a matrix optical switch control model according to the comprehensive membership degree calculation formula.

2. The matrix optical switch array switching method based on fuzzy control algorithm as claimed in claim 1, characterized in that: Also includes: The optimal matrix optical switch array switching strategy is obtained, the optimal matrix optical switch array switching strategy is executed, a program control instruction for controlling the matrix optical switch is generated, the program control instruction is compiled in real time, and a matrix optical switch operation control electrical signal is obtained.

3. The matrix optical switch array switching method based on fuzzy control algorithm as claimed in claim 1, characterized in that: The method for obtaining the working path of the matrix optical switch specifically includes: In response to the power-on instruction, the matrix optical switch is powered on; The matrix optical switch generates TCP / IP network instructions and collects the voltage at the BK terminal of the amplifier output terminal at high speed through ADC+DMA.

4. The matrix optical switch array switching method based on fuzzy control algorithm as claimed in claim 3, characterized in that: The method for obtaining the working path of the matrix optical switch specifically further includes: The switch compilation path and control path are collected separately through TCP / IP.

5. The matrix optical switch array switching method based on fuzzy control algorithm as claimed in claim 1, characterized in that: The method for constructing the preset switching evaluation model specifically includes: Import the virtual evaluation model template; Calling multiple sets of virtual evaluation model plug-ins, reading the multiple sets of virtual evaluation model plug-ins, and converting the virtual evaluation model plug-ins into execution programs to create standard virtual evaluation models; The standard virtual evaluation model is adjusted, and the standard data is used as input. Multiple standard virtual evaluation model trainings are performed, and after multiple trainings, a switching evaluation model is obtained.

6. The matrix optical switch array switching method based on fuzzy control algorithm as claimed in claim 5, characterized in that: The training method of the switching evaluation model specifically includes: Obtain test result sample data and normalize the test results; Extract the path element in the sample data, and determine whether the light variable corresponding to the extracted path element is greater than a preset threshold. If the light variable is greater than the preset threshold, retain the test result sample data; if not, determine that the path element is an invalid path element.

7. The matrix optical switch array switching method based on fuzzy control algorithm as claimed in claim 6, characterized in that: The training method of the switching evaluation model specifically includes: Fusing the path elements and the associated quantities of the valid test result sample data to obtain a first fused element set; Remove the noise data of the path elements and the associated quantities to obtain a second fusion element set, determine the weight values ​​of the path elements in the first fusion element and the second fusion element respectively, and obtain a weight value database; Taking a single data in the weight value database as input, the switching evaluation model to be trained is trained multiple times to obtain a mature switching evaluation model.