Method and system for automatically and intelligently planning OTN (Optical Transport Network) service of power communication network

Abstract

The invention provides a method and a system for automatically and intelligently planning an OTN (Optical Transport Network) service of a power communication network, and the method comprises the steps: enabling an intra-domain service to directly search an equipment multiplexing layer logic path according to the relation between a site and equipment, and sequentially executing set service strategies when the logic path is searched in an end-to-end path deep learning model, until the logic path data meeting the business requirements are found; when a starting site and a termination site at the two ends of the service do not belong to the same subnet management domain, the service is judged to be a cross-domain service, the cross-domain service needs to use the starting site as a parameter, a logic path is searched in an end-to-end path deep learning model, and the found service path termination site needs to exist in a cross-domain management node list; and then continuously searching the cross-domain logic path through the cross-domain node until a business cross-domain termination site is found, and executing business strategies set in the domain respectively according to the found cross-domain logic path until a logic path data set meeting business requirements is searched.

Description

Technical Field

[0001] The present invention belongs to the technical field of power communication network maintenance, and in particular relates to a method and system for automatic intelligent planning of OTN services of a power communication network. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] The communication technologies currently used in the field of power communication networks are diverse and very mature. Due to the diversity of technologies, flexible networking, and large-scale equipment, more convenient means of service activation are needed. While providing more powerful communication capabilities, the new OTN network also adds more intelligent operation and maintenance solutions to meet users' needs for high-speed, low-latency and reliable data transmission.

[0004] The method of automatic intelligent planning of OTN services in power communication networks is an important means to achieve intelligent operation and maintenance of power communication networks. Even though intelligent configuration algorithms already exist in the communication field, they are similar to the intelligent algorithms of power communication networks but are not applicable. Summary of the invention

[0005] In order to overcome the shortcomings of the above-mentioned prior art, the present invention provides a method for automatic intelligent planning of OTN services in power communication networks, which uses algorithms to aggregate, mine, calculate and other technical means to intelligently plan the service path, and provide the optimal planning solution according to service requirements. It is targeted at intelligent operation and maintenance design of OTN services in power communication networks in the field of power communication, and has stronger applicability and practicality.

[0006] To achieve the above objectives, one or more embodiments of the present invention provide the following technical solutions:

[0007] In a first aspect, a method for automatic intelligent planning of OTN services in a power communication network is disclosed, comprising:

[0008] When the starting site and the ending site at both ends of the service belong to the same subnet management domain, it is judged as an intra-domain service. The intra-domain service directly searches for the logical path of the device multiplexing layer based on the relationship between the site and the device. When the logical path is found in the end-to-end path deep learning model, the set service policies are executed in sequence until the logical path data that meets the service requirements is found;

[0009] When the starting site and the ending site at both ends of the service do not belong to the same subnet management domain, it is judged as a cross-domain service. The cross-domain service needs to use the starting site as a parameter to find the logical path in the end-to-end path deep learning model. The end site of the service path found needs to exist in the cross-domain management node list, and then continue to search for the cross-domain logical path through the cross-domain node until the cross-domain end site of the service is found. The service policies set in the domain are executed respectively according to the found cross-domain logical path until the logical path data set that meets the service requirements is found;

[0010] Output a list of business paths that meet the policy conditions, and output a list of solutions sorted by policy weights, and select the required planned path as the final decision solution.

[0011] As a further technical solution, for intra-domain services, when a logical path is found in the end-to-end path deep learning model, the set service policies are executed in sequence, including:

[0012] Search for devices based on the relationship between the start and end sites and the devices, and search for logical paths based on the devices at both ends. When searching, first determine whether a logical path exists. If so, determine whether to execute the business path shortest strategy. If so, execute the business path shortest strategy. If not, determine whether to execute the network load balancing strategy. If so, execute the network load balancing strategy. If not, determine whether to execute the business path routing strategy. If so, execute the business path routing strategy. If not, determine whether there is a path that meets the strategy. If so, end the search. Otherwise, there is no logical path.

[0013] As a further technical solution, regarding the network load balancing strategy, it is necessary to me (E a , E z , idx) path, and prioritize the logical path with the least channel occupancy to develop a planning scheme.

[0014] As a further technical solution, according to CH me (E a , E z , idx) routing paragraphs summarize and calculate the channel occupied capacity, and do not distinguish the logical channel CH of the multiplex layer device in the calculation data me (E a , E z , idx) path validity, take the non-repetitive occupied channel data on the full path section for summary calculation, the formula is described as follows:

[0015] OCH all (E a , E z , idx) = SUM(CHR me (Ea , E z , idx), CHR me (E a , E z , idx))

[0016] According to OCH all (E a , E z , idx) Channel occupancy capacity judgment OCH all (E a , E z , idx) path is the path with the lowest load, loop iterative comparison, and take the path data with the smallest occupied capacity. The formula is described as follows:

[0017]

[0018] OCH min (E a , E z , idx) is the path with the lowest load on the optical cable of the logical channel of the multiplexing layer equipment, which meets the effectiveness of use.

[0019] As a further technical solution, when the shortest service path strategy is needed, CH me (E a , E z , idx) path routing nodes are summarized and the planning scheme is formulated with priority given to the logical path with the shortest path.

[0020] As a further technical solution, according to CH me (E a , E z , idx) The routing section summarizes the number of device nodes in the calculation path, and does not distinguish the logical path CH of the multiplexing layer device in the calculation data me (E a , E z , idx) path validity, take the non-repeated path equipment data on the full path segment for summary calculation, the formula is described as follows:

[0021] CH count (E a , E z , idx) = SUM(CHR me (E a , E z , idx), CHR me (E a , E z , idx))

[0022] According to CH count (E a , Ez , idx) determines the number of device nodes through CH count (E a , E z , idx) path is the path with the smallest number of device nodes, loop iterative comparison, and take the path data with the smallest number of device nodes. The formula is described as follows:

[0023]

[0024] CH min (E a , E z , idx) is the path with the minimum number of device nodes through the logical path of the multiplexing layer device, which meets the usage effectiveness.

[0025] As a further technical solution, according to the characteristics of business data applications, when it is necessary to use a business path routing strategy, set the necessary device nodes or exclude the necessary device nodes. Set the device nodes that the business path must pass through according to business scenario requirements, or exclude the device nodes from the business path.

[0026] As a further technical solution, the business logic path exclusion device node formula is described as follows:

[0027]

[0028] The formula for the device nodes that the business logic path must pass through is described as follows:

[0029]

[0030] CH me (E a , E z , idx) is a valid multiplexing layer device logical path, which meets the use effectiveness. When setting the service path routing strategy, the exclusion strategy and the must-pass strategy can be implemented at the same time. After the two strategies are set at the same time, the conditions must be met at the same time to meet the use requirements.

[0031] In a second aspect, a system for automatic intelligent planning of OTN services in a power communication network is disclosed, comprising:

[0032] The intra-domain service module is configured as follows: when the starting site and the ending site at both ends of the service belong to the same subnet management domain, it is judged as an intra-domain service. The intra-domain service directly searches for the logical path of the device multiplexing layer according to the relationship between the site and the device. When the logical path is found in the end-to-end path deep learning model, the set service policies are executed in sequence until the logical path data that meets the service requirements is found;

[0033] The cross-domain service module is configured as follows: when the starting site and the ending site at both ends of the service do not belong to the same subnet management domain, it is judged as a cross-domain service. The cross-domain service needs to use the starting site as a parameter to find the logical path in the end-to-end path deep learning model. The found service path ending site needs to exist in the cross-domain management node list, and then continue to find the cross-domain logical path through the cross-domain node until the service cross-domain ending site is found. The service policies set in the domain are respectively executed according to the found cross-domain logical path until a logical path data set that meets the service requirements is found;

[0034] The business path planning module is configured to: output a list of business paths that meet the policy conditions, and output a list of solutions in accordance with the policy weights, and select the required planning path as the final decision solution based on the actual demand situation.

[0035] One or more of the above technical solutions have the following beneficial effects:

[0036] The technical solution of the present invention can provide an algorithm for automatic intelligent planning of OTN services of the power communication network, provide a service path planning solution for the opening of power communication network services, plan different routing strategies according to different service requirements, calculate the network load according to the number of services carried on the routing path, and plan the service path to keep the network load in a balanced state as much as possible.

[0037] The technical solution of the present invention realizes the rationalization, standardization and intelligence of business path planning by calculating, calculat- ing and mining network load data, reduces the workload of manual participation or provides decision-making references for business personnel. The method can provide intuitive business path selection for decision makers. The network topology structure is the optical cable segment that carries the optical signal transmission, and the business path is the optical cable segment through which the business signal is transmitted. The direction and position of the business path in the network can be viewed in combination with the network topology structure, and an attempt is made to solve the problem that the communication method is manually drawn and the communication method cannot automatically plan the route.

[0038] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0040] Figure 1 This is a service planning step in an embodiment of the present invention. DETAILED DESCRIPTION

[0041] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0042] It should be noted that the terms used herein are for describing specific embodiments only and are not intended to be limiting of exemplary embodiments according to the present invention.

[0043] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0044] Embodiment 1

[0045] See attached Figure 1 As shown, this embodiment discloses a method for automatic intelligent planning of OTN services in a power communication network, including:

[0046] When the starting site and the ending site at both ends of the service belong to the same subnet management domain, it is judged as an intra-domain service. The intra-domain service directly searches for the device multiplexing layer logical path based on the relationship between the site and the device. The multiplexing layer logical path is the multiplexing of service signals from low-order signals to high-order signals. When the logical path is found in the end-to-end path deep learning model, the set service policies are executed in sequence until the logical path data that meets the service requirements is found;

[0047] When the starting site and the ending site at both ends of the service do not belong to the same subnet management domain, it is judged as a cross-domain service. The cross-domain service needs to use the starting site as a parameter to find the logical path in the end-to-end path deep learning model. The end site of the service path found needs to exist in the cross-domain management node list, and then continue to search for the cross-domain logical path through the cross-domain node until the cross-domain end site of the service is found. The service policies set in the domain are executed respectively according to the found cross-domain logical path until the logical path data set that meets the service requirements is found;

[0048] Output a list of business paths that meet the policy conditions, and output a list of solutions sorted by policy weights. Select the required planning path as the final decision solution based on actual needs.

[0049] The technical principle of the sub-technical solution of this embodiment requires computing with basic resource data and a large amount of business data. Through the overall management of data, a set of data management models is established, including data model management, model relationship management and model parameter management. Each data model is independent of each other and has a low coupling degree. Relevant data is accessed through the data relationship model. The algorithm implementation is mainly divided into the following steps:

[0050] Data Model Management:

[0051] It is necessary to maintain basic resource data models such as site data, optical cable data, optical fiber data, equipment data, wiring data, topology data, crossover data, channel data, multiplex section data, etc. The subsequent processing flow is based on the data model;

[0052] Model parameter management:

[0053] Site model parameters include but are not limited to region, site number, site name, jurisdiction unit, voltage level, location information, geographic coordinates, etc. Optical cable model parameters include but are not limited to optical cable name, optical cable number, A-end site, Z-end site, optical cable type, optical cable age, optical cable length, etc. Optical fiber model parameters include but are not limited to owned optical cable, optical cable number, optical fiber name, optical fiber sequence number, optical fiber number, etc. Equipment model parameters include but are not limited to equipment number, equipment name, equipment type, equipment manufacturer, network access time, current status, equipment model, software version, equipment IP, etc. Wiring model parameters include but are not limited to wiring number, wiring equipment, equipment port, optical fiber number, etc. Topology model parameters include but are not limited to A-end site, Z-end site, A-end equipment, Z-end equipment, A-end port, Z-end port, owned optical fiber number, etc. Cross-connect model parameters include but are not limited to equipment number, A-end port, Z-end port, A-end time slot, Z-end time slot, cross-connect rate, etc. The multiplex section model parameters include but are not limited to multiplex section number, A-end site, Z-end site, A-end device, Z-end device, A-end port, Z-end port, etc. The channel model parameters include but are not limited to channel number, A-end site, Z-end site, A-end device, Z-end device, A-end port, Z-end port, channel number, channel frequency, channel layer rate, channel capacity, etc.

[0054] Model relationship management:

[0055] The main managed model relationships include but are not limited to the relationship between site and optical cable, the relationship between optical cable and optical fiber, the relationship between site and equipment, the relationship between topology and optical fiber, the relationship between equipment and optical fiber, the relationship between multiplexing segment and channel, etc.

[0056] Parameters and abstract model:

[0057] The business of the power communication network starts from one site and ends at another site. The logical connection data can be described as being connected and carried by many optical cables in order. The business model of the communication network can be abstracted into a formula, which is described as follows:

[0058] CIR(N,S a , S z ) is a logical description of an end-to-end service channel.

[0059] Description of other parameters in CIR:

[0060] N: the name of the end-to-end service channel;

[0061] S a : Business source site;

[0062] S z : Business host site.

[0063] Intra-domain end-to-end multiplexing layer path algorithm:

[0064] According to the networking characteristics of the OTN network, it is necessary to calculate the multiplexing layer path step from the device in the domain to any reachable device, create the multiplexing layer logical path between devices by iterating the relationship between the multiplexing layer devices, and obtain the routing device order of the device multiplexing layer logical path and sort and store it.

[0065] The formula for obtaining data results based on the device multiplexing layer logical path iteration algorithm is described as follows:

[0066] CH me (E a , E z , idx) is the logical path of the multiplexing layer of the end-to-end equipment within the domain.

[0067] CHR me (E a , E z , idx) is the end-to-end device multiplexing layer logical path device routing segment within the domain.

[0068] CH me With CHR me Other parameter descriptions in:

[0069] E a It is the source device of the link;

[0070] E z It is the link sink device;

[0071] idx is the same source and sink logical channel number;

[0072] End-to-end path management within the domain:

[0073] Intra-domain end-to-end path management requires multiplexing layer equipment logical channel CH me (E a , E z , idx) path validity is verified by using the multiplexing layer device logical path routing segment CHR me (E a , E z , idx) idle channel capacity is summarized to determine whether the routing segment is valid. If the routing segment is determined to be an invalid routing segment, the CH me (E a, E z , idx) path is judged as an invalid path and cannot meet the usage requirements and is removed from the data set. me (E a , E z , idx) path is a valid path, then CHR me (E a , E z , idx) The smallest channel capacity in the routing segment data set is used as CH me (E a , E z , idx) path’s maximum capacity.

[0074] According to CHR me (E a , E z , idx) routing segment summary calculation segment channel capacity, the formula is described as follows:

[0075] CHR rt (E a , E z , idx) = SUM(CHR me (E a , E z , idx))

[0076] According to CHR rt (E a , E z , idx) Channel capacity judgment CH me (E a , E z , idx) path is valid, the formula is described as follows:

[0077]

[0078] CH ok (E a , E z , idx) is the valid multiplexing layer device logical path, which meets the usage effectiveness.

[0079] Cross-domain node path management:

[0080] Summarize and calculate the network devices in the site, and summarize the cross-domain devices that may exist in the site, that is, network devices from different equipment manufacturers coexist in the same site. Establish connection relationships between multiplexing layer devices from different equipment manufacturers in the same site, that is, maintain cross-domain node path relationships.

[0081] The cross-domain node logical path data formula is described as follows:

[0082] CH ky(E a , E z ) is a device multiplexing layer logical path between cross-domain nodes;

[0083] CHR ky (E a , E z ) is the device routing segment of the device multiplexing layer logical path between cross-domain nodes.

[0084] In this implementation example, multiple strategies are used, including:

[0085] In order to solve the problem of network load imbalance, a network load balancing strategy is proposed:

[0086] According to the characteristics of business data applications, when a network load balancing strategy is needed, CH me (E a , E z , idx) path, and prioritize the logical path with the least number of occupied channels to make a planning plan. The network load balancing strategy only optimizes the load balancing of the intra-domain network, mainly to avoid the problem of optical cable overload.

[0087] According to CH me (E a , E z , idx) routing paragraphs summarize and calculate the channel occupied capacity, and do not distinguish the logical channel CH of the multiplex layer device in the calculation data me (E a , E z , idx) path validity, take the non-repetitive occupied channel data on the full path section for summary calculation, the formula is described as follows:

[0088] OCH all (E a , E z , idx) = SUM(CHR me (E a , E z , idx), CHR me (E a , E z , idx))

[0089] According to OCH all (E a , E z , idx) Channel occupancy capacity judgment OCH all (E a , E z , idx) path is the path with the lowest load, loop iterative comparison, and take the path data with the smallest occupied capacity. The formula is described as follows:

[0090]

[0091] OCH min (E a , E z , idx) is the path with the lowest load on the optical cable of the logical channel of the multiplexing layer equipment, which meets the effectiveness of use.

[0092] In order to solve the problem of the shortest service path, a shortest service path strategy is proposed:

[0093] According to the characteristics of business data applications, when the shortest business path strategy is needed, CH me (E a , E z , idx) path routing nodes are summarized and the planning scheme is formulated with priority given to the logical path with the shortest path.

[0094] According to CH me (E a , E z , idx) The routing section summarizes the number of device nodes in the calculation path, and does not distinguish the logical path CH of the multiplexing layer device in the calculation data me (E a , E z , idx) path validity, take the non-repeated path equipment data on the full path segment for summary calculation, the formula is described as follows:

[0095] CH count (E a , E z , idx) = SUM(CHR me (E a , E z , idx), CHR me (E a , E z , idx))

[0096] According to CH count (E a , E z , idx) determines the number of device nodes through CH count (E a , E z , idx) path is the path with the smallest number of device nodes, loop iterative comparison, and take the path data with the smallest number of device nodes. The formula is described as follows:

[0097]

[0098] CH min (E a , E z, idx) is the path with the minimum number of device nodes through the logical path of the multiplexing layer device, which meets the usage effectiveness.

[0099] Service path routing strategy:

[0100] According to the characteristics of business data applications, when you need to use the business path routing strategy, you can set the device nodes that must be passed or exclude the device nodes that must be passed. According to the business scenario requirements, set the device nodes that the business path must pass through, or exclude the device nodes from the business path.

[0101] The business logic path exclusion device node formula is described as follows:

[0102]

[0103] The formula for the device nodes that the business logic path must pass through is described as follows:

[0104]

[0105] CH me (E a , E z , idx) is a valid multiplexing layer device logical path, which meets the use effectiveness. When setting the service path routing strategy, the exclusion strategy and the must-pass strategy can be implemented at the same time. After the two strategies are set at the same time, the conditions must be met at the same time to meet the use requirements.

[0106] See again the attached Figure 1 As shown in the figure, the business intelligence planning solution:

[0107] At the initial stage of business planning, the pre-input conditions that need to be met are not limited to basic business information such as business name, starting site, and ending site. At the beginning of the plan, it is necessary to determine whether the business is a cross-domain business based on the sites at both ends of the business, so as to select different business logics for processing.

[0108] When the starting site and the ending site at both ends of the service belong to the same subnet management domain, it can be judged as an intra-domain service, and the service process selects the intra-domain service processing process. The intra-domain service can directly find the logical path of the device multiplexing layer based on the relationship between the site and the device. When the logical path is found in the end-to-end path deep learning model data, the set service policies are executed in sequence. When the shortest service routing strategy is executed, the logical paths of various service path lengths are stored and learned until the logical path data that meets the service requirements is found.

[0109] When the starting site and the ending site at both ends of the service do not belong to the same subnet management domain, it can be judged as a cross-domain service, and the service process selects the cross-domain service processing process. The cross-domain service needs to use the starting site as a parameter to find the logical path in the end-to-end path deep learning model data. The end site of the service path found needs to exist in the list of cross-domain management nodes, and then continue to search for the cross-domain logical path through the cross-domain node until the cross-domain end site of the service is found. According to the found cross-domain logical path, the service policies set in the domain are executed respectively until the logical path data set that meets the service requirements is found.

[0110] The above-mentioned service channel termination site is a designated cross-domain node, which is a critical point for the connection between equipment from different manufacturers.

[0111] The plan ultimately outputs a list of business paths that meet the policy conditions, and outputs a list of plans sorted by policy weights. The entire device routing of the path can be viewed through the business logic path, and business personnel can select the appropriate planned path as the final decision plan based on actual needs.

[0112] The technical solution of this embodiment establishes an end-to-end path deep learning model for the OTN network to solve the problem that the communication method is manually drawn and the communication method cannot automatically plan routes. It solves the problem that the communication method cannot automatically avoid safety hazards such as equipment overload and optical cable overload. The above network load balancing strategy is used to solve the overload problem.

[0113] Embodiment 2

[0114] The purpose of this embodiment is to provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the program.

[0115] Embodiment 3

[0116] The purpose of this embodiment is to provide a computer-readable storage medium.

[0117] A computer-readable storage medium stores a computer program, which executes the steps of the above method when executed by a processor.

[0118] Embodiment 4

[0119] The purpose of this embodiment is to provide a system for automatic intelligent planning of OTN services in a power communication network, including:

[0120] The intra-domain service module is configured as follows: when the starting site and the ending site at both ends of the service belong to the same subnet management domain, it is judged as an intra-domain service. The intra-domain service directly searches for the logical path of the device multiplexing layer according to the relationship between the site and the device. When the logical path is found in the end-to-end path deep learning model, the set service policies are executed in sequence until the logical path data that meets the service requirements is found;

[0121] The cross-domain service module is configured as follows: when the starting site and the ending site at both ends of the service do not belong to the same subnet management domain, it is judged as a cross-domain service. The cross-domain service needs to use the starting site as a parameter to find the logical path in the end-to-end path deep learning model. The found service path ending site needs to exist in the cross-domain management node list, and then continue to find the cross-domain logical path through the cross-domain node until the service cross-domain ending site is found. The service policies set in the domain are respectively executed according to the found cross-domain logical path until a logical path data set that meets the service requirements is found;

[0122] The business path planning module is configured to: output a list of business paths that meet the policy conditions, and output a list of solutions in accordance with the policy weights, and select the required planning path as the final decision solution based on the actual demand situation.

[0123] The steps involved in the apparatuses of the above embodiments 2, 3 and 4 correspond to the method embodiment 1, and the specific implementation methods can refer to the relevant description part of embodiment 1. The term "computer-readable storage medium" should be understood as a single medium or multiple media including one or more instruction sets; it should also be understood to include any medium that can store, encode or carry an instruction set for execution by a processor and enable the processor to execute any method in the present invention.

[0124] Those skilled in the art should understand that the modules or steps of the present invention described above can be implemented by a general-purpose computer device, or alternatively, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. The present invention is not limited to any specific combination of hardware and software.

[0125] Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without creative work are still within the scope of protection of the present invention.

Claims

1. A method for automatic intelligent planning of OTN services in a power communication network, characterized in that: include: When the starting site and the ending site at both ends of the service belong to the same subnet management domain, it is judged as an intra-domain service. The intra-domain service directly searches for the logical path of the device multiplexing layer based on the relationship between the site and the device. When the logical path is found in the end-to-end path deep learning model, the set service policies are executed in sequence until the logical path data that meets the service requirements is found; When the starting site and the ending site at both ends of the service do not belong to the same subnet management domain, it is judged as a cross-domain service. The cross-domain service needs to use the starting site as a parameter to find the logical path in the end-to-end path deep learning model. The end site of the service path found needs to exist in the cross-domain management node list, and then continue to search for the cross-domain logical path through the cross-domain node until the cross-domain end site of the service is found. The service policies set in the domain are executed respectively according to the found cross-domain logical path until the logical path data set that meets the service requirements is found; Output a list of business paths that meet the policy conditions, and output a list of solutions sorted by policy weights, and select the required planned path as the final decision solution.

2. A method for automatic intelligent planning of OTN services in a power communication network as claimed in claim 1, characterized in that: For intra-domain services, when a logical path is found in the end-to-end path deep learning model, the set service policies are executed in sequence, including: Search for devices based on the relationship between the start and end sites and the devices, and search for logical paths based on the devices at both ends. When searching, first determine whether a logical path exists. If so, determine whether to execute the business path shortest strategy. If so, execute the business path shortest strategy. If not, determine whether to execute the network load balancing strategy. If so, execute the network load balancing strategy. If not, determine whether to execute the business path routing strategy. If so, execute the business path routing strategy. If not, determine whether there is a path that meets the strategy. If so, end the search. Otherwise, there is no logical path.

3. The method for automatic intelligent planning of OTN services in a power communication network as claimed in claim 1, characterized in that: Regarding the network load balancing strategy, CH me (E a , E z , idx) path, and prioritize the logical path with the least channel occupancy to develop a planning scheme.

4. The method for automatic intelligent planning of OTN services in a power communication network as claimed in claim 1, characterized in that: According to CH me (E a , E z , idx) routing paragraphs summarize and calculate the channel occupied capacity, and do not distinguish the logical channel CH of the multiplex layer device in the calculation data me (E a , E z , idx) path validity, take the non-repetitive occupied channel data on the full path section for summary calculation, the formula is described as follows: OCH all (E a ,E z ,idx)=SUM(CHR me (E a ,E z ,idx),CHR me (E a ,E z , idx)) According to OCH all (E a , E z , idx) Channel occupancy capacity judgment OCH all (E a , E z , idx) path is the path with the lowest load, loop iterative comparison, and take the path data with the smallest occupied capacity. The formula is described as follows: OCH min (E a , E z , idx) is the path with the lowest load on the optical cable of the logical channel of the multiplexing layer equipment, which meets the effectiveness of use.

5. The method for automatic intelligent planning of OTN services in a power communication network as claimed in claim 1, characterized in that: When you need to use the shortest service path strategy, you need to me (E a , E z , idx) path routing nodes are summarized and the planning scheme is formulated with priority given to the logical path with the shortest path.

6. The method for automatic intelligent planning of OTN services in a power communication network as claimed in claim 1, characterized in that: According to CH me (E a , E z , idx) The routing section summarizes the number of device nodes in the calculation path, and does not distinguish the logical path CH of the multiplexing layer device in the calculation data me (E a , E z ,idx) path validity, take the non-repeated path equipment data on the full path segment for summary calculation, the formula is described as follows: CH count (E a ,E z ,idx)=SUM(CHR me (E a ,E z ,idx),CHR me (E a ,E z ,idx)) According to CH count (E a , E z , idx) determines the number of device nodes through CH count (E a , E z , idx) path is the path with the smallest number of device nodes, loop iterative comparison, and take the path data with the smallest number of device nodes. The formula is described as follows: CH min (E a , E z , idx) is the path with the minimum number of device nodes through the logical path of the multiplexing layer device, which meets the usage effectiveness.

7. The method for automatic intelligent planning of OTN services in a power communication network as claimed in claim 1, characterized in that: According to the characteristics of business data applications, when a business path routing strategy is needed, set the device nodes that must be passed through or exclude the device nodes that must be passed through. Set the device nodes that the business path must pass through or exclude the device nodes from the business path according to the business scenario requirements; As a further technical solution, the business logic path exclusion device node formula is described as follows: The formula for the device nodes that the business logic path must pass through is described as follows: CH me (E a , E z , idx) is a valid multiplexing layer device logical path, which meets the use effectiveness. When setting the service path routing strategy, the exclusion strategy and the must-pass strategy can be implemented at the same time. After the two strategies are set at the same time, the conditions must be met at the same time to meet the use requirements.

8. A system for automatic intelligent planning of OTN services in a power communication network, characterized by comprising: The intra-domain service module is configured as follows: when the starting site and the ending site at both ends of the service belong to the same subnet management domain, it is judged as an intra-domain service. The intra-domain service directly searches for the logical path of the device multiplexing layer according to the relationship between the site and the device. When the logical path is found in the end-to-end path deep learning model, the set service policies are executed in sequence until the logical path data that meets the service requirements is found; The cross-domain service module is configured as follows: when the starting site and the ending site at both ends of the service do not belong to the same subnet management domain, it is judged as a cross-domain service. The cross-domain service needs to use the starting site as a parameter to find the logical path in the end-to-end path deep learning model. The found service path ending site needs to exist in the cross-domain management node list, and then continue to find the cross-domain logical path through the cross-domain node until the service cross-domain ending site is found. The service policies set in the domain are respectively executed according to the found cross-domain logical path until a logical path data set that meets the service requirements is found; The business path planning module is configured to: output a list of business paths that meet the policy conditions, and output a list of solutions in accordance with the policy weights, and select the required planning path as the final decision solution based on the actual demand situation.

9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method described in any one of claims 1 to 7 are performed.

Images