An optical network operation and maintenance system and method based on digital twinning and augmented reality

Abstract

The application discloses an optical network operation and maintenance system and method based on digital twinning and augmented reality, and relates to the technical field of optical network operation and maintenance.The system comprises a digital twinning platform connected with at least one AR terminal and at least one internet terminal; and the digital twinning platform is internally provided with a main control module, a network twinning module, a fault diagnosis module and a data pool.The application combines digital twinning and augmented reality technology into optical network operation and maintenance, facilitates real-time monitoring and maintenance of optical network equipment by staff, makes operation and maintenance more efficient and accurate, and enables professional operation and maintenance personnel to perform remote auxiliary diagnosis through the internet terminal equipment for faults that cannot be solved by the digital twinning platform, solves the problems of complex and diverse equipment and communication distortion, realizes collaborative cooperation across space and time limitations, reduces operation and maintenance time and cost, and meets actual application requirements.

Description

Technical Field

[0001] This invention relates to the field of optical network operation and maintenance technology, specifically to an optical network operation and maintenance system and method based on digital twins and augmented reality. Background Technology

[0002] Traditional optical network operation and maintenance (O&M) models typically involve professional O&M personnel conducting on-site inspections to identify faults; or, if the professional O&M personnel are not present, on-site staff communicate with them by phone to understand the problem. However, the number of experts is generally limited, and the experience and skill level of outsourced personnel vary. If unforeseen emergencies prevent O&M personnel from being on-site, or if the engineer is traveling, residing in a remote area, on vacation, or reassigned, emergency repairs may be delayed. In such situations, on-site O&M undoubtedly presents significant challenges, necessitating innovative O&M models.

[0003] Digital twin technology refers to the use of digital means to create a virtual entity in the digital world for a physical entity, thereby enabling dynamic observation, analysis, simulation, control, and optimization of the physical entity.

[0004] Augmented reality (AR) technology is a technology that merges real-world information with virtual-world information. It can overlay real environments and virtual objects onto the same screen or space in real time, and present them through display devices or AR glasses.

[0005] Because the combination of digital twins and augmented reality (AR) technologies can better present the fusion of the virtual and physical worlds, overlaying virtual digital information onto physical entities can enhance the visual experience. Therefore, research has begun to explore the application of digital twins and AR technologies to the monitoring and maintenance of various systems. For example, Chinese invention patent application CN113359640A, entitled "A Predictive Maintenance System and Method for Production Lines Based on Digital Twins and Augmented Reality," proposes applying digital twins and AR technologies to predictive maintenance of production lines, enabling accurate prediction of equipment failures and facilitating timely maintenance.

[0006] However, in practical applications, the existing monitoring (maintenance) systems based on digital twins and augmented reality still have the following problems:

[0007] Problem 1: In existing monitoring (maintenance) systems, the solutions (or prediction solutions) for equipment failures are fixed and preset. When a failure occurs that cannot be resolved by the preset solution, the existing system cannot be used to solve the problem and cannot meet the actual application requirements well.

[0008] Question 2: As usage time and the number of AR terminals continue to increase, the computational burden on the AR terminal processor will become increasingly heavy. When multiple AR terminals have data processing tasks that need to be computed, significant latency and energy consumption issues will occur, which will not only affect the overall network performance but also reduce the overall system efficiency. Summary of the Invention

[0009] The purpose of this invention is to provide an optical network operation and maintenance system and method based on digital twins and augmented reality, which at least solves one of the above-mentioned technical problems.

[0010] To achieve the above objectives, in a first aspect, embodiments of the present invention provide an optical network operation and maintenance system based on digital twins and augmented reality, including a digital twin platform, wherein the digital twin platform is connected to at least one AR terminal and at least one Internet terminal; and the digital twin platform is provided with a main control module, a network twin module, a fault diagnosis module and a data pool;

[0011] The AR terminal is used to: collect real-time information from a first-person perspective at the scene; when the fault diagnosis module provides a solution, it receives the operation and maintenance instructions issued by the main control module; otherwise, it sends the rendered real-time information from the first-person perspective to the main control module and receives the remote diagnosis results fed back by the Internet terminal.

[0012] The main control module is used to: send the real-time information from the first perspective and the physical network information stored in the data pool to the network twin module; receive the diagnostic results fed back by the fault diagnosis module, and if a solution is provided, issue an operation and maintenance instruction to the AR terminal; otherwise, send the rendered real-time information from the first perspective and the generated twin network to the Internet terminal.

[0013] The network twin module is used to: simulate and model the physical network to generate a twin network of the physical network;

[0014] The fault diagnosis module is used to: perform network fault diagnosis based on the twin network;

[0015] The Internet terminal is used for: performing remote real-time diagnosis based on rendered first-person perspective real-time information and twin network.

[0016] As a preferred embodiment, the system also includes an edge cloud, within which a controller and at least one edge node are configured;

[0017] The AR terminal is also used to: when there is a data processing task that needs to be calculated, determine whether the task exceeds the local computing capacity; if it does, send a computing request to the controller of the edge cloud, and after receiving the migration strategy from the controller, migrate the data processing task to the corresponding edge node for execution according to the migration strategy; if it does not exceed the capacity, perform the data processing task locally.

[0018] The controller is configured to: upon receiving a computing request, generate a migration strategy based on the bandwidth and computing resources of all edge nodes in the edge cloud, and feed it back to the corresponding AR terminal and the corresponding edge node;

[0019] The edge node is used to: complete the calculation task according to the received migration strategy, and feed back the calculation result to the corresponding AR terminal.

[0020] As a preferred implementation, the AR terminal determines whether the task exceeds its local computing power, specifically including:

[0021] Get the maximum allowable latency for the computing task

[0022] Calculate the time for local computation The calculation formula is: Where D i β represents the size of the task data to be computed. i This indicates the percentage of computing resources allocated to this task by AR terminal i. This indicates the local computing power of the AR terminal i;

[0023] Compare and like Then it is determined that the local computing power is not exceeded; if If the local computing power is exceeded, it will be determined that the local computing power is exceeded.

[0024] As a preferred implementation, when the controller generates a migration strategy based on the bandwidth and computing resources of all edge nodes in the edge cloud, it adopts a method that minimizes the total cost of computing tasks for all AR terminals.

[0025] As a preferred implementation, the controller generates a migration strategy by minimizing the total cost of computing tasks across all AR terminals, specifically including:

[0026] The controller is the AR terminal i that needs to perform task migration, and it generates a task migration table f. ij , Where x ij Indicates whether the task of AR terminal i has been migrated to edge node j; if so, then x ij =1, otherwise 0, λ ijB represents the percentage of bandwidth allocated from edge node j to AR terminal i. j β represents the bandwidth of edge node j. ij This represents the percentage of computing resources allocated from edge node j to AR terminal i. This represents the computational power of edge node j;

[0027] Based on the f ij Table F, which comprises all the different migration strategies of AR terminal i ik F ik ={f ij}, and x ij When k = 1, k = j;

[0028] Based on the migration strategy table F for all AR terminals that need to be migrated ik Generate a total migration strategy set F, F = {F ik};

[0029] Based on F, calculate the total computational cost of different migration strategies. Among them, the Total latency including migration execution Total energy consumption

[0030] The final migration strategy is obtained by minimizing the total cost of the computational tasks. The formula for minimizing the total cost of the computational tasks is as follows:

[0031]

[0032] As a preferred embodiment, the controller calculates the total computational cost of different migration strategies. Specifically, it includes:

[0033] Calculate the total latency of task migration execution from AR terminal i to edge node j. The calculation formula is:

[0034]

[0035] In the formula, This represents the transmission latency of AR terminal i uploading computing tasks to edge node j; This represents the computation time of AR terminal i's task on edge node j; This represents the transmission delay from edge node j to AR terminal i.

[0036] Calculate the total energy consumption of the task migration execution from AR terminal i to edge node j. The calculation formula is:

[0037]

[0038] In the formula, Indicates transmission power consumption; This indicates the local standby power consumption of the AR terminal. Indicates the power consumption of the receiver;

[0039] According to the formula Obtain the total cost of the computation task Where α is the assigned weight.

[0040] As a preferred embodiment, the value of α increases when the task is a latency-sensitive task and decreases when the task is an energy-sensitive task.

[0041] As a preferred implementation, the controller generates the migration strategy by minimizing the total cost of computing tasks for all AR terminals, and also satisfies the following constraints:

[0042] The total latency of migrating the task to edge node j for execution shall not exceed the maximum allowable latency of the computation task.

[0043] Furthermore, the bandwidth allocated to each task by edge node j shall not exceed the bandwidth of that node.

[0044] Furthermore, the computing resources allocated to each task by edge node j do not exceed the computing power of that node.

[0045] Secondly, embodiments of the present invention also provide a method for optical network operation and maintenance based on digital twins and augmented reality, applying the system of the first aspect embodiment, the method comprising the following steps:

[0046] The AR terminal collects real-time information from a first-person perspective at the scene.

[0047] The main control module sends the real-time information from the first perspective and the physical network information data stored in the data pool to the network twin module;

[0048] The network twin module generates a twin network of the physical network by simulating and modeling the physical network based on the real-time information from the first perspective and the physical network information data.

[0049] The fault diagnosis module performs network fault diagnosis based on the twin network and feeds back the diagnosis results to the main control module. If the diagnosis results provide a solution, the main control module issues corresponding operation and maintenance instructions to the AR terminal based on the solution. Otherwise, it obtains the rendered first-view real-time information from the AR terminal, obtains the twin network from the network twin module, and sends it to the Internet terminal.

[0050] The Internet terminal performs remote real-time diagnosis based on the rendered first-view real-time information and the twin network, and feeds back the remote diagnosis results to the AR terminal.

[0051] As a preferred embodiment, the optical network operation and maintenance system used in this method further includes an edge cloud, which is equipped with a controller and at least one edge node; based on this, the method further includes the following steps:

[0052] When the AR terminal has a data processing task that requires calculation, the AR terminal determines whether the task exceeds its local computing capacity.

[0053] If the limit is not exceeded, the data processing task will be computed and executed locally.

[0054] If the limit is exceeded, a computing request is sent to the controller of the edge cloud. After receiving the computing request, the controller generates a migration strategy based on the bandwidth and computing resources of all edge nodes in the edge cloud, and feeds it back to the corresponding AR terminal and the corresponding edge node.

[0055] After receiving the migration strategy from the controller, the corresponding AR terminal migrates the data processing task to the corresponding edge node for execution according to the migration strategy; the corresponding edge node completes the calculation task according to the received migration strategy and feeds back the calculation result to the corresponding AR terminal.

[0056] The beneficial effects of this invention are as follows:

[0057] (1) In this invention, not only are digital twin and augmented reality technologies combined into optical network operation and maintenance, making it convenient for staff to monitor and maintain the health status of optical network equipment in real time based on the digital twin platform, making operation and maintenance more efficient and accurate; but also, for faults that the digital twin platform cannot solve, professional operation and maintenance personnel (or experts) can remotely assist in diagnosis by viewing the twin network and the real-time first-person perspective images of the on-site staff through Internet terminal devices, and work with on-site staff to solve faults. This solves the problems of complex and diverse equipment and communication transmission distortion, and realizes collaborative cooperation between on-site staff and remote operation and maintenance personnel across spatial and temporal limitations, reducing operation and maintenance time and costs, and meeting the needs of practical applications.

[0058] (2) This invention proposes a collaborative computing scheme, which introduces an edge cloud into the optical network operation and maintenance system based on digital twins and augmented reality. By migrating some AR terminal data processing tasks to edge nodes in the edge cloud for collaborative computing, the computing burden of the terminal processor is reduced, latency and energy consumption are reduced, and the working efficiency of the entire operation and maintenance system is improved. Attached Figure Description

[0059] Figure 1This is a structural block diagram of an optical network operation and maintenance system based on digital twins and augmented reality, as described in an embodiment of the present invention.

[0060] Figure 2 This is a block diagram of an optical network operation and maintenance system based on digital twins and augmented reality, as described in another embodiment.

[0061] Figure 3 This is a schematic diagram of edge nodes in an embodiment of the present invention;

[0062] Figure 4 This is a flowchart of an optical network operation and maintenance method based on digital twins and augmented reality in an embodiment of the present invention. Detailed Implementation

[0063] To make the technical problems, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0064] However, it should be noted that the examples described below are merely specific examples and are not intended to limit the embodiments of the present invention to the specific steps, values, conditions, data, order, etc. Those skilled in the art can utilize the concept of the present invention to construct more embodiments not mentioned herein by reading this specification.

[0065] Example 1

[0066] See Figure 1 As shown, this embodiment provides an optical network operation and maintenance system based on digital twins and augmented reality. The system includes a digital twin platform, which connects at least one AR terminal and at least one Internet terminal. The digital twin platform is equipped with a main control module (also known as the "main service and control module"), a network twin module, a fault diagnosis module, and a data pool.

[0067] The AR terminal is used to: collect real-time first-person perspective information from the site and send it to the main control module; when the fault diagnosis module provides a solution, it receives maintenance operation instructions issued by the main control module; when the fault diagnosis module does not provide a solution, it sends the rendered first-person perspective real-time information to the main control module and receives remote diagnostic results from the internet terminal through the main control module. It can be understood that in this embodiment, the AR terminal's rendering operation is only performed when remote diagnosis is required. This not only allows remote professional maintenance personnel to view the real-time first-person perspective image (i.e., the rendered first-person perspective real-time information) of the on-site staff realistically and clearly through the internet terminal device, but also minimizes unnecessary rendering operations and saves AR terminal resources.

[0068] The main control module is used to: send the real-time information from the first perspective and the physical network information data stored in the data pool to the network twin module; receive the diagnostic results fed back by the fault diagnosis module; if the diagnostic results provide a solution, then issue corresponding operation and maintenance instructions to the AR terminal according to the solution; if no solution is provided, then send the real-time information from the first perspective rendered by the AR terminal and the twin network generated by the network twin module to the Internet terminal, and send the remote diagnostic results fed back by the Internet terminal to the AR terminal. It is understood that the physical network information data stored in the data pool includes, but is not limited to: real-time performance, status, and service configuration data reported by the physical network.

[0069] The network twin module is used to: simulate and model the physical network based on the real-time information from the first perspective and the physical network information data to generate a twin network of the physical network.

[0070] The fault diagnosis module is used to: perform network fault diagnosis based on the twin network and feed back the diagnosis results to the main control module. It is understood that in practical applications, when the fault diagnosis module performs network fault diagnosis, it will search for corresponding solutions in a preset solution library and include the found solutions in the diagnosis results; if no corresponding solution is found, no solution will be provided in the diagnosis results.

[0071] The internet terminal is used to: perform remote real-time diagnosis based on the rendered first-view real-time information and the twin network, and feed back the remote diagnosis results to the main control module. It is understood that in practical applications, internet terminals include, but are not limited to, computers, smartphones, and smart TVs.

[0072] As can be seen from the above, this embodiment not only integrates digital twin and augmented reality technologies into optical network operation and maintenance, facilitating real-time health monitoring and maintenance of optical network equipment by staff using the digital twin platform, making operation and maintenance more efficient and accurate; but also, for faults that the digital twin platform cannot resolve, professional operation and maintenance personnel (or experts) can remotely assist in diagnosis by viewing real-time images of the twin network and on-site staff from a first-person perspective through internet terminal devices, collaborating with on-site staff to resolve faults. This solves the problems of complex and diverse equipment and communication distortion, enabling collaborative cooperation between on-site staff and remote operation and maintenance personnel across spatial and temporal limitations, reducing operation and maintenance time and costs, and meeting practical application needs.

[0073] Example 2

[0074] It is understandable that in practical applications, various data processing tasks need to be computed on each AR terminal. For example, when an AR terminal collects real-time information from a first-person perspective, it performs various data processing tasks to complete the collection task; or, when remote diagnosis is required, the AR terminal performs rendering operations to render a real-time image from the first-person perspective of the on-site staff, which also requires various data processing tasks to complete the rendering task. Therefore, in order to effectively reduce the computational burden on each AR terminal processor and avoid large latency and energy consumption when multiple AR terminals have data processing tasks to compute, resulting in poor overall network performance and low work efficiency, this embodiment proposes a collaborative computing scheme. It introduces an edge cloud into the optical network operation and maintenance system based on digital twins and augmented reality. By migrating some AR terminal data processing tasks to edge nodes in the edge cloud for collaborative computing, the computational burden on the terminal processor is reduced, latency and energy consumption are decreased, and the overall work efficiency of the operation and maintenance system is improved.

[0075] Specifically, this embodiment provides an optical network operation and maintenance system based on digital twins and augmented reality. Its basic structure is the same as that of Embodiment 1, except that, see [link to Embodiment 1]. Figure 2 As shown, in a preferred embodiment, the system further includes an edge cloud, in which a controller and at least one edge node are provided.

[0076] The AR terminal is further configured to: when a data processing task requires computation (such as when collecting real-time information from a first-person perspective at the scene as described above, or when it needs to be rendered into a real-time image from the first-person perspective of the on-site staff), determine whether the data processing task exceeds the local computing capacity. If it does, the main control module sends a computation request to the controller of the edge cloud, and after receiving the migration strategy from the controller, migrates the data processing task to the corresponding edge node for execution according to the migration strategy. If the task does not exceed the capacity, the data processing task is computed and executed locally.

[0077] The controller is configured to: upon receiving a computing request, generate a migration strategy based on the bandwidth and computing resources of all edge nodes in the edge cloud, and feed it back to the corresponding AR terminal and the corresponding edge node;

[0078] The edge node is used to: complete the calculation task according to the received migration strategy, and feed back the calculation result to the corresponding AR terminal through the controller.

[0079] Understandably, in this embodiment, when the task data that the AR terminal needs to process exceeds its local computing capabilities, it can send a computing request to the main control module. The main control module will then forward the request to the controller in the edge cloud. The controller will generate a migration strategy based on the bandwidth and computing resources of all edge nodes in the edge cloud and feed it back to the corresponding AR terminal and the corresponding edge node. Then, the corresponding edge node will collaborate with the AR terminal to complete the computing task according to the migration strategy and feed the computing results back to the corresponding AR terminal through the controller and the main control module. Through this collaborative computing scheme, some data processing tasks that the AR terminal cannot handle can be migrated to edge nodes in the edge cloud for collaborative computing, thereby reducing the computing burden on the terminal processor, reducing latency and energy consumption, and improving the overall efficiency of the operation and maintenance system.

[0080] Furthermore, as a preferred implementation, the AR terminal in this embodiment determines whether the data processing task exceeds its local computing power, specifically including:

[0081] (1) Obtain the maximum allowable latency of the computing task

[0082] (2) Calculate the local computation time The calculation formula is: Where D i β represents the size of the task data to be computed. i This indicates the percentage of computing resources allocated to this task by AR terminal i. This indicates the local computing power of the AR terminal i;

[0083] (3) Comparison and like Then it is determined that the local computing power has not been exceeded; if If the local computing power is exceeded, it will be determined that the local computing power is exceeded.

[0084] It is understandable that in practical applications, the system of this embodiment typically defines a network model before performing the above operations to facilitate subsequent computational analysis. For example, in this embodiment, *i* represents the i-th AR terminal, where *i* ∈ {1, 2, ..., N}; *j* represents the j-th edge node, where *j* ∈ {0, 1, 2, ..., M}. When *j* = 0, it specifically refers to the AR terminal itself (i.e., no migration is performed, and the task is computed and executed locally on the AR terminal). Each AR terminal can migrate computational tasks to designated edge nodes, and the edge nodes can allocate bandwidth and computing resources for the migrated computational tasks. In this embodiment, based on shared bandwidth and computing resources, it is assumed that each computational task is an independent execution unit, and the correlation between computational tasks is not considered.

[0085] Furthermore, as an optional implementation, see [link to relevant documentation]. Figure 3 As shown, the edge node may include a computing module and a data module. The computing module is used to perform computing tasks. The data module is used to receive and store the task data required for the computing tasks.

[0086] Example 3

[0087] This embodiment provides an optical network operation and maintenance system based on digital twins and augmented reality. Its basic structure is the same as that of Embodiment 2. The difference lies in that, as an optimized scheme for collaborative computing between local AR terminals and edge nodes, preferably, the controller in the edge cloud generates the optimal migration strategy by minimizing the total cost of all AR terminal computing tasks when generating the migration strategy based on the bandwidth and computing resources of all edge nodes in the edge cloud. This optimization scheme minimizes latency and energy consumption, maximizing overall network performance and the efficiency of the entire operation and maintenance system.

[0088] Specifically, as a preferred implementation, the controller in this embodiment generates a migration strategy by minimizing the total cost of computing tasks across all terminals, which may include:

[0089] (1) The controller is the AR terminal i that needs to perform task migration, and generates a task migration table f. ij The task migration table Where x ij This indicates whether the task of AR terminal i has been migrated to edge node j. If it has been migrated to edge node j, then x... ij =1, otherwise 0 (for example, if it migrates to another edge node instead of edge node j, then x = 1). ij =0), λ ij B represents the percentage of bandwidth allocated from edge node j to AR terminal i. j β represents the bandwidth of edge node j. ij This represents the percentage of computing resources allocated from edge node j to AR terminal i. This represents the computing power of edge node j; based on the task migration table f ij Table F, which comprises all the different migration strategies of AR terminal i ik The migration strategy table F ik ={f ij}, and x ij =1 when k=j; according to the migration strategy table F of all AR terminals that need to be migrated. ik Generate a total migration strategy set F, wherein the total migration strategy set F = {F... ik}

[0090] For example, suppose AR terminal 1's task needs to be migrated, and there are three edge nodes in the edge cloud. Then, the corresponding generated task migration table f ij and migration strategy table F ik Then it can be as follows:

[0091] f 11 = {1, 10, 45, 200, 6}, f 12 = {0, 15, 20, 200, 6}, f 13 ={0, 20, 60, 200, 6}, F 11 ={f 11 f 12 f 13}; where F 11 This represents the migration strategy table for AR terminal 1 to migrate its tasks to edge node 1, and the migration strategy table includes f. 11 = {1, 10, 45, 200, 6}, f 12 = {0, 15, 20, 200, 6}, f 13 = {0, 20, 60, 200, 6}, these are the three task migration tables.

[0092] f 11 = {0, 10, 45, 200, 6}, f 12 = {1, 15, 20, 200, 6}, f 13 ={0, 20, 60, 200, 6}, F 12 ={f 11 f 12 f 13}; where F 12 This represents the migration strategy table for AR terminal 1 to migrate its tasks to edge node 2, and the migration strategy table includes f. 11 = {0, 10, 45, 200, 6}, f 12 = {1, 15, 20, 200, 6}, f 13 = {0, 20, 60, 200, 6}, these are the three task migration tables.

[0093] f 11 = {0, 10, 45, 200, 6}, f 12 = {0, 15, 20, 200, 6}, f 13 = {1, 20, 60, 200, 6}, F 13 ={f 11 f 12 f 13}; where F 13 This represents the migration strategy table for AR terminal 1 to migrate its tasks to edge node 3, and the migration strategy table includes f.11 = {0, 10, 45, 200, 6}, f 12 = {0, 15, 20, 200, 6}, f 13 ={1, 20, 60, 200, 6}, these are the three task migration tables.

[0094] (2) Based on the total migration strategy set F, calculate different migration strategies (F ik Total cost of computational tasks Wherein, the total cost of the computing task Total latency including migration execution Total energy consumption

[0095] Furthermore, as an optional implementation, this embodiment calculates different migration strategies (F ik Total cost of computational tasks Specifically, it may include:

[0096] 1. Calculate the total latency of task migration from AR terminal i to edge node j. The calculation formula is:

[0097]

[0098] In the formula, This represents the transmission latency of AR terminal i uploading computing tasks to edge node j, and The uplink rate for task migration to edge node j; This represents the computation time of AR terminal i's task on edge node j, and β ij This represents the percentage of computing resources allocated from edge node j to AR terminal i. This represents the computational power of edge node j; This represents the transmission delay from edge node j to AR terminal i, and For downlink speed, Returns the size of the calculated data for edge node j.

[0099] 2. Calculate the total energy consumption for the migration execution of the task from AR terminal i to edge node j. The calculation formula is:

[0100]

[0101] In the formula, Indicates transmission energy consumption, and The uplink transmission power consumption of AR terminal i per unit time; This indicates the local standby power consumption of the AR terminal, and The energy consumption of AR terminal i per unit time while in the waiting state; Indicates the energy consumption of the receiver, and This represents the downlink transmission power consumption of AR terminal i per unit time.

[0102] 3. According to the formula Obtain the total cost of the computation task Where α is the assigned weight.

[0103] It is understandable that different tasks should be assigned different weights based on their task type. When a task is latency-sensitive, the value of α should be increased appropriately; when a task is energy-sensitive, the value of α should be decreased appropriately.

[0104] (3) By minimizing the total cost of the computational task, the final migration strategy is obtained, wherein the formula for minimizing the total cost of the computational task is:

[0105]

[0106] The above method yields the optimal migration strategy for the computational task, enabling the AR terminal and edge nodes to collaboratively complete the computation with minimal time and energy consumption. Furthermore, it's understood that in practical applications, when minimizing the total cost of the computational task using the above formula to obtain the final migration strategy, the following constraint must also be satisfied: the total latency of migrating the task to edge node j cannot exceed the maximum permissible latency of the computational task. The bandwidth allocated to each task by edge node j cannot exceed the bandwidth of that node, and the computing resources allocated to each task by edge node j cannot exceed the computing power of that node.

[0107] To better understand how the controller generates the optimal migration strategy by minimizing the total cost of computational tasks across all AR terminals, a specific example is provided below to illustrate the implementation process of this optimization method.

[0108] Assuming there are 5 AR terminals in the system, and 5 tasks that need to be calculated, what is the local computing power of each AR terminal? It is 50Mb / s.

[0109] AR terminal 1 task data size D1 is 200Mb, which is a latency-sensitive task. The maximum allowable latency of the task is... The uplink transmission power consumption is 6 seconds. The downlink transmission energy consumption per unit time is 0.05J. The waiting energy consumption per unit time is 0.01J. It is 0.001J.

[0110] AR Terminal 2 task data size D2 is 100Mb, which is a latency-sensitive task. The maximum allowable latency of the task is... The uplink transmission power consumption is 6 seconds. The downlink transmission energy consumption per unit time is 0.01J. The waiting energy consumption per unit time is 0.01J. It is 0.001J.

[0111] The AR terminal 3 task data size D3 is 500Mb, which is an energy-sensitive task, and the maximum allowable latency of the task is... The uplink transmission power consumption is 15 seconds. The downlink transmission energy consumption per unit time is 0.03J. The waiting energy consumption per unit time is 0.02J. It is 0.002J.

[0112] The AR terminal 4 task data size D4 is 300Mb, which is an energy-sensitive task, and the maximum allowable latency of the task is... The uplink transmission power consumption is 10 seconds. The downlink transmission energy consumption per unit time is 0.02J. The waiting energy consumption per unit time is 0.02J. It is 0.002J.

[0113] The AR terminal 5 task data size D5 is 400Mb, which is an energy-sensitive task, and the maximum allowable latency of the task is... The uplink transmission power consumption is 15 seconds. The downlink transmission energy consumption per unit time is 0.05J. The waiting energy consumption per unit time is 0.01J. It is 0.001J.

[0114] Assume there are 3 edge nodes in the edge cloud:

[0115] Edge node 1 has a bandwidth B1 of 100MHz and a computing power of It is 450Mb / s;

[0116] Edge node 2 has a bandwidth of 150MHz and a computing power of [missing information]. It is 200Mb / s;

[0117] Edge node 3 has a bandwidth of 200MHz and computing power. It is 600Mb / s.

[0118] The percentage of bandwidth allocated to AR terminals by edge nodes λ ij and the proportion of computing resources β ij Both are 0.1, representing the proportion of computing resources β allocated locally by the AR terminal to the task. i The weight is 0.6. Based on expert experience and experiments, in this example, the weight is set as follows: when the task is a latency-sensitive task, the weight is assigned α = 0.75; when the task is an energy-sensitive task, the weight is assigned α = 0.25.

[0119] Therefore, the local computation time for each task was calculated as follows: Comparing the maximum allowable latency of the task, it can be seen that the tasks of AR terminal 1 and AR terminal 3 need to be migrated.

[0120] So, after the edge cloud receives the computing request and processes the data, the corresponding task migration table f is generated. ij and migration strategy table F ik Then it is as follows:

[0121] f 11 = {1, 10, 45, 200, 6}, f 12 = {0, 15, 20, 200, 6}, f 13 ={0, 20, 60, 200, 6}; F 11 ={f 11 f 12 f 13}

[0122] f 11 = {0, 10, 45, 200, 6}, f 12 = {1, 15, 20, 200, 6}, f 13 ={0, 20, 60, 200, 6}; F 12 ={f 11 f 12 f 13}

[0123] f 11 = {0, 10, 45, 200, 6}, f 12 = {0, 15, 20, 200, 6}, f 13 ={1, 20, 60, 200, 6}; F 13 ={f 11 f 12 f 13}

[0124] f 31 = {1, 10, 45, 500, 15}, f 32= {0, 15, 20, 500, 15}, f 33 ={0, 20, 60, 500, 15}; F 31 ={f 31 f 32 f 33}

[0125] f 31 = {0, 10, 45, 500, 15}, f 32 = {1, 15, 20, 500, 15}, f 33 ={0, 20, 60, 500, 15}; F 32 ={f 31 f 32 f 33}

[0126] f 31 = {0, 10, 45, 500, 15}, f 32 = {0, 15, 20, 500, 15}, f 33 ={1, 20, 60, 500, 15}; F 33 ={f 31 f 32 f 33}

[0127] Then generate the total migration strategy set F = {F 11 F 12 F 13 F 31 F 32 F 33}

[0128] Assume that the uplink rates of AR terminal 1 uploading computing tasks to the edge node are respectively Downlink rates are respectively

[0129] Then calculate the different migration strategies (F) respectively. ik Total cost of computational tasks as follows:

[0130] (1)F 11 -AR terminal 1 migration task to edge node 1

[0131] Migration transmission delay Calculation time Calculation result data size Result transmission delay The total latency is: Less than the maximum allowable latency of 6 seconds for the computation task.

[0132] Transmission power consumption Receiver power consumption AR terminal 1 local waiting power consumption Total energy consumption is:

[0133] AR terminal 1's task is a latency-sensitive task. The total computational cost of migrating the task to edge node 1 is...

[0134] (2)F 12 -AR terminal 1 migrates the task to edge node 2

[0135] Migration transmission delay Calculation time The latency is already greater than the maximum allowable latency of 6 seconds for the computation task, therefore this migration strategy is not feasible.

[0136] (3)F 13 -AR terminal 1 migration task to edge node 3

[0137] Migration transmission delay Calculation time Calculation result data size Result transmission delay The total latency is: Less than the maximum allowable latency of 6 seconds for the computation task.

[0138] Transmission power consumption Receiver power consumption AR terminal 1 local waiting power consumption Total energy consumption is:

[0139] The AR terminal 1 task is a latency-sensitive task. The total computational cost of migrating the task to edge node 3 is...

[0140] (4)F 31 -AR terminal 3 migration task to edge node 1

[0141] Migration transmission delay Calculation time Calculation result data size Result transmission delay The total latency is: Less than 15 seconds of the maximum allowable latency for the computation task.

[0142] Transmission power consumption Receiver power consumption AR Terminal 3 Local Waiting Power Consumption Total energy consumption is:

[0143] AR terminal 3 is an energy-sensitive task. The total computational cost of migrating the task to edge node 1 is...

[0144] (5)F 32 -AR terminal 3 migration task to edge node 2

[0145] Migration transmission delay Calculation time The latency is already greater than the maximum allowable latency of 15 seconds for the computation task, therefore this migration strategy is not feasible.

[0146] (6)F 33 —AR terminal 3 migration task to edge node 3

[0147] Migration transmission delay Calculation time Calculation result data size Result transmission delay The total latency is: Less than 15 seconds of the maximum allowable latency for the computation task.

[0148] Transmission power consumption Receiver power consumption AR Terminal 3 Local Waiting Power Consumption Total energy consumption is:

[0149] AR terminal 3 tasks are energy-sensitive tasks, and the total computational cost of migrating to edge node 3 computing is...

[0150] Based on the calculated total cost of the computational tasks for different migration strategies, the final migration strategy that minimizes the total cost is obtained by minimizing the total cost of the computational tasks.

[0151]

[0152] The optimal strategy is to migrate the tasks of AR terminal 1 and AR terminal 3 to edge node 3 for computation. Furthermore, the bandwidth allocated to task 1 and task 3 on edge node 3 does not exceed the node's bandwidth, and the computational resources do not exceed the node's computational capacity, thus meeting practical application requirements. It should be noted that in this example, the final calculation result is that multiple AR terminals migrate to the same edge node. However, in real-world applications, different results may occur due to variations in the aforementioned data, such as multiple AR terminals migrating to different nodes.

[0153] Example 4

[0154] See Figure 4As shown, based on the same inventive concept, this embodiment of the invention also provides a method for optical network operation and maintenance based on digital twins and augmented reality, which includes the following steps:

[0155] S401. The AR terminal collects real-time information from the first-person perspective of the scene and sends it to the main control module;

[0156] S402, the main control module sends the real-time information from the first perspective and the physical network information data stored in the data pool to the network twin module;

[0157] S403. The network twin module simulates and models the physical network based on the real-time information from the first perspective and the physical network information data to generate a twin network model of the physical network, and sends it to the fault diagnosis module.

[0158] S404. The fault diagnosis module performs network fault diagnosis based on the twin network and feeds back the diagnosis results to the main control module.

[0159] S405. The main control module receives the diagnostic results and determines whether a solution is provided in the diagnostic results.

[0160] S406. If the diagnostic results provide a solution, the main control module shall issue corresponding operation and maintenance instructions to the AR terminal according to the provided solution.

[0161] S407. If no solution is provided in the diagnostic results, the main control module obtains the rendered first-view real-time information from the AR terminal and the twin network from the network twin module, and sends it to the Internet terminal; the Internet terminal performs remote real-time diagnosis based on the rendered first-view real-time information and the twin network, and feeds back the remote diagnostic results to the AR terminal through the main control module.

[0162] As can be seen from the above, the method of this embodiment not only combines digital twin and augmented reality technologies into optical network operation and maintenance, making it convenient for staff to monitor and maintain the health status of optical network equipment in real time based on the digital twin platform, thus making operation and maintenance more efficient and accurate; but also, for faults that the digital twin platform cannot resolve, professional operation and maintenance personnel (or experts) can remotely assist in diagnosis by viewing the twin network and the real-time first-person perspective images of the on-site staff through Internet terminal devices, and work with on-site staff to resolve faults. This solves the problems of complex and diverse equipment and communication distortion, and enables collaborative cooperation between on-site staff and remote operation and maintenance personnel across spatial and temporal limitations, reducing operation and maintenance time and costs, and meeting practical application needs.

[0163] Furthermore, as a preferred embodiment, the optical network operation and maintenance system to which this method is applied also includes an edge cloud, wherein a controller and at least one edge node are configured within the edge cloud. Based on this, the method of this embodiment further includes the following operations:

[0164] When the AR terminal has a data processing task that requires calculation, the AR terminal determines whether the task exceeds its local computing capacity.

[0165] If the limit is not exceeded, the data processing task will be computed and executed locally.

[0166] If the limit is exceeded, a computing request is sent to the controller of the edge cloud. After receiving the computing request, the controller generates a migration strategy based on the bandwidth and computing resources of all edge nodes in the edge cloud, and feeds it back to the corresponding AR terminal and the corresponding edge node.

[0167] After receiving the migration strategy from the controller, the corresponding AR terminal migrates the data processing task to the corresponding edge node for execution according to the migration strategy; the corresponding edge node completes the calculation task according to the received migration strategy and feeds back the calculation result to the corresponding AR terminal.

[0168] It is understood that the above preferred implementation scheme proposes a collaborative computing scheme, which reduces the computing burden of the AR terminal processor, reduces latency and energy consumption, and improves the working efficiency of the entire operation and maintenance system by migrating some of the AR terminal's data processing tasks to edge nodes in the edge cloud for collaborative computing.

[0169] It should be noted that the various variations and specific examples in the foregoing system embodiments are also applicable to the method in this embodiment. Through the detailed description of the foregoing system, those skilled in the art can clearly understand the implementation method of the method in this embodiment. Therefore, for the sake of brevity, they will not be described in detail here.

[0170] Note: The specific embodiments described above are merely examples and not limitations. Those skilled in the art can combine and integrate some steps and devices from the various embodiments described separately above to achieve the effects of the present invention. Such combined and integrated embodiments are also included in the present invention, but will not be described one by one here.

[0171] The advantages, benefits, and effects mentioned in the embodiments of this invention are merely examples and not limitations. They should not be considered as essential features of each embodiment of this invention. Furthermore, the specific details disclosed in the embodiments of this invention are for illustrative and facilitative purposes only and are not limitations. These details do not restrict the embodiments of this invention from being implemented using these specific details.

[0172] The block diagrams of devices, apparatuses, devices, and systems involved in the embodiments of this invention are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as "comprising," "including," "having," etc., are open-ended terms meaning "including but not limited to," and are used interchangeably with them. The terms "or" and "and" as used in the embodiments of this invention refer to the terms "and / or," and are used interchangeably with them unless the context explicitly indicates otherwise. The term "such as" as used in the embodiments of this invention refers to the phrase "such as but not limited to," and is used interchangeably with it.

[0173] The flowcharts and method descriptions in the embodiments of this invention are merely illustrative examples and are not intended to require or imply that the steps of the various embodiments must be performed in the given order. As those skilled in the art will recognize, the steps in the above embodiments can be performed in any order. Words such as "then," "next," etc., are not intended to limit the order of steps; these words are only used to guide the reader through the description of these methods. Furthermore, any reference to a singular element, such as the use of the articles "a," "one," or "the," is not to be construed as limiting that element to the singular.

[0174] Furthermore, the steps and apparatus in the various embodiments of the present invention are not limited to any one embodiment. In fact, new embodiments can be conceived by combining relevant steps and apparatus in the various embodiments of the present invention with the concepts of the present invention, and these new embodiments are also included within the scope of the present invention.

[0175] The various operations in the embodiments of the present invention can be performed by any suitable means capable of performing the corresponding functions. Such means may include various hardware and / or software components and / or modules, including but not limited to hardware circuits or processors.

[0176] The method of this invention includes one or more actions for implementing the method described above. The methods and / or actions may be interchanged without departing from the scope of the claims. In other words, unless a specific order of actions is specified, the order and / or use of specific actions may be modified without departing from the scope of the claims.

[0177] The functions in the embodiments of the present invention can be implemented in hardware, software, firmware, or any combination thereof. If implemented in software, the functions can be stored as one or more instructions on a physical computer-readable medium. The storage medium can be any available physical medium that can be accessed by a computer. By way of example and not limitation, such a computer-readable medium can include RAM, ROM, EEPROM, CD-ROM or other optical disc storage, magnetic disk storage or other magnetic storage devices, or any other physical medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer. As used herein, disk and disc include compact disc (CD), laser disc, optical disc, DVD (Digital Versatile Disc), floppy disk, and Blu-ray disc, wherein a disk reproduces data magnetically, while a disc optically reproduces data using lasers.

[0178] Therefore, a computer program product can perform the operations described herein. For example, such a computer program product can be a computer-readable tangible medium having instructions tangibly stored (and / or encoded) thereon, which can be executed by one or more processors to perform the operations described herein. The computer program product may include packaging materials.

[0179] Other examples and implementations are within the scope and spirit of the embodiments of the present invention and the appended claims. For example, due to the nature of software, the functions described above can be implemented using software executed by a processor, hardware, firmware, hardwired, or any combination thereof. Features implementing the functions can also be physically located in various locations, including being distributed so that portions of the function are implemented at different physical locations.

[0180] Those skilled in the art can make various changes, substitutions, and modifications to the technology described herein without departing from the teachings defined by the appended claims. Furthermore, the scope of the claims of this disclosure is not limited to the specific aspects of the processes, machines, manufactures, events, means, methods, and actions described above. Currently existing or later-developed processes, machines, manufactures, events, means, methods, or actions that perform substantially the same function or achieve substantially the same result as the corresponding aspects described herein can be utilized. Therefore, the appended claims include such processes, machines, manufactures, events, means, methods, or actions within their scope.

[0181] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the invention. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of the invention. Therefore, the invention is not intended to be limited to the aspects shown herein, but rather to be carried out within the widest scope consistent with the principles and novel features disclosed herein.

[0182] The above description has been given for illustrative and descriptive purposes. Furthermore, this description is not intended to limit the embodiments of the invention to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations therein. Moreover, anything not described in detail in this specification is prior art well known to those skilled in the art.

Claims

1. An optical network operation and maintenance system based on digital twins and augmented reality, characterized in that: The system includes a digital twin platform, which connects at least one AR terminal and at least one Internet terminal; and the digital twin platform is equipped with a main control module, a network twin module, a fault diagnosis module and a data pool. The AR terminal is used to: collect real-time information from a first-person perspective at the scene; when the fault diagnosis module provides a solution, it receives the operation and maintenance instructions issued by the main control module; otherwise, it sends the rendered real-time information from the first-person perspective to the main control module and receives the remote diagnosis results fed back by the Internet terminal. The main control module is used to: send real-time information from the first perspective and physical network information data stored in the data pool to the network twin module; Receive the diagnostic results from the fault diagnosis module. If a solution is provided, issue an operation and maintenance instruction to the AR terminal. Otherwise, send the rendered first-person perspective real-time information and the generated twin network to the Internet terminal. The network twin module is used to: simulate and model the physical network to generate a twin network of the physical network; The fault diagnosis module is used to: perform network fault diagnosis based on the twin network; The Internet terminal is used for: performing remote real-time diagnosis based on rendered first-person perspective real-time information and twin network; The system also includes an edge cloud, which contains a controller and at least one edge node; The AR terminal is also used to: when there is a data processing task that needs to be calculated, determine whether the task exceeds the local computing capacity. If it does, send a computing request to the controller of the edge cloud, and after receiving the migration strategy from the controller, migrate the data processing task to the corresponding edge node for execution according to the migration strategy. The controller is configured to: upon receiving a computing request, generate a migration strategy based on the bandwidth and computing resources of all edge nodes in the edge cloud, and feed it back to the corresponding AR terminal and the corresponding edge node; The edge node is used to: complete the calculation task according to the received migration strategy, and feed back the calculation result to the corresponding AR terminal.

2. The optical network operation and maintenance system based on digital twins and augmented reality as described in claim 1, characterized in that, The AR terminal determines whether the task exceeds its local computing power, specifically including: Get the maximum allowable latency for the computing task ; Calculate the time for local computation The calculation formula is: ,in Indicates the size of the task data to be calculated. Indicates AR terminal i The percentage of computing resources allocated to this task. Indicates AR terminal i Local computing power; Compare and ,like ≤ If so, it is determined that the local computing power is not exceeded; if > If so, it is determined that the local computing capacity is exceeded.

3. The optical network operation and maintenance system based on digital twins and augmented reality as described in claim 2, characterized in that, When the controller generates a migration strategy by combining the bandwidth and computing resources of all edge nodes in the edge cloud, it adopts a method that minimizes the total cost of computing tasks for all AR terminals.

4. The optical network operation and maintenance system based on digital twins and augmented reality as described in claim 3, characterized in that, The controller generates a migration strategy by minimizing the total cost of computing tasks across all AR terminals, specifically including: The controller is an AR terminal that needs to perform task migration. i Generate task migration table , ,in Indicates AR terminal i Should the task be migrated to the edge node? j If so =1, otherwise 0 Represents edge nodes j Assigned to AR terminals i bandwidth percentage Represents edge nodes j bandwidth, Represents edge nodes j Assigned to AR terminals i The proportion of computing resources Represents edge nodes j Computational power; Based on the above To form an AR terminal i Table of all different migration strategies , = ,and =1 k = j ; Based on the migration strategy table for all AR terminals that need to be migrated Generate the total migration strategy set F , F = ; Based on the above F Calculate the total computational cost of different migration strategies. , wherein Total latency including migration execution Total energy consumption ; The final migration strategy is obtained by minimizing the total cost of the computational tasks. The formula for minimizing the total cost of the computational tasks is as follows: 。 5. The optical network operation and maintenance system based on digital twins and augmented reality as described in claim 4, characterized in that, The controller calculates the total computational cost of different migration strategies. Specifically, it includes: Computing AR Terminal i Migrate tasks to edge nodes j Total latency of migration execution The calculation formula is: = ； In the formula, Indicates AR terminal i Upload computing tasks to edge nodes j Transmission delay; Indicates AR terminal i The task is at the edge node j The computation time on it; Represents edge nodes j Feedback results to AR terminal i Transmission delay; Computing AR Terminal i Migrate tasks to edge nodes j Total energy consumption of migration execution The calculation formula is: = ； In the formula, Indicates transmission power consumption; Indicates AR terminal i Local waiting energy consumption; Indicates the power consumption of the receiver; According to the formula = +(1- ) The total cost of the computation task is obtained. ;in, The weights assigned.

6. The optical network operation and maintenance system based on digital twins and augmented reality as described in claim 5, characterized in that: When the task is a latency-sensitive task, the The value increases; when the task is an energy-sensitive task, the value of... The value decreases.

7. The optical network operation and maintenance system based on digital twins and augmented reality as described in claim 4, characterized in that, The controller generates a migration strategy by minimizing the total cost of computing tasks across all AR terminals, while also satisfying the following constraints: Migrate tasks to edge nodes j The total execution latency shall not exceed the maximum allowable latency of the computation task. ; And edge nodes j The bandwidth allocated to each task and not exceeding the bandwidth of that node; And edge nodes j The computing resources allocated to each task and the computing power not exceeding that of the node.

8. A method for optical network operation and maintenance based on digital twins and augmented reality, applying the system described in any one of claims 1 to 7, characterized in that, The method includes the following steps: The AR terminal collects real-time information from a first-person perspective at the scene. The main control module sends the real-time information from the first perspective and the physical network information data stored in the data pool to the network twin module; The network twin module generates a twin network of the physical network by simulating and modeling the physical network based on the real-time information from the first perspective and the physical network information data. The fault diagnosis module performs network fault diagnosis based on the twin network and feeds back the diagnosis results to the main control module. If the diagnosis results provide a solution, the main control module issues corresponding operation and maintenance instructions to the AR terminal based on the solution. Otherwise, it obtains the rendered first-view real-time information from the AR terminal, obtains the twin network from the network twin module, and sends it to the Internet terminal. The Internet terminal performs remote real-time diagnosis based on the rendered first-view real-time information and the twin network, and feeds back the remote diagnosis results to the AR terminal. When the AR terminal has a data processing task that requires calculation, the AR terminal determines whether the task exceeds its local computing capacity. If the limit is exceeded, a computing request is sent to the controller of the edge cloud. After receiving the computing request, the controller generates a migration strategy based on the bandwidth and computing resources of all edge nodes in the edge cloud, and feeds it back to the corresponding AR terminal and the corresponding edge node. After receiving the migration strategy from the controller, the corresponding AR terminal migrates the data processing task to the corresponding edge node for execution according to the migration strategy; the corresponding edge node completes the calculation task according to the received migration strategy and feeds back the calculation result to the corresponding AR terminal.

Images