Backbone transmission network and data network multi-domain cooperative routing reconstruction method and system

Abstract

The invention belongs to the technical field of data transmission, and provides a multi-domain cooperative routing reconstruction method and system for a backbone transmission network and a data network, and the method comprises the steps: collecting power service data, and calculating the transmission time delay of the power service data between routing nodes and the transmission risk of the power service data in a link; constructing a route selection reconstruction Markov decision process MDP model by taking minimization of transmission delay and transmission risk as a target; initializing a matching price and a state action value function of the routing selection reconstruction MDP model, and constructing a routing selection reconstruction preference list based on the state action value function; and sending a transmission request to the routing node with the highest ranking in the preference list, carrying out matching application, and outputting a routing reconstruction optimal decision. According to the method, the continuity and stability of data network services can be improved, the accuracy of risk modeling is enhanced, routing selection is optimized, time delay and risks are reduced, routing selection conflicts are effectively solved, the utilization rate of network resources is improved, and the adaptivity and expandability of the network are enhanced.

Description

Technical Field

[0001] The present invention belongs to the technical field of data transmission, and in particular relates to a method and system for reconstructing multi-domain collaborative routing of a backbone transmission network and a data network. Background Art

[0002] With the accelerated construction of new power systems with new energy as the main body, source-grid-load-storage interaction and multi-energy complementarity have become important means to support the consumption of clean energy. Various emerging power businesses that have been developed are inseparable from the backbone transmission network as a data transmission channel. The surge in demand for network bandwidth from various businesses has led to an increasingly prominent problem of load imbalance in the backbone transmission network, and the high-density business carrying of local links has increased network vulnerability. In addition, the backbone transmission network and the data network are closely coupled. Cases of data network business interruption caused by backbone transmission network failures, which in turn lead to cascading power grid failures, are not uncommon. Therefore, how to ensure the reliable and efficient coordinated operation of the backbone transmission network and the data network, and reduce the transmission risk and transmission delay of important business data, is of great significance to improving the support for the safe and stable operation of the power grid.

[0003] The routing reconstruction method can cope with the ever-changing data and business transmission requirements by dynamically optimizing the network communication path, thereby balancing the network load, optimizing resource allocation, reducing data transmission delay, and ensuring the continuity and reliability of power business data transmission. However, the existing routing reconstruction method does not consider how to quickly switch the transmission path of the backbone transmission network or restore the fault to ensure the continuity and stability of the data network service. In addition, the dual-network coupling risk modeling is inaccurate. The transmission of power business faces risks in multiple dimensions such as the business layer, transmission layer, and physical layer. It is necessary to consider the risk of backbone transmission network transmission link failure and the risk of data network business data interruption in a coordinated manner. However, the existing risk modeling method does not consider the coupling and coordinated operation of the backbone transmission network and the data network, and does not consider risk modeling from multiple dimensions, resulting in poor modeling accuracy. Finally, the existing routing reconstruction method does not fully consider the dual-network coupling risk characteristics of the backbone transmission network and the data network in solving the routing node selection conflict problem. It is difficult to effectively measure the degree of routing selection conflict and cannot achieve the approximation and reconstruction of the optimal routing selection strategy. Summary of the invention

[0004] The purpose of the present invention is to provide a backbone transmission network and data network multi-domain collaborative routing reconstruction method and system to solve the problem that it is difficult to effectively measure the degree of routing conflict and cannot achieve the approximation and reconstruction of the optimal routing strategy.

[0005] To achieve the above object, the present invention adopts the following technical solutions: In a first aspect, the present invention provides a method for reconfiguring multi-domain collaborative routing of a backbone transmission network and a data network, comprising: Collect power business data, calculate the transmission delay of power business data between routing nodes and the transmission risk on the link; With the goal of minimizing transmission delay and transmission risk, a routing reconstruction Markov decision process MDP model is constructed; Initialize the matching price and state-action value function of the routing reconstruction MDP model, and construct a routing reconstruction preference list based on the state-action value function; Send a transmission request to the highest-ranked routing node in the preference list to apply for matching. Determine whether the routing node has received transmission requests that exceed the quota. If so, there is a matching conflict. Resolve the matching conflict by increasing the matching price, updating the preference list, and resubmitting the matching application. Output the routing to reconstruct the optimal decision.

[0006] Optionally, collecting the electric power business data and calculating the transmission delay of the electric power business data between routing nodes includes: First, the data node receives different business data uploaded by multiple power business devices. Power business The data packet is represented as

[0007] In the formula, express The destination node of ; express Importance of data; express The amount of data; Data Pack Through the transmission network from the generating node Transmit to the destination node During the process, each time slot will select a routing node as the next hop for data transmission. The next hop routing node set is ; Routing Node The set of previous hop routing nodes is ; The routing reconstruction indicator variable is ,in , Indicates time slot Routing Node Data on Select routing node As the next hop for data transmission, otherwise ;data At the routing node and The transmission delay between

[0008] In the formula, Indicates the transmission rate.

[0009] Optionally, collecting the power business data and calculating the transmission risk of the power business data in the link includes: Link The transmission reliability is expressed as

[0010] In the formula, Indicates link Length; Indicates link The transmission reliability of a unit length of optical cable is defined as the service risk in the network, which is defined as the impact on the stable operation of the power grid if a certain link fails suddenly. Business layer risk model: Business layer risk model on a single link of the transmission network It is the product of data importance and link failure rate. When the data packet By routing node The business layer risk of transmitting to the next hop routing node is

[0011] In the formula, Represents a data node Power business Importance of data; Transport layer risk model: Transmission risk model on a single link of the transmission network It is the product of the service data packet size and the link failure rate; When the data packet By routing node The transport layer risk of transmission to the next hop routing node is

[0012] Physical layer risk model: The physical layer risk on a single link in the transmission network is expressed by the growth rate of the optical fiber link length; When the data packet By routing node The physical layer risk of transmission to the next-hop routing node is

[0013] In the formula, Indicates time slot Routing Node Data packets on The shortest path length selected using Dijkstra’s algorithm; use , , Represent the normalized business layer, transport layer and physical layer risks respectively, in the time slot When the data packet By routing node The overall risk of transmitting to the next-hop routing node is expressed as

[0014] In the formula, , and They represent the weights of business layer risk, transport layer risk and physical layer risk respectively.

[0015] Optionally, the constructing of a routing reconstruction MDP model with the goal of minimizing transmission delay and transmission risk includes: The optimization problem of the coordinated operation of the backbone transmission network and the data network is modeled as follows:

[0016] In the formula, represent A collection of; For routing nodes quota; Represents the constraints on the values ​​of the routing reconstruction indicator variables; Indicates data packet At most one routing node can be selected as the next hop in each time slot; Represents a routing node In each time slot, a maximum of Data packets; For each agent , data packet The optimization problem is expressed as

[0017] The routing node selection and reconstruction problem is modeled as a Markov decision process, which is described as follows: 1) State space: defining data packets The state space of is the data size, data importance, data transmission delay and overall risk, expressed as ; 2) Action space: In each time slot, the routing node For data packets Select a routing node as the next hop for data transmission; define routing nodes For data packets The action space for selecting the next-hop routing node is ; 3) Bonus: Defining Routing Nodes For data packets choose The reward for the next-hop routing node is the product of the data volume, transmission delay and transmission risk, that is, the optimization goal , expressed as .

[0018] Optionally, the initialization of the matching price and state-action value function of the routing reconstruction MDP model and the construction of a routing reconstruction preference list based on the state-action value function include: Initialize matching price and the state-action-value function ; Based on the state-action value function, the selection of routing nodes for power business data transmission is optimized, the optimal next-hop routing node is determined, and the matching relationship between the two parties is represented by mapping:

[0019] In the formula, Indicates data packet To the next hop routing node The mapping of Routing Node For data packets The matching rule for selecting the next hop routing node is expressed as

[0020] In the formula, For routing nodes The quota of routing nodes in the same time slot Maximum transmission Data packets; Represents a routing node Can and can only be data packets Select a routing node as the next hop; Represents a routing node At most one can accept Matching request for packets; exist At the beginning of the time slot, the routing node For data packets Select routing nodes based on the state-action value function; define Time Slot Packet Select routing node The preference value for the next hop is

[0021] In the formula, For data packets The state-action-value function of To match the price; based on the routing preference, the preference values ​​are sorted in descending order to get the data packets A list of preferences for next-hop routing nodes.

[0022] Optionally, the sending of a transmission request to the highest ranking routing node in the preference list to apply for matching, and determining whether the routing node has received transmission requests exceeding the quota, if so, there is a matching conflict, including: All data packets send transmission requests to the routing node with the highest ranking in their respective preference lists, represented as

[0023] If the routing node The number of transfer requests received is less than or equal to , then the routing node directly matches all data packets that send transmission requests; if the routing node The number of transfer requests received is greater than , a matching conflict occurs.

[0024] Optionally, the step of re-submitting a matching application to resolve the matching conflict by increasing the matching price, updating the preference list, and outputting the routing to reconstruct the optimal decision includes: For routing nodes with matching conflicts , add all competing packets to the set and improve The matching price of all data packets in is

[0025] In the formula, To match the price step; The preference list is updated for all data packets in the preference list, and then a matching application is resubmitted to the routing node ranked first in the preference list until no matching conflict occurs, and the optimal routing selection reconstruction decision is output.

[0026] In a second aspect, the present invention provides a backbone transmission network and data network multi-domain collaborative routing reconstruction system, comprising: The data collection module is used to collect power business data and calculate the transmission delay of power business data between routing nodes and the transmission risk in the link; The model building module is used to build a route selection reconstruction Markov decision process MDP model with the goal of minimizing transmission delay and transmission risk; The preference list acquisition module is used to initialize the matching price and state-action value function of the routing reconstruction MDP model and construct a routing reconstruction preference list based on the state-action value function; The optimal output module is used to send transmission requests to the highest-ranked routing node in the preference list, make matching applications, and determine whether the routing node has received transmission requests that exceed the quota. If so, there is a matching conflict. The matching conflict is resolved by increasing the matching price, updating the preference list, and resubmitting the matching application. The output routing reconstructs the optimal decision.

[0027] Optionally, collecting the electric power business data and calculating the transmission delay of the electric power business data between routing nodes includes: First, the data node receives different business data uploaded by multiple power business devices. Power business The data packet is represented as

[0028] In the formula, express The destination node of ; express Importance of data; express The amount of data; Data Pack Through the transmission network from the generating node Transmit to the destination node During the process, each time slot will select a routing node as the next hop for data transmission. The next hop routing node set is ; Routing Node The set of previous hop routing nodes is ; The routing reconstruction indicator variable is ,in , Indicates time slot Routing Node Data on Select routing node As the next hop for data transmission, otherwise ;data At the routing node and The transmission delay between

[0029] In the formula, Indicates the transmission rate.

[0030] In a third aspect, the present invention provides a computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of a method for reconstructing multi-domain collaborative routing of a backbone transmission network and a data network when executing the computer program.

[0031] In a fourth aspect, the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for reconstructing multi-domain collaborative routing of a backbone transmission network and a data network are implemented.

[0032] Compared with the prior art, the present invention has the following technical effects: The backbone transmission network and data network multi-domain collaborative operation routing reconstruction method proposed in the present invention can quickly switch the transmission path or restore the fault when a backbone transmission network fails, ensuring the continuous transmission of data network services. This is achieved through real-time routing selection and reconstruction, reducing the service interruption time caused by network failures and improving the overall stability of the data network.

[0033] The method constructs a three-layer risk model of the business layer, transport layer and physical layer, and comprehensively considers the risk of transmission link failure in the backbone transmission network and the risk of service data interruption in the data network. This multi-level risk modeling method can more comprehensively reflect the actual risk status of network operation and provide a more accurate decision-making basis for routing selection.

[0034] By modeling the routing reconstruction problem as a Markov decision process (MDP) and combining it with the Q learning algorithm, the present invention can dynamically select the optimal routing path based on the network status and business needs. This method not only takes into account the current network status, but also makes smarter routing decisions by predicting the future network status, thereby effectively reducing the delay and transmission risk of business data transmission.

[0035] In the process of routing selection, multiple data packets may compete for the same routing node. The present invention introduces a global penalty function to evaluate the degree of routing conflict, and updates the Q value and preference list through an ascending price matching algorithm, thereby solving the routing conflict problem. This method ensures the fairness and effectiveness of routing selection, and avoids network congestion and performance degradation caused by conflicts.

[0036] Through intelligent routing selection and reconstruction, the present invention can allocate network resources more reasonably and avoid waste and idleness of resources. This can not only improve the transmission efficiency of the network, but also reduce the operating cost of the network, providing strong support for the efficient transmission of power services.

[0037] The routing reconstruction method proposed in the present invention is adaptive and scalable. It can dynamically adjust the routing strategy according to network changes and business needs to ensure that the network always remains in the optimal state. At the same time, the method can also be extended to other types of networks and application scenarios to provide solutions for a wider range of network optimization.

[0038] In summary, the backbone transmission network and data network multi-domain collaborative operation routing reconstruction method proposed in the present invention has significant technical effects, can improve the continuity and stability of data network services, enhance the accuracy of risk modeling, optimize routing selection and reduce latency and risk, effectively resolve routing selection conflicts, improve the utilization of network resources, and enhance the network's adaptability and scalability. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 Schematic diagram of the routing reconstruction system for the backbone transmission network and data network multi-domain collaborative operation.

[0040] Figure 2 Schematic diagram of routing reconstruction module for multi-domain collaborative operation of backbone transmission network and data network.

[0041] Figure 3 Flowchart of the present invention. DETAILED DESCRIPTION

[0042] The present invention is further described below in conjunction with the accompanying drawings: Example 1, please refer to Figure 3 The present invention provides a backbone transmission network and a data network multi-domain collaborative routing reconstruction method, comprising: Collect power business data, calculate the transmission delay of power business data between routing nodes and the transmission risk on the link; With the goal of minimizing transmission delay and transmission risk, a routing reconstruction Markov decision process MDP model is constructed; Initialize the matching price and state-action value function of the routing reconstruction MDP model, and construct a routing reconstruction preference list based on the state-action value function; Send a transmission request to the highest-ranked routing node in the preference list to apply for matching. Determine whether the routing node has received transmission requests that exceed the quota. If so, there is a matching conflict. Resolve the matching conflict by increasing the matching price, updating the preference list, and resubmitting the matching application. Output the routing to reconstruct the optimal decision.

[0043] The present invention first collects power business data to provide detailed basic information for subsequent routing selection. By processing these data, especially calculating the transmission delay of power business data between routing nodes and the transmission risk of links, a key decision-making basis is provided for routing reconstruction. This efficient data collection and processing mechanism ensures the accuracy and reliability of routing selection.

[0044] By constructing a routing reconstruction Markov decision process (MDP) model, the present invention transforms the routing problem into a dynamic optimization problem. With the goal of minimizing transmission delay and transmission risk, the model can comprehensively consider the current network status, business requirements and possible future network changes to select the optimal routing path. This optimized routing selection strategy not only improves the transmission efficiency of the network, but also reduces the risk of business data transmission.

[0045] The present invention constructs a routing reconstruction preference list based on the state action value function by initializing the matching price and state action value function of the routing reconstruction MDP model. This intelligent decision-making mechanism can dynamically adjust the routing strategy according to the actual situation of the network and business needs. At the same time, by sending a transmission request to the highest-ranking routing node in the preference list and making a matching application, the routing selection is fast and accurate.

[0046] In the process of routing selection, it is inevitable that multiple data packets will compete for the same routing node, resulting in matching conflicts. The present invention timely discovers and resolves such conflicts by judging whether the routing node has received transmission requests exceeding the quota. By increasing the matching price, updating the preference list and resubmitting the matching application, the present invention can effectively resolve matching conflicts and ensure the fairness and effectiveness of routing selection.

[0047] Through the above technical means, the present invention can significantly improve the overall performance of the network. The optimized routing selection strategy and intelligent routing reconstruction decision-making reduce the delay and risk of business data transmission and improve the transmission efficiency and stability of the network. At the same time, the effective conflict resolution mechanism avoids network congestion and performance degradation caused by conflicts, further improving the overall performance of the network.

[0048] The backbone transmission network and data network multi-domain collaborative routing reconstruction method proposed in the present invention is not only applicable to the current network environment, but also has strong flexibility and scalability. With the continuous expansion of network scale and the continuous changes in business needs, the method can dynamically adjust the routing selection strategy to ensure that the network always remains in the optimal state. At the same time, the method can also be extended to other types of networks and application scenarios, providing solutions for a wider range of network optimization.

[0049] In summary, the backbone transmission network and data network multi-domain collaborative routing reconstruction method provided by the present invention provides powerful technical support for the efficient transmission of power services and the stable operation of the network through technical effects such as efficient data collection and processing, optimized routing selection strategy, intelligent routing reconstruction decision-making, effective conflict resolution mechanism, and improved overall performance and flexibility of the network.

[0050] Embodiment 2, the present invention provides a backbone transmission network and data network multi-domain collaborative routing reconstruction method, specifically comprising: Step 1: The delay calculation submodule is responsible for calculating the transmission delay of data packets between routing nodes. First, the data node receives different business data packets uploaded by multiple power business devices. Power business The data packet can be represented as (1) In the formula, express The destination node of . express The importance of data. express The amount of data.

[0051] Data Pack Through the transmission network from the generating node Transmit to the destination node During the process, each time slot will select a routing node as the next hop for data transmission. The next hop routing node set is . Define routing nodes The set of previous hop routing nodes is . Define the routing reconstruction indicator variable as ,in , Indicates time slot Routing Node Data packets on Select routing node As the next hop for data transmission, otherwise Data Pack At the routing node and The transmission delay between (2) In the formula, Indicates the transmission rate.

[0052] Step 2: Construct the business layer risk model, transport layer risk model, and physical layer risk model in the risk reconstruction submodule. The transmission reliability is expressed as (3) In the formula, Indicates link Length. Indicates link The transmission reliability of a unit length of optical cable is defined as the service risk in the network, which is the impact on the stable operation of the power grid when a certain link fails suddenly.

[0053] Business layer risk model: The business layer risk model is related to the importance of the business data transmitted by the link. Link failure leads to interruption of high-importance business transmission, which will inevitably affect the safe and stable operation of the power system. It is the product of data importance and link failure rate. When the data packet By routing node The business layer risk of transmitting to the next hop routing node is (4) In the formula, Represents a data node Power business The importance of data.

[0054] Transport layer risk model: The transport layer risk model is mainly related to the traffic volume of the services carried by the link. Link failure leads to the loss of a large number of low-importance services, which may also trigger the cascading effect of power grid failure. It is the product of the service data packet size and the link failure rate. When the data packet By routing node The transport layer risk of transmission to the next hop routing node is (5) Physical layer risk model: Due to the suddenness and randomness of optical cable interruption events, the increase in route length will lead to an increase in the probability of power service transmission interruption. Therefore, the physical layer risk on a single link in the transmission network can be expressed by the growth rate of the optical fiber link length. When the data packet By routing node The physical layer risk of transmission to the next-hop routing node is (6) In the formula, Indicates time slot Routing Node Data packets on The shortest path length selected using Dijkstra's algorithm.

[0055] 4) Normalization and total risk model: Since risks at different levels have different dimensions and magnitudes, they need to be normalized first. , , They represent the normalized risks of the service layer, transport layer and physical layer respectively. For example, it can be expressed as (7) In the formula, and They represent the theoretical upper and lower bounds of the transport layer risk respectively.

[0056] In summary, in the time slot When the data packet By routing node The overall risk of transmitting to the next-hop routing node can be expressed as (8) In the formula, , and They represent the weights of business layer risk, transport layer risk and physical layer risk respectively.

[0057] Step 2: The present invention aims to minimize the transmission delay and transmission risk of the power business data in the whole network through appropriate routing reconstruction from the perspective of long-term operation of the transmission network. The final optimization problem of the coordinated operation of the backbone transmission network and the data network can be modeled as follows: (9) In the formula, represent A collection of . For routing nodes quota. Represents the constraints on the values ​​of the routing reconstruction indicator variables. Indicates data packet At most one routing node can be selected as the next hop in each time slot. Represents a routing node In each time slot, a maximum of data packets.

[0058] Data Pack During the transmission process, the data packet passes through multiple routing nodes, and each routing node is deployed with a backbone transmission network and a data network multi-domain collaborative routing reconstruction module. These modules can be regarded as intelligent agents, which are responsible for making decisions, that is, determining the routing node for the next hop of the data packet. For each intelligent agent , data packet The optimization problem can be expressed as (10) Step 3: In the routing selection reconstruction MDP model submodule, the routing node selection reconstruction problem can be modeled as a Markov decision process, which is described in detail as follows.

[0059] 1) State space: defining data packets The state space of is the data size, data importance, data transmission delay and overall risk, which can be expressed as .

[0060] 2) Action space: In each time slot, the routing node For data packets Select a routing node as the next hop for data transmission. Define routing nodes For data packets The action space for selecting the next-hop routing node is .

[0061] 3) Bonus: Defining Routing Nodes For data packets choose The reward for the next-hop routing node is the product of the data volume, transmission delay and transmission risk, that is, the optimization goal , which can be expressed as .

[0062] Step 4: In the initialization submodule, initialize the matching price and the state-action-value function .

[0063] Step 5: In the routing reconstruction preference list construction submodule, the routing reconstruction preference list based on the Q value is constructed. The present invention optimizes the selection of the power business data transmission routing node based on coupled Q learning, determines the optimal next-hop routing node, and can use mapping to represent the matching relationship between the two parties, that is, (11) In the formula, Indicates data packet To the next hop routing node 's mapping.

[0064] Routing Node For data packets The matching rule for selecting the next hop routing node is expressed as (12) In the formula, For routing nodes The quota of routing nodes in the same time slot Maximum transmission Data packets; Represents a routing node Can and can only be data packets Select a routing node as the next hop; Represents a routing node At most one can accept A matching request for packets.

[0065] exist At the beginning of the time slot, the routing node For data packets Routing node selection is performed based on the state-action value function. Definition Time Slot Packet Select routing node The preference value for the next hop is (13) In the formula, For data packets The state-action-value function. To match the price. Based on the routing preference, the preference values ​​are sorted in descending order to obtain the data packets. A list of preferences for next-hop routing nodes.

[0066] Step 6: In the matching application and conflict judgment submodule, all data packets send transmission requests to the routing node with the highest ranking in their respective preference lists, which can be expressed as (14) If the routing node The number of transfer requests received is less than or equal to , then the routing node directly matches all data packets that send transmission requests; if the routing node The number of transfer requests received is greater than , a matching conflict occurs.

[0067] Step 7: In the conflict coordination submodule, resolve the matching conflict. , add all competing packets to the set and improve The matching price of all data packets in is (15) In the formula, is the matching price step. All data packets in the update preference list according to (13), and then resubmit the matching application to the routing node ranked first in the preference list. For example, update the collection , repeat steps 5-7 until no matching conflict occurs.

[0068] Step 8: In the collaborative learning submodule, observe and , based on the calculated reward, transfer to the next state. At the same time, a global penalty function is introduced to quantify the degree of routing conflict, which is defined as (16) In the formula, Represents competing routing nodes The number of packets, The total number of packets transmitted by the routing network.

[0069] Step 9: Output the optimal routing reconstruction decision in the optimal decision output submodule.

[0070] Step 10: In the action-value function update submodule, update the state-action-value function To update, it can be expressed as (17) In the formula, is the learning efficiency. The greater the learning efficiency, the faster the convergence. Is the discount factor, which indicates the influence of the state return. The larger the discount factor, the greater the influence of the state return.

[0071] The backbone transmission network and data network multi-domain collaborative operation routing reconstruction system, its architecture is as shown in the attached Figure 1 As shown, it includes power equipment layer, backbone transmission network layer and data network layer.

[0072] The power equipment layer mainly includes power generation equipment, power transformation and distribution equipment, power consumption equipment, and transmission lines connecting each node, and uploads the equipment operation status data to the backbone transmission network layer through optical fiber communication. The backbone transmission network layer deploys the backbone transmission network and data network multi-domain collaborative operation routing reconstruction module on each routing node. Each routing node performs routing selection and transmits power business data through optical fiber links. The data network layer is built on the backbone transmission network layer, and the data forwarding node deploys communication, computing, and storage functions to achieve effective processing of business data.

[0073] The backbone transmission network and the data network multi-domain collaborative operation routing reconstruction module, the architecture of which is as shown in the attached Figure 2As shown, it includes data acquisition submodule, delay calculation submodule, risk reconstruction submodule, routing reconstruction MDP model submodule, initialization submodule, routing reconstruction preference list construction submodule, matching application and conflict judgment submodule, conflict coordination submodule, collaborative learning submodule, optimal decision output submodule, action value function update submodule and communication submodule.

[0074] The data acquisition submodule is responsible for collecting power business data packets; The delay calculation submodule is responsible for calculating the transmission delay of data packets between routing nodes; The risk reconstruction submodule is responsible for constructing the business layer risk model, the transport layer risk model, and the physical layer risk model; The routing selection and reconstruction MDP model submodule is responsible for constructing the routing selection and reconstruction MDP model; The initialization submodule is responsible for matching price and state-action-value functions; The routing reconstruction preference list construction submodule is responsible for the routing reconstruction preference list construction based on Q value; The matching application and conflict judgment submodule is responsible for matching applications between routing nodes and judging conflicts; The conflict coordination submodule is responsible for coordinating conflicts until no matching conflicts occur; The collaborative learning submodule is responsible for collaborative learning among routing nodes; The optimal decision output submodule is responsible for outputting the optimal decision for routing reconstruction; The action-value function update submodule is responsible for updating the action-value function; The communication submodule is responsible for sending the selection decision to the routing node.

[0075] The present invention proposes a method for routing reconstruction of a backbone transmission network and a data network in a multi-domain collaborative operation. When a backbone transmission network fails and further causes a data network service interruption, the method can quickly switch the backbone transmission network transmission path or restore the failure to ensure the continuity and stability of the data network service. At the same time, the method can also collaboratively consider the risk of backbone transmission network transmission link failure and the risk of data network service data interruption, and perform risk modeling of the service layer, transmission layer and physical layer, thereby improving the accuracy of the modeling.

[0076] The present invention proposes a routing reconstruction method for the coordinated operation of multiple domains of a backbone transmission network and a data network. Based on the traditional Q learning algorithm, the method models the routing reconstruction problem as a Markov decision process model. When solving the routing node selection conflict problem, the dual-network coupling characteristics are considered, and a global penalty function is introduced to evaluate the routing conflict degree. By adopting an ascending price matching algorithm to update the Q value and preference list, the method realizes the approximation and reconstruction of the optimal routing selection strategy, thereby reducing the delay and transmission risk of service data transmission.

[0077] In yet another embodiment of the present invention, a backbone transmission network and data network multi-domain collaborative routing reconstruction system is provided, which can be used to implement the above-mentioned backbone transmission network and data network multi-domain collaborative routing reconstruction method. Specifically, the system includes: The data collection module is used to collect power business data and calculate the transmission delay of power business data between routing nodes and the transmission risk in the link; The model building module is used to build a route selection reconstruction Markov decision process MDP model with the goal of minimizing transmission delay and transmission risk; The preference list acquisition module is used to initialize the matching price and state-action value function of the routing reconstruction MDP model and construct a routing reconstruction preference list based on the state-action value function; The optimal output module is used to send transmission requests to the highest-ranked routing node in the preference list, make matching applications, and determine whether the routing node has received transmission requests that exceed the quota. If so, there is a matching conflict. The matching conflict is resolved by increasing the matching price, updating the preference list, and resubmitting the matching application. The output routing reconstructs the optimal decision.

[0078] The division of modules in the embodiments of the present invention is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, each functional module in each embodiment of the present invention may be integrated into one processor, or may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated modules may be implemented in the form of hardware or in the form of software functional modules.

[0079] In another embodiment of the present invention, a computer device is provided, the computer device including a processor and a memory, the memory is used to store a computer program, the computer program includes program instructions, and the processor is used to execute the program instructions stored in the computer storage medium. The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is suitable for implementing one or more instructions, and is specifically suitable for loading and executing one or more instructions in a computer storage medium to implement the corresponding method flow or corresponding function; the processor described in the embodiment of the present invention can be used for the operation of a backbone transmission network and a multi-domain collaborative routing reconstruction method for a data network.

[0080] In another embodiment of the present invention, the present invention also provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a computer device for storing programs and data. It can be understood that the computer-readable storage medium here can include both built-in storage media in a computer device and, of course, extended storage media supported by the computer device. The computer-readable storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by a processor are also stored in the storage space, and these instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of the method for reconstructing multi-domain collaborative routing of a backbone transmission network and a data network in the above embodiment.

[0081] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0082] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0083] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0084] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0085] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for reconfiguring multi-domain collaborative routing of a backbone transmission network and a data network, characterized in that: include: Collect power business data, calculate the transmission delay of power business data between routing nodes and the transmission risk on the link; With the goal of minimizing transmission delay and transmission risk, a routing reconstruction Markov decision process MDP model is constructed; Initialize the matching price and state-action value function of the routing reconstruction MDP model, and construct a routing reconstruction preference list based on the state-action value function; Send a transmission request to the highest-ranked routing node in the preference list to apply for matching. Determine whether the routing node has received transmission requests that exceed the quota. If so, there is a matching conflict. Resolve the matching conflict by increasing the matching price, updating the preference list, and resubmitting the matching application. Output the routing to reconstruct the optimal decision.

2. The method for reconfiguring multi-domain collaborative routing of a backbone transmission network and a data network according to claim 1, characterized in that: The collecting of electric power business data and calculating the transmission delay of the electric power business data between routing nodes includes: First, the data node receives different business data uploaded by multiple power business devices. Power business The data packet is represented as In the formula, express The destination node of ; express The importance of data; express The amount of data; Data Pack Through the transmission network from the generating node Transmit to the destination node During the process, each time slot will select a routing node as the next hop for data transmission. The next hop routing node set is ; Routing Node The set of previous hop routing nodes is ; The routing reconstruction indicator variable is ,in , Indicates time slot Routing Node Data on Select routing node As the next hop for data transmission, otherwise ;data At the routing node and The transmission delay between In the formula, Indicates the transmission rate.

3. The method for reconfiguring multi-domain collaborative routing of a backbone transmission network and a data network according to claim 2, characterized in that: The collecting of electric power business data and calculating the transmission risk of the electric power business data in the link include: Link The transmission reliability is expressed as In the formula, Indicates link Length; Indicates link The transmission reliability of a unit length of optical cable is defined as the service risk in the network, which is defined as the impact on the stable operation of the power grid if a certain link fails suddenly. Business layer risk model: Business layer risk model on a single link of the transmission network It is the product of data importance and link failure rate. When the data packet By routing node The business layer risk of transmitting to the next hop routing node is In the formula, Represents a data node Power business The importance of data; Transport layer risk model: Transmission risk model on a single link of the transmission network It is the product of the service data packet size and the link failure rate; When the data packet By routing node The transport layer risk of transmission to the next hop routing node is Physical layer risk model: The physical layer risk on a single link in the transmission network is expressed by the growth rate of the optical fiber link length; When the data packet By routing node The physical layer risk of transmission to the next-hop routing node is In the formula, Indicates time slot Routing Node Data packets on The shortest path length selected using Dijkstra’s algorithm; use , , Represent the normalized business layer, transport layer and physical layer risks respectively, in the time slot When the data packet By routing node The overall risk of transmitting to the next-hop routing node is expressed as In the formula, , and They represent the weights of business layer risk, transport layer risk and physical layer risk respectively.

4. The method for reconfiguring multi-domain collaborative routing of a backbone transmission network and a data network according to claim 2, characterized in that: The routing reconstruction MDP model is constructed with the goal of minimizing transmission delay and transmission risk, including: The optimization problem of the coordinated operation of the backbone transmission network and the data network is modeled as follows: In the formula, represent A collection of; For routing nodes quota; Represents the constraints on the values ​​of the routing reconstruction indicator variables; Indicates data packet At most one routing node can be selected as the next hop in each time slot; Represents a routing node In each time slot, a maximum of Data packets; For each agent , data packet The optimization problem is expressed as The routing node selection and reconstruction problem is modeled as a Markov decision process, which is described as follows: 1) State space: defining data packets The state space of is the data size, data importance, data transmission delay and overall risk, expressed as ; 2) Action space: In each time slot, the routing node For data packets Select a routing node as the next hop for data transmission; define routing nodes For data packets The action space for selecting the next-hop routing node is ; 3) Bonus: Defining Routing Nodes For data packets choose The reward for the next-hop routing node is the product of the data volume, transmission delay and transmission risk, that is, the optimization goal , expressed as .

5. The method for reconfiguring multi-domain collaborative routing of a backbone transmission network and a data network according to claim 1, characterized in that: The initialization of the matching price and state-action value function of the routing reconstruction MDP model and the construction of a routing reconstruction preference list based on the state-action value function include: Initialize matching price and the state-action-value function ; Based on the state-action value function, the selection of routing nodes for power business data transmission is optimized, the optimal next-hop routing node is determined, and the matching relationship between the two parties is represented by mapping: In the formula, Indicates data packet To the next hop routing node The mapping of Routing Node For data packets The matching rule for selecting the next hop routing node is expressed as In the formula, For routing nodes The quota of routing nodes in the same time slot Maximum transmission Data packets; Represents a routing node Can and can only be data packets Select a routing node as the next hop; Represents a routing node At most one can accept Matching request for packets; exist At the beginning of the time slot, the routing node For data packets Select routing nodes based on the state-action value function; define Time Slot Packet Select routing node The preference value for the next hop is In the formula, For data packets The state-action-value function of To match the price; based on the routing preference, the preference values ​​are sorted in descending order to get the data packets A list of preferences for next-hop routing nodes.

6. The method for reconfiguring multi-domain collaborative routing of a backbone transmission network and a data network according to claim 5, characterized in that: The transmission request is sent to the highest ranking routing node in the preference list to apply for matching, and it is determined whether the routing node has received transmission requests exceeding the quota. If the quota is exceeded, there is a matching conflict, including: All data packets send transmission requests to the routing node with the highest ranking in their respective preference lists, represented as If the routing node The number of transfer requests received is less than or equal to , then the routing node directly matches all data packets that send transmission requests; if the routing node The number of transfer requests received is greater than , a matching conflict occurs.

7. The method for reconfiguring multi-domain collaborative routing of a backbone transmission network and a data network according to claim 6, characterized in that: The matching conflicts are resolved by increasing the matching price, updating the preference list, and resubmitting the matching application, and the output routing is used to reconstruct the optimal decision, including: For routing nodes with matching conflicts , add all competing packets to the set and improve The matching price of all data packets in is In the formula, To match the price step; The preference list is updated for all data packets in the preference list, and then a matching application is resubmitted to the routing node ranked first in the preference list until no matching conflict occurs, and the optimal routing selection reconstruction decision is output.

8. A backbone transmission network and data network multi-domain collaborative routing reconstruction system, characterized in that: include: The data collection module is used to collect power business data and calculate the transmission delay of power business data between routing nodes and the transmission risk in the link; The model building module is used to build a route selection reconstruction Markov decision process MDP model with the goal of minimizing transmission delay and transmission risk; The preference list acquisition module is used to initialize the matching price and state-action value function of the routing reconstruction MDP model and construct a routing reconstruction preference list based on the state-action value function; The optimal output module is used to send transmission requests to the highest-ranked routing node in the preference list, make matching applications, and determine whether the routing node has received transmission requests that exceed the quota. If so, there is a matching conflict. The matching conflict is resolved by increasing the matching price, updating the preference list, and resubmitting the matching application. The output routing reconstructs the optimal decision.

9. The backbone transmission network and data network multi-domain collaborative routing reconstruction system according to claim 8, characterized in that: The collecting of electric power business data and calculating the transmission delay of the electric power business data between routing nodes includes: First, the data node receives different business data uploaded by multiple power business devices. Power business The data packet is represented as In the formula, express The destination node of ; express The importance of data; express The amount of data; Data Pack Through the transmission network from the generating node Transmit to the destination node During the process, each time slot will select a routing node as the next hop for data transmission. The next hop routing node set is ; Routing Node The set of previous hop routing nodes is ; The routing reconstruction indicator variable is ,in , Indicates time slot Routing Node Data on Select routing node As the next hop for data transmission, otherwise ;data At the routing node and The transmission delay between In the formula, Indicates the transmission rate.

10. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of a method for reconstructing multi-domain collaborative routing of a backbone transmission network and a data network as described in any one of claims 1 to 7 are implemented.

11. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of a method for reconstructing multi-domain collaborative routing of a backbone transmission network and a data network as described in any one of claims 1 to 7 are implemented.

Images