Task submission path acquisition method for edge computing system
Patent Information
- Application Number
- CN202311412670.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-10-27
- Publication Date
- 2026-09-18
- Estimated Expiration
- 2043-10-27
AI Technical Summary
[0005]虽然现有的一些研究强调了对任务隐私的保护，但是大多数研究仍然为用户提供同等水平的隐私保护
[0006] To address one of the aforementioned technical problems, this disclosure provides a method for obtaining task deployment paths in edge computing systems.
Smart Images
Figure CN117478584B_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to a method for obtaining task delivery paths for edge computing systems. Background Technology
[0002] IoT devices have limited computing power to handle complex tasks. To address these limitations, edge computing has emerged as a new computing paradigm. Edge computing can provide relatively abundant computing resources while bringing computing closer to IoT devices, thereby reducing the burden on computationally intensive tasks.
[0003] Software-defined networking (SDN) facilitates efficient network management by providing a comprehensive view of the network. Although SND was not specifically designed to address the challenges of the Internet of Things (IoT), it still helps to resolve complexity issues and support the effective coordination of IoT services.
[0004] However, existing SDN technologies use centralized network management to direct network traffic from source to destination. Furthermore, different IoT devices have specialized functions, requiring various services from the network. In this context, the large volume of traffic and data from IoT devices can clog the network and increase the cost of transmitting data from IoT devices to cloud data centers. Simultaneously, the demand for privacy-sensitive services in SDN scenarios is constantly growing. In this context, privacy isolation is a key requirement that must be met to provide parallel services on public infrastructure.
[0005] While some existing research emphasizes the protection of task privacy, most studies still provide users with an equivalent level of privacy protection. However, a discrepancy remains between the number of user-generated tasks and the number of tasks loaded by the user. Therefore, despite the measures implemented in existing research, potential eavesdroppers can still infer the number of user-generated tasks based on available information, which could compromise data privacy. Summary of the Invention
[0006] To address one of the aforementioned technical problems, this disclosure provides a method for obtaining task deployment paths in edge computing systems.
[0007] According to one aspect of this disclosure, a method for obtaining task delivery paths in an edge computing system is provided, the edge computing system comprising M source nodes, N intermediate nodes, and K target nodes, comprising:
[0008] Obtain the transmission path points between the source node, intermediate nodes, and target node, as well as the corresponding transmission cost of each transmission path point;
[0009] For each source node, the target node, complete transmission path, and transmission cost corresponding to that source node are obtained based on the transmission path points and transmission costs.
[0010] Add an adjustable privacy cost to each path point in the transmission path; and
[0011] The delivery path matrix of all source nodes is obtained based on the transmission path corresponding to each source node. The total delivery cost corresponding to each transmission path in the delivery path matrix is obtained based on the transmission cost corresponding to the transmission path and the privacy cost corresponding to each transmission path point in the transmission path.
[0012] According to at least one embodiment of the task delivery path acquisition method for an edge computing system of this disclosure, the adjustable privacy cost is:
[0013]
[0014] Where, λ pri These are adjustable parameters; `<task_n>` is a Boolean variable representing the deployment status of task `n`: if task `n` is deployed from node `i` and transmitted to node `j`, then... otherwise The original transmission cost c i,j The punishment imposed.
[0015] According to at least one embodiment of the task delivery path acquisition method for an edge computing system of this disclosure, a penalty is imposed on the original transmission cost:
[0016]
[0017] Among them, S i Let |S| represent the set of next-hop nodes for collecting node i. i | represents a finite set S i The number of elements in the middle.
[0018] According to at least one embodiment of the task deployment path acquisition method for an edge computing system of the present disclosure, for each source node, obtaining the target node, complete transmission path, and transmission cost corresponding to the source node based on the transmission path points and transmission costs includes:
[0019] Initialize the path iteration list corresponding to the selected source node;
[0020] Add all feasible intermediate nodes to the access list and update the transmission cost synchronously;
[0021] Starting from the selected source node, obtain the complete transmission path to all target nodes through different intermediate nodes and the corresponding transmission cost of the complete transmission path; select the complete transmission path with the lowest transmission cost as the complete transmission path of the selected source node, and take the target node corresponding to the complete transmission path as the target node corresponding to the source node. Attached Figure Description
[0022] The accompanying drawings illustrate exemplary embodiments of the present disclosure and, together with the description thereof, serve to explain the principles of the present disclosure. These drawings are included to provide a further understanding of the present disclosure and are incorporated in and constitute a part of this specification.
[0023] Figure 1 This is a flowchart of a method for obtaining a task delivery path for an edge computing system according to one embodiment of the present disclosure. Detailed Implementation
[0024] The present disclosure will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the disclosure. Furthermore, it should be noted that, for ease of description, only the parts relevant to the present disclosure are shown in the accompanying drawings.
[0025] It should be noted that, where there is no conflict, the embodiments and features described in this disclosure can be combined with each other. The technical solutions of this disclosure will now be described in detail with reference to the accompanying drawings and embodiments.
[0026] Unless otherwise stated, the exemplary implementations / embodiments shown are to be understood as providing exemplary features of various details that provide ways in which the technical concepts of this disclosure can be implemented in practice. Therefore, unless otherwise stated, the features of various implementations / embodiments may be additionally combined, separated, interchanged and / or rearranged without departing from the technical concepts of this disclosure.
[0027] The use of crosshairs and / or shading in the accompanying drawings is generally used to clarify the boundaries between adjacent components. Thus, unless otherwise stated, the presence or absence of crosshairs or shading does not convey or indicate any preference or requirement for the specific material, material properties, dimensions, proportions, commonalities between the illustrated components, or any other characteristics, properties, etc., of the components. Furthermore, in the accompanying drawings, the dimensions and relative dimensions of components may be exaggerated for clarity and / or descriptive purposes. When exemplary embodiments can be implemented differently, a specific process sequence may be performed in a different order than that described. For example, two consecutively described processes may be performed substantially simultaneously or in the reverse order of their description. Furthermore, the same reference numerals denote the same components.
[0028] When a component is referred to as being "on" or "above" another component, "connected to," or "joined to" another component, the component may be directly on, directly connected to, or directly joined to the other component, or there may be intermediate components. However, when a component is referred to as being "directly on" another component, "directly connected to," or "directly joined to" another component, there are no intermediate components. Therefore, the term "connection" can refer to a physical connection, an electrical connection, etc., and may or may not have intermediate components.
[0029] For descriptive purposes, this disclosure may use spatial relative terms such as “below,” “under,” “below,” “down,” “above,” “above,” “higher,” and “side (e.g., in a “sidewall”)” to describe the relationship between one component and another component as shown in the accompanying drawings. In addition to the orientations depicted in the drawings, the spatial relative terms are also intended to encompass different orientations of the device during use, operation, and / or manufacture. For example, if the device in the drawings is flipped, a component described as “below” or “under” another component or feature would subsequently be positioned “above” said other component or feature. Thus, the exemplary term “below” can encompass both “above” and “below” orientations. Furthermore, the device may be otherwise positioned (e.g., rotated 90 degrees or in other orientations), thus interpreting the spatial relative descriptive terms used herein accordingly.
[0030] The terminology used herein is for the purpose of describing particular embodiments and is not intended to be limiting. As used herein, unless the context clearly indicates otherwise, the singular forms “a” and “the” are intended to include the plural forms as well. Furthermore, when the terms “comprising” and / or “including” and variations thereof are used in this specification, it indicates the presence of the stated features, integrals, steps, operations, parts, components, and / or groups thereof, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, parts, components, and / or groups thereof. It should also be noted that, as used herein, the terms “substantially,” “about,” and other similar terms are used as approximate terms rather than as terms of degree, thus explaining the inherent biases in measurements, calculated values, and / or provided values that would be recognized by one of ordinary skill in the art.
[0031] Figure 1 This is a flowchart of a method for obtaining a task delivery path for an edge computing system according to one embodiment of the present disclosure.
[0032] like Figure 1As shown, the task delivery path acquisition method for edge computing systems disclosed herein includes: S10, obtaining the transmission path point between the source node, intermediate node and target node and the transmission cost corresponding to the transmission path point.
[0033] The edge computing system includes M source nodes, N intermediate nodes, and K target nodes. It is a set of source nodes. It is a set of intermediate nodes. It is the set of target nodes.
[0034] In this disclosure, the source node can be an IoT device, and these source nodes cannot connect to each other. The source node can generate tasks, and these tasks need to be deployed to target nodes for processing. Accordingly, when these tasks are deployed to target nodes, a task deployment path is formed between the source node and the target node.
[0035] The target node can be an edge consolidation machine or a cloud device, which has relatively sufficient resources, such as computing power, memory capacity and energy supply, and can receive tasks from the source node for corresponding processing.
[0036] The source node and the intermediate node corresponding to the source node are connected through a wired or wireless network, the target node and the intermediate node corresponding to the target node are connected through a wired or wireless network, and the intermediate nodes can be connected to each other through a wired or wireless network, thereby forming multiple paths from the source node through a series of intermediate nodes to the target node.
[0037] In this disclosure, the method for obtaining the task delivery path for an edge computing system further includes: S20, for each source node, obtaining the target node, complete transmission path, and transmission cost corresponding to the source node based on the transmission path point and transmission cost.
[0038] More specifically, to prevent mutual eavesdropping, tasks from different source nodes (IoT devices) cannot be sent to the same target node. Therefore, in step S20, each source node needs to know which transmission path to use to transmit the task to which target node.
[0039] In this disclosure, step S20 specifically includes: initializing a path iteration list corresponding to the selected source node (the i-th source node); the path iteration list can be a path iteration list for a specific service, and the path iteration list can include multiple transmission paths, wherein each transmission path includes a source node and at least three intermediate nodes, and among these at least three intermediate nodes, there are an initial intermediate node connected to the source node, an end intermediate node connected to the target node, and Z transition intermediate nodes connecting the initial intermediate node and the end intermediate node, wherein Z is greater than or equal to 1.
[0040] In the embodiments of this disclosure, since the source node is connected to only one initial intermediate node, correspondingly, multiple paths in the path iteration list all include the same initial intermediate node; of course, the source node of this disclosure can also directly connect to multiple intermediate nodes, so that the initial intermediate nodes in the path iteration list are not the same. The following description uses the same initial intermediate node as an example.
[0041] Based on this, step S20 can be performed on the selected source node. More preferably, after step S20 is performed on each source node, the target node, complete transmission path, and transmission cost corresponding to each source node can be obtained.
[0042] After obtaining the path iteration list, all intermediate nodes are added to the visit list. Specifically, this can be achieved by executing Dijkstra's algorithm, iteratively adding all intermediate nodes P to the visit list.
[0043] Starting from the selected source node, obtain the complete transmission paths to all target nodes D via different intermediate nodes P and the corresponding transmission costs of the complete transmission paths; select the complete transmission path with the lowest transmission cost as the complete transmission path of the selected source node, and take the target node corresponding to the complete transmission path as the target node corresponding to the source node.
[0044] On the other hand, to prevent the transmission path from becoming too long, this disclosure requires determining the number of intermediate nodes traversed by the selected complete transmission path. Specifically, if the number of intermediate nodes traversed by the selected transmission path is greater than or equal to a preset value, the selected complete transmission path is replaced with a complete transmission path whose transmission cost is adjacent (from the positive direction) to the selected complete transmission path. The determination of the number of intermediate nodes is then repeated until the number of intermediate nodes traversed by the selected transmission path is less than the preset value. The transmission cost adjacent (from the positive direction) to the selected complete transmission path is slightly greater than the transmission cost of the selected complete transmission path.
[0045] In other words, complete transmission paths with more than or equal to a preset number of intermediate nodes can be deleted, and the complete transmission path with the lowest transmission cost among the remaining complete transmission paths can be selected as the complete transmission path of the selected source node.
[0046] Specifically, each transition intermediate node y in the path iteration list is obtained, where y takes values from 1 to Z, and the initial transmission path point e from the initial intermediate node to the transition intermediate node is obtained. ini，y (y is 1, i.e., e) ini，1 And the transmission cost C of the initial transmission path point. ini，y (y is 1, i.e., C) ini，1 ); Obtain the transmission path point e between intermediate nodes. y，y+1 And the transmission cost C of this transmission path point y，y+1 ; (y is an integer less than Z) and the final transmission path point e between the transition intermediate node and the final intermediate node. z，ov And the transmission cost C of the ending transmission path z，ov .
[0047] For the initial transmission path point e ini，y and the end of the transmission path point e z，ov It can be a uniquely identifiable item and can be set to a specified value; correspondingly, the transmission cost C of this initial transmission path point... ini，y And the transmission cost C at the end of the transmission path. z，ov These values are also fixed and will not be discussed in detail here.
[0048] For each intermediate transmission path point e between intermediate nodes y，y+1 Iterate through all intermediate nodes and determine whether each intermediate node has been visited. If an intermediate node has not been visited, set an unvisited flag w for it. Then, determine the transmission cost C between intermediate node y and intermediate node w. y，w And the transmission cost C of intermediate node w and intermediate node y+1. w，y+1 Is the sum less than the transmission cost C? y，y+1 .
[0049] Accordingly, if C y，w +C w，y+1 Less than C y，y+1 Then, the intermediate node w is added to the path iteration list, and the transmission cost of each transmission path in the path iteration list is updated.
[0050] For the end of the transmission path point e z，ovIf the target node corresponding to the end transmission path is not selected, the end transmission path point is added to the path iteration list. If the target node corresponding to the end transmission path has already been selected, the entire transmission path corresponding to the end transmission path point is removed from the path iteration list.
[0051] Using the above method, the path iteration list may contain only one complete transmission path or multiple complete transmission paths. Based on this, when there is only one complete transmission path in the path iteration list, the complete transmission path and the target node included in the complete transmission path are output. Correspondingly, when there are multiple complete transmission paths in the path iteration list, the complete transmission cost of each complete transmission path is obtained, and the complete transmission path with the minimum complete transmission cost and the target node corresponding to the complete transmission path are output.
[0052] Furthermore, as shown above, by backtracking the path iteration list, it is determined whether the complete transmission path recorded in the path iteration list meets the maximum length limit. If the complete transmission path recorded in the path iteration list meets the maximum length limit, the complete transmission path in the path iteration list is selected as the transmission path corresponding to the source node, and the target node corresponding to the complete transmission path in the path iteration list is selected as the target node corresponding to the source node. On the other hand, when the complete transmission path recorded in the path iteration list does not meet the maximum length limit, that is, when the number of intermediate nodes traversed by the complete transmission path is greater than or equal to a preset value, the complete transmission path exceeding the maximum length limit is deleted.
[0053] In other words, the complete transmission path includes a set of consecutive path points. e i,j These are the path points between nodes i and j. Transmitting tasks along these path points incurs a transmission cost c. i,j . It is the set of all costs between different nodes.
[0054] In this disclosure, if a task chooses a pathpoint that has already been used by other tasks, the transmission cost of that task will be higher. Specifically, pathpoint e i,j The transmission cost is positively correlated with the number of tasks traversed previously, m.
[0055] In other words, the path point e that has been used m times i,j Transmission cost:
[0056]
[0057] Where λ∈[0,1] is an adjustable parameter, representing the privacy protection level under different application requirements; `<task_n>` is a Boolean variable representing the deployment status of task `n`: if task `n` is deployed from node `i` and transmitted to node `j`, then... otherwise The original transmission cost c i,j The punishment imposed Let |S| represent the set of next-hop nodes for collecting node i. i | represents a finite set S i The number of elements in the middle.
[0058] In this disclosure, the method for obtaining the task delivery path for an edge computing system further includes: S30, adding an adjustable privacy cost to each transmission path point in the transmission path.
[0059] Specifically, the adjustable privacy cost:
[0060]
[0061] Where, λ pri This is an adjustable parameter, which can be set to be related to λ; `<task_n>` is a Boolean variable representing the deployment status of task `n`: if task `n` is deployed from node `i` and transmitted to node `j`, then... otherwise The original transmission cost c i,j The punishment imposed.
[0062] The task delivery path acquisition method for edge computing systems disclosed herein further includes S40: obtaining a delivery path matrix for all source nodes based on the transmission path corresponding to each source node, and obtaining the total delivery cost corresponding to each transmission path in the delivery path matrix based on the transmission cost corresponding to the transmission path and the privacy cost corresponding to each transmission path point in the transmission path.
[0063] Therefore, the method disclosed herein can establish an optimal transmission path between the source node and the target node while satisfying privacy requirements, minimizing the total transmission cost of the edge computing system, and ensuring that each target node can only be used once as much as possible.
[0064] In particular, by adding an adjustable privacy cost, it is possible to effectively prevent subsequent nodes from accessing nodes that have already been accessed, thereby accelerating the convergence of the model.
[0065] In the description of this specification, the references to terms such as "one embodiment / mode," "some embodiments / modes," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment / mode or example is included in at least one embodiment / mode or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment / mode or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments / modes or examples. Furthermore, without contradiction, those skilled in the art can combine and integrate the different embodiments / modes or examples described in this specification, as well as the features of different embodiments / modes or examples.
[0066] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.
[0067] Those skilled in the art should understand that the above embodiments are merely for illustrating the present disclosure and are not intended to limit the scope of the disclosure. Those skilled in the art can make other changes or modifications based on the above disclosure, and these changes or modifications still fall within the scope of the present disclosure.
Claims
1. A method for obtaining task delivery paths in an edge computing system, the edge computing system comprising M source nodes, N intermediate nodes, and K target nodes, characterized in that, include: Obtain the transmission path points between the source node, intermediate nodes, and target node, as well as the corresponding transmission cost of each transmission path point; For each source node, the target node, complete transmission path, and transmission cost corresponding to that source node are obtained based on the transmission path points and transmission costs. Add an adjustable privacy cost to each path point in the transmission path; and The delivery path matrix of all source nodes is obtained based on the transmission path corresponding to each source node. The total delivery cost corresponding to each transmission path in the delivery path matrix is obtained based on the transmission cost corresponding to the transmission path and the privacy cost corresponding to each transmission path point in the transmission path. Specifically, for each source node, obtaining the target node, complete transmission path, and transmission cost corresponding to that source node based on the transmission path points and transmission costs includes: initializing the path iteration list corresponding to the selected source node; adding all feasible intermediate nodes to the access list and synchronously updating the transmission cost; starting from the selected source node, obtaining the complete transmission path to all target nodes via different intermediate nodes and the corresponding transmission cost of the complete transmission path; and selecting the complete transmission path with the lowest transmission cost as the complete transmission path of the selected source node, and the target node corresponding to the complete transmission path as the target node corresponding to that source node. When the number of intermediate nodes traversed by the selected transmission path is greater than or equal to a preset value, the complete transmission path is replaced by the complete transmission path corresponding to the transmission cost of the adjacent complete transmission path, and the determination of the number of intermediate nodes is performed again until the number of intermediate nodes traversed by the selected transmission path is less than the preset value. The complete transmission path includes a set of consecutive path points. , These are the path points between nodes i and j. Transmitting tasks along these path points incurs a transmission cost. ; Let be the set of all costs between different nodes; where, It is a set of source nodes. It is a set of intermediate nodes. It is a set of target nodes; among them, path points The transmission cost is positively correlated with the number of times the task has been traversed (m); the path points used m times Transmission cost: ， in, It is an adjustable parameter that indicates the level of privacy protection for different application needs; `<task_n>` is a Boolean variable representing the deployment status of task `n`: if task `n` is deployed from node `i` and transmitted to node `j`, then... =1; otherwise = 0; The original transmission cost The punishment imposed , This represents the set of next-hop nodes for collecting node i. Representing a finite set The number of elements in the middle; The adjustable privacy cost includes: ； in, These are adjustable parameters; `<task_n>` is a Boolean variable representing the deployment status of task `n`: if task `n` is deployed from node `i` and transmitted to node `j`, then... = 1; otherwise = 0; The original transmission cost The punishment imposed; Among them, the penalty imposed on the original transmission cost is: ； in, This represents the set of next-hop nodes for collecting node i. Representing a finite set The number of elements in the middle.