Method and system for generating and transmitting signal carrying multi-dimensional optical label

Abstract

The invention provides a method and a system for generating and transmitting a signal carrying a multi-dimensional optical label. The method comprises the following steps: a sending end of an optical network generates an original optical signal, generates a modulation signal and converts the modulation signal into a driving current signal; superposing the driving current signal and a working current signal of the semiconductor optical amplifier to obtain a modulation current signal; inputting the original optical signal into a semiconductor optical amplifier, modulating the original optical signal according to the modulation current signal, and generating an optical signal carrying one-dimensional optical label information; the steps of modulation signal generation, conversion and current superposition are repeatedly executed for multiple times, an optical signal which is generated last time and carries corresponding dimension optical label information is input into a semiconductor optical amplifier each time, and the optical signal which carries the corresponding dimension optical label information is modulated according to a modulation current signal obtained each time, and generating an optical signal carrying the multi-dimensional optical label information and sending the optical signal to the switching node. According to the invention, the optical signal carrying the multi-dimensional optical label can be generated on the premise that the original optical signal is not interfered.

Description

[0001] This application is a divisional application of a Chinese patent application with an application date of July 31, 2024, an application number of 202411043309.9, and an invention name of “Optical network operation and maintenance method, signal generation and transmission method and system carrying multi-dimensional optical labels”. Technical Field

[0002] The present invention relates to the field of optical communication technology, and in particular to a network operation and maintenance method for a multi-dimensional optical label, and a signal generation and transmission method and system carrying a multi-dimensional optical label. Background Art

[0003] At present, with the continuous expansion of the scale of optical switches in optical networks, in-band optical labels based on top-modulated signals have attracted much attention due to their flexible spectrum characteristics and no additional bandwidth consumption. Especially in passive elastic optical networks, the increasing spectral granularity has brought challenges to operation and maintenance, and the use of optical labels to indicate bandwidth, center frequency and destination can greatly reduce operation and maintenance costs. Despite the progress made in autonomous maintenance of optical networks, there are still challenges in the rapid generation and identification of optical labels and the autonomous setting of optical paths, which limits the scope of application of optical labels.

[0004] The traditional method of generating optical label signals relies on the digital signal processor (DSP) driver, which requires modification of the signal transmission equipment in the optical network, increasing the complexity and cost of the optical network system. In addition, it relies on the DSP algorithm to identify the optical label. The complex algorithm takes a long time to process, which may introduce additional signal processing delays and affect the real-time performance of the system. In addition, due to the low-frequency characteristics of the top-modulation signal, the signal capture and analysis time may be very long, making it difficult for the switching node to quickly respond to changes in the optical path. In order to realize the active operation and maintenance functions of the optical transmission network, the network controller needs to automatically identify the optical label.

[0005] Moreover, in the field of optical networks, the communication tasks between nodes are becoming increasingly heavy, the amount of data transmission is huge, and the timeliness requirements of data packets vary. Therefore, how to improve the operation and maintenance efficiency of optical networks and reduce operating costs without changing the existing data transmission protocols, improve the utilization efficiency of network resources, and improve service quality at the same time, is particularly critical and challenging in the current network optimization practice. Summary of the invention

[0006] In view of this, the embodiments of the present invention provide a network operation and maintenance method of a multi-dimensional optical label, and a signal generation and transmission method and system carrying a multi-dimensional optical label, so as to eliminate or improve one or more defects existing in the prior art.

[0007] A first aspect of the present invention provides a network operation and maintenance method for a multi-dimensional optical label, the method being applied to each switching node of an optical network, comprising the following steps:

[0008] The switching node of the optical network receives an optical signal carrying multidimensional optical label information generated by a transmitting end or forwarded by other switching nodes, and splits the optical signal carrying multidimensional optical label information into an optical signal carrying multidimensional optical label information with a higher power and an optical signal carrying multidimensional optical label information with a lower power;

[0009] Performing recovery preprocessing on the relatively low-power optical signal carrying the multi-dimensional optical label information to obtain a plurality of recovered one-dimensional optical label signals;

[0010] Inputting the two-dimensional matrix representations of the restored multiple one-dimensional optical label signals into a multi-dimensional optical label recognition model deployed in a switching node for recognition, so that the multi-dimensional optical label recognition model outputs multi-dimensional optical label information, wherein the multi-dimensional optical label recognition model includes a spatial module, an activation function layer, a time module, a splicing module, a fully connected layer, and a normalized exponential function output layer connected in sequence, and the output of the spatial module is also connected to the input of the splicing module;

[0011] A multi-level dynamic feedback queue is constructed according to the output multi-dimensional optical label information, and the higher-power optical signal carrying the multi-dimensional optical label information is forwarded in a wavelength division multiplexing manner according to the multi-level dynamic feedback queue.

[0012] In some embodiments of the present invention, the restoring preprocessing of the lower-power optical signal carrying the multi-dimensional optical label information to obtain the restored multiple one-dimensional optical label signals includes:

[0013] The optical signal with lower power carrying multi-dimensional optical label information is sequentially subjected to photoelectric conversion, analog-to-digital conversion and fast Fourier transform to obtain multiple digital electrical signals carrying one-dimensional optical label information;

[0014] Obtaining corresponding multiple carrier signals from the multiple digital electrical signals carrying the one-dimensional optical tag information by using the Costas ring method;

[0015] The multiple carrier signals are subjected to carrier synchronization, clock synchronization and demodulation in sequence to obtain multiple restored one-dimensional optical label signals.

[0016] In some embodiments of the present invention, the spatial module includes a multi-layer graph convolutional neural network, which is used to extract the spatial features of the restored multiple one-dimensional optical tag signals and output multiple two-dimensional matrices and multiple one-dimensional vectors containing corresponding spatial features;

[0017] The activation function layer is used to filter the element values ​​in a plurality of two-dimensional matrices containing corresponding spatial features;

[0018] The time module is used to extract the time features of the filtered multiple two-dimensional matrices containing corresponding spatial features, and output multiple one-dimensional vectors containing corresponding time features;

[0019] The splicing module is used to splice a plurality of one-dimensional vectors containing corresponding spatial features and a plurality of one-dimensional vectors containing corresponding time features respectively;

[0020] The fully connected layer is used to integrate the spatial features and temporal features of the concatenated multiple one-dimensional vectors and output multiple global features;

[0021] The normalized exponential function output layer is used to classify multiple global features and output multi-dimensional light label information.

[0022] In some embodiments of the present invention, before inputting the two-dimensional matrix representation of the restored multiple one-dimensional optical label signals into a multi-dimensional optical label identification model deployed in the switching node, the method further includes:

[0023] The restored multiple one-dimensional optical tag signals are respectively regarded as multiple two-dimensional matrix images composed of multiple pixel points, and each two-dimensional matrix image is divided into multiple pixel blocks;

[0024] Constructing a feature matrix based on the multiple pixel blocks, wherein the element value in the feature matrix is ​​the average value of the RGB value of each pixel point in the corresponding pixel block, and constructing an adjacency matrix based on the adjacent relationship between the multiple pixel blocks;

[0025] The plurality of feature matrices are normalized to obtain a plurality of normalized feature matrices, wherein the two-dimensional matrix representation includes the normalized feature matrices and corresponding adjacency matrices.

[0026] In some embodiments of the present invention, the multi-dimensional optical label information includes wavelength information and priority information corresponding to the original optical signal generated by the transmitting end.

[0027] In some embodiments of the present invention, the step of constructing a multi-level dynamic feedback queue according to the output multi-dimensional optical tag information includes:

[0028] Dividing a plurality of optical signals of different wavelengths into a plurality of first groups according to the wavelength information;

[0029] In each first group, a first-level queue is constructed in descending order of priority according to priority information carried by different optical signals of the same wavelength, wherein different optical signals of the same priority form a second group in the first-level queue;

[0030] In each second group, a first-in first-out queue is constructed as a secondary queue according to the order in which different optical signals of the same priority level arrive at the switching node;

[0031] If the length, waiting time and service quality of the queue all reach corresponding preset thresholds, dynamically adjust and increase the priority of the queue;

[0032] If an optical signal with a higher priority than the optical signal being transmitted is received during the forwarding process, the transmission of the current queue is stopped until the optical signal with a higher priority than the optical signal being transmitted is forwarded.

[0033] A second aspect of the present invention provides a method for generating and transmitting a signal carrying a multi-dimensional optical label, the method being applied to a transmitting end of an optical network, comprising the following steps:

[0034] The transmitting end of the optical network generates an original optical signal through a high-speed transceiver, and drives a digital-to-analog conversion module through a programmable logic array to generate a modulated signal, wherein the frequency of the modulated signal is lower than the frequency of the original optical signal;

[0035] Converting the modulation signal into a driving current signal through a voltage-controlled current source circuit;

[0036] The driving current signal and the working current signal of the semiconductor optical amplifier are superimposed by a semiconductor optical amplifier to obtain a modulated current signal;

[0037] Inputting the original optical signal into the semiconductor optical amplifier, and fine-tuning the original optical signal according to the modulation current signal through the semiconductor optical amplifier to generate an optical signal carrying one-dimensional optical label information;

[0038] Repeat the steps of generating, converting and superimposing the modulation signal multiple times, inputting the optical signal carrying the corresponding dimension optical label information generated last time into the semiconductor optical amplifier each time, and fine-tuning the optical signal carrying the corresponding dimension optical label information by the semiconductor optical amplifier according to the modulation current signal obtained each time, so as to generate an optical signal carrying multi-dimensional optical label information, wherein the frequency of the modulation signal generated each time is different;

[0039] The optical signal carrying the multi-dimensional optical label information is sent to a switching node of the optical network.

[0040] In some embodiments of the present invention, the method further comprises: connecting a temperature controller via the semiconductor optical amplifier to suppress temperature drift of the current signal.

[0041] In some embodiments of the present invention, after converting the modulation signal into a driving current signal by a voltage-controlled current source circuit, the method further includes:

[0042] Converting the drive current signal into a differential enable signal through a driver / receiver chip;

[0043] The differential enable signal and the working current signal of the semiconductor optical amplifier are superimposed through the semiconductor optical amplifier to obtain a modulated current signal.

[0044] In some embodiments of the present invention, the multi-dimensional optical label information includes wavelength information and priority information corresponding to the original optical signal generated by the transmitting end.

[0045] A third aspect of the present invention provides a network operation and maintenance system for a multi-dimensional optical label, which is deployed in each switching node in an optical network and includes: an optical coupler, an optical label signal recovery module, a processor, a memory, and computer instructions stored in the memory.

[0046] The optical coupler is used to receive an optical signal carrying multidimensional optical label information generated by a transmitting end or forwarded by other switching nodes, and split the optical signal carrying multidimensional optical label information into an optical signal carrying multidimensional optical label information with a higher power and an optical signal carrying multidimensional optical label information with a lower power;

[0047] The optical label signal recovery module includes a photodiode, a transimpedance amplifier, an analog-to-digital converter, a fast Fourier transform circuit, a Costas loop circuit, a carrier synchronization module, a clock synchronization module and a demodulation module connected in sequence, and is used to recover and pre-process the lower-power optical signal carrying multi-dimensional optical label information to obtain a plurality of recovered one-dimensional optical label signals;

[0048] The processor is used to execute the computer instructions. When the computer instructions are executed, the system implements the following steps in the network operation and maintenance method of the multi-dimensional optical tag described in the first aspect:

[0049] Inputting the two-dimensional matrix representations of the restored multiple one-dimensional optical label signals into a multi-dimensional optical label recognition model deployed in a switching node for recognition, so that the multi-dimensional optical label recognition model outputs multi-dimensional optical label information, wherein the multi-dimensional optical label recognition model includes a spatial module, an activation function layer, a time module, a splicing module, a fully connected layer, and a normalized exponential function output layer connected in sequence, and the output of the spatial module is also connected to the input of the splicing module;

[0050] A multi-level dynamic feedback queue is constructed according to the output multi-dimensional optical label information, and the higher-power optical signal carrying the multi-dimensional optical label information is forwarded in a wavelength division multiplexing manner according to the multi-level dynamic feedback queue.

[0051] A fourth aspect of the present invention provides a signal generation and transmission system carrying a multi-dimensional optical tag, which is deployed at the transmitting end of an optical network and includes: a high-speed transceiver, a programmable logic array, a digital-to-analog conversion module, a voltage-controlled current source circuit, and a semiconductor optical amplifier.

[0052] The high-speed transceiver is used to generate an original optical signal;

[0053] The programmable logic array is used to drive the digital-to-analog conversion module to generate a modulation signal multiple times, the frequency of the modulation signal is lower than the frequency of the original optical signal, and the frequency of the modulation signal generated each time is different;

[0054] The voltage-controlled current source circuit is used to convert the modulation signal generated each time into a driving current signal;

[0055] The semiconductor optical amplifier is used to superimpose the driving current signal obtained each time and the working current signal of the semiconductor optical amplifier to obtain the modulated current signal multiple times; receive the original optical signal, modulate the original optical signal according to the modulated current signal obtained for the first time, and generate an optical signal carrying one-dimensional optical label information; and is also used to receive the optical signal carrying the corresponding dimensional optical label information generated each time multiple times, modulate the optical signal carrying the corresponding dimensional optical label information according to the modulated current signal obtained each time, generate an optical signal carrying multi-dimensional optical label information, and send the optical signal carrying the multi-dimensional optical label information to the switching node of the optical network.

[0056] In some embodiments of the present invention, the system further comprises: a driver / receiver chip, the driver / receiver chip being used to convert the driving current signal obtained each time into a differential enable signal;

[0057] The semiconductor optical amplifier is also used to superimpose the differential enable signal obtained each time and the working current signal of the semiconductor optical amplifier to obtain the modulated current signal multiple times.

[0058] In some embodiments of the present invention, the system further comprises: a temperature controller, which is connected to the semiconductor optical amplifier and is used to suppress temperature drift of the current signal.

[0059] In some embodiments of the present invention, the multi-dimensional optical label information includes wavelength information and priority information corresponding to the original optical signal generated by the transmitting end.

[0060] A fifth aspect of the present invention provides an electronic device, which is deployed at each switching node in an optical network, comprising: a processor, a memory, and computer instructions stored in the memory, wherein the processor is used to execute the computer instructions, and when the computer instructions are executed, the system implements the following steps of the network operation and maintenance method of the multi-dimensional optical label described in the first aspect:

[0061] Input the two-dimensional matrix representation of the restored multiple one-dimensional optical label signals into the multidimensional optical label recognition model deployed in the switching node for recognition, so that the multidimensional optical label recognition model outputs multidimensional optical label information, the multidimensional optical label recognition model includes a spatial module, an activation function layer, a time module, a splicing module, a fully connected layer and a normalized exponential function output layer connected in sequence, and the output of the spatial module is also connected to the input of the splicing module; wherein the restored multiple one-dimensional optical label signals are obtained by restoring and preprocessing the optical signal carrying the multidimensional optical label information with a lower power, and the optical signal carrying the multidimensional optical label information generated by the sending end or forwarded by other switching nodes of the optical network is received by the switching node, and the optical signal carrying the multidimensional optical label information is shunted to obtain a higher-power optical signal carrying the multidimensional optical label information and a lower-power optical signal carrying the multidimensional optical label information;

[0062] A multi-level dynamic feedback queue is constructed according to the output multi-dimensional optical label information, and the higher-power optical signal carrying the multi-dimensional optical label information is forwarded in a wavelength division multiplexing manner according to the multi-level dynamic feedback queue.

[0063] A sixth aspect of the present invention provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the following steps of the network operation and maintenance method of the multi-dimensional optical tag described in the first aspect are implemented:

[0064] Input the two-dimensional matrix representation of the restored multiple one-dimensional optical label signals into the multidimensional optical label recognition model deployed in the switching node for recognition, so that the multidimensional optical label recognition model outputs multidimensional optical label information, the multidimensional optical label recognition model includes a spatial module, an activation function layer, a time module, a splicing module, a fully connected layer and a normalized exponential function output layer connected in sequence, and the output of the spatial module is also connected to the input of the splicing module; wherein the restored multiple one-dimensional optical label signals are obtained by restoring and preprocessing the optical signal carrying the multidimensional optical label information with a lower power, and the optical signal carrying the multidimensional optical label information generated by the sending end or forwarded by other switching nodes of the optical network is received by the switching node, and the optical signal carrying the multidimensional optical label information is shunted to obtain a higher-power optical signal carrying the multidimensional optical label information and a lower-power optical signal carrying the multidimensional optical label information;

[0065] A multi-level dynamic feedback queue is constructed according to the output multi-dimensional optical label information, and the higher-power optical signal carrying the multi-dimensional optical label information is forwarded in a wavelength division multiplexing manner according to the multi-level dynamic feedback queue.

[0066] A seventh aspect of the present invention provides a computer program product, the computer program product comprising computer instructions, which, when executed by a processor, implement the following steps of the network operation and maintenance method of the multi-dimensional optical tag described in the first aspect:

[0067] Input the two-dimensional matrix representation of the restored multiple one-dimensional optical label signals into the multidimensional optical label recognition model deployed in the switching node for recognition, so that the multidimensional optical label recognition model outputs multidimensional optical label information, the multidimensional optical label recognition model includes a spatial module, an activation function layer, a time module, a splicing module, a fully connected layer and a normalized exponential function output layer connected in sequence, and the output of the spatial module is also connected to the input of the splicing module; wherein the restored multiple one-dimensional optical label signals are obtained by restoring and preprocessing the optical signal carrying the multidimensional optical label information with a lower power, and the optical signal carrying the multidimensional optical label information generated by the sending end or forwarded by other switching nodes of the optical network is received by the switching node, and the optical signal carrying the multidimensional optical label information is shunted to obtain a higher-power optical signal carrying the multidimensional optical label information and a lower-power optical signal carrying the multidimensional optical label information;

[0068] A multi-level dynamic feedback queue is constructed according to the output multi-dimensional optical label information, and the higher-power optical signal carrying the multi-dimensional optical label information is forwarded in a wavelength division multiplexing manner according to the multi-level dynamic feedback queue.

[0069] The network operation and maintenance method of the multidimensional optical label of the present invention, the signal generation and transmission method and system carrying the multidimensional optical label, the network operation and maintenance method can receive the optical signal carrying the multidimensional optical label through each switching node in the optical network and perform diversion, separate the multidimensional optical label signal carried from the optical signal with lower power after diversion, and input the separated multidimensional optical label signal into the improved GraphFormer model for rapid and accurate identification, finally construct a multi-level dynamic feedback queue according to the identified multidimensional optical label result, and efficiently forward the optical signal carrying the multidimensional optical label with higher power after diversion according to the queue and optical fiber wavelength division multiplexing technology. This scheme not only improves the optical path utilization efficiency of the entire optical network, saves link resources, and ensures the timeliness of data, but also greatly reduces the network operation and maintenance cost without occupying additional bandwidth of the optical network and without changing the original transmission protocol of the network. The method can also be extended to the transmission of optical signals carrying useful information of other dimensions or more dimensions.

[0070] Additional advantages, purposes, and features of the present invention will be described in part in the following description, and will become apparent to those skilled in the art after studying the following, or may be learned from the practice of the present invention. The purposes and other advantages of the present invention may be achieved and obtained by the structures specifically indicated in the specification and the accompanying drawings.

[0071] Those skilled in the art will appreciate that the objectives and advantages that can be achieved with the present invention are not limited to the above specific description, and the above and other objectives that can be achieved by the present invention will be more clearly understood from the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] The drawings described herein are used to provide a further understanding of the present invention, constitute a part of this application, and do not constitute a limitation of the present invention.

[0073] Figure 1 A schematic diagram of a flow chart of a method for generating and transmitting a signal carrying a multi-dimensional optical tag in one embodiment of the present invention;

[0074] Figure 2 A schematic diagram of an optical signal carrying a multi-dimensional optical tag generated in one embodiment of the present invention;

[0075] Figure 3 A schematic diagram of a flow chart of a network operation and maintenance method of a multi-dimensional optical tag in one embodiment of the present invention;

[0076] Figure 4 It is a structural diagram of an improved GraphFormer model in one embodiment of the present invention;

[0077] Figure 5 The figure is a schematic diagram of a wavelength- and priority-based multi-level dynamic feedback queue constructed in one embodiment of the present invention. DETAILED DESCRIPTION

[0078] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the embodiments and the accompanying drawings. Here, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0079] It should also be noted that, in order to avoid obscuring the present invention due to unnecessary details, only structures and / or processing steps closely related to the solutions according to the present invention are shown in the accompanying drawings, while other details that are not closely related to the present invention are omitted.

[0080] It should be emphasized that the term “include / comprises” when used herein refers to the presence of features, elements, steps or components, but does not exclude the presence or addition of one or more other features, elements, steps or components.

[0081] It should also be noted that, unless otherwise specified, the term “connection” herein may refer not only to a direct connection but also to an indirect connection involving an intermediate.

[0082] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. In the accompanying drawings, the same reference numerals represent the same or similar components, or the same or similar steps.

[0083] In view of the operation and maintenance efficiency and cost issues brought about by the continuous expansion of the scale of optical switches in optical networks, and the challenges caused by the increase in spectrum granularity in passive elastic optical networks, the purpose of the present invention is to provide a network operation and maintenance method for multidimensional optical labels, a signal generation and transmission method carrying multidimensional optical labels, and a corresponding method system. The method and system focus on deploying a signal generation system or an optical label modulation system carrying a multidimensional optical label at the transmitting end of the optical network without changing the existing network transmission protocol, pre-multi-modulating the original optical signal to generate a multidimensional optical label, and superimposing the generated multidimensional optical label on the original optical signal, and deploying a deep recognition model of the multidimensional optical label at each switching node of the optical network, which can quickly and intelligently identify and process the multidimensional optical label information, thereby realizing data transmission based on optical label information and wavelength division multiplexing, for example, the optical fiber link utilization and the priority of the optical signal can be combined to complete the differentiated processing of data packets of different importance.

[0084] Since the traditional signal generation method carrying optical labels has the problem of superimposing multi-dimensional optical labels, which makes the optical network system more complicated and increases the network maintenance cost, and the multi-dimensional optical labels superimposed by this method make the DSP algorithm relied on unable to quickly and automatically identify the multi-dimensional optical labels, and may also introduce additional signal processing delays, affecting the real-time performance of the system, the signal generation and transmission method and system carrying multi-dimensional optical labels provided in the embodiments of the present invention do not require any modification to the sending end equipment of the optical network, and completely overcome the above-mentioned defects.

[0085] Figure 1 FIG. 1 is a flow chart of a method for generating and transmitting a signal carrying a multi-dimensional optical tag according to an embodiment of the present invention. Figure 1 As shown, an embodiment of the present invention provides a method for generating and transmitting a signal carrying a multi-dimensional optical label, which is applied to a transmitting end of an optical network, and includes the following steps:

[0086] Step S110, the transmitting end of the optical network generates an original optical signal through a high-speed transceiver, and drives a digital-to-analog conversion module through a programmable logic array to generate a modulated signal, wherein the frequency of the modulated signal is lower than the frequency of the original optical signal.

[0087] In this embodiment, the original data stream transmitted in the optical network is generated by modulation of a high-speed transceiver, and the original high-speed optical signal is generated by the high-speed transceiver. Therefore, when superimposing the optical label, it is a key consideration to avoid any interference with the normal forwarding of the superimposed signal. In order to solve this problem, since the field programmable logic array (FPGA) can achieve high-precision and low-latency signal generation and processing, it is ensured that the signal generation carrying the multi-dimensional optical label will not introduce additional delay or noise, thereby not interfering with the normal transmission of the high-speed data stream. In this embodiment, the programmable logic array is used to drive the digital-to-analog conversion module to generate a low-speed modulation signal.

[0088] It should be noted that in the field of communications, optical labels are also called pilot tones, low-frequency perturbation signals or overmodulated signals. They refer to generating a low-speed optical path-associated signal by means of top modulation, and loading it on the main signal of the wavelength channel to realize wavelength monitoring and transmission of optical path-associated overhead, etc., so they can also be called top modulation signals. If the wavelength information is to be carried in the original optical signal, the top modulation signal can be loaded on the wavelength signal of the optical transmitter in the wavelength division multiplexing system, and top modulation signals of different frequencies are superimposed on the original optical signals of each different wavelength. The receiving end can obtain the wavelength information by detecting the frequency of the top modulation signal. It can be seen that the low-speed modulation signal generated in the embodiment of the present invention is the optical label that the transmitter wants to carry, which can be a low-speed sinusoidal signal with adjustable frequency and peak-to-peak value, and the frequency range is 500KHz to 100MHz. High-speed optical signals refer to information signals that are transmitted at extremely high speeds through optical waves (usually lasers) using optical fibers as transmission media. The high-speed optical signals generated by high-speed transceivers use the characteristics of extremely fast light speed (close to the speed of light in a vacuum), high frequency, and large bandwidth to achieve efficient, fast, and long-distance transmission of data. The frequency of the low-speed modulation signal is lower than the frequency of the original high-speed optical signal.

[0089] Step S120: converting the modulation signal into a driving current signal through a voltage-controlled current source circuit.

[0090] In this embodiment, since the current value allowed to be input by the SOA has an upper limit, it is necessary to convert the low-speed modulation signal generated in step S110 into a driving current suitable for the SOA. The voltage-controlled current source circuit uses a voltage-controlled current source circuit built with TL431P, which can convert the sinusoidal voltage signal with a peak value of 5 volts output by the digital-to-analog conversion module into a sinusoidal current signal with a fluctuation of 2 mA. In other embodiments, other types of chips and voltage-controlled current source circuits of other structures can also be used to implement this function.

[0091] Step S130: superimpose the driving current signal and the working current signal of the semiconductor optical amplifier through the semiconductor optical amplifier to obtain a modulated current signal.

[0092] In this step, the current signal output by the voltage-controlled current source is superimposed on the direct current of the SOA to obtain the modulated working current of the SOA, so that the SOA can subsequently modulate the intensity of the original high-speed optical signal without affecting the transmission of the original high-speed optical signal.

[0093] Step S140: input the original optical signal into a semiconductor optical amplifier, and fine-tune the original optical signal according to the modulation current signal through the semiconductor optical amplifier to generate an optical signal carrying one-dimensional optical label information.

[0094] In this step, the semiconductor optical amplifier (SOA) receives the original high-speed optical signal generated by the high-speed transceiver at the input end, and slightly modulates the intensity of the input original high-speed optical signal by modulating the working current of the SOA. This modulation does not significantly change the characteristics of the original optical signal, but can introduce a low-speed modulated signal, i.e., an optical label, into the original optical signal. Due to the optical gain characteristics of the SOA, modulating the working current of the SOA generates an optical signal containing a low-speed modulated signal at the output end of the SOA, i.e., the optical signal contains the information of the first-dimensional optical label while maintaining the main characteristics of the original high-speed optical signal.

[0095] The first-dimensional optical label information may be wavelength information of the original optical signal, or may be any other label information.

[0096] Step S150, repeatedly execute the steps of generating, converting and superimposing the modulation signal, each time inputting the optical signal carrying the corresponding dimension optical label information generated last time into the semiconductor optical amplifier, and fine-tuning the optical signal carrying the corresponding dimension optical label information by the semiconductor optical amplifier according to the modulation current signal obtained each time, to generate an optical signal carrying multi-dimensional optical label information, and the frequency of the modulation signal generated each time is different.

[0097] In this step, after the step of generating the low-speed modulation signal in step S110 and steps S120 to S130 are executed for the second time, the frequency of the low-speed modulation signal generated for the second time is different from that of the low-speed modulation signal generated for the first time, the optical signal carrying the one-dimensional optical label information generated for the first time is input into the input end of the SOA, and the intensity of the optical signal carrying the one-dimensional optical label information is fine-tuned by the modulation current signal generated after the second execution of steps S120 to S130, so as to generate an optical signal carrying the two-dimensional optical label information, thereby realizing the superposition of the two-dimensional optical label information on the original optical signal. The third, fourth and even more execution processes are similar, and through multiple executions, an optical signal carrying the multi-dimensional optical label information is finally generated. In this process, the modulation signal considers multiple frequencies from low frequency to high frequency to realize multiple modulation of the original optical signal.

[0098] In a specific example, the optical signal carrying the two-dimensional optical label information is superimposed with the optical label information representing the original optical signal wavelength, and the optical label information representing the priority of the original optical signal (the service priority transmitted in the optical network) is superimposed again, that is, the superimposed second-dimensional optical label information is the service priority information of the original optical signal transmitted in the optical network, and can also be represented as other information according to specific needs, such as the service type transmitted by the original optical signal. In the optical signal carrying the two-dimensional optical label information obtained in this specific example, the formula of the two-dimensional optical label signal is as follows:

[0099]

[0100] Among them, f1 and f2 represent the frequencies of the first-dimensional optical label signal (indicating the wavelength carried) and the second-dimensional optical label signal (indicating the service priority carried), respectively, and the frequencies are both between 500KHz and 100MHz. In order for the receiving end to correctly receive and identify the two optical label signals, the interval between f1 and f2 should generally be greater than 30MHz, and f1>f2. The optical signal carrying the two-dimensional optical label information obtained by the two modulations is as follows: Figure 2 shown.

[0101] Step S160: sending the optical signal carrying the multi-dimensional optical label information to the switching nodes of the optical network, so that each switching node in the optical network receives the optical signal carrying the multi-dimensional optical label information and processes the signal.

[0102] In another embodiment of the present invention, after the modulation signal is converted into a driving current signal by the voltage-controlled current source circuit, the signal generation and transmission method carrying the multi-dimensional optical tag further includes the following steps:

[0103] Step S230: converting the driving current signal into a differential enable signal through the driver / receiver chip.

[0104] In this embodiment, the driver / receiver chip selects the DS90LV019TMLVDS chip, the input of the DS90LV019TMLVDS chip is high level, and the output is a pair of differential signals of LVDS level standard. By converting the drive current signal into a differential enable signal through this chip, the anti-interference of the signal can be improved to ensure the stability of signal transmission.

[0105] Step S240: superimpose the differential enable signal and the working current signal of the semiconductor optical amplifier through the semiconductor optical amplifier to obtain a modulated current signal.

[0106] The other steps in this embodiment are the same as steps S110, S120, S140 and S150, and are not described in detail. In step S240, the differential enable signal is added to the working current of the SOA, so that the SOA can be properly modulated.

[0107] In another embodiment of the present invention, the method for generating and transmitting a signal carrying a multi-dimensional optical tag further includes the following steps: connecting a temperature controller via a semiconductor optical amplifier to suppress temperature drift of the current signal.

[0108] In this embodiment, the HTC1500 chip is used as a temperature controller, which can prevent the drift of the SOA working current and ensure the stability of the system and the accuracy of the optical signal carrying the optical tag.

[0109] Through the above steps, different from the traditional method, the signal generation and transmission method carrying multi-dimensional optical labels in each embodiment of the present invention adopts a semiconductor optical amplifier (SOA) as an optical label modulation device, and realizes the multi-dimensional superposition of optical labels, which can generate and load optical signals carrying multi-dimensional optical label information without interfering with the original high-speed optical signal. And by sending the optical signal, the receiving end (the switching node in the optical network) can realize the rapid automatic recognition of the multi-dimensional optical label information superimposed here. The wavelength of the transmitted signal can also be superimposed on the transmitted signal as the first-dimensional optical label, and the corresponding priority is set in advance for different signals at the transmitting end, and the priority is also superimposed on the transmitted signal as the second-dimensional optical label, that is, the wavelength of the transmitted signal and the task priority information are embedded in the data packet transmitted in the optical network, so as to realize the differentiated processing of data packets of different importance.

[0110] Figure 3 FIG. 1 is a flow chart of a network operation and maintenance method of a multi-dimensional optical tag in one embodiment of the present invention. Figure 3 As shown, the network operation and maintenance method of the multi-dimensional optical label of this embodiment is applied to each switching node of the optical network, and includes the following steps:

[0111] In step S310, a switching node of an optical network receives an optical signal carrying multidimensional optical label information generated by a transmitting end or forwarded by other switching nodes, and splits the optical signal carrying the multidimensional optical label information into a higher-power optical signal carrying the multidimensional optical label information and a lower-power optical signal carrying the multidimensional optical label information.

[0112] In this step, when the optical signal carrying multi-dimensional optical label information sent by the transmitting end or forwarded by the switching node arrives at the switching node, the optical signal is divided into two parts according to the signal power by the optical coupler deployed at the switching node, and the power ratio of the two parts of the optical signal is approximately 1:9, and the optical signal with higher power in the two parts of the optical signal is sent to the server deployed at the switching node to wait for the switching node to receive the identified multi-dimensional optical label information and then be forwarded by the switching node, and the optical signal with lower power is sent to the host of the deep recognition model of the multi-dimensional optical label deployed at the switching node, and is used to identify the multi-dimensional optical label information, thereby realizing signal diversion. If the above power ratio is too large, it will affect the reception of the optical signal. On the contrary, if the ratio is too small, it will affect the automatic recognition of the multi-dimensional optical label.

[0113] In one embodiment of the present invention, the multi-dimensional optical label information includes wavelength information and priority information corresponding to the original optical signal generated by the transmitting end.

[0114] Step S320 , performing recovery preprocessing on the relatively low-power optical signal carrying the multi-dimensional optical label information to obtain a plurality of restored one-dimensional optical label signals.

[0115] In this step, before being recognized by the deep recognition model of the multidimensional optical label, the multidimensional optical label information carried needs to be recovered from the lower-power optical signal carrying the multidimensional optical label information, so as to achieve accurate recognition of the multidimensional optical label. In one embodiment, the recovered multiple one-dimensional optical label signals are signals respectively representing the wavelength information and priority information to be carried.

[0116] In one embodiment of the present invention, a low-power optical signal carrying multi-dimensional optical label information is restored and pre-processed to obtain a plurality of restored one-dimensional optical label signals, including the following steps:

[0117] Step S321 , the optical signal with lower power carrying multi-dimensional optical label information is subjected to photoelectric conversion, analog-to-digital conversion and fast Fourier transform in sequence to obtain multiple digital electrical signals carrying one-dimensional optical label information.

[0118] In this embodiment, a low-power optical signal carrying multi-dimensional optical label information is converted into a modulated analog electrical signal by a low-speed photodiode (APD) and a transimpedance amplifier (TIA) deployed at the switch point, and the analog electrical signal is converted into a digital electrical signal by an analog-to-digital converter with a sampling frequency of 250MHz. The sampling output bit width of the analog-to-digital converter is 14 bits, and then the digital electrical signal is subjected to a fast Fourier transform by a fast Fourier transform circuit to obtain multiple digital electrical signals carrying one-dimensional optical label information. In a specific example, the fast Fourier transform circuit is constructed using internal resources such as FPGA logic gates and lookup tables. The circuit input is a digital electrical signal after analog-to-digital conversion, and the output is a discrete spectrum of the digital electrical signal. By finding the coordinates n1 and n2 of the two largest values ​​of the spectrum, n1>n2, the signal frequency of the two-dimensional optical label containing the wavelength information and priority information carried can be obtained, as follows:

[0119]

[0120] Among them, f3 and f4 are two signal frequencies of the two-dimensional optical tag. The two-dimensional optical tag can be understood as the first-dimensional optical tag in the two-dimensional optical tag × the second-dimensional optical tag in the two-dimensional optical tag. s =250·M(Hz), M is the number of sampling points of the fast Fourier transform. According to f3=f1+f2, f4=f1-f2, we can get the signal frequencies of the first dimension optical label (wavelength) and the second dimension optical label (priority) in the two-dimensional optical label are respectively

[0121] Step S322: Obtain corresponding multiple carrier signals from multiple digital electrical signals carrying one-dimensional optical label information by using the Costas cycle method.

[0122] This step is implemented through a Costas loop circuit. Specifically, the lookup table, logic gates and other resources inside the programmable gate array FPGA are converted into corresponding hardware circuits through hardware description (RTL) language programming, comprehensive layout and routing, timing optimization and other operations. The hardware circuit is used to build the above-mentioned Costas loop circuit.

[0123] Step S323, the multiple carrier signals are subjected to carrier synchronization, clock synchronization and demodulation in sequence to obtain multiple restored one-dimensional optical label signals.

[0124] Through the above steps, the multidimensional optical tag information can be recovered from the lower-power optical signal carrying the multidimensional optical tag information, and the multidimensional optical tag's deep recognition model can be used to accurately recognize and classify the multidimensional optical tag.

[0125] Step S330, input the two-dimensional matrix representation of the restored multiple one-dimensional optical label signals into the multidimensional optical label recognition model deployed in the switching node for recognition, so that the multidimensional optical label recognition model outputs multidimensional optical label information. The multidimensional optical label recognition model includes a spatial module, an activation function layer, a time module, a splicing module, a fully connected layer and a normalized exponential function output layer connected in sequence, and the output of the spatial module is also connected to the input of the splicing module.

[0126] In this step, the multi-dimensional optical label recognition model is an improved GraphFormer model. The improved GraphFormer model is used to recognize the restored multi-dimensional optical label information. The improved GraphFormer model is deployed in the host at the switching node.

[0127] Specifically, Figure 4 As shown, the spatial module includes a multi-layer graph convolutional neural network (GCN), which is used to extract the spatial features of the restored multiple one-dimensional light tag signals, and output multiple two-dimensional matrices and multiple one-dimensional vectors containing corresponding spatial features; the activation function layer is used to filter the element values ​​in the multiple two-dimensional matrices containing corresponding spatial features; the time module includes multiple Transformer layers, each Transformer layer includes an embedding layer, a first linear layer, a multi-head attention layer, an attention splicing layer, and a second linear layer connected in sequence, which is used to extract the time features of the filtered multiple two-dimensional matrices containing corresponding spatial features, and output multiple one-dimensional vectors containing corresponding time features; the splicing module is used to splice the multiple one-dimensional vectors containing corresponding spatial features and the multiple one-dimensional vectors containing corresponding time features respectively; the fully connected layer is used to integrate the spatial features and time features of the multiple one-dimensional vectors after splicing, and output multiple global features; the normalized exponential function (SoftMax) output layer is used to classify the multiple global features and output multi-dimensional light tag information.

[0128] After the model automatically identifies the final multidimensional optical label result, the host deployed at the switching node sends the final multidimensional optical label result to the server deployed at the switching node, so that the switching node can efficiently forward the high-power optical signal carrying multidimensional optical label information located in the server according to the automatically identified multidimensional optical label result, and can save optical fiber link resources. The multidimensional optical label result can be the specific wavelength information of the original optical signal and the specific level of priority, high and low priority information.

[0129] Step S340: construct a multi-level dynamic feedback queue according to the output multi-dimensional optical label information, and forward the higher-power optical signal carrying the multi-dimensional optical label information in a wavelength division multiplexing manner according to the multi-level dynamic feedback queue.

[0130] In one embodiment of the present invention, a multi-level dynamic feedback queue is constructed according to the output multi-dimensional optical tag information, including the following steps:

[0131] Step S341, dividing a plurality of optical signals of different wavelengths into a plurality of first groups according to the wavelength information;

[0132] Step S342, in each first group, a first-level queue is constructed in descending order of priority according to the priority information carried by different optical signals of the same wavelength, wherein different optical signals of the same priority form a second group in the first-level queue;

[0133] Step S343, in each second group, a first-in first-out queue is constructed as a secondary queue according to the order in which different optical signals of the same priority level arrive at the switching node;

[0134] Step S344, if the queue length, waiting time and service quality all reach corresponding preset thresholds, dynamically adjust and increase the priority of the queue;

[0135] Step S345: If an optical signal with a higher priority than the optical signal being transmitted is received during the forwarding process, the transmission of the current queue is stopped until the optical signal with a higher priority than the optical signal being transmitted is forwarded.

[0136] like Figure 5 As shown in the above steps, the multi-level dynamic feedback queue forwarding mechanism constructed is as follows: according to different wavelengths λ1, λ2, ..., λ n Construct n first groups, and under each first group, construct the first-level queues P1, P2, ..., P in descending order of priority. m , P1 is the highest priority, P m The lowest priority, where different optical signals with the same priority form a second group in the first-level queue, such as P1, etc. Under each second group, a second-level queue, i.e., a first-in-first-out (FIFO) queue, is constructed according to the order of arrival at the switching node, forming a total of n×m queues, where n is the total number of signal wavelength types sent by the transmitter, and m is the total number of priority levels preset by the transmitter. After each optical signal arrives at the switching node and is automatically identified by the multidimensional optical label, the switching node adds the corresponding optical signal to the above corresponding queue according to the identified multidimensional optical label-wavelength and priority. The length of each queue is L1, L2, ..., L pInversely proportional to the priority of the queue. Based on the fiber wavelength division multiplexing technology, each switching node sends signals of multiple wavelengths in parallel, and preferentially forwards the signals in the queue with higher priority under each wavelength group. For example, only when all the signals in P1 under the second group of wavelength λ1 are forwarded, the signals in P2 under the second group of wavelength λ1 are forwarded. In this embodiment, in order to ensure that high-priority signals can be forwarded in time, during the forwarding process, if the switching node receives a higher-priority signal, it will discard the currently transmitted lower-priority signal and stop the transmission of the current queue, and instead transmit the higher-priority signal just received.

[0137] In addition, in order to prevent extreme situations such as queue overflow or starvation of lower-priority members, which may lead to a large number of packet losses and thus affect service quality and reduce network throughput, the queue priority is dynamically adjusted to solve this problem. Specifically, the priority is dynamically adjusted through the following formula:

[0138]

[0139] Among them, P i1 Indicates priority, i1 = 1, 2, ..., m, L i2，th , T wait，th and QoS th are the preset thresholds for expected queue length, waiting time and service quality, i2 = 1, 2, ..., p. When the actual queue length L i2 The preset threshold L of the expected queue length is reached i2，th , the actual waiting time T wait The preset waiting time threshold T is reached wait，th The actual quality of service (QoS) reaches the preset threshold value of the quality of service (QoS). th When the number of packets received is greater than 0, the priority of the corresponding queue is increased, so that the data forwarding of the queue is processed first. α, β, and γ are influencing factors, which are randomly generated between 0 and 0.5. The quality of service (QoS) is affected by data such as packet loss rate, delay, jitter, and bandwidth.

[0140] It can be seen that according to the above-mentioned multi-level dynamic feedback queue, the optical signal superimposed with multi-dimensional optical labels can be more efficiently forwarded based on wavelength division multiplexing and priority in the optical network, and data packets with different task priorities and importance can be forwarded differently, thereby significantly improving the utilization efficiency and service quality of optical fiber link resources in the entire optical network, and realizing the time-sensitive security of data.

[0141] In another embodiment of the present invention, in order to facilitate inputting the recovered multidimensional optical label information into the model and accurately identifying it, before inputting the two-dimensional matrix representation of the recovered multiple one-dimensional optical label signals into the multidimensional optical label identification model deployed in the switching node, the network operation and maintenance method of the multidimensional optical label further includes the following steps:

[0142] Step S326: The restored multiple one-dimensional optical tag signals are respectively regarded as multiple two-dimensional matrix images composed of multiple pixel points, and each two-dimensional matrix image is divided into multiple pixel blocks.

[0143] Step S327, constructing a feature matrix based on the multiple pixel blocks, the element value in the feature matrix is ​​the average value of the RGB value of each pixel point in the corresponding pixel block, and constructing an adjacency matrix based on the adjacent relationship between the multiple pixel blocks.

[0144] Step S328, normalize the multiple feature matrices to obtain multiple normalized feature matrices, and the two-dimensional matrix representation includes the normalized feature matrix and the corresponding adjacency matrix. In other words, the multiple adjacency matrices and the multiple normalized feature matrices obtained by preprocessing the restored multiple one-dimensional optical tag signals are used as inputs of the improved GraphFormer model.

[0145] Since there are countless pixels constituting the two-dimensional matrix graph, in order to avoid the problem of too large a matrix resulting in a surge in computational complexity due to too many pixels in the image, this embodiment divides multiple two-dimensional matrix graphs into several 16×16 pixel blocks, each pixel block is regarded as a node, and each image can be regarded as a combination of several pixel blocks. The adjacent relationship between pixel blocks is regarded as the edge connecting the nodes, and the adjacency matrix is ​​constructed according to the connection relationship. In this way, two types of matrices of the GCN layer of the spatial module in the input improved GraphFormer model are obtained, namely, the feature matrix X composed of each pixel block and the adjacency matrix A used to represent the connection relationship between each pixel block in each image. Both the feature matrix X and the adjacency matrix A are multiple. Each matrix element value in the feature matrix is ​​the result obtained by averaging the RGB values ​​of each pixel point in the corresponding pixel block, that is, the average value of the RGB values ​​of each pixel point in the corresponding pixel block.

[0146] Before inputting the above feature matrix and adjacency matrix into the model, each feature matrix is ​​normalized and preprocessed. The specific formula for feature matrix normalization is as follows:

[0147]

[0148] Among them, X n represents the normalized feature matrix, X i，j represents the element in the i-th row and j-th column of the feature matrix, X minrepresents the minimum value among the elements of the feature matrix, X max Represents the maximum value among the elements of the feature matrix.

[0149] Multiple normalized feature matrices and corresponding multiple adjacency matrices are input into the improved GraphFormer model. The spatial features of multiple normalized feature matrices and multiple adjacency matrices corresponding to multiple one-dimensional optical tag signals are first extracted through the multi-layer GCN of the spatial module, that is, the spatial correlation relationship of each signal waveform is obtained. The output of each layer of GCN is as follows:

[0150]

[0151]

[0152] Among them, H (l+1) H represents the two-dimensional matrix output after the activation of the l+1th layer GCN, (l) Represents the two-dimensional matrix output after the activation of the l-th layer GCN, H (l) ∈R M*D , M represents the number of nodes in each graph, D represents the dimension of the output feature of each node, and H (0) =X n , X n Represents the normalized feature matrix of the input; σ represents the activation function of each layer of GCN; Represents the normalized matrix, which is the result of adding the out-degree matrix and the identity matrix. The out-degree matrix represents the matrix described by the edges that each pixel block in the image can extend out of; represents the self-connected adjacency matrix, A represents the adjacency matrix; W (l) Represents the self-learning weight matrix of the th layer GCN; I represents the identity matrix, N represents the dimension of the identity matrix, and in the specific example, N is one-dimensional.

[0153] It can be seen that the output of the spatial module is a plurality of two-dimensional spatial feature matrices containing the spatial correlation and spatial features of the corresponding one-dimensional optical tag signals. In order to avoid the spatial features of the two-dimensional matrix being insignificant after passing through the time module, the spatial module of this embodiment also uses the TopK algorithm to retain the spatial features learned by the spatial module. Specifically, for each pixel block in the two-dimensional spatial feature matrix, the score of each pixel block is calculated by the following formula:

[0154] Score i，j =H i，j +∑A i，j H i，j

[0155] Among them, H i，jRepresents the eigenvalue of the pixel block in the i-th row and j-th column in the two-dimensional spatial feature matrix, that is, the matrix element value, ∑A i，j H i，j Represents the sum of the features of other pixel blocks in the two-dimensional spatial feature matrix connected to the pixel block in the i-th row and j-th column. Sort each element value in each two-dimensional spatial feature matrix output by the last layer of GCN in descending order according to the calculated score of each element value, and select the top 50% of the part, expand it into a one-dimensional spatial feature vector containing spatial features, denoted as Spatial output , thereby forming multiple one-dimensional spatial feature vectors, which are used to splice with the one-dimensional vector output by the subsequent time module to complete the recognition of multi-dimensional optical tags.

[0156] The multiple two-dimensional spatial feature matrices H output by the last layer of GCN in the spatial module are used as the input of the time module. The time features of the matrix data are extracted through the time module. In order to make the improved GraphFormer model better understand the sequential relationship of the input matrix data in the time series, the time module uses position embedding (embedding layer) to distinguish the elements at different positions in the time series, thereby understanding the relationship between the elements in the input matrix. The calculation formula of position embedding is as follows:

[0157]

[0158]

[0159] Among them, pos represents the data position in the time series, k represents the time series index, and PE (pos，2k) and PE (pos，2k+1) Represents odd-dimensional and even-dimensional data, d model Represents the embedding dimension.

[0160] Through the above position embedding formula, a new feature matrix expression can be obtained, that is, the vector representing the position of the input matrix data of the time module - the two-dimensional space feature matrix in the time series. In addition, in order to better obtain the correlation between data, a multi-head attention mechanism is also added to the time module. The purpose of the attention mechanism is to enable the model to dynamically focus on different parts of the sequence when processing sequence data. The traditional standard attention mechanism calculates a single weighted sum, while the multi-head attention mechanism calculates through multiple independent attention heads. Each attention head can focus on different features or positions, thereby capturing richer contextual information. Multi-head attention will perform attention calculations on the input data separately, and finally splice the calculation results of all attention heads together to obtain the final output result. The key is to generate multiple groups of QKV values, decompose the input two-dimensional space feature matrix into multiple different subspaces, so that the model can focus on different positions in each space. The specific process is as follows:

[0161] The first is the linear transformation. For each attention head, the embedding of the input sequence will be linearly transformed into query, key, and value matrices, as shown in the following formula:

[0162] Q=YW Q , K=YW K , V=YW V

[0163] Among them, W Q , W K , W V is a learnable weight matrix and Y represents the output of the embedding.

[0164] Then the attention of each attention head is calculated by the following formula:

[0165]

[0166] Among them, d K is the dimension of the key vector, T represents the transpose operation, and the normalized exponential function (SoftMax) can transform a real number vector into a probability vector as follows: Among them, z j represents the input vector, j=1, 2,…, q, q represents the number of elements in the input vector, which is the length of the input sequence here.

[0167] Finally, the attention output from each attention head is concatenated together using the following formula:

[0168] MultiHead(Q,K,V)=Concat(head1,...,head h )W o

[0169] Among them, MultiHead() represents the multi-head attention function, Concat() represents the concatenation function, head h represents the output of each attention head, h represents the number of attention heads, and W o A weight matrix representing a linear transformation.

[0170] The time module finally outputs a one-dimensional time feature vector, which is similar to the one-dimensional space feature vector output by the space module and is recorded as Time output , and finally the vector Spatial output and Time output After concatenation, the optical labels are passed through a fully connected layer and a SoftMax output layer in turn to obtain the final optical label recognition result. In a specific example, the optical label recognition result is the wavelength information and priority information of the original optical signal sent by the transmitter.

[0171] The network operation and maintenance method of the multidimensional optical label of each embodiment of the present invention receives and diverts the optical signal carrying the multidimensional optical label through each switching node in the optical network, separates the multidimensional optical label signal from the optical signal with lower power after diversion, and inputs the separated multidimensional optical label signal into the improved GraphFormer model for rapid and accurate identification, and finally constructs a multi-level dynamic feedback queue according to the identified multidimensional optical label result, and efficiently forwards the optical signal carrying the multidimensional optical label with higher power after diversion according to the queue and optical fiber wavelength division multiplexing technology. This scheme realizes the effective combination of optical fiber link and signal priority without occupying additional bandwidth of the optical network and without changing the original transmission protocol of the network, which not only improves the optical path utilization efficiency of the entire optical network, saves link resources, and ensures the timeliness of data, but also greatly reduces the network operation and maintenance cost, and the method can also be extended to the transmission of optical signals carrying useful information of other dimensions or more dimensions.

[0172] The present invention aims to optimize the operation and maintenance process of optical networks, improve network performance, reduce operating costs, and meet the growing demand for optical network communications through innovative multi-dimensional optical label generation technology and a deep identification model of multi-dimensional optical labels.

[0173] Corresponding to the above method, an embodiment of the present invention further provides a network operation and maintenance system of a multi-dimensional optical label, which is deployed in each switching node of the optical network and includes an optical coupler, an optical label signal recovery module and a computer device.

[0174] The optical coupler is used to receive an optical signal carrying multidimensional optical label information generated by a transmitting end or forwarded by other switching nodes, and split the optical signal carrying multidimensional optical label information into an optical signal carrying multidimensional optical label information with a higher power and an optical signal carrying multidimensional optical label information with a lower power;

[0175] The optical label signal recovery module includes a photodiode, a transimpedance amplifier, an analog-to-digital converter, a fast Fourier transform circuit, a Costas loop circuit, a carrier synchronization module, a clock synchronization module and a demodulation module connected in sequence, and is used to recover and pre-process the low-power optical signal carrying multi-dimensional optical label information to obtain a plurality of recovered one-dimensional optical label signals;

[0176] The computer device includes a processor and a memory, wherein the memory stores computer instructions, and the processor is used to execute the computer instructions stored in the memory. When the computer instructions are executed by the processor, the system implements the following steps in the network operation and maintenance method of the multi-dimensional optical tag:

[0177] Inputting the two-dimensional matrix representations of the restored multiple one-dimensional optical label signals into a multi-dimensional optical label recognition model deployed in the switching node for recognition, so that the multi-dimensional optical label recognition model outputs multi-dimensional optical label information, the multi-dimensional optical label recognition model includes a spatial module, an activation function layer, a time module, a splicing module, a fully connected layer and a normalized exponential function output layer connected in sequence, and the output of the spatial module is also connected to the input of the splicing module;

[0178] A multi-level dynamic feedback queue is constructed according to the output multi-dimensional optical label information, and a high-power optical signal carrying the multi-dimensional optical label information is forwarded in a wavelength division multiplexing manner according to the multi-level dynamic feedback queue.

[0179] An embodiment of the present invention also provides a signal generation and transmission system carrying a multi-dimensional optical tag, which is deployed at the transmitting end of an optical network and includes a high-speed transceiver, a programmable logic array, a digital-to-analog conversion module, a voltage-controlled current source circuit, a driver / receiver chip, a semiconductor optical amplifier, and a temperature controller.

[0180] Among them, a high-speed transceiver is used to generate the original optical signal;

[0181] The programmable logic array is used to drive the digital-to-analog conversion module to generate a modulation signal multiple times. The frequency of the modulation signal is lower than the frequency of the original optical signal, and the frequency of the modulation signal generated each time is different.

[0182] The voltage-controlled current source circuit is used to convert the modulation signal generated each time into a driving current signal;

[0183] The driver / receiver chip is used to convert the driving current signal obtained each time into a differential enable signal;

[0184] The semiconductor optical amplifier is used to superimpose the differential enable signal obtained each time and the working current signal of the semiconductor optical amplifier to obtain the modulated current signal multiple times; receive the original optical signal, fine-tune the original optical signal according to the modulated current signal obtained for the first time, and generate an optical signal carrying one-dimensional optical label information; and is also used to receive the optical signal carrying the corresponding dimensional optical label information generated each time multiple times, fine-tune the optical signal carrying the corresponding dimensional optical label information according to the modulated current signal obtained each time, generate an optical signal carrying multi-dimensional optical label information, and send the optical signal carrying the multi-dimensional optical label information to the switching node of the optical network;

[0185] The temperature controller is connected to the semiconductor optical amplifier to suppress the temperature drift of the current signal.

[0186] An embodiment of the present invention further provides an electronic device, which is deployed at each switching node in an optical network, including: a processor, a memory, and computer instructions stored in the memory, wherein the processor is used to execute the computer instructions. When the computer instructions are executed, the system implements the following steps of the network operation and maintenance method of the multi-dimensional optical label:

[0187] Input the two-dimensional matrix representation of the restored multiple one-dimensional optical label signals into the multidimensional optical label recognition model deployed in the switching node for recognition, so that the multidimensional optical label recognition model outputs multidimensional optical label information, the multidimensional optical label recognition model includes a spatial module, an activation function layer, a time module, a splicing module, a fully connected layer and a normalized exponential function output layer connected in sequence, and the output of the spatial module is also connected to the input of the splicing module; wherein the restored multiple one-dimensional optical label signals are obtained by restoring and preprocessing the optical signal carrying the multidimensional optical label information with a lower power, and the optical signal carrying the multidimensional optical label information generated by the sending end or forwarded by other switching nodes of the optical network is received by the switching node, and the optical signal carrying the multidimensional optical label information is shunted to obtain a higher-power optical signal carrying the multidimensional optical label information and a lower-power optical signal carrying the multidimensional optical label information;

[0188] A multi-level dynamic feedback queue is constructed according to the output multi-dimensional optical label information, and a high-power optical signal carrying multi-dimensional optical label information is forwarded in a wavelength division multiplexing manner according to the multi-level dynamic feedback queue. The electronic device can be various mobile terminals, desktop computers, servers, etc.

[0189] The embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the following steps of the network operation and maintenance method of the multi-dimensional optical tag are implemented:

[0190] Input the two-dimensional matrix representation of the restored multiple one-dimensional optical label signals into the multidimensional optical label recognition model deployed in the switching node for recognition, so that the multidimensional optical label recognition model outputs multidimensional optical label information, the multidimensional optical label recognition model includes a spatial module, an activation function layer, a time module, a splicing module, a fully connected layer and a normalized exponential function output layer connected in sequence, and the output of the spatial module is also connected to the input of the splicing module; wherein the restored multiple one-dimensional optical label signals are obtained by restoring and preprocessing the optical signal carrying the multidimensional optical label information with a lower power, and the optical signal carrying the multidimensional optical label information generated by the sending end or forwarded by other switching nodes of the optical network is received by the switching node, and the optical signal carrying the multidimensional optical label information is shunted to obtain a higher-power optical signal carrying the multidimensional optical label information and a lower-power optical signal carrying the multidimensional optical label information;

[0191] A multi-level dynamic feedback queue is constructed according to the output multi-dimensional optical label information, and a high-power optical signal carrying the multi-dimensional optical label information is forwarded in a wavelength division multiplexing manner according to the multi-level dynamic feedback queue. The computer-readable storage medium may be a tangible storage medium, such as a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a floppy disk, a hard disk, a removable storage disk, a CD-ROM, or any other form of storage medium known in the technical field.

[0192] The embodiment of the present invention further provides a computer program product, including computer instructions, which, when executed by a processor, implement the following steps of the network operation and maintenance method of the multi-dimensional optical tag:

[0193] Input the two-dimensional matrix representation of the restored multiple one-dimensional optical label signals into the multidimensional optical label recognition model deployed in the switching node for recognition, so that the multidimensional optical label recognition model outputs multidimensional optical label information, the multidimensional optical label recognition model includes a spatial module, an activation function layer, a time module, a splicing module, a fully connected layer and a normalized exponential function output layer connected in sequence, and the output of the spatial module is also connected to the input of the splicing module; wherein the restored multiple one-dimensional optical label signals are obtained by restoring and preprocessing the optical signal carrying the multidimensional optical label information with a lower power, and the optical signal carrying the multidimensional optical label information generated by the sending end or forwarded by other switching nodes of the optical network is received by the switching node, and the optical signal carrying the multidimensional optical label information is shunted to obtain a higher-power optical signal carrying the multidimensional optical label information and a lower-power optical signal carrying the multidimensional optical label information;

[0194] A multi-level dynamic feedback queue is constructed according to the output multi-dimensional optical label information, and a high-power optical signal carrying the multi-dimensional optical label information is forwarded in a wavelength division multiplexing manner according to the multi-level dynamic feedback queue.

[0195] It should be understood by those skilled in the art that the exemplary components, systems and methods described in conjunction with the embodiments disclosed herein can be implemented in hardware, software or a combination of the two. Whether it is performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present invention are programs or code segments used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link via a data signal carried in a carrier.

[0196] It should be clear that the present invention is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present invention.

[0197] In the present invention, features described and / or illustrated for one embodiment may be used in the same or similar manner in one or more other embodiments, and / or combined with features of other embodiments or replace features of other embodiments.

[0198] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the embodiments of the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for generating and transmitting a signal carrying a multi-dimensional optical tag, characterized in that: The method comprises: The transmitting end of the optical network generates an original optical signal through a high-speed transceiver, and drives a digital-to-analog conversion module through a programmable logic array to generate a modulated signal, wherein the frequency of the modulated signal is lower than the frequency of the original optical signal; Converting the modulation signal into a driving current signal through a voltage-controlled current source circuit; The driving current signal and the working current signal of the semiconductor optical amplifier are superimposed by a semiconductor optical amplifier to obtain a modulated current signal; Inputting the original optical signal into the semiconductor optical amplifier, modulating the original optical signal according to the modulation current signal through the semiconductor optical amplifier to generate an optical signal carrying one-dimensional optical label information; Repeat the steps of generating, converting and superimposing the modulation signal multiple times, inputting the optical signal carrying the corresponding dimension optical label information generated last time into the semiconductor optical amplifier each time, modulating the optical signal carrying the corresponding dimension optical label information by the semiconductor optical amplifier according to the modulation current signal obtained each time, and generating an optical signal carrying multi-dimensional optical label information, wherein the frequency of the modulation signal generated each time is different; The optical signal carrying the multi-dimensional optical label information is sent to a switching node of the optical network.

2. The method according to claim 1, characterized in that The method further includes: connecting a temperature controller via the semiconductor optical amplifier to suppress temperature drift of the current signal.

3. The method according to claim 1, characterized in that After converting the modulation signal into a driving current signal through a voltage-controlled current source circuit, the method further includes: Converting the drive current signal into a differential enable signal through a driver / receiver chip; The differential enable signal and the working current signal of the semiconductor optical amplifier are superimposed through the semiconductor optical amplifier to obtain a modulated current signal.

4. The method according to any one of claims 1 to 3, characterized in that The multi-dimensional optical label information includes wavelength information and priority information corresponding to the original optical signal generated by the transmitting end.

5. A signal generation and transmission system carrying a multi-dimensional optical tag, characterized in that: The system is deployed at the transmitting end of the optical network, and includes: a high-speed transceiver, a programmable logic array, a digital-to-analog conversion module, a voltage-controlled current source circuit, and a semiconductor optical amplifier. The high-speed transceiver is used to generate an original optical signal; The programmable logic array is used to drive the digital-to-analog conversion module to generate a modulation signal multiple times, the frequency of the modulation signal is lower than the frequency of the original optical signal, and the frequency of the modulation signal generated each time is different; The voltage-controlled current source circuit is used to convert the modulation signal generated each time into a driving current signal; The semiconductor optical amplifier is used to superimpose the driving current signal obtained each time and the working current signal of the semiconductor optical amplifier to obtain the modulated current signal multiple times; receive the original optical signal, modulate the original optical signal according to the modulated current signal obtained for the first time, and generate an optical signal carrying one-dimensional optical label information; and is also used to receive the optical signal carrying the corresponding dimensional optical label information generated each time multiple times, modulate the optical signal carrying the corresponding dimensional optical label information according to the modulated current signal obtained each time, generate an optical signal carrying multi-dimensional optical label information, and send the optical signal carrying the multi-dimensional optical label information to the switching node of the optical network.

6. The system according to claim 5, characterized in that The system further comprises: a driver / receiver chip, the driver / receiver chip being used to convert the driving current signal obtained each time into a differential enable signal; The semiconductor optical amplifier is also used to superimpose the differential enable signal obtained each time and the working current signal of the semiconductor optical amplifier to obtain the modulated current signal multiple times.

7. The system according to claim 5, characterized in that The system further comprises: a temperature controller, which is connected to the semiconductor optical amplifier and is used to suppress the temperature drift of the current signal.

8. The system according to any one of claims 5 to 7, characterized in that The multi-dimensional optical label information includes wavelength information and priority information corresponding to the original optical signal generated by the transmitting end.

Images