Electric power communication planning method, system and device based on cross-layer slicing and medium

Abstract

The invention relates to the technical field of electric power communication, in particular to an electric power communication planning method, system, equipment and medium based on cross-layer slicing, and the method comprises the steps: classifying all services in an electric power communication network, and obtaining the service type of the electric power communication network; dividing the power communication network resource into a plurality of slices among a plurality of network layers according to the service communication key index of each service type and the available state of the current network resource, and forming a cross-layer slice model comprising the plurality of network layers; determining cross-layer slicing resources of the cross-layer slicing model by using a reinforcement learning algorithm according to the service communication key indexes of the service types; and searching an optimal power communication path by using a path optimization algorithm according to the current power communication network state and the cross-layer slice resources. Through the cross-layer slicing model and the reinforcement learning algorithm, dynamic scheduling and efficient management of power communication network resources are realized, and the utilization rate of the network resources is improved.

Description

Technical Field

[0001] The present invention relates to the field of power communication technology, and in particular to a power communication planning method, system, device and medium based on cross-layer slicing. Background Art

[0002] With the development of intelligent power systems, the business demands they carry are increasing, including diversified business demands such as dispatching control, status monitoring, remote meter reading, and load management. These businesses have different requirements for communication quality, such as data transmission rate, latency, reliability, and security.

[0003] However, traditional power communication network planning methods are often based on fixed network architectures and resource allocation strategies, which are difficult to meet the differentiated demands of diversified business needs for communication resources, resulting in low network resource utilization and difficulty in achieving dynamic optimization and efficient utilization of resources. Therefore, with the increasing types and number of services carried by power communication networks, traditional planning methods can no longer meet the development needs of current and future power systems. There is an urgent need for a new communication planning method that can fully utilize existing network resources and flexibly adapt to different business needs, realize dynamic scheduling and efficient management of resources, and ensure the stability and reliability of power communication networks. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides a power communication planning method, system, device and medium based on cross-layer slicing.

[0005] In a first aspect, the present invention provides a method for planning power communication based on cross-layer slicing, the method comprising the following steps:

[0006] Classify all services in the power communication network to obtain service types of the power communication network;

[0007] According to the key indicators of business communication of each business type and the available status of current network resources, the power communication network resources are divided into several slices between multiple network layers to form a cross-layer slice model containing multiple network layers;

[0008] According to the key indicators of business communication of each business type, the cross-layer slice resources of the cross-layer slice model are determined using the reinforcement learning algorithm;

[0009] According to the current power communication network status and cross-layer slice resources, the path optimization algorithm is used to find the optimal power communication path.

[0010] In a further embodiment, the service types of the electric power communication network include one or more of high-priority real-time services, medium-priority dispatch services, and low-priority non-real-time services.

[0011] In a further implementation scheme, the key service communication indicators of each service type include bandwidth indicators, transmission delay indicators and reliability indicators of each service type.

[0012] In a further implementation scheme, the network layer includes at least a transport layer, a network layer and an application layer, and the power communication network resources include physical resources of the transport layer; the steps of dividing the power communication network resources into a plurality of slices between multiple network layers according to the key indicators of business communication of each business type and the available status of the current network resources, and forming a cross-layer slice model including multiple network layers include:

[0013] According to the key indicators of business communication of each business type and the available status of current network resources, the physical resources of the transport layer are divided into multiple virtual transport slices using a multi-dimensional resource allocation method; each virtual transport slice has an independent physical link and transmission bandwidth;

[0014] Virtualize the routing of the network layer according to business needs to obtain virtual routing slices;

[0015] The virtual transport slice and the virtual routing slice are associated with the application layer service through a mapping mechanism, and the application layer service is divided into multiple application layer slices;

[0016] The virtual transport slice, the virtual routing slice and the application layer slice are integrated to construct a cross-layer slicing model.

[0017] In a further implementation scheme, the step of determining the cross-layer slice resources of the cross-layer slice model using a reinforcement learning algorithm according to the key indicators of service communication of each service type includes:

[0018] Taking minimizing the comprehensive cost between key indicators of business communication as the optimization goal, a slicing objective function is constructed;

[0019] The bandwidth utilization, delay status and failure rate of each slice collected in real time are constructed into a current network status matrix;

[0020] An initial scheduling strategy function is set, and the current network state matrix and the key indicators of business communication are used as the state space, the slice resource allocation scheme executable by the cross-layer slicing model between multiple network layers is defined as the action space, and the merits of the resource allocation actions taken by the scheduling strategy function in different state spaces are evaluated as the reward function;

[0021] The slice objective function is used as the optimization target of the reinforcement learning algorithm. The initial scheduling strategy function is iteratively learned and optimized through the reinforcement learning algorithm until the scheduling strategy function converges and generates a resource allocation matrix.

[0022] The resource allocation of each slice in the cross-layer slice model is determined according to the resource allocation matrix to obtain the cross-layer slice resources.

[0023] In a further embodiment, the step of constructing a slicing objective function with minimizing the comprehensive cost between key indicators of business communication as the optimization goal includes:

[0024] According to the bandwidth index required by each service type and the total available network bandwidth, the relative importance of service bandwidth is obtained;

[0025] According to the transmission delay index of each service type and the maximum network delay, the service delay is obtained;

[0026] The slicing objective function is constructed by minimizing the weighted sum of the relative importance of the service bandwidth, the service delay and the normalized reliability index of all services.

[0027] In a further embodiment, the bandwidth utilization is obtained by calculating the ratio of the bandwidth value actually used in the current slice to the allocated bandwidth value;

[0028] The delay state is obtained by calculating the ratio between the average data packet transmission delay of the current slice and the maximum allowed delay.

[0029] In a further implementation, the step of finding the optimal power communication path using a path optimization algorithm according to the current power communication network state and cross-layer slice resources includes:

[0030] According to the cross-layer slicing model, resource requirements required by each service type are mapped to cross-layer slicing resources to obtain slice resource requirements;

[0031] Determine the link information of paths in different slices according to the current power communication network status;

[0032] The depth-first search algorithm is used to search for paths in each slice, and all conflicting paths are replanned based on the link information of paths in different slices, and the path with the lowest transmission cost is selected as the optimal power communication path.

[0033] In a second aspect, the present invention provides a power communication planning system based on cross-layer slicing, the system comprising:

[0034] A service classification module is used to classify all services in the power communication network and obtain service types of the power communication network;

[0035] A slice partitioning module is used to divide the power communication network resources into several slices between multiple network layers according to the key indicators of business communication of each business type and the available status of the current network resources, so as to form a cross-layer slice model including multiple network layers;

[0036] The slice resource analysis module is used to determine the cross-layer slice resources of the cross-layer slice model using a reinforcement learning algorithm based on the key indicators of business communication of each business type;

[0037] The optimal path planning module is used to find the optimal power communication path using a path optimization algorithm based on the current power communication network status and cross-layer slice resources.

[0038] In a further embodiment, the service types of the electric power communication network include one or more of high-priority real-time services, medium-priority dispatch services, and low-priority non-real-time services.

[0039] In a third aspect, the present invention further provides a computer device, comprising a processor and a memory, wherein the processor is connected to the memory, the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory so that the computer device performs the steps of implementing the above method.

[0040] In a fourth aspect, the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program implements the steps of the above method when executed by a processor.

[0041] The present invention provides a method, system, device and medium for planning electric communication based on cross-layer slicing. The method classifies all services in the electric communication network to obtain the service type of the electric communication network; divides the electric communication network resources between multiple network layers into several slices according to the key indicators of service communication of each service type and the available status of the current network resources, so as to form a cross-layer slicing model including multiple network layers; determines the cross-layer slicing resources of the cross-layer slicing model according to the key indicators of service communication of each service type by using a reinforcement learning algorithm; and finds the optimal electric communication path according to the current state of the electric communication network and the cross-layer slicing resources by using a path optimization algorithm. Compared with the prior art, the method can allocate and utilize network resources more effectively and improve resource utilization through a cross-layer slicing model, and can dynamically adjust resource allocation according to service requirements and network status by using a reinforcement learning algorithm and a path optimization algorithm, so as to realize flexible allocation and dynamic scheduling of electric communication network resources, and ensure the stability and reliability of the electric communication network in the face of different service requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 It is a schematic diagram of a flow chart of a power communication planning method based on cross-layer slicing provided by an embodiment of the present invention;

[0043] Figure 2is a schematic diagram of changes in bandwidth utilization over time before and after slicing is referenced according to an embodiment of the present invention;

[0044] Figure 3 is a schematic diagram of the change of average delay of different service types over time provided by an embodiment of the present invention;

[0045] Figure 4 It is a block diagram of a power communication planning system based on cross-layer slicing provided by an embodiment of the present invention;

[0046] Figure 5 It is a schematic diagram of the structure of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0047] The following specifically illustrates the implementation mode of the present invention in conjunction with the accompanying drawings. The embodiments are provided for illustrative purposes only and are not to be construed as limitations of the present invention. The accompanying drawings are provided for reference and illustration only and do not constitute limitations on the scope of patent protection of the present invention, because many changes may be made to the present invention without departing from the spirit and scope of the present invention.

[0048] refer to Figure 1 , an embodiment of the present invention provides a power communication planning method based on cross-layer slicing, such as Figure 1 As shown, the method comprises the following steps:

[0049] S1. Classify all services in the power communication network to obtain service types of the power communication network.

[0050] This embodiment classifies all services involved in the power communication network to determine the service types of the power communication network, so as to more accurately understand the communication requirements of various services. Specifically, this embodiment divides the services into three priority categories according to the different characteristics and requirements of the services: first, high-priority real-time services, such as relay protection; second, medium-priority dispatching services, such as power grid status monitoring; and finally, low-priority non-real-time services, including remote meter reading, etc. The service types of the power communication network may include one or more of high-priority real-time services, medium-priority dispatching services, and low-priority non-real-time services. Through service classification and cross-layer slicing model, this embodiment can flexibly adapt to the differentiated needs of different services for communication resources.

[0051] S2. According to the key indicators of business communication of each business type and the available status of current network resources, the power communication network resources are divided into several slices between multiple network layers to form a cross-layer slice model containing multiple network layers.

[0052] In this embodiment, the network layer includes at least a transport layer, a network layer and an application layer; the steps of dividing the power communication network resources into a plurality of slices between the plurality of network layers according to the key indicators of the business communication of each business type and the available status of the current network resources, and forming a cross-layer slice model including a plurality of network layers include:

[0053] According to the key indicators of business communication of each business type and the available status of current network resources, the physical resources of the transport layer are divided into multiple virtual transport slices using a multi-dimensional resource allocation method; each virtual transport slice has an independent physical link and transmission bandwidth;

[0054] Virtualize the routing of the network layer according to business needs to obtain virtual routing slices;

[0055] The virtual transport slice and the virtual routing slice are associated with the application layer service through a mapping mechanism, and the application layer service is divided into multiple application layer slices;

[0056] The virtual transport slice, the virtual routing slice and the application layer slice are integrated to construct a cross-layer slicing model.

[0057] Specifically, the key business communication indicators of each business type include bandwidth indicators, transmission delay indicators and reliability indicators of each business type. Those skilled in the art may set other key business communication indicators according to the specific implementation situation, such as delay, jitter, throughput and other indicators. This embodiment comprehensively analyzes the power communication network resources according to the key business communication indicators of each business type and the available status of the current network resources (such as network bandwidth, device status, link quality, etc.), and uses a multi-dimensional resource allocation method (such as resource allocation in dimensions such as time, space, and frequency) to divide the physical resources of the transmission layer into multiple virtual transmission slices, each of which has an independent physical link and transmission bandwidth, providing a stable physical connection and bandwidth support for the upper layer, wherein the power communication network resources include the physical resources of the transmission layer; then, according to business requirements and network policies, the network layer routing is virtualized using virtualization technologies such as software defined networking (SDN) to obtain virtual routing slices to achieve flexible data forwarding and routing selection to meet the needs of different businesses for network connections.

[0058] On the basis of dividing the power communication network resources into virtual transmission slices and virtual routing slices, this embodiment associates the slices of these two levels with the application layer services through a mapping mechanism according to the actual needs of the application layer services. Specifically, this embodiment searches for the most suitable matching items in the divided virtual transmission slices and virtual routing slices according to the specific communication needs of the application layer services (such as service type, data volume, real-time performance, etc.), and establishes a mapping relationship between the most suitable virtual transmission slices and virtual routing slices and the application layer services. The mapping relationship may include information such as service ID, slice ID, resource allocation status (such as bandwidth, delay, etc.). After establishing the mapping relationship, this embodiment can divide the application layer service into multiple slices according to the resources provided by the virtual transmission slice and the virtual routing slice. These slices are logically independent, but can share the underlying resources through the mapping relationship. The obtained application layer slices are used for business data processing and application service provision, ensuring that the business can run efficiently on virtualized resources. The constructed virtual transmission slices, virtual routing slices and application layer slices are integrated to construct a cross-layer slicing model including multiple network layers. The cross-layer slicing model realizes the flexible division and efficient utilization of power communication network resources between multiple network layers, and meets the communication needs of different business types.

[0059] S3. According to the key indicators of business communication of each business type, the reinforcement learning algorithm is used to determine the cross-layer slice resources of the cross-layer slice model.

[0060] In this embodiment, the step of determining the cross-layer slice resources of the cross-layer slice model by using a reinforcement learning algorithm according to the key service communication indicators of each service type includes:

[0061] Taking minimizing the comprehensive cost between key indicators of business communication as the optimization goal, a slicing objective function is constructed;

[0062] The bandwidth utilization, delay status and failure rate of each slice collected in real time are constructed into a current network status matrix;

[0063] An initial scheduling strategy function is set, and the current network state matrix and the key indicators of business communication are used as the state space, the slice resource allocation scheme executable by the cross-layer slicing model between multiple network layers is defined as the action space, and the merits of the resource allocation actions taken by the scheduling strategy function in different state spaces are evaluated as the reward function;

[0064] The slice objective function is used as the optimization target of the reinforcement learning algorithm. The initial scheduling strategy function is iteratively learned and optimized through the reinforcement learning algorithm until the scheduling strategy function converges and generates a resource allocation matrix.

[0065] The resource allocation of each slice in the cross-layer slice model is determined according to the resource allocation matrix to obtain the cross-layer slice resources.

[0066] Specifically, this embodiment takes minimizing the comprehensive cost between the key indicators of business communication (bandwidth, delay, reliability) as the optimization goal, and constructs a slice objective function. The function needs to consider the bandwidth demand, delay demand and reliability requirements of the business, and weighs them through the bandwidth weight coefficient, delay weight coefficient and reliability weight coefficient. The optimization goal is to minimize the comprehensive cost between the key indicators of business communication. The steps of constructing the slice objective function include: obtaining the relative importance of the business bandwidth according to the bandwidth indicator required by each business type and the total available bandwidth of the network; obtaining the business delay according to the transmission delay indicator of each business type and the maximum network delay; constructing the slice objective function by minimizing the weighted sum of the relative importance of the business bandwidth, the business delay and the normalized reliability indicator of all businesses. In this embodiment, the mathematical expression of the slice objective function is:

[0067]

[0068] In the formula, i is the number of the business; n is the total number of businesses; BW i BW is the bandwidth index required for the i-th service; total is the total available bandwidth in the network; L i is the transmission delay index of the ith service; L max is the maximum delay allowed in the entire network; R i is the reliability index of the ith service; α i is the bandwidth weight coefficient; β i is the delay weight coefficient; γ i is the reliability weight coefficient.

[0069] Then, the bandwidth utilization, delay status and failure rate of each slice are collected in real time through the network monitoring module, wherein the bandwidth utilization is obtained by calculating the ratio of the bandwidth value actually used in the current slice to the allocated bandwidth value; the delay status is obtained by calculating the ratio between the average data packet transmission delay of the current slice and the maximum allowed delay. In this embodiment, the bandwidth utilization, delay status and failure rate of each slice collected in real time are constructed into a current network state matrix, and then the current network state matrix and the key indicators of business communication (i.e., bandwidth demand, delay demand and reliability requirement) are used as the state space, and a reward function is defined at the same time. The reward function is used to evaluate the advantages and disadvantages of the actions (i.e., resource allocation scheme) taken by the intelligent agent (i.e., scheduling strategy) under a given state. For example, when the bandwidth utilization is reduced, the delay is reduced and the failure rate is reduced, a higher reward can be given, thereby guiding the optimization direction of the scheduling strategy function to minimize the comprehensive cost between the total bandwidth utilization, delay and reliability.

[0070] This embodiment sets an initial scheduling policy function f(M, C), which is used to calculate an optimized resource allocation plan based on input state information (i.e., the current network state matrix M and the business communication key indicator C). This embodiment selects actions based on the current state and the scheduling policy function, takes the slice objective function as the optimization target of the reinforcement learning algorithm, calculates rewards by executing actions, and optimizes the initial scheduling policy function based on reward feedback. The scheduling policy function is iteratively adjusted through the reinforcement learning algorithm to minimize the comprehensive cost represented by the slice objective function. During the iteration process, the pros and cons of each resource allocation plan are evaluated according to the reward function, and the scheduling policy function is adjusted accordingly. After multiple iterations, until the scheduling policy function converges, a stable and optimized resource allocation plan is achieved, a resource allocation matrix A=f(M, C) is generated, and the resource allocation of each slice in the cross-layer slice model is determined according to the resource allocation matrix A.

[0071] S4. According to the current power communication network status and cross-layer slice resources, the path optimization algorithm is used to find the optimal power communication path.

[0072] In this embodiment, the step of searching for the optimal power communication path using a path optimization algorithm according to the current power communication network state and cross-layer slice resources includes:

[0073] According to the cross-layer slicing model, resource requirements required by each service type are mapped to cross-layer slicing resources to obtain slice resource requirements;

[0074] Determine the link information of paths in different slices according to the current power communication network status;

[0075] The depth-first search algorithm is used to search for paths in each slice, and all conflicting paths are replanned based on the link information of paths in different slices, and the path with the lowest transmission cost is selected as the optimal power communication path.

[0076] Specifically, this embodiment maps the resources required for each service type to the cross-layer slice resources according to the cross-layer slice model, obtains the slice resource requirements, and then determines the link information of the paths in different slices in combination with the current power communication network status. Finally, a depth-first search algorithm is used to perform path search within each slice. At the same time, the link information in different slices is integrated to re-plan the conflicting paths that appear, so as to ensure that the final selected path has the minimum transmission cost. This is used as the optimal power communication path. On the premise of meeting the business requirements, the total transmission cost of the path is reduced as much as possible. The mathematical expression for the path to achieve the minimum transmission cost is:

[0077]

[0078] Where j is the path number; m is the total number of all service paths; P j is the weight factor selected for the jth path; C path (P j ) is the transmission cost of the i-th path.

[0079] This embodiment utilizes a reinforcement learning algorithm and a path optimization algorithm, and can dynamically adjust resource allocation according to business needs and network status to achieve efficient resource management. In addition, in order to improve the fault tolerance of the network, this embodiment adopts a backup path pre-allocation strategy. When the network controller detects a failure in the main path, it can quickly switch to the backup path, thereby minimizing the impact of the failure on the communication service and ensuring the stability and reliability of the power communication network.

[0080] For ease of understanding, the following will take the power communication network in a smart grid as an example for a brief description. In the power communication network of the smart grid, the services carried by the network include real-time relay protection services, dispatching control services, status monitoring services, and non-real-time remote meter reading services. In order to ensure the service quality of these services and improve the resource utilization efficiency and reliability of the network, this embodiment adopts cross-layer slicing technology for network planning. First, this embodiment performs service classification and demand analysis. Within the smart grid, the services are divided into the following three categories according to demand:

[0081] Relay protection service (high priority): This service has extremely high requirements for latency and reliability. Although its data packets are small, they are transmitted at a very high frequency. It is mainly used for rapid detection and isolation of faults. Specifically, its latency requirement is less than 50 milliseconds and its reliability requirement is more than 99.99%.

[0082] Dispatch control business (medium priority): This business involves real-time monitoring of the power grid status and the issuance of dispatch instructions. It has certain requirements for latency and bandwidth, and reliability must also be maintained at a high level. Its latency requirement is less than 100 milliseconds, the bandwidth requirement is about 50 kilobits per second, and the reliability requirement is more than 99.9%;

[0083] Condition monitoring and remote meter reading services (low priority): This type of service is mainly used to collect meter data and sensor data from end users. The data volume is large, but the latency requirement is relatively low and the reliability requirement is also at a medium level. The latency requirement is less than 500 milliseconds and the reliability requirement is more than 99%.

[0084] Next, this embodiment constructs a cross-layer slicing model. At the transport layer, this embodiment reasonably configures the bandwidth and redundancy of the physical link according to the bandwidth requirements and reliability requirements of each type of service. For example, high-priority service slices are configured with dedicated links and redundant paths to ensure their stability and reliability.

[0085] At the network layer, this embodiment designs a low-latency routing strategy for relay protection service slices to ensure that its data packets can reach the target node quickly and accurately. For scheduling control and status monitoring services, this embodiment adopts a dynamic bandwidth adjustment strategy to adapt to fluctuations in their bandwidth requirements.

[0086] At the application layer, this embodiment reserves high-priority processing resources for the relay protection service to ensure that its data packets are quickly responded to during the application processing. This processing method can further improve the real-time performance and reliability of its service.

[0087] Finally, this embodiment performs slice resource allocation and optimization. Assuming that the total network bandwidth is 100 megabits per second, resources are allocated according to the bandwidth requirements and reliability weights of each service. For example, in the relay protection service slice, in order to ensure its high reliability, this embodiment reserves 20% of the link bandwidth as redundancy. Through this resource allocation method, this embodiment can maximize the resource utilization efficiency and reliability of the network while meeting the needs of each service.

[0088] In actual operation, the network controller continuously monitors the traffic dynamics of each service. When it detects that the traffic of the relay protection service has increased, the network controller will respond quickly and increase its transmission bandwidth through a dynamic adjustment mechanism to ensure that the low-latency transmission demand is met. On the contrary, when the traffic of the remote meter reading service is large, since the priority of this service is relatively low, the network controller will take flow limiting measures in a timely manner to balance the allocation of overall network resources. For example, at a certain moment, when the traffic of the relay protection service suddenly increases to 15Mbps, the network controller can capture this change and automatically adjust the originally reserved 10Mbps bandwidth to 15Mbps, while limiting the status quo. The bandwidth usage of the status monitoring and remote meter reading services ensures the efficient use of network resources. In order to ensure the high reliability of the relay protection service, this embodiment adopts redundant path design at both the transmission layer and the network layer, providing multiple low-latency backup transmission paths. When the main path is interrupted due to hardware failure or other reasons, the network controller can respond quickly and switch to the backup path to ensure the continuity and stability of the service. For example, in an actual network, when a link suddenly fails, the network controller will immediately start the pre-set fault-tolerant recovery strategy and quickly switch to the backup path, thereby avoiding affecting the relay protection service and further improving the reliability and stability of the power communication network.

[0089] In order to verify the effectiveness of the cross-layer slicing-based power communication planning method proposed in this embodiment, refer to Figure 2 and Figure 3 In this embodiment, two key indicators, bandwidth utilization and average delay, are mainly used for evaluation on the simulation platform:

[0090] Bandwidth utilization: By counting the bandwidth utilization of each slice, the resource allocation efficiency of the cross-layer slicing model is evaluated. The simulation results show that under the cross-layer slicing model, the overall bandwidth utilization can be stabilized at more than 80%, which fully demonstrates the advantage of this embodiment in resource utilization.

[0091] Average delay: By collecting statistics on the average delay data of different services, we verify whether the delay requirements of the planning scheme for relay protection and dispatching control services are met. The simulation results show that the delay of the relay protection service is always kept within 50 milliseconds.

[0092] In summary, the power communication planning method proposed in this embodiment can flexibly adjust network resource allocation according to the actual needs of power communication services by introducing cross-layer slicing technology, effectively respond to fluctuations in business loads, and significantly improve resource utilization efficiency.

[0093] The embodiment of the present invention provides a method for planning electric communication based on cross-layer slicing, wherein the method classifies all services in the electric communication network to obtain the service type of the electric communication network; divides the electric communication network resources between multiple network layers into several slices according to the key indicators of service communication of each service type and the available status of the current network resources, and forms a cross-layer slicing model including multiple network layers; determines the cross-layer slicing resources of the cross-layer slicing model according to the key indicators of service communication of each service type by using a reinforcement learning algorithm; and finds the optimal electric communication path according to the current state of the electric communication network and the cross-layer slicing resources by using a path optimization algorithm. Compared with the prior art, the method can more effectively allocate and utilize network resources and improve resource utilization through a cross-layer slicing model, and can dynamically adjust resource allocation according to service requirements and network status by using a reinforcement learning algorithm and a path optimization algorithm, thereby solving the problem that the traditional electric communication network planning method is difficult to meet the differentiated requirements of diversified service requirements for communication resources, resulting in low resource utilization, and realizes the flexible allocation and dynamic scheduling of electric communication network resources, and can flexibly adapt to different service requirements, thereby ensuring the stability and reliability of the electric communication network in the face of different service requirements.

[0094] It should be noted that the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0095] In one embodiment, Figure 4 As shown, an embodiment of the present invention provides a power communication planning system based on cross-layer slicing, and the system includes:

[0096] The service classification module 101 is used to classify all services in the power communication network to obtain service types of the power communication network; wherein the service types of the power communication network include one or more of high-priority real-time services, medium-priority scheduling services, and low-priority non-real-time services;

[0097] The slice division module 102 is used to divide the power communication network resources into a plurality of slices between multiple network layers according to the key indicators of business communication of each business type and the available status of the current network resources, so as to form a cross-layer slice model including multiple network layers;

[0098] The slice resource analysis module 103 is used to determine the cross-layer slice resources of the cross-layer slice model by using a reinforcement learning algorithm according to the key indicators of service communication of each service type;

[0099] The optimal path planning module 104 is used to find the optimal power communication path using a path optimization algorithm according to the current power communication network status and cross-layer slice resources.

[0100] For the specific definition of a power communication planning system based on cross-layer slicing, please refer to the above-mentioned definition of a power communication planning method based on cross-layer slicing, which will not be repeated here. A person of ordinary skill in the art will appreciate that the various modules and steps described in conjunction with the embodiments disclosed in this application can be implemented in hardware, software, or a combination of both. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0101] The embodiment of the present invention provides a power communication planning system based on cross-layer slicing, wherein the system classifies all services in the power communication network through a service classification module to obtain the service type of the power communication network; the slice division module divides the power communication network resources between multiple network layers into several slices according to the key indicators of the service communication of each service type and the available status of the current network resources, so as to form a cross-layer slicing model containing multiple network layers; the slice resource analysis module determines the cross-layer slicing resources of the cross-layer slicing model by using a reinforcement learning algorithm according to the key indicators of the service communication of each service type; the optimal path planning module uses a path optimization algorithm to find the optimal power communication path according to the current power communication network status and cross-layer slicing resources. Compared with the prior art, the system can allocate and utilize network resources more effectively and improve resource utilization through a cross-layer slicing model, and at the same time, it can dynamically adjust resource allocation according to business needs and network status by using a reinforcement learning algorithm and a path optimization algorithm, so as to solve the problem that the traditional power communication network planning method is difficult to meet the differentiated needs of diversified business needs for communication resources, resulting in low resource utilization, and realizes the flexible allocation and dynamic scheduling of power communication network resources, which can flexibly adapt to different business needs and ensure the stability and reliability of the power communication network in the face of different business needs.

[0102] Figure 5 A computer device provided by an embodiment of the present invention includes a memory, a processor and a transceiver, which are connected via a bus; the memory is used to store a set of computer program instructions and data, and can transmit the stored data to the processor, and the processor can execute the program instructions stored in the memory to perform the steps of the above method.

[0103] The memory may include a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories; the processor may be a central processing unit, a microprocessor, an application-specific integrated circuit, a programmable logic device, or a combination thereof. By way of example but not limitation, the programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic, or any combination thereof.

[0104] Additionally, the memory may be a physically separate unit or may be integrated with the processor.

[0105] It can be understood by those skilled in the art that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have the same component arrangement.

[0106] In one embodiment, the present invention provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the above method are implemented.

[0107] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., an SSD), etc.

[0108] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing related hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods.

[0109] The above-mentioned embodiments only express several preferred implementation modes of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for ordinary technicians in the technical field, several improvements and substitutions can be made without departing from the technical principles of the present invention, and these improvements and substitutions should also be regarded as the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be based on the protection scope of the claims.

Claims

1. A power communication planning method based on cross-layer slicing, characterized in that: The following steps are involved: Classify all services in the power communication network to obtain service types of the power communication network; According to the key indicators of business communication of each business type and the available status of current network resources, the power communication network resources are divided into several slices between multiple network layers to form a cross-layer slice model containing multiple network layers; According to the key indicators of business communication of each business type, the cross-layer slice resources of the cross-layer slice model are determined using the reinforcement learning algorithm; According to the current power communication network status and cross-layer slice resources, the path optimization algorithm is used to find the optimal power communication path.

2. The method for planning power communication based on cross-layer slicing according to claim 1, characterized in that: The service type of the electric power communication network includes one or more of a high-priority real-time service, a medium-priority dispatch service, and a low-priority non-real-time service.

3. The method for planning power communication based on cross-layer slicing according to claim 1, characterized in that: The key service communication indicators of each service type include bandwidth indicators, transmission delay indicators and reliability indicators of each service type.

4. The method for planning power communication based on cross-layer slicing according to claim 1, characterized in that: The network layer includes at least a transport layer, a network layer and an application layer, and the power communication network resources include physical resources of the transport layer; the steps of dividing the power communication network resources into a plurality of slices between multiple network layers according to the key indicators of business communication of each business type and the available status of the current network resources, and forming a cross-layer slice model including multiple network layers include: According to the key indicators of business communication of each business type and the available status of current network resources, the physical resources of the transport layer are divided into multiple virtual transport slices using a multi-dimensional resource allocation method; each virtual transport slice has an independent physical link and transmission bandwidth; Virtualize the routing of the network layer according to business needs to obtain virtual routing slices; The virtual transport slice and the virtual routing slice are associated with the application layer service through a mapping mechanism, and the application layer service is divided into multiple application layer slices; The virtual transport slice, the virtual routing slice and the application layer slice are integrated to construct a cross-layer slicing model.

5. The method for planning power communication based on cross-layer slicing according to claim 3, characterized in that: The step of determining the cross-layer slice resources of the cross-layer slice model by using a reinforcement learning algorithm according to the key service communication indicators of each service type includes: Taking minimizing the comprehensive cost between key indicators of business communication as the optimization goal, a slicing objective function is constructed; The bandwidth utilization, delay status and failure rate of each slice collected in real time are constructed into a current network status matrix; An initial scheduling strategy function is set, and the current network state matrix and the key indicators of business communication are used as the state space, the slice resource allocation scheme executable by the cross-layer slicing model between multiple network layers is defined as the action space, and the merits of the resource allocation actions taken by the scheduling strategy function in different state spaces are evaluated as the reward function; The slice objective function is used as the optimization target of the reinforcement learning algorithm. The initial scheduling strategy function is iteratively learned and optimized through the reinforcement learning algorithm until the scheduling strategy function converges and generates a resource allocation matrix. The resource allocation of each slice in the cross-layer slice model is determined according to the resource allocation matrix to obtain the cross-layer slice resources.

6. The method for planning power communication based on cross-layer slicing according to claim 5, characterized in that: The steps of constructing a slice objective function with minimizing the comprehensive cost between key indicators of business communication as the optimization goal include: According to the bandwidth index required by each service type and the total available network bandwidth, the relative importance of service bandwidth is obtained; According to the transmission delay index of each service type and the maximum network delay, the service delay is obtained; The slicing objective function is constructed by minimizing the weighted sum of the relative importance of the service bandwidth, the service delay and the normalized reliability index of all services.

7. The method for planning power communication based on cross-layer slicing according to claim 5, characterized in that: The bandwidth utilization is obtained by calculating the ratio of the bandwidth value actually used in the current slice to the allocated bandwidth value; The delay state is obtained by calculating the ratio between the average data packet transmission delay of the current slice and the maximum allowed delay.

8. The method for planning power communication based on cross-layer slicing according to claim 1, characterized in that: The step of finding the optimal power communication path using a path optimization algorithm according to the current power communication network state and cross-layer slice resources includes: According to the cross-layer slicing model, resource requirements required by each service type are mapped to cross-layer slicing resources to obtain slice resource requirements; Determine the link information of paths in different slices according to the current power communication network status; The depth-first search algorithm is used to search for paths in each slice, and all conflicting paths are replanned based on the link information of paths in different slices, and the path with the lowest transmission cost is selected as the optimal power communication path.

9. A power communication planning system based on cross-layer slicing, characterized in that: The system comprises: A service classification module is used to classify all services in the power communication network and obtain service types of the power communication network; A slice partitioning module is used to divide the power communication network resources into several slices between multiple network layers according to the key indicators of business communication of each business type and the available status of the current network resources, so as to form a cross-layer slice model including multiple network layers; The slice resource analysis module is used to determine the cross-layer slice resources of the cross-layer slice model using a reinforcement learning algorithm based on the key indicators of business communication of each business type; The optimal path planning module is used to find the optimal power communication path using the path optimization algorithm according to the current power communication network status and cross-layer slice resources.

10. The cross-layer slicing-based power communication planning system according to claim 9, characterized in that: The service type of the electric power communication network includes one or more of a high-priority real-time service, a medium-priority dispatch service, and a low-priority non-real-time service.

11. A computer device, characterized in that: The computer device comprises a processor and a memory, wherein the processor is connected to the memory, the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the computer device executes the method according to any one of claims 1 to 8.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed, the method according to any one of claims 1 to 8 is implemented.

Images