Optical transport network cable and fiber adding method and device, storage medium and computer equipment

Abstract

The application discloses an optical transmission network fiber and cable adding method and device, a storage medium and computer equipment. The method comprises the following steps: obtaining the service demand and the network element data corresponding to the target area, the service demand comprising the optimization target and the constraint condition of the optical transmission network in the target area, and the network element data representing the arrangement of the optical communication equipment in the optical transmission network; generating the target network topology of the digital twin model of the optical transmission network in the target area corresponding to the target area according to the service demand and the network element data, the target network topology comprising the connection mode between the optical communication equipment in the optical transmission network; and generating a task issuing instruction according to the target network topology, wherein the task issuing instruction is used for instructing the fiber and cable adding of the optical transmission network in the target area, so as to achieve the purpose of reasonably utilizing the optical transmission network resources, thereby realizing the technical effect of intelligent planning fiber and cable adding, and further solving the technical problem of fiber and cable adding at the minimum cost.

Description

Technical Field

[0001] The present invention relates to the field of optical transmission, and in particular to a method, device, storage medium and computer equipment for adding fibers and cables to an optical transmission network. Background Art

[0002] The sheer number of optical cables across China presents significant challenges for equipment maintenance. For example, optical distribution frames (ODFs) require extensive tasks such as fiber pulling, patching, troubleshooting, fiber usage statistics, fiber splicing, and emergency patching. Manual maintenance alone increases costs and limits the optical transmission network's evolution toward full automation. While artificial intelligence has been introduced to enable automated management of certain equipment and operations within the optical transmission network, a comprehensive intelligent management platform is still lacking, hindering accurate monitoring, online management, real-time control, and rapid maintenance of optical communication systems and networks.

[0003] To address the above-mentioned problems, no effective solutions have been proposed so far. Summary of the Invention

[0004] Embodiments of the present invention provide a method, apparatus, storage medium, and computer equipment for adding fibers and cables to an optical transmission network, to at least solve the technical problem of adding fibers and cables at a minimum cost.

[0005] According to one aspect of an embodiment of the present invention, a method for adding fibers and cables to an optical transmission network is provided, including: obtaining business requirements and network element data corresponding to a target area, the business requirements including optimization goals and constraints of the optical transmission network in the target area, and the network element data characterizing the layout of optical communication equipment in the optical transmission network; generating a target network topology corresponding to the target area based on the business requirements and network element data, wherein the target network topology is a digital twin model of the optical transmission network in the target area, and the target network topology includes the connection method between optical communication equipment in the optical transmission network; generating a task issuing instruction based on the target network topology, wherein the task issuing instruction is used to instruct the optical transmission network in the target area to be added fibers and cables.

[0006] Optionally, based on the business requirements and the network element data, a target network topology corresponding to the target area is generated, including: creating an initial network topology corresponding to the target area based on the network element data; determining decision pairs based on the business requirements and the initial network topology, wherein any decision pair in the decision pair includes a site selection decision and a link selection decision; determining decision priorities corresponding to the decision pairs, wherein the decision priorities reflect the degree of proximity to the optimization target; updating the initial network topology based on the decision pairs and the decision priorities, and generating candidate network topologies corresponding one-to-one to the decision pairs; screening from the candidate network topologies, and selecting the target network topology that meets the business requirements.

[0007] Optionally, screening is performed from candidate network topologies to select a target network topology that meets business needs, including: when the optimization target is network construction cost and the constraints include network reliability and / or resource utilization, determining the candidate network construction cost corresponding to each candidate network topology, and determining the candidate network reliability and / or candidate resource utilization corresponding to each candidate network topology; based on the candidate network construction cost, the candidate network reliability and / or the candidate resource utilization, screening the target network topology from the candidate network topologies, wherein the network construction cost of the target network topology is less than a first threshold, the network reliability of the target network topology is greater than a second threshold, and the resource utilization of the target network topology is less than a third threshold.

[0008] Optionally, determining the candidate network reliability corresponding to each candidate network topology includes: determining the number of ring communication sites and the total number of communication sites based on the candidate network topology; determining the site ring rate of each candidate network topology based on the number of ring communication sites and the total number of communication sites, wherein the site ring rate is the ratio of the number of ring communication sites to the total number of communication sites; determining the degree of the ring communication site based on the candidate network topology; determining the ring site degree of each candidate network topology based on the degree of the ring communication site, wherein the ring site degree is the sum of the degrees of the ring communication sites; determining the ring site voltage of each candidate network topology based on the candidate network topology; determining a first weight value corresponding to the site ring rate, a second weight value corresponding to the ring site degree, and a third weight value corresponding to the ring site voltage, wherein the sum of the first weight value, the second weight value, and the third weight value is 1; determining the candidate network reliability corresponding to each candidate network topology based on the site ring rate, the ring site degree, the ring site voltage, the first weight value, the second weight value, and the third weight value.

[0009] Optionally, determining the candidate resource utilization corresponding to each candidate network topology includes: determining the link bandwidth utilization of each candidate network topology based on the candidate network topology; determining the optical fiber occupancy of each candidate network topology based on the candidate network topology; determining a fourth weight value corresponding to the link bandwidth utilization and a fifth weight value corresponding to the optical fiber occupancy, wherein the sum of the fourth weight value and the fifth weight value is 1; determining the candidate resource utilization corresponding to each candidate network topology based on the link bandwidth utilization, the optical fiber occupancy, the fourth weight value and the fifth weight value.

[0010] Optionally, the initial network topology is updated according to the decision pairs and decision priorities respectively, and a candidate network topology corresponding to the decision pairs is generated, including: inputting the decision pairs into the dual deep Q network algorithm in order from high to low decision priorities to generate a decision network topology; when the decision network topology meets the constraints, determining the decision network topology as the candidate network topology.

[0011] Optionally, a task issuing instruction is generated based on the target network topology, including: performing topological pruning on the target network topology to obtain a target communication link, wherein the target communication link is a communication link in the target network topology whose available bandwidth is less than a preset threshold; determining the link load corresponding to each target communication link, wherein each link load in the link load is the sum of the priorities of the business demands allocated on the corresponding target communication link, and the link load represents the usage and performance status of the communication link; determining the routing path in the target network topology based on the link load; and generating a task issuing instruction based on the target network topology and the routing path.

[0012] According to another aspect of an embodiment of the present invention, a device for adding fibers and cables to an optical transmission network is provided, including: an acquisition module for acquiring business requirements and network element data corresponding to a target area, the business requirements including optimization objectives and constraints of the optical transmission network in the target area, and the network element data characterizing the layout of optical communication equipment in the optical transmission network; a first generation module for generating a target network topology corresponding to the target area based on the business requirements and network element data, wherein the target network topology is a digital twin model of the optical transmission network in the target area, and the target network topology includes the connection method between optical communication equipment in the optical transmission network; a second generation module for generating a task issuing instruction based on the target network topology, wherein the task issuing instruction is used to instruct the optical transmission network in the target area to be added fibers and cables.

[0013] According to another aspect of an embodiment of the present invention, a non-volatile storage medium is provided, which includes a stored program, wherein when the program is running, the device where the non-volatile storage medium is located is controlled to execute any of the above-mentioned optical transmission network fiber and cable adding methods.

[0014] According to another aspect of an embodiment of the present invention, a computer device is provided, which includes a memory and a processor, wherein the memory is used to store programs, and the processor is used to run the programs stored in the memory, wherein any one of the above-mentioned methods for adding fibers and cables to an optical transmission network is executed when the program is running.

[0015] In an embodiment of the present invention, by obtaining business requirements and network element data corresponding to the target area, the business requirements include the optimization goals and constraints of the optical transmission network in the target area, and the network element data characterizes the layout of the optical communication equipment in the optical transmission network; based on the business requirements and network element data, a target network topology corresponding to the target area is generated, wherein the target network topology is a digital twin model of the optical transmission network in the target area, and the target network topology includes the connection method between the optical communication equipment in the optical transmission network; based on the target network topology, a task issuance instruction is generated, wherein the task issuance instruction is used to instruct the optical transmission network in the target area to add fibers and cables, thereby achieving the purpose of rationally utilizing the resources of the optical transmission network, thereby realizing the technical effect of intelligent planning of fiber addition and cabling, and further solving the technical problem of adding fibers and cables at the lowest cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings, which constitute part of this application, are intended to provide a further understanding of this application. The exemplary embodiments and descriptions of this application are intended to explain this application and do not constitute an improper limitation on this application. In the accompanying drawings:

[0017] Figure 1 A hardware structure block diagram of a computer terminal used in a method for adding fiber and cable to an optical transmission network is shown;

[0018] Figure 2 is a schematic diagram of a method for adding fibers and cables to an optical transmission network according to an embodiment of the present invention;

[0019] Figure 3 is a schematic diagram of an initial network topology provided according to an optional embodiment of the present invention;

[0020] Figure 4 is a schematic diagram of a target network topology provided according to an optional embodiment of the present invention;

[0021] Figure 5 2. This is a schematic diagram of the architecture of an optical transmission network automated scheduling system based on digital twins according to an optional embodiment of the present invention;

[0022] Figure 6 A structural block diagram of a fiber and cable adding device for an optical transmission network provided according to an optional embodiment of the present invention. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0024] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0025] According to an embodiment of the present invention, an embodiment of a method for adding fibers and cables to an optical transmission network is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0026] The optical transmission network fiber and cable adding method embodiment provided in the embodiment of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 The hardware structure block diagram of a computer terminal for implementing a method for adding fiber and cable to an optical transmission network is shown. Figure 1 As shown, the computer terminal 10 may include one or more processors (processors 102a, 102b, ..., 102n are used as examples in the figure) (the processors may include but are not limited to processing devices such as microprocessors MCU or programmable logic devices FPGA), and a memory 104 for storing data. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply, and / or a camera. It will be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1More or fewer components than shown, or with Figure 1 Different configurations shown.

[0027] It should be noted that the one or more processors and / or other data processing circuits described above may generally be referred to herein as "data processing circuitry." The data processing circuitry may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuitry may be a single, independent processing module, or may be incorporated in whole or in part into any of the other components of the computer terminal 10. As described in the embodiments of the present application, the data processing circuitry serves as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0028] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the optical transmission network fiber and cable addition method in the embodiment of the present invention. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, implementing the security alarm verification method of the above-mentioned application. The memory 104 may include a high-speed random access memory and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely located relative to the processor, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0029] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 .

[0030] Figure 2 FIG. 1 is a flow chart of a method for adding fibers and cables to an optical transmission network according to an embodiment of the present invention. Figure 2 As shown, the method includes the following steps:

[0031] Step S202 : obtaining service requirements and network element data corresponding to the target area. The service requirements include optimization targets and constraints of the optical transmission network in the target area. The network element data represents the layout of optical communication equipment in the optical transmission network.

[0032] In the above steps, network data can come from the infrastructure layer, where the infrastructure layer can be composed of optical communication equipment, mainly including optical line terminals (OLTs), optical network units (ONUs), and the optical transmission channels (ODNs) between the two (composed of supporting components such as optical fiber cables, optical cross-connect boxes (FDTs), optical distribution frames (ODFs), and optical fiber distribution boxes (FATs). The ODN uses a series of intelligent devices, including intelligent FDTs, intelligent ODFs, and intelligent FATs. Compared with ordinary ODN equipment, intelligent ODNs can realize automatic collection and reporting of port status information, fiber ID management, and other functions. In intelligent ODN equipment, electronic labels (eIDs) are used to replace traditional paper labels. Information such as the serial position of the optical fiber in the optical cable, the fiber route, and the distribution module connected to this optical fiber can be automatically reported to automatically generate the network topology. At the same time, the management of the optical fiber link can also be completed by operating the eID.

[0033] Network element data can be acquired by the data acquisition module. This module is primarily responsible for collecting network element data from the infrastructure layer at regular intervals. This data includes information such as device ID, device type, device number connected to the upstream and downstream devices, device operating status, active and idle ports, and other information. This data is stored in the network element database and used to build the basic model. The basic model primarily generates a service model based on service requirements and a topology model based on the network element data. The topology model primarily reflects the connection relationships between communication sites and optical cable lines in the optical transmission network.

[0034] The data acquisition module contains a time slot model, and the time interval between adjacent time slots is It is assumed that the physical network state remains unchanged within each time slot. Network element data is collected from the infrastructure layer within each time slot. The shorter the collection interval, the closer the gap between the constructed DTN and the physical network, and the more accurate the decisions made. Specific data collection sources include network operation logs, electronic tags, and other sensors. Network operation logs can be used to obtain information such as resource utilization, notification messages, delay jitter, and blocking rate. Electronic tags can be used to obtain information such as the fiber's sequence position in the cable, fiber routing, and the distribution module connected to it. Other sensors can also be used to obtain information such as optical signal-to-noise ratio, modulation format, transmission speed, and system impairments. After acquiring these heterogeneous data from multiple sources, a series of data fusion processes, including desensitization, cleaning, labeling, naming, and normalization, are required before storage in the network element database.

[0035] Business requirements can include demand indicators such as maximum construction cost, network reliability, and resource utilization, providing optimization goals and constraints for the topology planning model. As more DTN models are constructed, more business demand indicators can be added.

[0036] The DTN model consists of four components: a data acquisition module, a foundational model, a topology planning model, and a routing model. The interaction between these components in the DTN provides an effective solution for automated scheduling of optical transmission networks. Future research will explore the potential addition of additional models to the DTN, tailored to the actual network operation and maintenance requirements, to enhance scheduling and management capabilities.

[0037] Step S204: Generate a target network topology corresponding to the target area based on business requirements and network element data, wherein the target network topology is a digital twin model of the optical transmission network in the target area, and the target network topology includes the connection method between optical communication devices in the optical transmission network.

[0038] As an optional embodiment, a target network topology corresponding to a target area is generated according to business requirements and network element data, including: creating an initial network topology corresponding to the target area according to the network element data; determining decision pairs according to business requirements and the initial network topology, wherein any decision pair in the decision pair includes a site selection decision and a link selection decision; determining decision priorities corresponding to the decision pairs, wherein the decision priorities reflect the degree of proximity to the optimization target; updating the initial network topology according to the decision pairs and the decision priorities, and generating candidate network topologies corresponding one-to-one to the decision pairs; screening from the candidate network topologies, and selecting a target network topology that meets the business requirements.

[0039] In the aforementioned optional embodiment, the topology planning model selects the decision pairs. This model is responsible for selecting appropriate sites and links from among the candidate sites and links to expand into the existing topology model, thereby planning a cabling solution that meets service requirements. The decision solution is first verified in the base model and, once verified, is distributed to the infrastructure layer, reducing trial-and-error costs. The routing model is responsible for planning routing paths for the latest service requests in the service model based on the latest topology model. Similarly, the planned routes must be verified in the base model before being distributed to the infrastructure layer.

[0040] The basic model construction cycle is consistent with the data collection cycle, including the construction of business models and topology models. However, it should be noted that due to the short interval of the data collection cycle, there may not be new business requests in every time slot.

[0041] Assume that the service set requested in time slot t is Each business S q is defined as a four-tuple, namely where v o , v d Represents the actual node and the termination node of the business, B q Indicates the bandwidth requirement of the link for the service, which is set according to the service type. qIndicates the service priority, which is defined based on the importance of the service. When the basic model receives a series of service requests, it needs to sort the services according to their priority, and input higher-priority services into the routing model for processing earlier.

[0042] The topology model at time slot t is defined as G t =(V t , E t ). Where V t is the set of communication sites in the physical network, E t Represents the collection of communication links between communication sites. is defined as a two-tuple, namely in Indicates the degree of the site, Represents the voltage value of the station at time slot t. i，j ∈E t Define a triple, namely in Indicates link l i，j The remaining bandwidth, Indicates the number of idle fibers. Indicates link l i，j The service set carried on i，j Indicates the number of services carried. The set of candidate communication sites at time slot t is The set of candidate links is

[0043] As an optional embodiment, candidate network topologies are screened to select a target network topology that meets business needs. When the optimization target is network construction cost and the constraints include network reliability and / or resource utilization, the candidate network construction costs corresponding to each candidate network topology are determined, as well as the candidate network reliability and / or candidate resource utilization corresponding to each candidate network topology are determined; based on the candidate network construction cost, the candidate network reliability and / or the candidate resource utilization, the target network topology is screened from the candidate network topologies, wherein the network construction cost of the target network topology is less than a first threshold, the network reliability of the target network topology is greater than a second threshold, and the resource utilization of the target network topology is less than a third threshold.

[0044] In the aforementioned optional embodiment, the candidate network topologies can be selected using a topology planning model. This model primarily selects candidate communication sites and links based on the indicators in the business requirements layer and adds them to the existing topology model to form a new topology. By adding appropriate fiber and cable, the network's carrying capacity can be doubled to accommodate business changes and development needs.

[0045] Define the site selection decision as When selecting an alternative site v o，m hour, Otherwise 0. Site v o，m The construction cost is CV o，m ; Similarly, define the link selection decision as When you select link e o，n hour, Otherwise it is 0, link e o，n The construction cost is CE o，n Therefore, the network construction cost is: After the node and link selection, a new network topology will be formed, which is defined as NG t =(NV t ,NE t ). Only when NG t The selection is successful only when the business demand indicators are met. The present invention comprehensively evaluates network reliability through three aspects: site loop rate, loop site degree, and loop site voltage. Resource utilization is evaluated through link bandwidth utilization and fiber occupancy. First, the site degree and site voltage are normalized and mapped to the same dimension as the loop rate. The processed site degree and voltage values ​​are: in, Represent the maximum and minimum values ​​of site degree respectively; Represent the maximum and minimum values ​​of the site voltage respectively. The site loop rate is expressed as: in Represents the total number of nodes in the new topology. When In a ring, otherwise it is 0. The degree of the ring site is:

[0046] The voltage of the looped site is: Therefore, network reliability is defined as: Rel t =α×pl t +β×pd t +γ×pv t Where α+β+γ=1. Bandwidth utilization is expressed as: in Indicates a link The initial bandwidth of the fiber is: Likewise, Indicates a link The total amount of optical fiber. The resource utilization is: Where λ+μ=1.

[0047] In order to reasonably and economically add fiber and cable to the existing topology, the present invention constructs a topology planning problem model with the goal of minimizing construction cost and other demand indicators as constraints. The specific model is as follows: OP: min Cost t ,stC1:Cost t <Cost max , C2:Rel t ≥Rel min , The constraint C1 indicates that the construction cost cannot be higher than the maximum value of the specified construction cost. max ; C2 means that the network reliability cannot be lower than the minimum reliability threshold Rel min ; C3 means resource utilization cannot be higher than the maximum utilization RU max ;C4 The judgment variable representing the connectivity of the graph requires that the new network topology must be a connected graph, that is, The specific steps of the topology planning algorithm are as follows: State space: mainly includes the topology model G within the time slot t t , Alternative Site Collection Alternative link set Therefore, the state space is defined as:

[0048] Action space: mainly includes the site selection decision set Link selection decision set Therefore, the action space is defined as:

[0049] Reward function: corresponds to the optimization objective of the problem model. Since the DRL algorithm aims to maximize the cumulative reward, and the optimization objective of the model is to minimize the construction cost, the immediate reward is set to the difference between the maximum construction cost and the actual cost. When the state does not meet the constraints of the problem model, the reward is 0. Therefore, the reward function is:

[0050] The DDQN-based topology planning algorithm is shown in Algorithm 1. When calculating the target Q value, the DQN algorithm always selects the maximum Q value in the next state. While this can quickly bring the Q value closer to the possible optimization target, it can easily lead to overestimation. To address this issue, DDQN eliminates the overestimation problem by decoupling the selection of the target Q value action and the calculation of the target Q value. The target Q value calculation formula is updated to: Use mean square error to calculate the loss function:

[0051] Algorithm 1: The pseudo code of the DDQN-based topology planning algorithm is as follows:

[0052] Initialize the playback memory unit R to a capacity of N R

[0053] Initialize Q network Q θ The parameter is θ; initialize the target Q network Q θ- Parameter θ - =θ

[0054] for episode=1:MaxEpisode:

[0055]

[0056] As an optional embodiment, the candidate network reliability corresponding to each candidate network topology is determined, and based on the candidate network topology, the number of ring communication sites and the total number of communication sites are determined; based on the number of ring communication sites and the total number of communication sites, the site ring rate of each candidate network topology is determined, wherein the site ring rate is the ratio of the number of ring communication sites to the total number of communication sites; based on the candidate network topology, the degree of the ring communication site is determined; based on the degree of the ring communication site, the ring site degree of each candidate network topology is determined, wherein the ring site degree is the sum of the degrees of the ring communication sites; based on the candidate network topology, the ring site voltage of each candidate network topology is determined; a first weight value corresponding to the site ring rate, a second weight value corresponding to the ring site degree, and a third weight value corresponding to the ring site voltage are determined, wherein the sum of the first weight value, the second weight value, and the third weight value is 1; based on the site ring rate, the ring site degree, the ring site voltage, the first weight value, the second weight value, and the third weight value, the candidate network reliability corresponding to each candidate network topology is determined.

[0057] As an optional embodiment, the candidate resource utilization corresponding to each candidate network topology is determined, and the link bandwidth utilization of each candidate network topology is determined based on the candidate network topology; the fiber occupancy rate of each candidate network topology is determined based on the candidate network topology; a fourth weight value corresponding to the link bandwidth utilization and a fifth weight value corresponding to the fiber occupancy rate are determined, wherein the sum of the fourth weight value and the fifth weight value is 1; based on the link bandwidth utilization, the fiber occupancy rate, the fourth weight value and the fifth weight value, the candidate resource utilization corresponding to each candidate network topology is determined.

[0058] As an optional embodiment, the initial network topology is updated according to the decision pairs and decision priorities, and a candidate network topology corresponding to the decision pairs is generated, including: inputting the decision pairs into the dual deep Q network algorithm in order from high to low decision priorities to generate a decision network topology; when the decision network topology meets the constraint conditions, determining the decision network topology as the candidate network topology.

[0059] Step S204: Generate a task issuing instruction based on the target network topology, wherein the task issuing instruction is used to instruct to add fibers and cables to the optical transmission network in the target area.

[0060] As an optional embodiment, a task issuing instruction is generated based on the target network topology, including: performing topological pruning on the target network topology to obtain a target communication link, wherein the target communication link is a communication link in the target network topology whose available bandwidth is less than a preset threshold; determining the link load corresponding to each target communication link, wherein each link load in the link load is the sum of the priorities of the business demands allocated on the corresponding target communication link, and the link load represents the usage and performance status of the communication link; determining the routing path in the target network topology based on the link load; and generating a task issuing instruction based on the target network topology and the routing path.

[0061] In the above optional embodiment, the topology pruning of the target network topology can be performed by the routing model. The specific operation steps of the routing model are as follows: q , the routing selection step in the present invention is to first perform topology pruning, from NE t Remove the available bandwidth less than B q The system then calculates the link load by summing the service priorities of each link after topology pruning. Load balancing is then used as a constraint to plan a suitable transmission path for the service using routing algorithms, including the shortest path algorithm. After completing the path planning, it must be verified in the basic model and only delivered to the infrastructure after it meets service requirements.

[0062] For example, a certain city's power communication backbone network is selected for verification. The initial network topology is as follows: Figure 3 As shown. The gray sites represent candidate sites and the dotted lines represent candidate links. First, a DTN is constructed for the network topology. The data acquisition module is used to collect data at time intervals. The network topology metadata is collected periodically, and then the network topology model and service model are constructed in each time slot. The topology planning model and model solving algorithm are used to make the optimal fiber and cable addition decision. After verification in the basic model, it is sent to the physical network to complete the fiber distribution and other actions, and the target network topology is obtained. Figure 4 Finally, based on the target topology model, topology pruning and load balancing are used to select the appropriate path for communication for the services requested in the business model. Similarly, after passing verification in the basic model, the path is sent to the physical network.

[0063] Through the above steps, the business requirements and network element data corresponding to the target area are obtained. The business requirements include the optimization goals and constraints of the optical transmission network in the target area, and the network element data represents the layout of optical communication equipment in the optical transmission network. Based on the business requirements and network element data, the target network topology corresponding to the target area is generated, where the target network topology is a digital twin model of the optical transmission network in the target area, and the target network topology includes the connection method between optical communication equipment in the optical transmission network. Based on the target network topology, a task issuance instruction is generated, where the task issuance instruction is used to instruct the optical transmission network in the target area to add fiber and cable. The technical goal of rationally utilizing optical transmission network resources is achieved, thereby realizing the technical effect of intelligent planning of fiber and cable addition, and further solving the problem of adding fiber and cable at the lowest cost.

[0064] Figure 5 This is a schematic diagram of the architecture flow of the optical transmission network automation scheduling system based on digital twins according to an embodiment of the present invention. Figure 5 As shown, the method includes the following steps: The optical transmission network automated scheduling system architecture has a three-layer structure: the business requirements layer, the DTN layer, and the infrastructure layer. The business requirements layer can include demand indicators such as maximum construction cost, network reliability, and resource utilization, providing optimization objectives and constraints for the topology planning model. When focusing on the construction of more DTN models, more business requirements indicators can be added. The DTN layer can be composed of four parts: a data acquisition module, a basic model, a topology planning model, and a routing model. Information such as device type, device number connected to the upstream device, device number connected to the downstream device, device operating status, device used port information, and device idle port information is stored in the network element database and used to build the basic model. The basic model primarily generates a business model based on business requirements and a topology model based on network element data. The topology model primarily reflects the connection relationship between each communication site and optical cable line in the optical transmission network. The topology planning model is responsible for selecting appropriate sites and links from candidate sites and links to expand into the existing topology model, thereby planning a cabling solution that meets business requirements. The decision solution is first verified in the basic model and, upon successful verification, is distributed to the infrastructure layer, reducing trial and error costs. The routing model is responsible for planning routing paths for the latest service requests in the service model based on the latest topology model. Similarly, the planned routes must be verified in the base model before being delivered to the infrastructure layer. The interaction between the various components of the DTN forms an effective solution for automated scheduling of optical transport networks. Future research will allow for the addition of additional models to the DTN to improve scheduling and management capabilities based on actual network operation and maintenance requirements.

[0065] The infrastructure layer can be composed of optical communication equipment, mainly including optical line terminals (OLTs), optical network units (ONUs), and the optical transmission channels (ODNs) between the two (composed of supporting components such as optical fiber cables, optical cross-connect boxes (FDTs), optical distribution frames (ODFs), and optical fiber splitters (FATs). The ODN uses a series of intelligent devices, including intelligent FDTs, intelligent ODFs, and intelligent FATs. Compared with ordinary ODN equipment, intelligent ODNs can realize automatic collection and reporting of port status information, fiber ID management, and other functions. In intelligent ODN equipment, electronic labels (eIDs) are used to replace traditional paper labels. They can automatically report information such as the serial position of the optical fiber in the optical cable, the fiber route, and the distribution module connected to this optical fiber, automatically generate the network topology, and also manage the optical fiber link by operating the eIDs.

[0066] According to an embodiment of the present invention, a safety alarm verification device for implementing the above-mentioned optical transmission network fiber and cable adding method is also provided. Figure 6 is a structural block diagram of an optical transmission network fiber adding and cable adding device provided according to an embodiment of the present invention, such as Figure 6 As shown, the optical transmission network fiber adding and cabling device includes: an acquisition module 602, a first generation module 604 and a second generation module 606. The optical transmission network fiber adding and cabling device is described below.

[0067] The acquisition module 602 is used to acquire the service requirements and network element data corresponding to the target area. The service requirements include the optimization goals and constraints of the optical transmission network in the target area. The network element data represents the layout of the optical communication equipment in the optical transmission network.

[0068] The first generation module 604 is connected to the acquisition module 602 and is used to generate a target network topology corresponding to the target area based on business requirements and network element data, wherein the target network topology is a digital twin model of the optical transmission network in the target area, and the target network topology includes the connection method between optical communication devices in the optical transmission network.

[0069] The second generating module 606 is connected to the first generating module 604 and generates a task issuing instruction according to the target network topology, wherein the task issuing instruction is used to instruct to add fibers and cables to the optical transmission network in the target area.

[0070] It should be noted that the acquisition module 602, the first generation module 604, and the second generation module 606 correspond to steps S202 to S206 in Example 2. The examples and application scenarios implemented by the three modules and the corresponding steps are the same, but are not limited to the contents disclosed in the above embodiment. It should be noted that the above modules, as part of the device, can be run in the computer terminal 10 provided in the embodiment.

[0071] An embodiment of the present invention may provide a computer device. Optionally, in this embodiment, the computer device may be located in at least one of a plurality of network devices in a computer network. The computer device includes a memory and a processor.

[0072] Among them, the memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the optical transmission network fiber addition and cabling method and device in the embodiment of the present invention. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, realizing the above-mentioned security alarm verification method. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely located relative to the processor, and these remote memories may be connected to the computer terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0073] The processor can call the information and application programs stored in the memory through the transmission device to perform the following steps: obtain the business requirements and network element data corresponding to the target area, the business requirements include the optimization goals and constraints of the optical transmission network in the target area, and the network element data characterizes the layout of the optical communication equipment in the optical transmission network; based on the business requirements and network element data, generate the target network topology corresponding to the target area, wherein the target network topology is a digital twin model of the optical transmission network in the target area, and the target network topology includes the connection method between the optical communication equipment in the optical transmission network; based on the target network topology, generate a task issuance instruction, wherein the task issuance instruction is used to instruct the optical transmission network in the target area to add fiber and cable.

[0074] Optionally, the processor may also execute program code for the following steps: generating a target network topology corresponding to the target area based on business requirements and network element data, including: creating an initial network topology corresponding to the target area based on the network element data; determining decision pairs based on business requirements and the initial network topology, wherein any decision pair in the decision pairs includes a site selection decision and a link selection decision; determining decision priorities corresponding to the decision pairs, wherein the decision priorities reflect the degree of proximity to the optimization target; updating the initial network topology based on the decision pairs and the decision priorities, and generating candidate network topologies corresponding one-to-one to the decision pairs; screening from the candidate network topologies to select the target network topology that meets the business requirements.

[0075] Optionally, the processor may also execute the program code of the following steps: when the optimization target is the network construction cost and the constraints include network reliability and / or resource utilization, determining the candidate network construction cost corresponding to each candidate network topology, and determining the candidate network reliability and / or candidate resource utilization corresponding to each candidate network topology; based on the candidate network construction cost, the candidate network reliability and / or the candidate resource utilization, screening out the target network topology from the candidate network topologies, wherein the network construction cost of the target network topology is less than a first threshold, the network reliability of the target network topology is greater than a second threshold, and the resource utilization of the target network topology is less than a third threshold.

[0076] Optionally, the processor may also execute the program code of the following steps: determining the number of looped communication sites and the total number of communication sites according to the candidate network topology; determining the site loop rate of each candidate network topology according to the number of looped communication sites and the total number of communication sites, wherein the site loop rate is the ratio of the number of looped communication sites to the total number of communication sites; determining the degree of the looped communication site according to the candidate network topology; determining the looped site degree of each candidate network topology according to the degree of the looped communication site, wherein the looped site degree is the sum of the degrees of the looped communication sites; determining the looped site voltage of each candidate network topology according to the candidate network topology; determining a first weight value corresponding to the site loop rate, a second weight value corresponding to the looped site degree, and a third weight value corresponding to the looped site voltage, wherein the sum of the first weight value, the second weight value, and the third weight value is 1; determining the candidate network reliability corresponding to each candidate network topology according to the site loop rate, the looped site degree, the looped site voltage, the first weight value, the second weight value, and the third weight value.

[0077] Optionally, the processor may also execute the program code of the following steps: determining the candidate resource utilization corresponding to each candidate network topology, including: determining the link bandwidth utilization of each candidate network topology based on the candidate network topology; determining the fiber occupancy of each candidate network topology based on the candidate network topology; determining a fourth weight value corresponding to the link bandwidth utilization and a fifth weight value corresponding to the fiber occupancy, wherein the sum of the fourth weight value and the fifth weight value is 1; determining the candidate resource utilization corresponding to each candidate network topology based on the link bandwidth utilization, the fiber occupancy, the fourth weight value and the fifth weight value.

[0078] Optionally, the processor may also execute the program code of the following steps: updating the initial network topology according to the decision pairs and decision priorities, and generating candidate network topologies corresponding one-to-one to the decision pairs, including: inputting the decision pairs into the dual deep Q network algorithm in order from high to low decision priorities to generate a decision network topology; and determining the decision network topology as a candidate network topology when the decision network topology meets the constraints.

[0079] Optionally, the processor may also execute the program code of the following steps: performing topology pruning on the target network topology to obtain a target communication link, wherein the target communication link is a communication link in the target network topology whose available bandwidth is less than a preset threshold; determining the link load corresponding to each target communication link, wherein each link load in the link load is the sum of the priorities of the business demands allocated on the corresponding target communication link, and the link load represents the usage and performance status of the communication link; determining the routing path in the target network topology based on the link load; and generating a task issuing instruction based on the target network topology and the routing path.

[0080] By adopting the embodiment of the present invention, a solution for adding fibers and cables to an optical transmission network is provided. By obtaining the business requirements and network element data corresponding to the target area, the business requirements include the optimization goals and constraints of the optical transmission network in the target area, and the network element data characterizes the layout of the optical communication equipment in the optical transmission network; based on the business requirements and network element data, a target network topology corresponding to the target area is generated, wherein the target network topology is a digital twin model of the optical transmission network in the target area, and the target network topology includes the connection mode between the optical communication equipment in the optical transmission network; based on the target network topology, a task issuance instruction is generated, wherein the task issuance instruction is used to instruct the optical transmission network in the target area to add fibers and cables. The purpose of rationally utilizing the resources of the optical transmission network is achieved, thereby realizing the technical effect of intelligent planning of adding fibers and cables, and further solving the technical problem of adding fibers and cables at the lowest cost.

[0081] A person skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a non-volatile storage medium, which may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0082] The embodiment of the present invention further provides a non-volatile storage medium. Optionally, in this embodiment, the non-volatile storage medium can be used to store program codes executed by the method for adding fibers and cables to an optical transmission network provided by the embodiment.

[0083] Optionally, in this embodiment, the non-volatile storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.

[0084] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for executing the following steps: generating a target network topology corresponding to the target area based on business requirements and network element data, including: creating an initial network topology corresponding to the target area based on the network element data; determining decision pairs based on business requirements and the initial network topology, wherein any decision pair in the decision pairs includes a site selection decision and a link selection decision; determining decision priorities corresponding to the decision pairs, wherein the decision priorities reflect the degree of proximity to the optimization target; updating the initial network topology based on the decision pairs and the decision priorities, and generating candidate network topologies corresponding one-to-one to the decision pairs; screening from the candidate network topologies to select the target network topology that meets the business requirements.

[0085] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for executing the following steps: screening from candidate network topologies to select a target network topology that meets business needs, including: when the optimization target is network construction cost and the constraints include network reliability and / or resource utilization, determining the candidate network construction cost corresponding to each candidate network topology, and determining the candidate network reliability and / or candidate resource utilization corresponding to each candidate network topology; screening the target network topology from the candidate network topologies based on the candidate network construction cost, the candidate network reliability and / or the candidate resource utilization, wherein the network construction cost of the target network topology is less than a first threshold, the network reliability of the target network topology is greater than a second threshold, and the resource utilization of the target network topology is less than a third threshold.

[0086] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: determining the candidate network reliability corresponding to each candidate network topology, including: determining the number of ring communication sites and the total number of communication sites based on the candidate network topology; determining the site ring rate of each candidate network topology based on the number of ring communication sites and the total number of communication sites, wherein the site ring rate is the ratio of the number of ring communication sites to the total number of communication sites; determining the degree of the ring communication site based on the candidate network topology; determining the ring site degree of each candidate network topology based on the degree of the ring communication site, wherein the ring site degree is the sum of the degrees of the ring communication sites; determining the ring site voltage of each candidate network topology based on the candidate network topology; determining a first weight value corresponding to the site ring rate, a second weight value corresponding to the ring site degree, and a third weight value corresponding to the ring site voltage, wherein the sum of the first weight value, the second weight value, and the third weight value is 1; determining the candidate network reliability corresponding to each candidate network topology based on the site ring rate, the ring site degree, the ring site voltage, the first weight value, the second weight value, and the third weight value.

[0087] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: determining the candidate resource utilization corresponding to each candidate network topology, including: determining the link bandwidth utilization of each candidate network topology based on the candidate network topology; determining the fiber occupancy of each candidate network topology based on the candidate network topology; determining a fourth weight value corresponding to the link bandwidth utilization and a fifth weight value corresponding to the fiber occupancy, wherein the sum of the fourth weight value and the fifth weight value is 1; determining the candidate resource utilization corresponding to each candidate network topology based on the link bandwidth utilization, the fiber occupancy, the fourth weight value and the fifth weight value.

[0088] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for executing the following steps: updating the initial network topology according to the decision pairs and decision priorities, and generating candidate network topologies corresponding one-to-one to the decision pairs, including: inputting the decision pairs into the dual deep Q network algorithm in order from high to low decision priority to generate a decision network topology; and determining the decision network topology as a candidate network topology when the decision network topology meets the constraints.

[0089] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for executing the following steps: generating a task issuing instruction based on the target network topology, including: performing topology pruning on the target network topology to obtain a target communication link, wherein the target communication link is a communication link in the target network topology whose available bandwidth is less than a preset threshold; determining the link load corresponding to each target communication link, wherein each link load in the link load is the sum of the priorities of the business demands allocated on the corresponding target communication link, and the link load represents the usage and performance status of the communication link; determining the routing path in the target network topology based on the link load; and generating a task issuing instruction based on the target network topology and the routing path.

[0090] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0091] In the above embodiments of the present invention, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0092] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only exemplary. For example, the division of units can be a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0093] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple units. Some or all of the units may be selected to achieve the purpose of the present embodiment according to actual needs.

[0094] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0095] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a non-volatile storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk, and other media that can store program codes.

[0096] The above are only preferred embodiments of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for adding fibers and cables to an optical transmission network, characterized in that: include: Obtaining service requirements and network element data corresponding to a target area, wherein the service requirements include optimization objectives and constraints of an optical transmission network within the target area, and the network element data represents a layout of optical communication equipment in the optical transmission network; Generating a target network topology corresponding to the target area according to the business requirements and the network element data, wherein the target network topology is a digital twin model of the optical transmission network in the target area, and the target network topology includes a connection mode between the optical communication devices in the optical transmission network; Generating a task issuing instruction according to the target network topology, wherein the task issuing instruction is used to instruct to add fiber and cable to the optical transmission network in the target area; Among them, according to the business requirements and the network element data, a target network topology corresponding to the target area is generated, including: creating an initial network topology corresponding to the target area according to the network element data; determining a decision pair according to the business requirements and the initial network topology, wherein any decision pair in the decision pair includes a site selection decision and a link selection decision; determining the decision priorities corresponding to the decision pairs, wherein the decision priorities reflect the degree of proximity to the optimization target; updating the initial network topology according to the decision pairs and the decision priorities, and generating candidate network topologies corresponding one-to-one to the decision pairs; screening from the candidate network topologies to select the target network topology that meets the business requirements.

2. The method according to claim 1, characterized in that Screening the candidate network topologies to select the target network topology that meets the business requirements includes: When the optimization target is network construction cost and the constraint conditions include network reliability and / or resource utilization, determining the candidate network construction cost corresponding to each of the candidate network topologies, and determining the candidate network reliability and / or candidate resource utilization corresponding to each of the candidate network topologies; The target network topology is screened out from the candidate network topologies based on the candidate network construction cost, the candidate network reliability and / or the candidate resource utilization, wherein the network construction cost of the target network topology is less than a first threshold, the network reliability of the target network topology is greater than a second threshold, and the resource utilization of the target network topology is less than a third threshold.

3. The method according to claim 2, characterized in that Determining the reliability of candidate networks corresponding to the candidate network topologies includes: Determining the number of ring communication sites and the total number of communication sites based on the candidate network topology; Determining, based on the number of the ring communication sites and the total number of communication sites, a site ring ratio of each of the candidate network topologies, wherein the site ring ratio is a ratio of the number of the ring communication sites to the total number of communication sites; Determining the degree of the ring communication site according to the candidate network topology; Determining the ring site degree of each of the candidate network topologies according to the degrees of the ring communication sites, wherein the ring site degree is the sum of the degrees of the ring communication sites; Determining, according to the candidate network topology, voltages of respective looped sites of the candidate network topology; Determine a first weight value corresponding to the site loop rate, a second weight value corresponding to the loop site degree, and a third weight value corresponding to the loop site voltage, wherein a sum of the first weight value, the second weight value, and the third weight value is 1; The reliability of the candidate networks corresponding to the candidate network topologies is determined according to the site loop rate, the loop site degree, the loop site voltage, the first weight value, the second weight value, and the third weight value.

4. The method according to claim 2, characterized in that Determining the candidate resource utilization corresponding to each of the candidate network topologies includes: Determining link bandwidth utilization of each of the candidate network topologies according to the candidate network topologies; Determining, based on the candidate network topologies, optical fiber occupancy rates of the respective candidate network topologies; Determining a fourth weight value corresponding to the link bandwidth utilization and a fifth weight value corresponding to the optical fiber occupancy rate, wherein a sum of the fourth weight value and the fifth weight value is 1; The candidate resource utilizations corresponding to the candidate network topologies are determined according to the link bandwidth utilization, the optical fiber occupancy, the fourth weight value, and the fifth weight value.

5. The method according to claim 1, wherein The initial network topology is updated according to the decision pairs and the decision priorities, and candidate network topologies corresponding to the decision pairs are generated, including: Inputting the decision pairs into a dual deep Q network algorithm in descending order of decision priority to generate a decision network topology; In a case where the decision network topology meets the constraint condition, the decision network topology is determined as the candidate network topology.

6. The method according to any one of claims 1 to 5, characterized in that Generating a task issuing instruction according to the target network topology includes: Performing topology pruning on the target network topology to obtain a target communication link, wherein the target communication link is a communication link in the target network topology whose available bandwidth is less than a preset threshold; Determining link loads corresponding to the target communication links, wherein each of the link loads is the sum of priorities of service demands allocated on the corresponding target communication link, and the link loads represent usage and performance of the communication links; determining a routing path in the target network topology according to the link load; The task issuing instruction is generated according to the target network topology and the routing path.

7. A device for adding fiber and cable to an optical transmission network, characterized in that: include: an acquisition module, configured to acquire service requirements and network element data corresponding to a target area, wherein the service requirements include optimization objectives and constraints of an optical transmission network within the target area, and the network element data represents a layout of optical communication equipment in the optical transmission network; A first generating module is configured to generate a target network topology corresponding to the target area according to the business requirements and the network element data, wherein the target network topology is a digital twin model of the optical transmission network in the target area, and the target network topology includes a connection mode between the optical communication devices in the optical transmission network; A second generating module generates a task issuing instruction according to the target network topology, wherein the task issuing instruction is used to instruct to add fiber and cable to the optical transmission network in the target area; Among them, the first generation module is also used to create an initial network topology corresponding to the target area based on the network element data; determine a decision pair based on the business requirements and the initial network topology, wherein any decision pair in the decision pair includes a site selection decision and a link selection decision; determine the decision priorities corresponding to the decision pairs, wherein the decision priorities reflect the degree of proximity to the optimization target; update the initial network topology according to the decision pairs and the decision priorities, and generate candidate network topologies corresponding one-to-one to the decision pairs; screen from the candidate network topologies to select the target network topology that meets the business requirements.

8. A non-volatile storage medium, characterized in that: The non-volatile storage medium includes a stored program, wherein when the program is running, the device where the non-volatile storage medium is located is controlled to execute the method for adding fibers and cables to an optical transmission network as claimed in any one of claims 1 to 6.

9. A computer device, characterized in that: The method comprises one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method for adding fibers and cables to an optical transmission network as described in any one of claims 1 to 6.

Images