A method and system for multi-domain collaborative routing reconstruction of a backbone transmission network and a data network

Abstract

The application belongs to the technical field of data transmission, and provides a backbone transmission network and a data network multi-domain cooperative routing reconstruction method and system. The method comprises the following steps: collecting power service data, calculating the transmission delay of the power service data between routing nodes and the transmission risk of the power service data in a link; taking minimizing the transmission delay and the transmission risk as a target, constructing a routing reconstruction Markov decision process (MDP) model; initializing the matching price and the state-action value function of the routing reconstruction MDP model, constructing a routing reconstruction preference list based on the state-action value function; sending a transmission request to the routing node with the highest ranking in the preference list, performing a matching application, and outputting an optimal decision of routing reconstruction. The application can improve the continuity and stability of data network services, enhance the accuracy of risk modeling, optimize routing selection and reduce the delay and risk, effectively solve routing selection conflicts, improve the utilization rate of network resources, and enhance the adaptability and scalability of the network.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of data transmission, and particularly relates to a backbone transmission network and data network multi-domain cooperative routing reconstruction method and system. BACKGROUND

[0002] With the accelerated construction of new power systems dominated by new energy, source-grid-load-storage interaction and multi-energy complementation have become important means to support clean energy consumption. Various emerging power businesses cannot be carried out without the backbone transmission network as a data transmission channel. The rapid increase in network bandwidth demand of various businesses has led to an increasingly prominent problem of unbalanced load in the backbone transmission network, and high-density business bearing of local links has increased network vulnerability. In addition, the backbone transmission network and the data network are closely coupled. Data network business interruption caused by backbone transmission network network failure has led to cascading power grid failure cases. Therefore, how to ensure reliable and efficient cooperative 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 safe and stable operation of the power grid.

[0003] The routing reconstruction method can cope with changing data and business transmission demands by dynamically optimizing network communication paths, thereby balancing network load, optimizing resource allocation, and 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 recover from failure to ensure the continuity and stability of the data network business. In addition, the double-network coupling risk modeling is not accurate. The transmission of power businesses faces risks in multiple dimensions such as the business layer, the transmission layer, and the physical layer, and the coupling and cooperative operation of the backbone transmission network and the data network need to be considered. The existing risk modeling method does not consider the coupling and cooperative 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 double-network coupling risk characteristics of the backbone transmission network and the data network in solving routing node selection conflict problems, making it difficult to effectively measure the routing selection conflict degree and unable to achieve the approximation and reconstruction of the best routing selection strategy. SUMMARY

[0004] The purpose of the present application is to provide a backbone transmission network and data network multi-domain cooperative routing reconstruction method and system to solve the problem of being difficult to effectively measure the routing selection conflict degree and unable to achieve the approximation and reconstruction of the best routing selection strategy.

[0005] To achieve the above-mentioned purpose, the following technical solutions are adopted in the present application:

[0006] In a first aspect, the present application provides a backbone transmission network and data network multi-domain cooperative routing reconstruction method, comprising:

[0007] collecting power service data, calculating transmission delay and transmission risk of the power service data between routing nodes;

[0008] constructing a routing reconstruction Markov decision process (MDP) model aiming at minimizing transmission delay and transmission risk;

[0009] initializing matching price and state-action value function of the routing reconstruction MDP model, and constructing a routing reconstruction preference list based on the state-action value function;

[0010] sending a transmission request to the routing node with the highest ranking in the preference list, making a matching application, judging whether the routing node receives a transmission request exceeding the quota, and if yes, there is a matching conflict, solving the matching conflict by raising the matching price, updating the preference list and making a new matching application, and outputting an optimal decision of routing reconstruction.

[0011] Optionally, the collecting power service data and calculating transmission delay of the power service data between routing nodes comprises:

[0012] First, the data node receives different service data uploaded by multiple power service devices, the data node the power service data packet is represented as

[0013]

[0014] In the formula, indicates the destination node of , and ; indicates the data importance of ; indicates the data size of ;

[0015] The data packet is transmitted from the generation node to the destination node through a transmission network. In the process, a routing node is selected as the next hop for data transmission at each time slot. The set of next hop routing nodes of the routing node is ; the set of previous hop routing nodes of the routing node is ; the routing reconstruction indication variable is , wherein , indicates the data on the routing node at the time slot selects the routing node transmit data as the next hop, otherwise ; data transmission delay between the routing nodes and is

[0016]

[0017] wherein, represents the transmission rate.

[0018] Optionally, the power service data is collected, and the transmission risk of the power service data on the link is calculated, including:

[0019] The transmission reliability of the link is represented as

[0020]

[0021] wherein, represents the length of the link ; represents the transmission reliability of the optical cable per unit length on the link ; the service risk in the network is defined as the impact on the stable operation of the power grid when a certain link suddenly fails;

[0022] Service layer risk model: the service layer risk on a single link of the transmission network is represented as , i.e., the product of the data importance and the link failure rate; at time slot , the service layer risk of the data packet transmitted from the routing node to the next hop routing node is

[0023]

[0024] wherein, represents the data importance of the power service of the data node ;

[0025] Transmission layer risk model: the transmission risk on a single link of the transmission network is represented as , i.e., the product of the service data packet size and the link failure rate; at time slot , the transmission layer risk of the data packet transmitted from the routing node to the next hop routing node is

[0026]

[0027] Physical layer risk model: the physical layer risk on a single link of the transmission network is represented by the growth rate of the optical fiber link length; at time slot When the data packet By routing node The physical layer risk of transmission to the next hop routing node is

[0028]

[0029] Where, Indicates time slot Routing Node Data packets on The shortest path length selected using Dijkstra's algorithm;

[0030] 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

[0031]

[0032] Where, 、 and They represent the weights of business layer risk, transport layer risk, and physical layer risk respectively.

[0033] Optionally, the routing reconstruction MDP model is constructed with the goal of minimizing transmission delay and transmission risk, including:

[0034] The optimization problem of the coordinated operation of backbone transmission network and data network is modeled as

[0035]

[0036] Where, represent A collection of For routing nodes quota; Indicates 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; Indicates a routing node The maximum amount of data that can be transmitted in each time slot is data packets;

[0037] For each agent , data packet The optimization problem is expressed as

[0038]

[0039] The routing node selection reconstruction problem is modeled as a Markov decision process, which is specifically introduced as follows:

[0040] 1) State space: define the state space of the data packet as the data size, data importance, data transmission delay, and overall risk, which is represented as ;

[0041] 2) Action space: at each time slot, the routing node selects a routing node as the next hop for data transmission for the data packet ; define the action space of the routing node selecting the next hop routing node for the data packet as ;

[0042] 3) Reward: define the reward brought by the routing node selecting the next hop routing node for the data packet as the product of the data size, transmission delay, and transmission risk, i.e., the optimization objective , which is represented as .

[0043] Optionally, the matching price and state-action value function of the initialized routing selection reconstruction MDP model are matched, and a routing selection reconstruction preference list based on the state-action value function is constructed, including:

[0044] Initialize the matching price and the state-action value function ; optimize the selection of the power service data transmission routing node based on the state-action value function to determine the optimal next hop routing node, and use mapping to represent the matching relationship between the two parties:

[0045]

[0046] In the formula, represents the mapping of the data packet to the next hop routing node ;

[0047] The matching rule for the routing node selecting the next hop routing node for the data packet is represented as

[0048]

[0049] In the formula, is the routing node a quota, i.e. in the same time slot routing nodes can transmit data packets at most; denote routing nodes can and only can match data packets select a routing node as the next hop; denote routing nodes in the same time slot accept matching requests of data packets at most;

[0050] at the beginning of a time slot, routing nodes match data packets select routing nodes according to a state-action value function; define a time slot data packet select a routing node as the next hop with a preference value of

[0051]

[0052] wherein is a state-action value function of data packets ; is a matching price; based on routing selection preferences, the preference values are arranged in descending order to obtain a preference list of data packets for the next hop routing node.

[0053] Optionally, the routing node ranked highest in the preference list is sent a transmission request for matching application, and it is judged whether the routing node receives a transmission request exceeding the quota. If yes, a matching conflict exists, including:

[0054] All data packets send transmission requests to the routing node ranked highest in the respective preference list, denoted as

[0055]

[0056] If the routing node receives a number of transmission requests less than or equal to , the routing node directly matches all data packets sending transmission requests; if the routing node receives a number of transmission requests greater than , a matching conflict occurs.

[0057] Optionally, the matching conflict is solved by raising the matching price, updating the preference list and re-proposing the matching application, and an optimal decision of routing reconstruction is output, including:

[0058] For the routing node in which a matching conflict occurs, all competing data packets are added to a set The matching price is raised The matching price of all data packets is raised, i.e.

[0059]

[0060] In the formula, is a matching price step; The preference list of all data packets is updated, and a matching application is re-submitted to the route node ranked first in the preference list until no matching conflict occurs, and an optimal route selection reconstruction decision is output.

[0061] In a second aspect, the present application provides a backbone transmission network and data network multi-domain cooperative route reconstruction system, comprising:

[0062] The data acquisition module is configured to acquire power service data and calculate transmission time delay of the power service data between route nodes and transmission risk on a link.

[0063] The model construction module is configured to construct a route selection reconstruction Markov decision process (MDP) model with the objective of minimizing transmission time delay and transmission risk.

[0064] The preference list acquisition module is configured to initialize a matching price and a state-action value function of the route selection reconstruction MDP model, and construct a route selection reconstruction preference list based on the state-action value function.

[0065] The optimal output module is configured to send a transmission request to a route node ranked highest in the preference list, submit a matching application, judge whether the route node receives a transmission request exceeding a quota, and if yes, a matching conflict exists, a matching application is re-submitted by raising the matching price and updating the preference list to solve the matching conflict, and an optimal decision of route reconstruction is output.

[0066] Optionally, the acquisition of the power service data and the calculation of the transmission time delay of the power service data between route nodes comprise:

[0067] First, the data node receives different service data uploaded by a plurality of power service devices, the data node The power service The data packet is represented as

[0068]

[0069] In the formula, represents a destination node, and ; represents a data importance degree; represents a data amount size;

[0070] Data packet from a generating node to a destination node In the process of transmission, each time slot selects a routing node as the next hop for data transmission, and the set of next hop routing nodes of the routing node is ; the set of previous hop routing nodes of the routing node is ; the routing reconfiguration indication variable is , wherein , represents that the routing node selects the routing node as the next hop for data transmission in the time slot , otherwise ; the transmission delay of data between the routing node and is

[0071]

[0072] In the formula, represents the transmission rate.

[0073] In a third aspect, the present application 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 the backbone transmission network and data network multi-domain collaborative routing reconfiguration method when executing the computer program.

[0074] In a fourth aspect, the present application provides a computer readable storage medium, which stores a computer program, wherein the computer program implements the steps of the backbone transmission network and data network multi-domain collaborative routing reconfiguration method when executed by a processor.

[0075] Compared with the prior art, the present application has the following technical effects:

[0076] The backbone transmission network and data network multi-domain collaborative routing reconfiguration method can quickly switch the transmission path or recover the fault when the backbone transmission network fails, ensuring the continuous transmission of data network services. This is achieved through real-time routing selection and reconfiguration, reducing the service interruption time caused by network failure and improving the overall stability of the data network.

[0077] ​In the method, a three-layer risk model of a business layer, a transmission layer and a physical layer is constructed, and the backbone transmission network transmission link failure risk and the data network service data interruption risk are comprehensively considered. The multi-level risk modeling method can more comprehensively reflect the actual risk status of network operation, and provide more accurate decision basis for route selection.

[0078] By modeling the route selection reconstruction problem as a Markov Decision Process (MDP) and combining the Q-learning algorithm, the application can dynamically select the optimal routing path according to the network state and service demand. This method not only considers the current network status, but also makes more intelligent routing decisions by predicting the future network state, thereby effectively reducing the transmission delay and transmission risk of service data.

[0079] In the route selection process, multiple data packets may compete for the same routing node. The application introduces a global penalty function to evaluate the degree of routing conflict, and updates the Q value and preference list through the price increase matching algorithm, thereby solving the routing conflict problem. This method ensures the fairness and effectiveness of route selection, avoiding network congestion and performance degradation caused by conflicts.

[0080] Through intelligent routing selection and reconstruction, the application can more reasonably allocate network resources, avoiding waste and idling of resources. This not only improves the transmission efficiency of the network, but also reduces the operating cost of the network, providing strong support for efficient transmission of power services.

[0081] The routing reconstruction method proposed by the application has adaptability and scalability. It can dynamically adjust the routing strategy according to the changes of the network and the demands of the service, ensuring 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 more extensive network optimization.

[0082] In summary, the backbone transmission network and data network multi-domain collaborative operation route reconstruction method proposed by the application has significant technical effects, which can improve the continuity and stability of data network services, enhance the accuracy of risk modeling, optimize route selection and reduce latency and risk, effectively solve routing conflicts, improve the utilization rate of network resources, and enhance the adaptability and scalability of the network. BRIEF DESCRIPTION OF DRAWINGS

[0083] Figure 1 Schematic diagram of a backbone transmission network and data network multi-domain collaborative operation route reconstruction system.

[0084] Figure 2 Schematic diagram of a backbone transmission network and data network multi-domain collaborative operation route reconstruction module.

[0085] Figure 3 Flowchart of the application. DETAILED DESCRIPTION

[0086] The application is further described below in conjunction with the accompanying drawings:

[0087] Embodiment 1, please refer to Figure 3 The application provides a backbone transport network and data network multi-domain cooperative routing reconstruction method, comprising:

[0088] Collecting power service data, calculating the transmission delay of the power service data between routing nodes and the transmission risk on the link;

[0089] Building a routing reconstruction Markov decision process (MDP) model with the goal of minimizing transmission delay and transmission risk;

[0090] Initializing the matching price and state-action value function of the routing reconstruction MDP model, and building a routing reconstruction preference list based on the state-action value function;

[0091] Sending a transmission request to the highest ranked routing node in the preference list, making a matching application, and determining whether the routing node has received a transmission request exceeding the quota. If it exceeds, there is a matching conflict. The matching conflict is resolved by raising the matching price, updating the preference list, and reapplying for matching. The optimal decision of routing reconstruction is output.

[0092] The application first collects power service data to provide detailed basic information for subsequent routing selection. Through the processing of these data, especially the calculation of the transmission delay of the power service data between routing nodes and the transmission risk on the link, the application provides a key decision basis for routing reconstruction. This efficient data collection and processing mechanism ensures the accuracy and reliability of routing selection.

[0093] By building a routing reconstruction Markov decision process (MDP) model, the application converts the routing selection problem into a dynamic optimization problem. With the goal of minimizing transmission delay and transmission risk, the model can consider the current network state, business demand and future possible network changes, thereby selecting 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.

[0094] The application initializes the matching price and state-action value function of the routing reconstruction MDP model, and builds a routing reconstruction preference list based on the state-action value function. This intelligent decision mechanism can dynamically adjust the routing selection strategy according to the actual network conditions and business demand. At the same time, by sending a transmission request to the highest ranked routing node in the preference list and making a matching application, the application realizes fast and accurate routing selection.

[0095] In the routing process, multiple data packets inevitably compete for the same routing node, leading to matching conflicts. The application can timely discover and solve such conflicts by judging whether the routing node has received more than the quota of transmission requests. By increasing the matching price, updating the preference list and reapplying for matching, the application can effectively solve the matching conflicts and ensure the fairness and effectiveness of the routing selection.

[0096] Through the above technical means, the application can significantly improve the overall performance of the network. The optimized routing strategy and intelligent routing reconstruction decision reduce the transmission delay and risk of business data, 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.

[0097] The backbone transmission network and data network multi-domain collaborative routing reconstruction method proposed by the application is not only suitable for the current network environment, but also has strong flexibility and scalability. As the network scale continues to expand and business demands continue to change, 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 be extended to other types of networks and application scenarios, providing solutions for more extensive network optimization.

[0098] In summary, the backbone transmission network and data network multi-domain collaborative routing reconstruction method provided by the application, through efficient data collection and processing, optimized routing selection strategy, intelligent routing reconstruction decision, effective conflict resolution mechanism and improvement of the overall performance and flexibility of the network, provides strong technical support for efficient transmission of power business and stable operation of the network.

[0099] In embodiment 2, the application provides a backbone transmission network and data network multi-domain collaborative routing reconstruction method, which specifically includes:

[0100] Step 1: The time delay calculation submodule is responsible for calculating the transmission time delay of the data packet between the routing nodes. First, the data node receives different service data packets uploaded by multiple power service devices, and the data node The power service The data packet can be represented as

[0101] (1)

[0102] In the formula, represents the destination node of , and . represents the data importance of . represents the data size of .

[0103] Data Packet 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 Packet At the routing node and The transmission delay between

[0104] (2)

[0105] Where, Indicates the transmission rate.

[0106] Step 2: Construct the business layer risk model, transport layer risk model, and physical layer risk model in the risk reconstruction submodule. Since the optical cable damage event is highly random and the longer the link, the higher the interruption risk, the present invention will link The transmission reliability is expressed as

[0107] (3)

[0108] Where, Indicates a link length. Indicates a link The transmission reliability of a unit length of optical cable is calculated. Service risk in a network is defined as the impact on the stable operation of the power grid if a link suddenly fails.

[0109] 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 the interruption of high-importance business transmission, which will inevitably affect the safe and stable operation of the power system. It represents the product of data importance and link failure rate. When the data packet By routing node The service layer risk of the data packet transmitted to the next hop routing node is

[0110] (4)

[0111] wherein, represents the data importance of the power service of the data node .

[0112] Transmission layer risk model: The transmission layer risk model is mainly related to the traffic size of the service carried by the link. The loss of a large number of low importance services caused by link failure can also trigger the cascading effect of power grid failure. The transmission risk on a single link of the transmission network is represented by , i.e., the product of the service data packet size and the link failure rate. At time slot , the data packet is transmitted by the routing node to the next hop routing node, and the transmission layer risk is

[0113] (5)

[0114] Physical layer risk model: Due to the burstiness and randomness of the optical cable interruption event, the increase of the routing length will increase the probability of power service transmission interruption. Therefore, the physical layer risk on a single link of the transmission network can be represented by the growth rate of the optical fiber link length. At time slot , the data packet is transmitted by the routing node to the next hop routing node, and the physical layer risk is

[0115] (6)

[0116] wherein, represents the shortest path length of the data packet at the routing node at time slot selected by the Dijkstra algorithm.

[0117] 4) Normalization and total risk model: Since different levels of risk have different dimensions and orders of magnitude, they need to be normalized first. The normalized service layer, transmission layer and physical layer risks are represented by , , respectively. Taking as an example, it can be represented as

[0118] (7)

[0119] wherein, and ​respectively represent the upper and lower bound of the transmission layer risk.

[0120] In summary, in the time slot , the data packet is transmitted to the next hop routing node. The overall risk of the data packet transmitted to the next hop routing node can be represented as

[0121] (8)

[0122] In the formula, , and respectively represent the weights of the service layer risk, the transmission layer risk and the physical layer risk.

[0123] Step 2: The present application aims to minimize the transmission delay and the transmission risk of the power service data in the whole network from the long-term operation perspective of the transmission network, and the final backbone transmission network and data network collaborative operation optimization problem can be modeled as

[0124] (9)

[0125] In the formula, represents the set of . is the quota of the routing node . represents the constraint of the routing selection reconstruction indicator variable. represents that the data packet can only select one routing node as the next hop in each time slot. represents that the routing node can transmit at most data packets in each time slot.

[0126] The data packet passes through multiple routing nodes in the transmission process, and a backbone transmission network and data network multi-domain collaborative operation routing reconstruction module is deployed on each routing node. These modules can be regarded as intelligent agents, which are responsible for making decisions, i.e. deciding the routing node of the next hop of the data packet. For each intelligent agent , the optimization problem of the data packet can be represented as

[0127] (10)

[0128] 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 specifically introduced as follows.

[0129] 1) State space: define the data packet The state space of the data packet is the data size, the data importance, the data transmission delay, and the overall risk, which can be expressed as .

[0130] 2) Action space: in each time slot, the routing node selects a routing node as the next hop for data transmission. The action space of the routing node selecting the next hop routing node for the data packet is . .

[0131] 3) Reward: the reward brought by the routing node selecting the next hop routing node for the data packet is the product of the data size, the transmission delay, and the transmission risk, i.e., the optimization objective , which can be expressed as . Step 4: In the initialization submodule, the matching price and the state-action value function

[0132] are initialized. Step 5: In the routing selection reconstruction preference list construction submodule, the routing selection reconstruction preference list construction is based on the Q value. The present application optimizes the selection of the power service data transmission routing node based on the coupled Q learning, determines the optimal next hop routing node, and can use the mapping to represent the matching relationship between the two, i.e.,

[0133]

[0134] (11)

[0135] In the formula, represents the mapping of the data packet to the next hop routing node .

[0136] The matching rule for the routing node selecting the next hop routing node for the data packet is expressed as

[0137] (12)

[0138] In the formula, is the quota of the routing node , i.e., the routing node can transmit at most data packets in the same time slot; represents that the routing node can and only can select a routing node as the next hop for the data packet .​​​ representing routing nodes at most one packet is accepted in the same time slot matching request.

[0139] at the beginning of a time slot, the routing node selects a packet according to a state-action value function. Define the packet selects a routing node as the next hop with a preference value

[0140] (13)

[0141] wherein is a state-action value function of the packet . is a matching price. Based on the routing selection preference, the preference values are arranged in descending order to obtain a preference list of the packet for the next hop routing node.

[0142] Step 6: In the matching application and conflict judgment submodule, all packets send transmission requests to the routing node with the highest ranking in the respective preference list, which can be represented as

[0143] (14)

[0144] If the number of transmission requests received by the routing node is less than or equal to , the routing node directly matches with all packets that send transmission requests; if the number of transmission requests received by the routing node is greater than , a matching conflict occurs.

[0145] Step 7: In the conflict coordination submodule, solve the matching conflict. For the routing node that has a matching conflict, all competing packets are added to the set , and the matching price of all packets in the set is raised, i.e.

[0146] (15)

[0147] wherein is a matching price step size. All packets in the set update the preference list according to (13), and then re-propose a matching application to the routing node with the highest ranking in the preference list. For the routing node , repeat steps 5-7 until no match conflict occurs.

[0148] Step 8: In the cooperative learning sub-module, observe and , based on the calculated reward, move to the next state. At the same time, introduce a global penalty function to quantify the degree of routing conflict, which is defined as

[0149] (16)

[0150] In the formula, represents the number of data packets of the competing routing node , is the total number of data packets transmitted by the routing network.

[0151] Step 9: Output the optimal routing reconstruction decision in the optimal decision output sub-module.

[0152] Step 10: In the action value function update sub-module, update the state-action value function , which can be represented as

[0153] (17)

[0154] In the formula, is the learning efficiency, the greater the learning efficiency, the faster the convergence; is the discount factor, which represents the degree of influence of state returns, the greater the discount factor, the greater the influence of state returns.

[0155] The backbone transmission network and data network multi-domain cooperative operation routing reconstruction system has a structure as shown in the accompanying Figure 1 , including a power equipment layer, a backbone transmission network layer, and a data network layer.

[0156] The power equipment layer mainly includes power generation equipment, power transformation and distribution equipment, power consumption equipment, and power transmission lines connecting each node, and uploads the equipment operation state data to the backbone transmission network layer through optical fiber communication. The backbone transmission network layer deploys a backbone transmission network and data network multi-domain cooperative operation routing reconstruction module on each routing node, and each routing node transmits power service data through optical fiber links. The data network layer is established on the backbone transmission network layer, and the data forwarding nodes are deployed with communication, calculation, and storage functions to realize effective processing of service data.

[0157] The backbone transmission network and data network multi-domain cooperative operation routing reconstruction module has a structure as shown in the accompanying Figure 2As shown, it comprises a data collection submodule, a time delay calculation submodule, a risk reconstruction submodule, a routing reconstruction MDP model submodule, an initialization submodule, a routing reconstruction preference list construction submodule, a matching application and conflict judgment submodule, a conflict coordination submodule, a collaborative learning submodule, an optimal decision output submodule, an action value function updating submodule and a communication submodule.

[0158] The data collection submodule is responsible for collecting power service data packets;

[0159] The time delay calculation submodule is responsible for calculating the transmission time delay of the data packets between the routing nodes;

[0160] The risk reconstruction submodule is responsible for constructing a service layer risk model, a transmission layer risk model and a physical layer risk model;

[0161] The routing reconstruction MDP model submodule is responsible for constructing a routing reconstruction MDP model;

[0162] The initialization submodule is responsible for matching the price and the state action value function;

[0163] The routing reconstruction preference list construction submodule is responsible for constructing a routing reconstruction preference list based on the Q value;

[0164] The matching application and conflict judgment submodule is responsible for the matching application between the routing nodes and the judgment of the selection conflict;

[0165] The conflict coordination submodule is responsible for coordinating the conflict until no matching conflict occurs;

[0166] The collaborative learning submodule is responsible for the collaborative learning between the routing nodes;

[0167] The optimal decision output submodule is responsible for outputting the optimal routing reconstruction decision;

[0168] The action value function updating submodule is responsible for updating the action value function;

[0169] The communication submodule is responsible for sending the selection decision to the routing nodes.

[0170] The application provides a backbone transmission network and data network multi-domain collaborative operation routing reconstruction method. When the backbone transmission network fails and further causes the data network service to be interrupted, the method can 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. At the same time, the method can also collaboratively consider the backbone transmission network transmission link fault risk and the data network service data interruption risk, and perform service layer, transmission layer and physical layer risk modeling, thereby improving the accuracy of modeling.

[0171] The application provides a backbone transmission network and data network multi-domain cooperative operation routing reconstruction method.

[0172] In another embodiment of the application, a backbone transmission network and data network multi-domain cooperative routing reconstruction system is provided, which can be used to implement the above-mentioned backbone transmission network and data network multi-domain cooperative routing reconstruction method.

[0173] A data acquisition module is configured to acquire power service data and calculate transmission time delay of the power service data between routing nodes and transmission risk on a link.

[0174] A model construction module is configured to construct a routing selection reconstruction Markov decision process (MDP) model with the objective of minimizing transmission time delay and transmission risk.

[0175] A preference list acquisition module is configured to initialize matching prices and state-action value functions of the routing selection reconstruction MDP model and construct a routing selection reconstruction preference list based on the state-action value functions.

[0176] An optimal output module is configured to send a transmission request to a routing node with the highest ranking in the preference list, make a matching application, judge whether the routing node receives a transmission request exceeding a quota, and if yes, a matching conflict exists, the matching conflict is solved by increasing the matching price, updating the preference list, making a new matching application, and outputting an optimal decision of routing reconstruction.

[0177] The division of the modules in the embodiments of the application is illustrative, and is only a logical function division, and another division mode can be used in actual implementation, and each function module in each embodiment of the application can be integrated in one processor, or can be physically separated, or two or more modules can be integrated in one module.

[0178] In still another embodiment of the present application, a computer device is provided, which comprises a processor and a memory, the memory being configured to store a computer program, the computer program comprising program instructions, and the processor being configured to execute the program instructions stored in the computer storage medium. The processor can be a central processing unit (CPU), and can also be 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, discrete hardware components, etc., which are the computing core and control core of the terminal, and are suitable for implementing one or more instructions, and are particularly suitable for loading and executing one or more instructions in the computer storage medium to implement a corresponding method flow or a corresponding function; the processor in the embodiments of the present application can be used for the operation of the backbone transmission network and data network multi-domain collaborative routing reconstruction method.

[0179] In still another embodiment of the present application, the present application further provides a storage medium, specifically a computer readable storage medium (Memory), which is a memory device in a computer device, and is configured to store programs and data. It can be understood that the computer readable storage medium herein can include an internal storage medium in the computer device, and of course can also include an extended storage medium supported by the computer device. The computer readable storage medium provides a storage space, and the storage space stores an operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space, and the instructions can be one or more computer programs (including program codes). It should be noted that the computer readable storage medium herein can be a high-speed RAM memory, or a non-volatile memory such as at least one disk memory. One or more instructions stored in the computer readable storage medium can be loaded and executed by the processor to implement the corresponding steps of the backbone transmission network and data network multi-domain collaborative routing reconstruction method in the above embodiments.

[0180] Those skilled in the art will appreciate that embodiments of the application can be devised for a method, a system, or a computer program product. Accordingly, the present application can be embodied in the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, etc.) embodying computer readable program code.

[0181] The present application is described in reference to the flowchart and / or block diagrams of the method, apparatus (system) and computer program product according to embodiments of the application. It will be understood that each block of the flowchart and / or block diagrams, and combinations of blocks in the flowchart and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processing device or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks.

[0182] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks.

[0183] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks.

[0184] Finally, it should be noted that the above-mentioned embodiments are merely intended for describing the technical solutions of the present application, but not for limiting it. Although the present application is described in detail with reference to the above embodiments, those skilled in the field should understand that the specific embodiments of the present application can be modified or replaced equivalently without departing from the spirit and scope of the present application, and any modification or equivalent replacement without departing from the spirit and scope of the present application should be covered in the protection scope of the claims of the present application.

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 and calculate the transmission delay and link transmission risk of power business data between routing nodes, including: First, the data node receives different business data uploaded by multiple power business devices. Power business The data packet is represented as Where, express The destination node; Indicates data packet Importance; express The amount of data; Data Packet 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 packets on Select routing node As the next hop for data transmission, otherwise ; 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 build 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 for matching. Determine whether the routing node has received transmission requests exceeding its quota. If so, a matching conflict exists. Resolve the matching conflict by increasing the matching price, updating the preference list, and resubmitting a matching request. Output the optimal routing decision. 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 backbone transmission network and data network is modeled as Where, represent A collection of For routing nodes quota; Indicates 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; Indicates a routing node The maximum amount of data that can be transmitted in each time slot is data packets; VC To generate a node set, (t) is the data packet At the routing node and The transmission delay between (t) is the time slot Time Data Packet By routing node The overall risk of transmission to the next-hop routing node; T is the set of time slots; m refers to the type of power business, and M is the set of power business types; 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, which is expressed as ; 2) Action space: In each time slot, routing nodes For data packets Select a routing node as the next hop for data transmission; define the routing node For data packets The action space for selecting the next hop routing node is ; 3) Bonus: Define routing nodes For data packets choose The reward for the next-hop routing node is the product of data size, transmission delay and transmission risk, that is, the optimization goal , expressed as .

2. The backbone transmission network and data network multi-domain collaborative routing reconstruction method 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: Data Packet At the routing node and The transmission delay between Where, Indicates the transmission rate.

3. The backbone transmission network and data network multi-domain collaborative routing reconstruction method according to claim 2, characterized in that: The collecting of electric power business data and the calculation of the transmission risk of the electric power business data on the link include: Link The transmission reliability is expressed as Where, Indicates a link length; Indicates a 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 link suddenly fails. Business layer risk model: Business layer risk model on a single link of the transmission network Indicates that the product of data importance and link failure rate; in time slot When the data packet By routing node The business layer risk of transmitting to the next hop routing node is Where, Represents a data node Power business The importance of data; Transport layer risk model: Transmission risk model on a single link in the transmission network Indicates that the product of the service data packet size and the link failure rate; in the time slot 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 Where, 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 Where, 、 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 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 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 a mapping: Where, Indicates data packet To the next hop routing node Mapping; Routing Node For data packets The matching rule for selecting the next hop routing node is expressed as Where, For routing nodes The quota of routing nodes in the same time slot Maximum transmission data packets; Indicates a routing node Can and can only be data packets Select a routing node as the next hop; Indicates a routing node At most, Matching request for data 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 data packets Select routing node The preference value for the next hop is Where, For data packets The state-action-value function of To match the price; based on the routing preference, the preference value is sorted in descending order to obtain the data packet A list of preferred next-hop routing nodes.

5. The backbone transmission network and data network multi-domain collaborative routing reconstruction method according to claim 4, characterized in that: The transmission request is sent to the routing node with the highest ranking in the preference list to make a matching application, and it is determined whether the routing node has received more transmission requests than the quota. If it exceeds the quota, there is a matching conflict, including: All data packets send transmission requests to the routing node with the highest ranking in their preference list, 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.

6. The backbone transmission network and data network multi-domain collaborative routing reconstruction method according to claim 5, characterized in that: The matching conflicts are resolved by increasing the matching price, updating the preference list, and resubmitting the matching application, and the optimal decision is reconstructed by outputting the routing, including: For routing nodes with matching conflicts , add all competing packets to the set and improve The matching price of all data packets in , i.e. Where, 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.

7. A backbone transmission network and data network multi-domain collaborative routing reconstruction system, characterized in that: include: The data acquisition module is used to collect power business data and calculate the transmission delay of power business data between routing nodes and the transmission risk on the link; First, the data node receives different business data uploaded by multiple power business devices. Power business The data packet is represented as Where, express The destination node; Indicates data packet Importance; express The amount of data; Data Packet 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 packets on Select routing node As the next hop for data transmission, otherwise ; The model building module is used to build a routing 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 the routing reconstruction preference list based on the state-action value function; The optimal output module is used to send transmission requests to the routing node with the highest ranking in the preference list for matching. It determines whether the routing node has received transmission requests that exceed its 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 request. The optimal routing decision is then reconstructed. 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 backbone transmission network and data network is modeled as Where, represent A collection of For routing nodes quota; Indicates 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; Indicates a routing node The maximum amount of data that can be transmitted in each time slot is data packets; VC To generate a node set, (t) is the data packet At the routing node and The transmission delay between (t) is the time slot Time Data Packet By routing node The overall risk of transmission to the next-hop routing node; T is the set of time slots; m refers to the type of power business, and M is the set of power business types; 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, which is expressed as ; 2) Action space: In each time slot, routing nodes For data packets Select a routing node as the next hop for data transmission; define the routing node For data packets The action space for selecting the next hop routing node is ; 3) Bonus: Define routing nodes For data packets choose The reward for the next-hop routing node is the product of data size, transmission delay and transmission risk, that is, the optimization goal , expressed as .

8. The backbone transmission network and data network multi-domain collaborative routing reconstruction system according to claim 7, 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: data At the routing node and The transmission delay between Where, Indicates the transmission rate.

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 computer program, the steps of the method for reconfiguring multi-domain collaborative routing of a backbone transmission network and a data network as described in any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method for reconfiguring multi-domain collaborative routing of a backbone transmission network and a data network as claimed in any one of claims 1 to 6 are implemented.

Images