5G network task unloading and shunting method and system

Abstract

The invention provides a 5G network task unloading and shunting method and system, and belongs to the technical field of wireless communication, and the method comprises the steps: determining all available paths of each network slice; constructing a first matrix and a plurality of second matrixes; all the second matrixes are optimized with the goal of maximizing the number of nodes contained in the selected available path, and an optimized matrix population is obtained; obtaining a node load matrix based on the first matrix and the optimized matrix population; sorting all nodes based on the value of each node load matrix element in the node load matrix to generate an array; traversing each array element in the array, allocating computing resources to the network slices passing through each node, and generating a computing resource allocation scheme; and issuing the computing resource allocation scheme to a physical network through an automatic interface. According to the method, by combining network slicing and intra-network calculation, multi-path selection and resource allocation are optimized, and the participation degree of network nodes is maximized, so that efficient task unloading and shunting are realized.

Description

Technical Field

[0001] The present invention relates to the field of wireless communication technologies, and in particular to a 5G network task offloading and diversion method and system. Background Art

[0002] With the rapid development of the fifth generation of mobile communication technology (5G), the demand for high speed, low latency and high reliability is growing. These demands have promoted the application of emerging technologies such as network slicing and in-network computing, enabling 5G networks to provide customized network resources for different types of services and applications. However, in such a complex and diverse network environment, how to efficiently offload tasks and distribute loads has become a technical problem that needs to be solved urgently.

[0003] In the current 5G network architecture, task offloading mainly relies on transferring computing tasks from mobile terminals or edge devices to cloud data centers or edge computing nodes to reduce the computing burden of terminal devices and improve the response speed of the overall system. However, this approach often focuses on single-path optimization and ignores multi-path coordination and full utilization of node resources. This approach not only limits the full utilization of network resources, but may also cause some nodes to be overloaded while other node resources are idle, thus affecting the load balancing and system performance of the entire network.

[0004] Therefore, how to comprehensively consider multi-path selection, node resource utilization and dynamic network conditions to achieve efficient task offloading and diversion has become a technical problem that needs to be solved urgently. Summary of the invention

[0005] The present invention provides a 5G network task unloading and diversion method, system, electronic device and storage medium, which are used to solve the defects in the prior art, comprehensively consider multi-path selection, node resource utilization and dynamic network conditions, and realize efficient task unloading and diversion.

[0006] The present invention provides a 5G network task offloading and offloading method, comprising the following steps: Determine all available paths for each network slice; each of the available paths includes at least one node; Constructing a first matrix and multiple second matrices, wherein the first matrix is ​​used to represent the relationship between available paths and nodes, and each of the second matrices is used to represent the relationship between each of the network slices and the selected available paths, and each of the network slices can only select at most one available path; Optimizing all the second matrices with the goal of maximizing the number of nodes included in the selected available path to obtain an optimized matrix population; Based on the first matrix and the optimized matrix population, a node load matrix is ​​obtained; Based on the size of the value of each node load matrix element in the node load matrix, all nodes are sorted to generate an array; Traversing each array element in the array, allocating computing resources to the network slice passing through each node, and generating a computing resource allocation plan, wherein each array element corresponds to a node; The computing resource allocation plan is sent to the physical network through an automation interface.

[0007] According to the present invention, a 5G network task offloading and diversion method is provided, wherein the first matrix element A(i, y)=1 in the first matrix indicates that the i-th available path will pass through node y, and A(i, y)=0 indicates that the i-th available path will not pass through node y; the second matrix element B(x, i)=1 in the second matrix indicates that network slice x uses available path i, and B(x, i)=0 indicates that network slice x does not use available path i.

[0008] According to the present invention, a 5G network task offloading and diversion method is provided, wherein the method aims to maximize the number of nodes included in the selected available path, optimizes all the second matrices, and obtains an optimized matrix population, specifically comprising: All the second matrices are optimized using a genetic algorithm, and after multiple iterations, the optimized matrix population is obtained.

[0009] According to the present invention, a 5G network task offloading and offloading method is provided, wherein the genetic algorithm specifically comprises: In each iteration, two second matrices are randomly selected from all the second matrices, and the same rows are randomly selected for exchange to generate new matrix individuals; Randomly select a second matrix and randomly select two different rows, exchange the second matrix elements with values ​​of 1 in the two rows, and generate a new matrix individual; Taking the number of nodes included in the selected available path as the evaluation criterion, matrix individuals with fitness values ​​higher than a preset threshold are selected to enter the next iteration, wherein the number of nodes included in the selected available path is in direct proportion to the fitness value.

[0010] According to the present invention, a 5G network task offloading and offloading method is provided, wherein the optimized matrix population includes a plurality of optimized second matrices; and the node load matrix is ​​obtained based on the first matrix and the optimized matrix population, specifically including: generating a plurality of third matrices, each of the third matrices being obtained by multiplying the first matrix by each of the optimized second matrices; Sum each of the third matrices by column to obtain a plurality of fourth matrices; The node load matrix is ​​determined from all the fourth matrices based on the value of each fourth matrix element in each of the fourth matrices.

[0011] According to the present invention, a 5G network task offloading and offloading method is provided, wherein the node load matrix is ​​determined from all the fourth matrices based on the value of each fourth matrix element in each of the fourth matrices, specifically comprising: When the number of non-zero fourth matrix elements in each of the fourth matrices is inconsistent, the fourth matrix containing the largest number of non-zero fourth matrix elements is used as the node load matrix; When the number of non-zero fourth matrix elements in any two of the fourth matrices is the same, calculating the variance of each of the fourth matrices; The fourth matrix with the smallest variance is used as the node load matrix.

[0012] According to the present invention, a 5G network task offloading and diversion method is provided, wherein each node load matrix element in the node load matrix corresponds to a node, and the value of each node load matrix element represents the number of network slices carried by each node.

[0013] According to the present invention, a 5G network task offloading and diversion method is provided, wherein all nodes are sorted based on the value of each node load matrix element in the node load matrix to generate an array, specifically comprising: When the values ​​of each of the node load matrix elements are inconsistent, all of the node load matrix elements are arranged from left to right in ascending order based on the values ​​of all of the node load matrix elements to generate the array; When the values ​​of any two of the node load matrix elements are consistent, the energy efficiency of the node corresponding to each of the node load matrix elements is calculated; Based on the magnitude of all the energy efficiencies, all the node load matrix elements are arranged from left to right in order from high to low to generate the array.

[0014] According to the present invention, a 5G network task offloading and offloading method is provided, wherein traversing each array element in the array, allocating computing resources to the network slice passing through each node, and generating a computing resource allocation plan specifically includes: When the value of an array element is zero, skip the node corresponding to the array element; When the value of an array element is 1, the minimum value of the remaining computing capacity of the node corresponding to the array element and the remaining computing demand of the corresponding network slice is allocated to the network slice, and the remaining resources of the node and the network slice are updated; When the value of an array element is greater than 1, the remaining computing power of the node corresponding to the array element is evenly distributed among the carried network slices, and the remaining resources of the node and network slice are updated.

[0015] According to the present invention, a 5G network task offloading and offloading method is provided. Before determining all available paths of each network slice, the method further includes: Calculating all possible paths for each of the network slices; Calculate the reliability value and the sum of delays of all the possible paths; wherein the reliability value is calculated by the product of the reliability of all passed nodes and the reliability of the communication link, and the sum of delays is calculated by the sum of the calculation delays of all passed nodes and the link delay of the communication link; Possible paths whose reliability values ​​and / or the total delays do not meet preset requirements are eliminated to obtain all available paths.

[0016] The present invention also provides a 5G network task offloading and diversion system, including the following modules: A first processing module, configured to determine all available paths for each network slice; each of the available paths comprising at least one node; A second processing module, used to construct a first matrix and multiple second matrices, wherein the first matrix is ​​used to represent the relationship between available paths and nodes, and each of the second matrices is used to represent the relationship between each of the network slices and the selected available paths, and each of the network slices can only select at most one available path; The second processing module is further used to optimize all the second matrices with the goal of maximizing the number of nodes included in the selected available path to obtain an optimized matrix population; The second processing module is further used to obtain a node load matrix based on the first matrix and the optimized matrix population; A third processing module is used to sort all nodes based on the value of each node load matrix element in the node load matrix to generate an array; A computing resource generation module, used to traverse each array element in the array, allocate computing resources to the network slice passing through each node, and generate a computing resource allocation plan, wherein each array element corresponds to a node; The resource delivery module is used to deliver the computing resource allocation plan to the physical network through an automation interface.

[0017] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the 5G network task unloading and diversion method as described above is implemented.

[0018] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the 5G network task offloading and diversion methods described above.

[0019] The present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements any of the 5G network task unloading and diversion methods described above.

[0020] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: By determining all available paths for each network slice and ensuring that each available path contains at least one node, the comprehensiveness and flexibility of path selection are improved, ensuring that task offloading can be optimized among multiple paths that meet the requirements of latency and reliability, and enhancing the fault tolerance and resource utilization of the network. By constructing a first matrix and multiple second matrices, the first matrix is ​​used to represent the relationship between available paths and nodes, and each second matrix is ​​used to represent the relationship between each network slice and the selected available path, and each network slice is limited to select at most one available path, thereby achieving a clear mapping of the relationship between paths and nodes and the standardization of network slice path selection, ensuring the orderliness and efficiency of resource allocation, and facilitating subsequent optimization and management. By optimizing all second matrices with the goal of maximizing the number of nodes contained in the selected available path, the optimized matrix population is obtained, thereby making full use of the computing resources of more nodes in the network, improving the load balancing capability and computing efficiency of the overall network, and avoiding the concentrated use of resources. Based on the first matrix and the optimized matrix population, the node load matrix is ​​obtained, thereby accurately reflecting the load situation of each node during the task offloading process, providing reliable data support for subsequent resource allocation and load balancing, and ensuring the efficient use of network resources. By sorting all nodes and generating an array based on the value of each node load matrix element in the node load matrix, the orderly management of network node load is achieved, which is convenient for identifying load levels, optimizing resource allocation strategies, and avoiding node overload or resource idleness. By traversing each array element in the array, computing resources are allocated to network slices passing through each node, and a computing resource allocation plan is generated, thereby ensuring the reasonable allocation and dynamic adjustment of computing resources, optimizing resource usage according to node load conditions, and improving task processing efficiency and overall system performance. The computing resource allocation plan is sent to the physical network through an automated interface, thereby achieving rapid deployment and real-time update of resource allocation, reducing manual intervention, and improving the system's response speed and management efficiency, thereby achieving efficient task offloading and diversion. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0022] Figure 1 This is one of the flow charts of the 5G network task offloading and diversion method provided by the present invention.

[0023] Figure 2 This is the second flow chart of the 5G network task offloading and diversion method provided by the present invention.

[0024] Figure 3 This is the third flow chart of the 5G network task offloading and diversion method provided by the present invention.

[0025] Figure 4 This is the fourth flow chart of the 5G network task offloading and diversion method provided by the present invention.

[0026] Figure 5 This is the fifth flow chart of the 5G network task offloading and diversion method provided by the present invention.

[0027] Figure 6 It is a structural diagram of the 5G network task offloading and diversion system provided by the present invention.

[0028] Figure 7 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0029] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0030] It should be noted that, in the description of the present invention, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "include one..." do not exclude the existence of other identical elements in the process, method, article or device including the elements. The orientation or positional relationship indicated by the terms "upper", "lower", etc. is based on the orientation or positional relationship shown in the accompanying drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the system or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to the specific circumstances.

[0031] The terms "first", "second", etc. in the present invention are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present invention can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are generally of the same type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" means at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0032] Combine the following Figure 1-Figure 7 The present invention describes the 5G network task offloading and offloading method, system, electronic device and storage medium provided by the present invention.

[0033] Figure 1 It is one of the flow charts of the 5G network task offloading and diversion method provided by the present invention, such as Figure 1 As shown, including but not limited to the following steps: Step 11: Determine all available paths for each network slice; each available path contains at least one node.

[0034] In step 11, determining all available paths for each network slice is the basis for the task offloading and load distribution process. In a complex 5G network environment, network slices often have different quality of service (QoS) requirements, such as latency, reliability, etc. In order to ensure that each network slice can obtain the best transmission path under different conditions, it is first necessary to calculate and screen all available paths that meet these requirements, thereby laying the foundation for subsequent path selection and resource allocation.

[0035] The following embodiments will explain in detail how to determine all available paths for each network slice.

[0036] In a possible implementation, before step 11, the method further includes the following steps: Compute all possible paths for each network slice; Calculate the reliability value and the total delay of all possible paths; the reliability value is calculated by the product of the reliability of all passed nodes and the reliability of the communication link, and the total delay is calculated by the sum of the calculation delay of all passed nodes and the link delay of the communication link; Eliminate possible paths whose reliability values ​​and / or total delays do not meet preset requirements to obtain all available paths.

[0037] Specifically, first, by calculating all possible paths for each network slice, a variety of options for task transmission are established. Specifically, the Dijkstra algorithm or other suitable path calculation algorithms, such as the A* algorithm, are used to calculate all possible path sets from the access point of each network slice to the target cloud data center. The purpose of this process is to fully explore the possible paths in the network in order to provide sufficient selection space for subsequent screening. Due to the complexity of the network topology, this step needs to consider the availability of the path and potential network nodes to ensure that different network slices have enough paths to choose from when transmitting.

[0038] Next, a detailed reliability and latency evaluation is performed on each possible calculated path. Specifically, the reliability value of each path is first calculated by calculating the product of the reliability of all passed nodes and communication links, which can effectively evaluate the stability and reliability of the path in task transmission. Then, the sum of the delays of the path is calculated by adding the calculated delays of all passed nodes on the path to the link delays of each communication link to obtain the total delay. By evaluating reliability and latency, a quantitative indicator of service quality can be provided for each path, helping to identify which paths can meet the needs of specific network slices.

[0039] Finally, all possible calculated paths are screened to remove paths that do not meet the reliability and / or latency requirements, thereby obtaining the final set of available paths. The screening process is based on the preset quality of service requirements, with the goal of ensuring that each available path can meet the reliability and low latency requirements of task transmission. After removing unqualified paths, the remaining paths are all available paths that each network slice can use to transmit tasks.

[0040] The effect of doing so is significant. On the one hand, it ensures high reliability and low latency of task transmission, ensuring the service quality of diversified tasks in 5G networks; on the other hand, by eliminating paths that do not meet the requirements, it reduces the complexity of subsequent optimization and resource allocation processes and improves computing efficiency.

[0041] Step 12: Construct a first matrix and multiple second matrices, where the first matrix is ​​used to represent the relationship between available paths and nodes, and each second matrix is ​​used to represent the relationship between each network slice and the selected available path, and each network slice can only select at most one available path.

[0042] In step 12, the first matrix and multiple second matrices are constructed to intuitively represent the relationship between network slices, nodes, and paths, laying a data foundation for subsequent path optimization and computing resource allocation. Through this matrix representation, the mapping relationship between paths and nodes, network slices and paths can be clearly established, thereby achieving more efficient and reasonable task offloading and load distribution.

[0043] In one possible implementation, the first matrix element A(i,y)=1 in the first matrix indicates that the i-th available path will pass through node y, and A(i,y)=0 indicates that the i-th available path will not pass through node y; the second matrix element B(x,i)=1 in the second matrix indicates that network slice x uses available path i, and B(x,i)=0 indicates that network slice x does not use available path i.

[0044] More specifically, a first matrix is ​​constructed, which is used to represent the relationship between available paths and nodes. Specifically, the first matrix element is defined as A(i,y). If the i-th available path passes through node y, then A(i,y)=1, otherwise A(i,y)=0. Through the construction of the first matrix A, the relationship between the path and the node is clearly represented, so that the distribution of network nodes passed by each path can be intuitively reflected in the subsequent path selection and allocation, thereby facilitating the optimization of the path and balanced resource allocation.

[0045] Construct multiple second matrices, each of which is used to represent the relationship between each network slice and the selected available path. Specifically, the second matrix element is defined as B(x,i), where B(x,i)=1 indicates that network slice x has selected available path i, and B(x,i)=0 indicates that the network slice has not selected path i. Since each network slice can only select at most one path, this constraint means that at most one element in each row of each second matrix B is 1. By constructing multiple second matrices B, the selection relationship between each network slice and the available path can be clearly defined, which plays a vital role in the subsequent task offloading and resource allocation based on network slicing.

[0046] By constructing a first matrix and multiple second matrices, complex network slicing and path selection problems can be converted into matrix expressions, making the relationship between network slices, paths, and nodes clear at a glance, thereby facilitating further optimization and calculation. Path selection and network node load analysis can be performed directly in matrix operations, which helps to achieve efficient management of network resources through optimization algorithms.

[0047] Step 13: With the goal of maximizing the number of nodes included in the selected available paths, optimize all second matrices to obtain an optimized matrix population.

[0048] In step 13, the entire second matrix is ​​optimized with the goal of maximizing the number of nodes included in the selected available path. This is to improve the resource utilization efficiency in the 5G network, enable more network nodes to participate in the task offloading and calculation process, maximize the use of network resources, and avoid the problem of idle node resources. By optimizing the second matrix, the load balancing performance of the overall network can be effectively improved, and ultimately the efficiency and reliability of task processing can be improved.

[0049] In a possible implementation manner, step 13 specifically includes the following steps: The genetic algorithm is used to optimize all the second matrices, and after multiple iterations, the optimized matrix population is obtained.

[0050] Specifically, step 13 optimizes all second matrices by using a genetic algorithm, and finally generates an optimized matrix population. Genetic algorithm is an optimization algorithm based on natural selection and genetic mechanism, which is suitable for solving complex combinatorial optimization problems. Its core idea is to simulate the biological evolution process, and continuously optimize individuals in the population through operations such as selection, crossover and mutation to find the global optimal solution. The genetic algorithm simulates the biological evolution process, performs selection, crossover and mutation, gradually optimizes the second matrix, and finds the optimal second matrix, so as to maximize the number of nodes contained in the selected path and enable more network nodes to participate in the calculation and offloading of tasks. This process provides an efficient path optimization method for task offloading of 5G networks, ensuring maximum resource utilization and load balancing.

[0051] In one possible implementation, refer to Figure 2 , Figure 2 This is the second flow chart of the 5G network task offloading and diversion method provided by the present invention. The genetic algorithm specifically includes steps 21-23: Step 21: In each iteration, two second matrices are randomly selected from all second matrices, and the same rows are randomly selected for exchange to generate new matrix individuals.

[0052] Step 22: Randomly select a second matrix and randomly select two different rows, exchange the second matrix elements with values ​​of 1 in the two rows, and generate a new matrix individual.

[0053] Step 23: Taking the number of nodes included in the selected available path as the evaluation criterion, select the matrix individuals with fitness values ​​higher than the preset threshold to enter the next iteration, wherein the number of nodes included in the selected available path is directly proportional to the fitness value.

[0054] Specifically, step 21 first performs a crossover operation. In each iteration, two second matrices are randomly selected from all second matrices, such as the second matrix Bp and the second matrix Bq, and the same rows are randomly selected for exchange to generate new matrix individuals. The crossover operation forms a new solution by exchanging genes between matrices, thereby increasing the diversity of the population. The new matrix individuals after the crossover can contain path selection combinations from different solutions, thereby exploring a wider solution space and avoiding falling into a local optimum too early.

[0055] Next, step 22 performs a mutation operation to introduce greater population diversity. The mutation operation generates new matrix individuals by randomly selecting two rows in a second matrix and exchanging matrix elements with values ​​of 1 in the two rows. This mutation process is equivalent to the redistribution of paths between network slices, but the mutation is only performed when the original path is available to maintain the legitimacy of the solution. Through mutation, the genetic algorithm can avoid falling into a homogenized state after convergence, effectively expanding the search range and creating the possibility of exploring the optimal solution.

[0056] Finally, step 23 performs fitness evaluation based on the number of nodes included in the selected available path. The fitness value is proportional to the number of nodes. Paths containing more nodes indicate that more network resources are activated to participate in task offloading, thereby increasing the overall resource utilization efficiency. In each iteration, matrix individuals with fitness values ​​higher than the preset threshold are selected to enter the next round. This selection strategy ensures the continuous optimization of high-quality solutions and eliminates individuals with low fitness, thereby gradually improving the quality of the population.

[0057] After multiple iterations, the optimal second matrix generated by the genetic algorithm and other second matrices with higher fitness together constitute the optimized matrix population.

[0058] Step 14: Based on the first matrix and the optimized matrix population, obtain the node load matrix.

[0059] In step 14, generating a node load matrix based on the first matrix A and the optimized matrix population is a key step in realizing 5G network task offloading and load distribution. The purpose of this is to accurately reflect the load of each node during the task offloading process, thereby providing reliable data support for subsequent resource allocation and load balancing, and ensuring efficient use of network resources.

[0060] In one possible implementation, refer to Figure 3 , Figure 3 This is the third flow chart of the 5G network task offloading and diversion method provided by the present invention, and step 14 specifically includes steps 141-143: Step 141: Generate multiple third matrices, each of which is obtained by multiplying the first matrix by each optimized second matrix.

[0061] Step 142: Sum each third matrix column by column to obtain a plurality of fourth matrices.

[0062] Step 143: Determine a node load matrix from all fourth matrices based on the value of each fourth matrix element in each fourth matrix.

[0063] In the specific implementation process, first in step 141, a plurality of third matrices are generated by performing matrix multiplication operations on the first matrix A and each optimized second matrix B. The first matrix A represents the relationship between the available paths and the nodes, while the optimized second matrix B represents the relationship between the network slices and the selected paths. The result of the matrix multiplication, i.e., the third matrix, specifically shows the number of network slices carried by each node under a specific path selection scheme. The purpose of this step is to closely combine path selection with node load to form the node load distribution under each path scheme.

[0064] Next, in step 142, each generated third matrix is ​​summed by column to obtain multiple fourth matrices. Each element in the fourth matrix represents the number of network slices carried by the corresponding node. By summing the columns of the third matrix, the load of each node under a specific path selection scheme can be quantified. This process converts complex matrix operation results into specific node load data, providing a clear numerical basis for subsequent load analysis and optimization.

[0065] Then, in step 143, a final node load matrix is ​​determined based on the values ​​of the elements in each fourth matrix.

[0066] In a possible implementation, step 143 specifically includes the following steps: When the number of non-zero fourth matrix elements in each fourth matrix is ​​inconsistent, the fourth matrix containing the largest number of non-zero fourth matrix elements is used as the node load matrix; When the number of non-zero fourth matrix elements in any two fourth matrices is the same, the variance of each fourth matrix is ​​calculated; The fourth matrix with the smallest variance is taken as the node load matrix.

[0067] Specifically, in order to determine the final node load matrix, it is necessary to screen and optimize the generated multiple fourth matrices to ensure the efficiency and balance of task offloading and load distribution. First, by comparing the number of non-zero elements in each fourth matrix, the fourth matrix containing the most non-zero elements is selected as the node load matrix. The purpose of this step is to ensure that as many nodes as possible participate in task offloading, thereby maximizing the utilization of network resources and avoiding potential bottleneck problems caused by the concentration of resources on a few nodes.

[0068] If there are the same number of non-zero elements in multiple fourth matrices, their load distribution balance is further evaluated by calculating the variance of each fourth matrix. A matrix with a smaller variance indicates that the tasks are more evenly distributed among the nodes, reducing the risk of some nodes being overloaded while other nodes have idle resources.

[0069] Finally, the fourth matrix with the smallest variance is selected as the final node load matrix. This selection ensures the balance of load distribution during task offloading and improves the overall network stability and system performance.

[0070] Through the implementation of the above steps, the generated node load matrix not only covers more nodes involved in task offloading, but also optimizes the utilization efficiency of network resources through balanced load distribution, significantly improving the task processing capability and service quality of 5G networks in complex environments.

[0071] Step 15: Based on the value of each node load matrix element in the node load matrix, all nodes are sorted to generate an array.

[0072] In step 15, all nodes are sorted and an array is generated based on the value of each node load matrix element in the node load matrix in order to optimize the subsequent computing resource allocation process and ensure the rationality and efficiency of resource allocation. By sorting the node load conditions, the load level of different nodes in the network can be clarified, so as to formulate a more targeted resource allocation strategy and improve the load balancing capability of the overall network and the utilization efficiency of computing resources.

[0073] In a possible implementation, each node load matrix element in the node load matrix corresponds to a node, and the value of each node load matrix element represents the number of network slices carried by each node.

[0074] In one possible implementation, refer to Figure 4 , Figure 4This is the fourth flow chart of the 5G network task offloading and offloading method provided by the present invention, and step 15 specifically includes steps 151-153: Step 151: When the values ​​of each node load matrix element are inconsistent, all node load matrix elements are arranged from left to right in an ascending order based on the values ​​of all node load matrix elements to generate an array.

[0075] Step 152: When the values ​​of any two node load matrix elements are consistent, the energy efficiency of the node corresponding to each node load matrix element is calculated.

[0076] Step 153: Based on the magnitude of all energy efficiencies, all node load matrix elements are arranged from left to right in a descending order to generate an array.

[0077] During the specific implementation process, it is first necessary to analyze each node load matrix element in the node load matrix. Each element in the node load matrix corresponds to a network node, and its value represents the number of network slices carried by the node. In order to effectively manage and allocate computing resources, it is necessary to understand the load of each node. If the load values ​​of all nodes are different, the values ​​of the node load matrix elements are sorted from small to large to generate an ordered array. This sorting process ensures that nodes with lower loads can obtain computing resource allocation first, thereby avoiding high-load nodes from becoming performance bottlenecks due to insufficient resources.

[0078] In some cases, there may be multiple nodes with the same load value. At this time, in order to further optimize resource allocation, it is necessary to introduce node energy efficiency indicators. Specifically, when the load matrix element values ​​of any two nodes are consistent, the energy efficiency of these nodes is calculated. Nodes with high energy efficiency should have a higher priority in resource allocation, because high energy efficiency nodes can complete more computing tasks with lower energy consumption and improve the energy efficiency performance of the overall network. Based on the calculation results of energy efficiency, these nodes with the same load are arranged in order from high to low energy efficiency to generate the final sorted array.

[0079] Through the above sorting process, the generated array not only reflects the load of each node, but also comprehensively considers the energy efficiency level of the node. The implementation effect of this sorting method is significant. First, it ensures that computing resources are preferentially allocated to nodes with lower load and higher energy efficiency, thereby optimizing resource utilization efficiency and avoiding the problem of performance degradation of some nodes due to overload. Secondly, the balanced resource allocation strategy improves the load balancing ability of the entire network, reduces the risk of single-point overload, and enhances the stability and reliability of the network.

[0080] Step 16: Traverse each array element in the array, allocate computing resources to the network slices passing through each node, and generate a computing resource allocation plan, where each array element corresponds to a node.

[0081] In step 16, traversing each array element in the sorted array, allocating computing resources to the network slices passing through each node, and generating a computing resource allocation plan are crucial links in the process of realizing 5G network task offloading and load distribution. In this way, the reasonable allocation and dynamic adjustment of computing resources can be ensured, thereby optimizing the overall performance and resource utilization efficiency of the network.

[0082] In one possible implementation, refer to Figure 5 , Figure 5 This is the fifth flow chart of the 5G network task offloading and diversion method provided by the present invention, and step 16 specifically includes steps 161-163: Step 161: When the value of an array element is zero, skip the node corresponding to the array element.

[0083] Step 162: When the value of an array element is 1, the minimum value of the remaining computing capacity of the node corresponding to the array element and the remaining computing demand of the corresponding network slice is allocated to the network slice, and the remaining resources of the node and the network slice are updated.

[0084] Step 163: When the value of an array element is greater than 1, the remaining computing power of the node corresponding to the array element is evenly distributed among the carried network slices, and the remaining resources of the node and network slice are updated.

[0085] In the specific implementation process, first in step 161, when the array element D(j)=0, it means that the node currently does not carry any network slices. Therefore, the system skips the node and does not perform any resource allocation operation. The purpose of this step is to avoid wasting computing resources on unnecessary nodes and to allocate resources to nodes with actual needs, thereby improving resource utilization efficiency.

[0086] Next, in step 162, when the array element D(j)=1, it means that the node only carries one network slice. At this time, the system calculates t=min{node remaining computing power, network slice remaining computing demand}, that is, the smaller value of the computing resources available to the node and the computing resources actually required by the network slice. Then, this value t is allocated to the corresponding network slice, while deducting the remaining computing power of the node and the remaining computing demand of the network slice. If all the computing requirements of a network slice are met, the slice is considered to have been allocated, removed from the list to be allocated, and the candidate matrix D is refreshed so that subsequent resource allocation is more efficient. This process ensures that a single slice can obtain sufficient computing resources to meet its needs while avoiding over-allocation of resources.

[0087] In step 163, when the array element D(j)>1, it means that the node carries multiple network slices at the same time. In order to achieve fair and efficient resource allocation, the system distributes the remaining computing power of the node evenly among the network slices it carries. The specific operation is to define t as the remaining computing demand of the network slice divided by D(j), that is, to evenly distribute the remaining computing power of the node to each slice. Then, the calculated t value is allocated to each corresponding network slice, and the remaining resources of the node and network slice are deducted accordingly. This average allocation method ensures the fairness of resource allocation among multiple slices, avoids performance bottlenecks caused by uneven resource allocation in some slices, and improves the load balancing capability of the overall system.

[0088] Through the implementation of steps 161 to 163, the system can dynamically and reasonably allocate computing resources to ensure that each network slice obtains corresponding computing power according to its actual needs. This not only improves the utilization efficiency of computing resources, avoids resource waste and node overload, but also improves the load balancing capability and overall performance of the network through a fair resource allocation strategy. In addition, dynamic adjustment of resource allocation can quickly respond to changes in network load and enhance the adaptability and stability of the system.

[0089] Step 17: Send the computing resource allocation plan to the physical network through the automation interface.

[0090] In step 17, the computing resource allocation plan is sent to the physical network through the automation interface, which is the last step to implement the 5G network task offloading and load distribution method, ensuring that the optimized resource allocation strategy can be actually applied in the network environment. Specifically, we first need to design and deploy an efficient automation interface that can seamlessly connect with the network management system and physical network devices. In actual operation, the automation interface will communicate with the physical network devices through standardized protocols (such as RESTful API, NETCONF, etc.) to ensure the accurate transmission and execution of the resource allocation plan. The interface not only needs to have efficient data transmission capabilities, but also error detection and correction mechanisms to ensure that the allocation plan is not tampered with or lost during transmission. In addition, the interface should also have real-time monitoring and feedback functions, so that after the resource allocation plan is issued, the execution status and feedback information of the network equipment can be obtained in time to ensure the effective implementation of the plan.

[0091] Through the implementation of this automated interface, computing resource allocation schemes can be quickly and accurately applied to physical networks, greatly reducing the need for manual intervention and improving the efficiency and accuracy of resource allocation. This not only ensures the timeliness and reliability of task offloading and load distribution processes, but also improves the response speed and service quality of the entire 5G network. The automated delivery mechanism can also support dynamic adjustment and real-time optimization. When the network environment changes, the interface can quickly update and re-deliver the resource allocation scheme to maintain the optimal utilization of network resources, further enhancing the adaptability and elasticity of the network.

[0092] Reference Figure 6 , Figure 6 It is a structural diagram of the 5G network task offloading and diversion system provided by the present invention, including: A first processing module, configured to determine all available paths for each network slice; each available path includes at least one node; A second processing module is used to construct a first matrix and multiple second matrices, where the first matrix is ​​used to represent the relationship between available paths and nodes, and each second matrix is ​​used to represent the relationship between each network slice and the selected available path, and each network slice can only select at most one available path; The second processing module is further used to optimize all second matrices with the goal of maximizing the number of nodes included in the selected available path to obtain an optimized matrix population; The second processing module is further used to obtain a node load matrix based on the first matrix and the optimized matrix population; The third processing module is used to sort all nodes based on the value of each node load matrix element in the node load matrix to generate an array; A computing resource generation module, used to traverse each array element in the array, allocate computing resources to the network slice passing through each node, and generate a computing resource allocation plan, wherein each array element corresponds to a node; The resource delivery module is used to deliver the computing resource allocation plan to the physical network through the automation interface.

[0093] In a possible implementation manner, the second processing module is further configured to optimize all second matrices using a genetic algorithm, and obtain an optimized matrix population after multiple iterations.

[0094] In a possible implementation manner, the second processing module is further configured to: In each iteration, two second matrices are randomly selected from all second matrices, and the same rows are randomly selected for exchange to generate new matrix individuals; Randomly select a second matrix and randomly select two different rows, exchange the second matrix elements with values ​​of 1 in the two rows, and generate a new matrix individual; Taking the number of nodes included in the selected available path as the evaluation criterion, matrix individuals with fitness values ​​higher than the preset threshold are selected to enter the next iteration, where the number of nodes included in the selected available path is directly proportional to the fitness value.

[0095] In a possible implementation manner, the second processing module is further configured to: generating a plurality of third matrices, each of which is obtained by multiplying the first matrix by each optimized second matrix; Sum each third matrix column by column to obtain multiple fourth matrices; A node load matrix is ​​determined from all fourth matrices based on the value of each fourth matrix element in each fourth matrix.

[0096] In a possible implementation manner, the second processing module is further configured to: When the number of non-zero fourth matrix elements in each fourth matrix is ​​inconsistent, the fourth matrix containing the largest number of non-zero fourth matrix elements is used as the node load matrix; When the number of non-zero fourth matrix elements in any two fourth matrices is the same, the variance of each fourth matrix is ​​calculated; The fourth matrix with the smallest variance is taken as the node load matrix.

[0097] In a possible implementation manner, the third processing module is further configured to: When the values ​​of each node load matrix element are inconsistent, all node load matrix elements are arranged from left to right in ascending order based on the values ​​of all node load matrix elements to generate an array; When the values ​​of any two node load matrix elements are consistent, the energy efficiency of the node corresponding to each node load matrix element is calculated; Based on the size of all energy efficiencies, all node load matrix elements are arranged from left to right in order from high to low to generate an array.

[0098] In a possible implementation, the computing resource generation module is further used to: When the value of an array element is zero, skip the node corresponding to the array element; When the value of an array element is 1, the minimum value of the remaining computing capacity of the node corresponding to the array element and the remaining computing demand of the corresponding network slice is allocated to the network slice, and the remaining resources of the node and the network slice are updated; When the value of an array element is greater than 1, the remaining computing power of the node corresponding to the array element is evenly distributed among the carried network slices, and the remaining resources of the node and network slice are updated.

[0099] In a possible implementation manner, the first processing module is further configured to: Compute all possible paths for each network slice; Calculate the reliability value and the total delay of all possible paths; the reliability value is calculated by the product of the reliability of all passed nodes and the reliability of the communication link, and the total delay is calculated by the sum of the calculation delay of all passed nodes and the link delay of the communication link; Eliminate possible paths whose reliability values ​​and / or total delays do not meet preset requirements to obtain all available paths.

[0100] It should be noted that the 5G network task offloading and offloading system provided by the present invention can execute the 5G network task offloading and offloading method of any of the above-mentioned embodiments during specific operation, which will not be elaborated in this embodiment.

[0101] Figure 7 is a schematic diagram of the structure of the electronic device provided by the present invention, such as Figure 7 As shown, the electronic device may include: a processor 710 (processor), a communication interface 720 (CommunicationsInterface), a memory 730 (memory) and a communication bus 740 , wherein the processor 710 , the communication interface 720 , and the memory 730 communicate with each other through the communication bus 740 . The processor 710 can call the logic instructions in the memory 730 to execute the 5G network task offloading and diversion method, which includes: determining all available paths for each network slice; each available path contains at least one node; constructing a first matrix and multiple second matrices, the first matrix is ​​used to represent the relationship between the available paths and the nodes, and each second matrix is ​​used to represent the relationship between each network slice and the selected available path, and each network slice can only select at most one available path; with the goal of maximizing the number of nodes contained in the selected available path, optimizing all the second matrices to obtain an optimized matrix population; based on the first matrix and the optimized matrix population, obtaining a node load matrix; based on the value of each node load matrix element in the node load matrix, sorting all nodes to generate an array; traversing each array element in the array, allocating computing resources to the network slice passing through each node, and generating a computing resource allocation plan, wherein each array element corresponds to a node; and sending the computing resource allocation plan to the physical network through an automation interface.

[0102] In addition, the logic instructions in the above-mentioned memory 730 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory 730 (ROM, Read-Only Memory), random access memory 730 (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0103] On the other hand, the present invention also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the 5G network task offloading and diversion method provided by the above embodiments, the method including: determining all available paths for each network slice; each available path contains at least one node; constructing a first matrix and multiple second matrices, the first matrix is ​​used to represent the relationship between the available paths and the nodes, and each second matrix is ​​used to represent the relationship between each network slice and the selected available path, and each network slice can only select at most one available path; with the goal of maximizing the number of nodes contained in the selected available path, all the second matrices are optimized to obtain an optimized matrix population; based on the first matrix and the optimized matrix population, a node load matrix is ​​obtained; based on the size of the value of each node load matrix element in the node load matrix, all nodes are sorted to generate an array; traverse each array element in the array, allocate computing resources to the network slice passing through each node, and generate a computing resource allocation plan, wherein each array element corresponds to a node; and send the computing resource allocation plan to the physical network through an automation interface.

[0104] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by the processor 710, is implemented to execute the 5G network task offloading and diversion method provided in the above-mentioned embodiments, the method comprising: determining all available paths for each network slice; each available path contains at least one node; constructing a first matrix and multiple second matrices, the first matrix being used to represent the relationship between the available paths and the nodes, each second matrix being used to represent the relationship between each network slice and the selected available path, and each network slice can only select at most one available path; with the goal of maximizing the number of nodes contained in the selected available path, optimizing all the second matrices to obtain an optimized matrix population; obtaining a node load matrix based on the first matrix and the optimized matrix population; sorting all nodes based on the value of each node load matrix element in the node load matrix to generate an array; traversing each array element in the array, allocating computing resources to the network slice passing through each node, and generating a computing resource allocation plan, wherein each array element corresponds to a node; and sending the computing resource allocation plan to the physical network through an automation interface.

[0105] The system embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, i.e., they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative effort.

[0106] Through the description of the above implementation modes, those skilled in the art can clearly understand that each implementation mode can be implemented by means of software plus a necessary general hardware platform, or of course by hardware. Based on such an understanding, the above technical solution can essentially or in other words be embodied in the form of a software product that contributes to the prior art. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each embodiment or some parts of the embodiment.

[0107] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A 5G network task offloading and offloading method, characterized in that: include: Determine all available paths for each network slice; Each of the available paths includes at least one node; Constructing a first matrix and multiple second matrices, wherein the first matrix is ​​used to represent the relationship between available paths and nodes, and each of the second matrices is used to represent the relationship between each of the network slices and the selected available paths, and each of the network slices can only select at most one available path; Optimizing all the second matrices with the goal of maximizing the number of nodes included in the selected available path to obtain an optimized matrix population; Based on the first matrix and the optimized matrix population, a node load matrix is ​​obtained; Based on the size of the value of each node load matrix element in the node load matrix, all nodes are sorted to generate an array; Traversing each array element in the array, allocating computing resources to the network slice passing through each node, and generating a computing resource allocation plan, wherein each array element corresponds to a node; The computing resource allocation plan is sent to the physical network through an automation interface.

2. The 5G network task offloading and offloading method according to claim 1 is characterized in that: The first matrix element A(i,y)=1 in the first matrix indicates that the i-th available path will pass through node y, and A(i,y)=0 indicates that the i-th available path will not pass through node y; the second matrix element B(x,i)=1 in the second matrix indicates that network slice x uses available path i, and B(x,i)=0 indicates that network slice x does not use available path i.

3. The 5G network task offloading and offloading method according to claim 1, characterized in that: The step of optimizing all the second matrices with the goal of maximizing the number of nodes included in the selected available path to obtain an optimized matrix population specifically includes: All the second matrices are optimized using a genetic algorithm, and after multiple iterations, the optimized matrix population is obtained.

4. The 5G network task offloading and offloading method according to claim 3 is characterized in that: The genetic algorithm specifically includes: In each iteration, two second matrices are randomly selected from all the second matrices, and the same rows are randomly selected for exchange to generate new matrix individuals; Randomly select a second matrix and randomly select two different rows, exchange the second matrix elements with values ​​of 1 in the two rows, and generate a new matrix individual; Taking the number of nodes included in the selected available path as the evaluation criterion, matrix individuals with fitness values ​​higher than a preset threshold are selected to enter the next iteration, wherein the number of nodes included in the selected available path is in direct proportion to the fitness value.

5. The 5G network task offloading and offloading method according to claim 1, characterized in that: The optimized matrix population includes a plurality of optimized second matrices; and obtaining a node load matrix based on the first matrix and the optimized matrix population specifically includes: generating a plurality of third matrices, each of the third matrices being obtained by multiplying the first matrix by each of the optimized second matrices; Sum each of the third matrices by column to obtain a plurality of fourth matrices; The node load matrix is ​​determined from all the fourth matrices based on the value of each fourth matrix element in each of the fourth matrices.

6. The 5G network task offloading and offloading method according to claim 5, characterized in that: The determining the node load matrix from all the fourth matrices based on the value of each fourth matrix element in each of the fourth matrices specifically includes: When the number of non-zero fourth matrix elements in each of the fourth matrices is inconsistent, the fourth matrix containing the largest number of non-zero fourth matrix elements is used as the node load matrix; When the number of non-zero fourth matrix elements in any two of the fourth matrices is the same, calculating the variance of each of the fourth matrices; The fourth matrix with the smallest variance is used as the node load matrix.

7. The 5G network task offloading and offloading method according to claim 1, characterized in that: Each node load matrix element in the node load matrix corresponds to a node, and the value of each node load matrix element represents the number of network slices carried by each node.

8. The 5G network task offloading and offloading method according to claim 7, characterized in that: The step of sorting all nodes based on the value of each node load matrix element in the node load matrix to generate an array specifically includes: When the values ​​of each of the node load matrix elements are inconsistent, all of the node load matrix elements are arranged from left to right in ascending order based on the values ​​of all of the node load matrix elements to generate the array; When the values ​​of any two of the node load matrix elements are consistent, the energy efficiency of the node corresponding to each of the node load matrix elements is calculated; Based on the magnitude of all the energy efficiencies, all the node load matrix elements are arranged from left to right in order from high to low to generate the array.

9. The 5G network task offloading and offloading method according to claim 1, characterized in that: The traversing each array element in the array, allocating computing resources to the network slice passing through each node, and generating a computing resource allocation plan specifically includes: When the value of an array element is zero, skip the node corresponding to the array element; When the value of an array element is 1, the minimum value of the remaining computing capacity of the node corresponding to the array element and the remaining computing demand of the corresponding network slice is allocated to the network slice, and the remaining resources of the node and the network slice are updated; When the value of an array element is greater than 1, the remaining computing power of the node corresponding to the array element is evenly distributed among the carried network slices, and the remaining resources of the node and network slice are updated.

10. The 5G network task offloading and offloading method according to claim 1, characterized in that: Before determining all available paths for each network slice, the method further includes: Calculating all possible paths for each of the network slices; Calculate the reliability value and the sum of delays of all the possible paths; wherein the reliability value is calculated by the product of the reliability of all passed nodes and the reliability of the communication link, and the sum of delays is calculated by the sum of the calculation delays of all passed nodes and the link delay of the communication link; Possible paths whose reliability values ​​and / or the total delays do not meet preset requirements are eliminated to obtain all available paths.

11. A 5G network task offloading and offloading system, characterized in that: include: A first processing module, configured to determine all available paths for each network slice; Each of the available paths includes at least one node; A second processing module, used to construct a first matrix and multiple second matrices, wherein the first matrix is ​​used to represent the relationship between available paths and nodes, and each of the second matrices is used to represent the relationship between each of the network slices and the selected available paths, and each of the network slices can only select at most one available path; The second processing module is further used to optimize all the second matrices with the goal of maximizing the number of nodes included in the selected available path to obtain an optimized matrix population; A second processing module is further used to obtain a node load matrix based on the first matrix and the optimized matrix population; A third processing module, used for sorting all nodes based on the value of each node load matrix element in the node load matrix to generate an array; A computing resource generation module, used to traverse each array element in the array, allocate computing resources to the network slice passing through each node, and generate a computing resource allocation plan, wherein each array element corresponds to a node; The resource delivery module is used to deliver the computing resource allocation plan to the physical network through an automation interface.

12. An electronic 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, it implements the 5G network task offloading and diversion method as described in any one of claims 1-10.

13. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the 5G network task offloading and diversion method as described in any one of claims 1-10.

14. A computer program product comprising a computer program, characterized in that When the computer program is executed by the processor, it implements the 5G network task offloading and diversion method as described in any one of claims 1-10.

Images