Heterogeneous end-side cloud cooperative computing method and system based on elastic coupling mechanism

Abstract

The invention discloses a heterogeneous end-side cloud cooperative computing method based on an elastic coupling mechanism. The method comprises the following steps: establishing a cross-domain joint elastic coupling model for distributed nodes of an end-side cloud system; a heterogeneous fusion resource pool is established among an end device, an edge computing node and a cloud center, and various available resources in an end-edge cloud system are comprehensively analyzed; and dynamically adjusting a task allocation strategy based on the elastic coupling model and a conjoint analysis result of various available resources, optimizing the load of the end-side cloud system, and generating an optimal load solution of the end-side cloud system. According to the method, a more intelligent and flexible resource scheduling and management mechanism is introduced in the field of cooperative computing, so that the maximization of resource utilization and the optimization of system performance are realized.

Description

Technical Field

[0001] The present application relates to a collaborative computing method in a heterogeneous end-edge-cloud system, and in particular to an end-edge-cloud collaborative computing method and system for large-scale terminal devices. Background Art

[0002] At present, the edge-cloud collaborative computing system has been widely used in various scenarios, such as the Internet of Things, smart manufacturing, and smart cities. However, the edge-cloud collaborative computing system in the existing technology has the following disadvantages:

[0003] 1) When dealing with large-scale distributed computing tasks, there are many challenges such as unbalanced resource allocation, high data transmission delay, and insufficient system scalability. The root cause of these problems is that traditional systems lack efficient resource scheduling and data management mechanisms, which leads to a significant decrease in computing efficiency in a high-concurrency environment and makes it difficult to flexibly respond to changing computing needs.

[0004] 2) In addition, traditional edge-cloud collaborative systems lack flexibility in resource allocation and task scheduling, and are difficult to adapt to dynamically changing computing scenarios in real time, resulting in low resource utilization and unstable overall system performance. In particular, when dealing with complex and changing computing tasks, existing systems usually rely on preset fixed computing mechanisms. This rigid design shows obvious limitations when faced with diverse application scenarios and needs. It is unable to give full play to the computing advantages of the edge and cloud, and it is difficult to provide flexible and adaptable solutions.

[0005] 3) With the increasing heterogeneity of computing resources and the increasing complexity of tasks, it is becoming increasingly difficult for existing systems to achieve optimal coordination of end, edge, and cloud resources while maintaining low latency and high performance.

[0006] In summary, the above defects not only lead to serious waste of computing resources and reduced task execution efficiency, but also make it difficult for the system to cope with dynamic and changing business needs, limiting its application prospects in highly complex and changeable computing environments.

[0007] Therefore, there is an urgent need to introduce more intelligent and flexible resource scheduling and management mechanisms in the field of end-edge-cloud collaborative computing to maximize resource utilization and optimize system performance, thereby meeting the increasingly complex needs of future computing tasks. Summary of the invention

[0008] In order to solve the problems of insufficient flexibility, low resource utilization efficiency, task processing delay and the like in the above-mentioned prior art, the present invention proposes a heterogeneous end-edge-cloud collaborative computing method based on an elastic coupling mechanism.

[0009] In a first aspect, an embodiment of the present application provides a heterogeneous end-edge-cloud collaborative computing method based on an elastic coupling mechanism, which is applied to an end-edge-cloud system. The method includes:

[0010] Steps for building an elastic coupling model: Establish a cross-domain joint elastic coupling model for the distributed nodes of the end-edge-cloud system. The distributed nodes include: end devices, edge computing servers, and cloud centers;

[0011] Resource pool establishment steps: By establishing a heterogeneous fusion resource pool between the end device, edge computing nodes and cloud center, a comprehensive analysis of various available resources in the end-edge-cloud system is performed. The resources include: computing resources, storage resources and communication resources;

[0012] Load optimization steps: Based on the joint analysis results of the elastic coupling model and various available resources, dynamically adjust the task allocation strategy, optimize the load of the end-edge-cloud system, and generate the optimal end-edge-cloud system load solution.

[0013] In a specific embodiment of the present invention, the elastic coupling model construction step includes:

[0014] Initialization step: Initialize the performance parameters, current load and target load level of each node; and initialize the coupling strength matrix between nodes;

[0015] Coupling strength calculation steps: By defining dynamic adjustment parameters, optimizing and calculating the performance and load matching values ​​of each node, and calculating the coupling strength values ​​between nodes, an elastic coupling model of the edge-cloud system is established;

[0016] Steps for establishing the dependency model: Analyze the dependency between the end, edge, and cloud, and define the calculation model of the dependency between the end, edge, and cloud based on the proportion of the amount of data received by each node and the evaluation strength value of the service dependency between the nodes.

[0017] In a specific embodiment of the present invention, the above resource pool establishment step includes:

[0018] Initialization step: Based on the elastic coupling model, a heterogeneous fusion resource pool model is established between the terminal device, edge computing node and cloud center to initialize the number of resources of each terminal device, edge server and cloud server, the capacity of resources and define the weights of different types of resources;

[0019] Steps to establish a heterogeneous resource fusion model: Based on the quantity of each resource, the capacity of the resource, and the weights of different types of resources, a computing model for heterogeneous resource fusion for the edge-cloud system architecture is established.

[0020] In a specific embodiment of the present invention, the load optimization step includes:

[0021] Fitness function initialization step: Initialize the calculation formula that defines the fitness function, and define the weight of the elasticity score and the weight of the load level of the edge-cloud system;

[0022] Meta-heuristic iterative optimization steps: select individuals based on fitness, and individuals with high fitness have a higher probability of being selected; perform crossover operations on the selected individuals with high fitness to generate new offspring, perform mutation operations on the offspring individuals, and evaluate the offspring individuals through the fitness function, select better individuals to enter the next generation, and continuously iterate and optimize;

[0023] When the preset number of iterations is reached or the stopping condition is met, the algorithm converges and outputs the optimal end-edge-cloud system load solution.

[0024] In a specific embodiment of the present invention, the elastic coupling model is: Where i represents node i and j represents node j, E represents the overall resilience score of the system, α, β, γ are adjustment parameters, and N is the number of devices; Used to optimize the performance and load matching of each node, Represents the coupling strength between node i and node j.

[0025] In a specific embodiment of the present invention, the calculation model of the dependency relationship between the terminal, edge and cloud is:

[0026] Where i represents node i and j represents node j, is the number of interactions between node i and node j, V i j represents the amount of data received by nodes i and j, V max is the maximum amount of data transmitted between any two nodes in the system, It is used to evaluate the average strength of the service dependency between node i and node j, w i represents the weight of node i, w j represents the weight of node j, represents the correlation coefficient between node i and node j, w i , w j , The value range is between 0 and 1.

[0027] In a specific embodiment of the present invention, the heterogeneous resource fusion model for the edge-cloud system architecture is: Among them, X end , X edge , X cloud Respectively represent the number of each terminal device, edge server and cloud server resources, I end , I edge , I cloudRespectively represent the capabilities of each terminal device, edge server and cloud server resource; D end , D edge , D cloud They respectively represent the weights of device resources of different types of terminal devices, edge servers, and cloud servers.

[0028] In a second aspect, an embodiment of the present application provides a heterogeneous end-edge-cloud collaborative computing system based on an elastic coupling mechanism, which is applied to an end-edge-cloud system and adopts the heterogeneous end-edge-cloud collaborative computing method based on an elastic coupling mechanism as described above. The system includes:

[0029] Elastic coupling model building module: used to establish a cross-domain joint elastic coupling model for the distributed nodes of the end-edge-cloud system. The distributed nodes include: end devices, edge computing servers, and cloud centers;

[0030] Resource pool establishment module: It is used to establish a heterogeneous fusion resource pool between the end device, edge computing node and cloud center to conduct a comprehensive analysis of various available resources in the end-edge-cloud system. The resources include computing resources, storage resources and communication resources.

[0031] Load optimization module: It is used to dynamically adjust the task allocation strategy based on the joint analysis results of the elastic coupling model and various available resources, optimize the load of the end-edge-cloud system, and generate the optimal end-edge-cloud system load solution.

[0032] In a third aspect, an embodiment of the present application provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of the heterogeneous end-edge-cloud collaborative computing method based on the elastic coupling mechanism are implemented.

[0033] In a fourth aspect, an embodiment of the present application 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 steps of the heterogeneous end-edge-cloud collaborative computing method based on the elastic coupling mechanism are implemented.

[0034] Compared with the related prior art, it has the following outstanding beneficial effects:

[0035] 1) The method of the present invention proposes a cross-domain joint elastic coupling model suitable for distributed nodes. By designing an elastic coupling model that includes three domains: computing nodes, network topology, and service requirements. Each domain contains multiple subdomains that interact dynamically through defined coupling coefficients, and considers the performance, load, and dependencies between components to adapt to different computing requirements and network conditions;

[0036] 2) The method of the present invention proposes a multi-level fusion method suitable for heterogeneous resources. By establishing a heterogeneous fusion resource pool between the terminal device, the edge computing node and the cloud center, large-scale computing tasks can be executed in a distributed manner at these three levels. By analyzing the task requirements and the changes in the real-time computing environment, the resource pool configuration is dynamically adjusted to ensure the optimal execution of computing tasks in terms of timeliness and efficiency;

[0037] 3) The method of the present invention proposes an end-edge-cloud load optimization method suitable for large-scale tasks. The distribution of complex computing tasks between end devices, edge nodes and cloud servers is optimized by imitating heuristic behaviors in nature. By defining a fitness function, evaluating factors such as the computing resources, task complexity and network status of each node, and dynamically adjusting the task allocation strategy through an iterative search optimization process, the load of the end-edge-cloud system is optimized. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0039] Figure 1 This is a schematic diagram of the process flow of the heterogeneous end-edge-cloud collaborative computing method of the present invention;

[0040] Figure 2 This is a schematic diagram of the process flow of a heterogeneous end-edge-cloud collaborative computing method according to an embodiment of the present invention;

[0041] Figure 3 This is a schematic diagram of a heterogeneous end-edge-cloud collaborative computing system according to an embodiment of the present invention;

[0042] Figure 4 Schematic diagram of computer hardware of the present invention. DETAILED DESCRIPTION

[0043] It should be noted that the processor described in the present invention is the control center of the electronic device, which may be a processor or a general term for multiple processing elements. For example, it may be one or more central processing units (CPUs), or application specific integrated circuits (ASICs), or one or more integrated circuits configured to implement the embodiments of the present invention, such as one or more digital signal processors (DSPs), or one or more field programmable gate arrays (FPGAs).

[0044] Optionally, the processor can perform various functions of the electronic device by running or executing a software program stored in the memory, and calling data stored in the memory.

[0045] In a specific implementation, as an embodiment, the processor may include one or more CPUs. Each of these processors may be a single core processor or a multi-core processor. The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions). Electronic devices may include: servers, desktop computers, laptops, smart phones, tablet computers, embedded computers, etc., wherein the embedded computers include vehicles and robots, etc.

[0046] The memory is used to store the software program for executing the solution of the present invention, and the execution is controlled by the processor. The specific implementation method can refer to the above method embodiment, which will not be repeated here.

[0047] It should be noted that the structure of the electronic device shown in the drawings of the present invention does not constitute a limitation thereto, and the actual knowledge structure recognition device may include more or fewer components than shown in the drawings, or a combination of certain components, or a different arrangement of components.

[0048] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware or any other combination. When implemented by software, the above embodiments 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 or computer programs. When the computer instructions or computer programs are loaded or 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 one website, computer, server or data center to another website, computer, server or data center by wired (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0049] It should also be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0050] In the present invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can be represented by: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0051] It should also be understood that in various embodiments of the present invention, 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 invention.

[0052] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0053] 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, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0054] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0055] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. 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 and includes several instructions for enabling 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 described in various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0056] In order to make the above features and effects of the present invention more clearly and understandably described, embodiments are given below and described in detail with reference to the accompanying drawings. This specification discloses one or more embodiments that include the features of the present invention. The disclosed embodiments are only for illustration. The scope of protection of the present invention is not limited to the disclosed embodiments, and the present invention is defined by the attached claims.

[0057] The following is a system embodiment corresponding to the above method embodiment. This embodiment can be implemented in conjunction with the above embodiment. The relevant technical details mentioned in the above embodiment are still valid in this embodiment. In order to reduce repetition, they are not repeated here. Accordingly, the relevant technical details mentioned in this embodiment can also be applied in the above embodiment.

[0058] When conducting research on end-edge-cloud collaborative computing, the present invention found that the existing technology is too dependent on preset fixed computing rules, resulting in obvious limitations when facing diversified application scenarios. The present invention proposes a heterogeneous end-edge-cloud collaborative computing method based on an elastic coupling mechanism. The formation process of the invention began with an in-depth analysis of the existing end-edge-cloud collaborative system, identifying its deficiencies in resource scheduling, task allocation and flexibility. In order to solve these problems, the present invention introduces an elastic coupling mechanism that can dynamically adjust the collaborative relationship between the end, edge and cloud according to real-time task requirements and resource status. In response to the fusion problem of heterogeneous resources, the inventor designed a multi-level fusion method to achieve efficient integration of multiple heterogeneous resources. It enables flexible adjustment of resource allocation strategies to ensure optimal resource utilization and task execution efficiency in different scenarios. In order to optimize the processing of large-scale tasks, the inventor also proposed a new load optimization method, which greatly improves the overall efficiency of the system by reasonably allocating task loads between the end, edge and cloud. Finally, this invention was formed, which can effectively improve the problems of low resource utilization efficiency and poor task execution flexibility in traditional end-edge-cloud systems.

[0059] The present invention aims to propose a heterogeneous end-edge-cloud collaborative computing method based on an elastic coupling mechanism. First, a cross-domain joint elastic coupling model is established to deal with the resource coordination problem between distributed nodes. The model can dynamically adjust the coupling strategy to achieve flexible scheduling and efficient utilization of cross-domain resources, thereby enhancing the adaptability and stability of the system in a dynamic environment. Secondly, a multi-level fusion method based on heterogeneous resources is used to solve the problem of inefficient management and integration of heterogeneous resources. The method can perform refined management and fusion optimization of heterogeneous resources at multiple levels, starting from multiple dimensions such as computing power, storage capacity, and network bandwidth, fully explore and utilize the advantages of different types of resources, and improve resource utilization and the overall efficiency of task processing. Finally, the load distribution and optimization problems during large-scale task processing are solved by an end-edge-cloud load optimization method based on large-scale tasks. The method introduces a dynamic load adjustment mechanism to achieve flexible task allocation and resource scheduling between the end, edge, and cloud according to task complexity and current resource status.

[0060] The following is a detailed description with reference to specific embodiments:

[0061] Embodiment 1

[0062] like Figure 1 As shown, the embodiment of the present application provides a heterogeneous end-edge-cloud collaborative computing method based on an elastic coupling mechanism, which is applied to an end-edge-cloud system. The method includes:

[0063] Elastic coupling model building step 101: establishing a cross-domain joint elastic coupling model for distributed nodes of the end-edge-cloud system, where the distributed nodes include: end devices, edge computing servers, and cloud centers;

[0064] Resource pool establishment step 102: by establishing a heterogeneous fusion resource pool between the end device, the edge computing node and the cloud center, a comprehensive analysis is performed on various available resources in the end-edge-cloud system, the resources including: computing resources, storage resources and communication resources;

[0065] Load optimization step 103: Based on the joint analysis results of the elastic coupling model and various available resources, dynamically adjust the task allocation strategy, optimize the load of the end-edge-cloud system, and generate the optimal end-edge-cloud system load solution.

[0066] like Figure 2 As shown, in a specific embodiment of the present invention, the elastic coupling model building step 101 includes:

[0067] Initialization step: Initialize the performance parameters, current load and target load level of each node; and initialize the coupling strength matrix between nodes;

[0068] First, assume that there is a system consisting of multiple computing nodes, each of which can be a cloud server, edge server, or IoT device. Each node i has a performance parameter P i 、Current load L i and a target load level T i , which is the load value under ideal conditions. The coupling strength between nodes is represented by the matrix C = [c ij ] indicates that c ij Represents the dependency strength between nodes i and j.

[0069] Coupling strength calculation steps: By defining dynamic adjustment parameters, optimizing and calculating the performance and load matching values ​​of each node, and calculating the coupling strength values ​​between nodes, an elastic coupling model of the edge-cloud system is established;

[0070] Establish an elastic scoring model for the edge-cloud system through flexible modular design: Where i represents node i and j represents node j, and E represents the total elasticity score of the system. The higher the value, the more optimized the system is. E can be used to adjust the load of each node to optimize the overall performance and elasticity of the system. For example, the resource allocation of the node can be adjusted according to the load of each node and the elasticity score E of the system. If the load of a node is too heavy, it may affect its elasticity score, and then affect the total score E. By adjusting the task or data allocation of the node, the load of each node is more balanced and the system bottleneck is reduced. α, β, and γ are adjustment parameters used to balance the effects of performance, load differences, and coupling between nodes. α mainly controls the impact of the overall system performance on the total score. A larger α value means that the performance is more important, so more attention is paid to optimizing the performance in terms of computing power, resource utilization, etc. α is adjusted in the range of [0,1]. The closer to 1, the greater the impact of performance on the score, and the closer to 0, the more important the impact of load differences on the score. β is used to balance the differences in load between nodes. A larger β value will increase the impact of load differences on the total score, prompting the system to pay more attention to load balancing and reduce the uneven load between nodes. β is also adjusted in the range of [0,1]. The closer it is to 1, the greater the impact of load differences on the score, and the closer it is to 0, the less the impact of load differences. γ mainly controls the impact of node coupling on the total score. A larger γ value means that the system needs to pay more attention to the dependencies or communication costs between nodes. γ is adjusted in the range of [0,1]. The closer it is to 1, the greater the impact of coupling on the system score, and the closer it is to 0, the less the impact of node coupling can be. N is the number of devices. It is mainly used to optimize the performance and load matching of each node, and emphasizes the importance of performance and load differences through exponential functions. It mainly considers the coupling strength between nodes i and j, aiming to reduce the load imbalance caused by dependencies.

[0071] Steps for establishing the dependency model: Analyze the dependency between the end, edge, and cloud, and define the calculation model of the dependency between the end, edge, and cloud based on the proportion of the amount of data received by each node and the evaluation strength value of the service dependency between the nodes.

[0072] Finally, we need to analyze the dependency relationship between the end, edge, and cloud. The calculation model for the dependency relationship between the end, edge, and cloud is:

[0073] where i represents node i and j represents node j, is the number of interactions between node i and node j, using a logarithmic function to slow down the linear growth effect of high-frequency interactions. i j represents the amount of data received by nodes i and j, V max It is the maximum amount of data transmitted between any two nodes in the system, which is used to normalize the data dependency. It is used to evaluate the average strength of the service dependency between node i and node j, w i represents the weight of node i, ranging from 0 to 1, w j Represents the weight of node j, ranging from 0 to 1. Represents the correlation coefficient between node i and node j, and its value range is between 0 and 1. Then, according to the real-time status of task execution and environmental changes, the connection strength and resource allocation between modules are dynamically adjusted. By dynamically adjusting the T i , E can be optimized at runtime to achieve load balancing and coupling optimization. Based on real-time performance monitoring and load prediction, the system can automatically adjust the α, β, and γ parameters to adapt to environmental changes and demand fluctuations. For systems with higher performance requirements, the value of α may need to be increased; for systems with large load differences between nodes, the value of β can be increased; and for systems with more complex communications or node dependencies, it is necessary to consider increasing the value of γ. By comprehensively considering the coupling relationship between the end, edge, and cloud, node performance, load balancing, and node dependencies, the overall efficiency of large model task processing and elastic computing can be improved.

[0074] In a specific embodiment of the present invention, the resource pool establishment step 102 includes:

[0075] Initialization step: Based on the elastic coupling model, a heterogeneous fusion resource pool model is established between the terminal device, edge computing node and cloud center to initialize the number of resources of each terminal device, edge server and cloud server, the capacity of resources and define the weights of different types of resources;

[0076] Based on the elastic coupling model, a heterogeneous fusion resource pool model is established between the end device, edge computing node and cloud center, so that large-scale computing tasks can be distributed and executed at these three levels. The end device is responsible for collecting data and performing some preliminary data processing tasks, while the edge computing node undertakes simple data processing and analysis tasks. The cloud platform is responsible for performing complex and computationally intensive tasks. Assume that we have three types of computing resources: end devices, edge servers, and cloud servers. The number of each type of end device, edge server and cloud server resource is X. end , X edge , X cloud The capabilities of each terminal device, edge server, and cloud server resource are represented by I end , I edge , I cloud These resource capabilities are not limited to the single dimensions of computing power, storage power, and communication power, but are a comprehensive reflection of the three. Specifically, the calculation of resource capabilities is based on the product of the computing resources, storage resources, and communication resources of the device or server.

[0077] Steps to establish a heterogeneous resource fusion model: Based on the quantity of each resource, the capacity of the resource, and the weights of different types of resources, a computing model for heterogeneous resource fusion for the edge-cloud system architecture is established.

[0078] Then, a calculation formula for heterogeneous resource integration for the edge-cloud system architecture is established: Among them, D end The weight of the device resources of the terminal device, D edge represents the weight of the device resources of the edge server and D cloud Represents the weight of the cloud server's device resources, including computing resources, storage resources, and communication resources. end , D edge and D cloud The value range of is 0 to 1. For example, in the actual task scheduling process, D end , D edge and D cloud The value of will determine the resource allocation strategy of each device or server in a specific task. A higher weight value means that the resource contributes more to the total resource capacity, and the system will give more priority to the availability of the resource. In some scenarios that require high computing power, the weight of computing resources can be set to a larger value, while in some storage-intensive or bandwidth-intensive applications, the weight of storage or communication resources will be increased accordingly. Through virtualization technology, physical resources are abstracted into virtual resources, so that resources of different types and sources can be logically managed and scheduled in a unified manner. Then, by designing a resource abstraction layer, the differences between heterogeneous hardware and software are shielded, and a unified resource interface is provided to facilitate upper-level application calls. It enables it to cross physical locations and network boundaries to achieve global optimization of resources.

[0079] In a specific embodiment of the present invention, the load optimization step 103 includes:

[0080] Fitness function initialization step: Initialize the calculation formula that defines the fitness function, and define the weight of the elasticity score and the weight of the load level of the edge-cloud system;

[0081] In edge-cloud load optimization, we first need to determine the calculation formula of the fitness function, which usually reflects the efficiency and effectiveness of task allocation. The purpose of fitness calculation is to provide an evaluation criterion for the algorithm so that a better solution can be selected during the iteration process. In order to better evaluate the pros and cons of the solution through the metaheuristic algorithm. The fitness value can be calculated by the following formula: F = ω 1 ·E+ω 2 ·L. Where E represents the total resilience score of the system, L is the total load of the system, ω 1 is the weight of elasticity score, ω 2is the weight of the load level, ω 1 and ω 2 The value range is 0 to 1.

[0082] Meta-heuristic iterative optimization steps: select individuals based on fitness, and individuals with high fitness have a higher probability of being selected; perform crossover operations on the selected individuals with high fitness to generate new offspring, perform mutation operations on the offspring individuals, and evaluate the offspring individuals through the fitness function, select better individuals to enter the next generation, and continuously iterate and optimize;

[0083] When the preset number of iterations is reached or the stopping condition is met, the algorithm converges and outputs the optimal end-edge-cloud system load solution. When the preset number of iterations is reached or the stopping condition is met, the algorithm converges and outputs the optimal solution. Usually, the convergence condition can be reaching the maximum number of iterations, the fitness function value no longer changes significantly, etc. Ultimately, by combining the global search capability of the metaheuristic algorithm and the elastic coupling mechanism of the end-edge-cloud system, it can effectively cope with load optimization problems in dynamic and heterogeneous resource environments.

[0084] Then the current solution is improved through continuous iteration. Iterative optimization is the core process of the metaheuristic algorithm. In each iteration, the algorithm generates new solutions and evaluates them through the fitness function, and then selects better individuals to enter the next generation. The updated formula is as follows: t+1 =Selection(Y t )∪Crossover(Y t )∪Mutation(Y t ). Among them, Y t is the population of generation t, Y t+1 is the population of the t+1th generation. It includes three processes: selection, crossover, and mutation. First, individuals need to be selected based on fitness. Individuals with high fitness have a higher probability of being selected. Then, crossover operations are performed on the selected individuals to produce new offspring. Finally, mutation operations are performed on the offspring individuals to increase the diversity of the population.

[0085] Embodiment 2

[0086] like Figure 3 As shown, the embodiment of the present application provides a heterogeneous end-edge-cloud collaborative computing system based on an elastic coupling mechanism, which is applied to an end-edge-cloud system and adopts the heterogeneous end-edge-cloud collaborative computing method based on an elastic coupling mechanism as described above. The system includes:

[0087] The elastic coupling model building module 201 is used to establish a cross-domain joint elastic coupling model for distributed nodes of the end-edge-cloud system, where the distributed nodes include: end devices, edge computing servers, and cloud centers;

[0088] Resource pool establishment module 202: used to establish a heterogeneous fusion resource pool between the end device, edge computing node and cloud center to comprehensively analyze various available resources in the end-edge-cloud system, including computing resources, storage resources and communication resources;

[0089] Load optimization module 203: used to dynamically adjust the task allocation strategy based on the joint analysis results of the elastic coupling model and various available resources, optimize the load of the end-edge-cloud system, and generate the optimal end-edge-cloud system load solution.

[0090] Embodiment 3

[0091] An embodiment of the present application provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of the heterogeneous end-edge-cloud collaborative computing method based on the elastic coupling mechanism are implemented.

[0092] Embodiment 4

[0093] An embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps of the heterogeneous end-edge-cloud collaborative computing method based on the elastic coupling mechanism are implemented.

[0094] In addition, combined Figure 1 The heterogeneous end-edge-cloud collaborative computing method based on the elastic coupling mechanism described in the embodiment of the present application can be implemented by an electronic device, such as a computer device. Figure 4 Schematic diagram of the hardware structure of a computer device according to an embodiment of the present application.

[0095] In some of these embodiments, the computer device may further include a communication interface 83 and a bus 80. Figure 4 As shown, the processor 81, the memory 82, and the communication interface 83 are connected via a bus 80 and communicate with each other.

[0096] Specifically, the processor 81 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0097] The memory 82 may be used to store or cache various data files required for processing and / or communication, as well as possible computer program instructions executed by the processor 81 .

[0098] The processor 81 reads and executes computer program instructions stored in the memory 82 to implement any one of the heterogeneous end-edge-cloud collaborative computing methods based on the elastic coupling mechanism in the above embodiments.

[0099] In summary, the present invention introduces a cross-domain joint elastic coupling model, which can dynamically schedule and integrate heterogeneous resources distributed in the end, edge, and cloud according to real-time needs. This mechanism not only improves the utilization efficiency of resources, but also effectively reduces the computing bottleneck caused by uneven resource allocation. For example, in the intelligent transportation scenario, the system can flexibly allocate computing resources of edge nodes and cloud servers according to real-time traffic conditions to ensure the real-time and accuracy of data processing. Through a multi-level integration method, the system can deeply integrate heterogeneous resources to meet the needs of different computing tasks. This integration method can optimize the allocation and scheduling of resources according to the complexity and priority of the task, thereby achieving efficient computing. For example, in smart medical care, the system can flexibly call local terminals, edge devices, and cloud resources according to the urgency of the patient and the complexity of the data, ensure the priority processing of key tasks, and improve the efficiency of overall medical services. The system also has a real-time adaptive load optimization mechanism that can dynamically adjust the computing load distribution between the end, edge, and cloud according to the current system status and task requirements. This mechanism not only improves the response speed of the system, but also reduces latency and ensures the efficient execution of computing tasks. For example, in video surveillance, the system can dynamically adjust the distribution of computing tasks at the edge and in the cloud according to the fluctuations in data traffic at the monitoring point, reduce data transmission delays, and improve real-time monitoring effects. Overall, the invention is different from the traditional computing architecture. The proposed system adopts an elastic coupling mechanism, which enables it to quickly adjust resource and task configurations in the face of changing computing environments and complex business needs, showing high scalability and adaptability.

[0100] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0101] The above-mentioned embodiments only express several implementation methods 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 a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A heterogeneous end-edge-cloud collaborative computing method based on elastic coupling mechanism, applied to the end-edge-cloud system, characterized in that: The method comprises: The elastic coupling model construction step is to establish a cross-domain joint elastic coupling model for the distributed nodes of the end-edge-cloud system, wherein the distributed nodes include: end devices, edge computing servers, and cloud centers; Resource pool establishment step: by establishing a heterogeneous fusion resource pool between the terminal device, edge computing node and cloud center, a comprehensive analysis of various available resources in the terminal-edge-cloud system is performed, and the resources include: computing resources, storage resources and communication resources; Load optimization step: Based on the joint analysis results of the elastic coupling model and the various available resources, dynamically adjust the task allocation strategy, optimize the load of the end-edge cloud system, and generate the optimal end-edge cloud system load solution.

2. The heterogeneous end-edge-cloud collaborative computing method based on elastic coupling mechanism according to claim 1 is characterized in that: The elastic coupling model building step includes: Initialization step: initializing the performance parameters, current load and target load level of each of the nodes; and initializing the coupling strength matrix between the defined nodes; Coupling strength calculation steps: By defining dynamic adjustment parameters, optimizing and calculating the performance and load matching values ​​of each node, and calculating the coupling strength values ​​between nodes, an elastic coupling model of the edge-cloud system is established; Dependency model establishment steps: Analyze the dependency between the end, edge and cloud, and define the calculation model of the dependency between the end, edge and cloud according to the proportion of the amount of data received by each node and the evaluation strength value of the service dependency between the nodes.

3. The heterogeneous end-edge-cloud collaborative computing method based on elastic coupling mechanism according to claim 1 is characterized in that: The resource pool establishment step comprises: Initialization step: Based on the elastic coupling model, a heterogeneous fusion resource pool model is established between the terminal device, edge computing node and cloud center, and the number and capacity of each terminal device, edge server and cloud server resources, as well as the weights of different types of resources are initialized; Steps for establishing a heterogeneous resource fusion model: Based on the quantity of each resource, the capacity of the resource and the weights of different types of resources, a computing model for heterogeneous resource fusion for the end-edge-cloud system architecture is established.

4. The heterogeneous end-edge-cloud collaborative computing method based on elastic coupling mechanism according to claim 1 is characterized in that: The load optimization step comprises: Fitness function initialization step: initializing a calculation formula for defining a fitness function, and defining a weight of an elasticity score and a weight of a load level of the end-edge-cloud system; Meta-heuristic iterative optimization steps: select individuals according to fitness, and individuals with high fitness have a higher probability of being selected; perform crossover operations on the selected individuals with high fitness to generate new offspring, perform mutation operations on the offspring individuals, and evaluate the offspring individuals through fitness functions, select better individuals to enter the next generation, and continuously iterate and optimize; When the preset number of iterations is reached or the stopping condition is met, the algorithm converges and outputs the optimal end-edge-cloud system load solution.

5. The heterogeneous end-edge-cloud collaborative computing method based on elastic coupling mechanism according to claim 2 is characterized in that: The elastic coupling model is: Where i represents node i and j represents node j, E represents the overall resilience score of the system, α, β, γ are adjustment parameters, and N is the number of devices; Used to optimize the performance and load matching of each node, Represents the coupling strength between node i and node j.

6. The heterogeneous end-edge-cloud collaborative computing method based on elastic coupling mechanism according to claim 2 is characterized in that: The calculation model of the dependency relationship between the end, edge and cloud is: Where i represents node i and j represents node j, is the number of interactions between node i and node j, V i j represents the amount of data received by nodes i and j, V max is the maximum amount of data transmitted between any two nodes in the system, It is used to evaluate the average strength of the service dependency between node i and node j, w i represents the weight of node i, w j represents the weight of node j, represents the correlation coefficient between node i and node j, w i , w j , The value range is between 0 and 1.

7. The heterogeneous end-edge-cloud collaborative computing method based on elastic coupling mechanism according to claim 3 is characterized in that: The heterogeneous resource fusion model for the edge-cloud system architecture is: Among them, X end , X edge , X cloud Respectively represent the number of each terminal device, edge server and cloud server resources, I end , I edge , I cloud Respectively represent the capabilities of each terminal device, edge server and cloud server resource; D end , D edge , D cloud They respectively represent the weights of device resources of different types of terminal devices, edge servers, and cloud servers.

8. A heterogeneous end-edge-cloud collaborative computing system based on an elastic coupling mechanism, applied to an end-edge-cloud system, adopting a heterogeneous end-edge-cloud collaborative computing method based on an elastic coupling mechanism as claimed in any one of claims 1 to 7, characterized in that: The system comprises: Elastic coupling model building module: used to establish a cross-domain joint elastic coupling model for distributed nodes of the end-edge-cloud system, wherein the distributed nodes include: end devices, edge computing servers and cloud centers; Resource pool establishment module: used to establish a heterogeneous fusion resource pool between the terminal device, edge computing node and cloud center to comprehensively analyze various available resources in the terminal-edge-cloud system, wherein the resources include computing resources, storage resources and communication resources; Load optimization module: used to dynamically adjust the task allocation strategy based on the joint analysis results of the elastic coupling model and the various available resources, optimize the load of the end-edge cloud system, and generate the optimal end-edge cloud system load solution.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the heterogeneous end-edge-cloud collaborative computing method based on an elastic coupling mechanism described in any one of claims 1-7 are implemented.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the heterogeneous end-edge-cloud collaborative computing method based on the elastic coupling mechanism are implemented as described in any one of claims 1 to 7.

Images