Intelligent high-speed access method and system based on edge computing

Abstract

The present application provides an intelligent high-speed access method and system based on edge computing, which relates to the field of data processing technology. The method includes: receiving the storage classification criteria information of the first storage system, establishing multiple edge computing nodes; generating task type identification results; performing node matching on multiple edge computing nodes based on the task type identification results to obtain a target computing node; performing user security verification on the target computing node, and if the security verification passes, performing edge computing optimization for task execution based on the target computing node and the cloud center node to obtain an optimization device; and performing the real-time access task with the optimization device. The present application can solve the technical problem in the prior art that the response speed is poor during task processing due to the large number of storage types and tasks. After task type identification, the target computing node is matched to perform edge computing optimization, thereby achieving the technical effect of improving task response efficiency and reducing power consumption.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to an intelligent high-speed access method and system based on edge computing. Background Art

[0002] Goods storage and retrieval are often required during the warehousing process. With the rapid development of Internet of Things technology and artificial intelligence technology, intelligent storage and retrieval tasks are gradually being realized.

[0003] However, due to the large number of storage types and tasks, unreasonable allocation of system computing resources is prone to occur, resulting in poor response speed during task processing.

[0004] In summary, the prior art has a technical problem of poor response speed during task processing due to the large number of storage types and tasks. Summary of the invention

[0005] The purpose of this application is to provide an intelligent high-speed access method and system based on edge computing, so as to solve the technical problem in the prior art that the response speed is poor during task processing due to the large number of storage types and tasks.

[0006] In view of the above problems, the present application provides an intelligent high-speed access method and system based on edge computing.

[0007] In a first aspect, the present application provides an intelligent high-speed access method based on edge computing, which is implemented by an intelligent high-speed access system based on edge computing, wherein the method includes: receiving storage classification criteria information of a first storage system, and establishing multiple edge computing nodes corresponding to multiple storage types based on the storage classification criteria information, wherein the multiple edge computing nodes include a preset edge computing device and a preset edge cloud server, and the multiple edge computing nodes are connected to a cloud center node; receiving real-time access tasks through the cloud center node, and performing task type identification on the real-time access tasks to generate task type identification results; performing node matching on the multiple edge computing nodes based on the task type identification results to obtain a target computing node; performing user security verification on the target computing node, and if the security verification passes, performing task execution edge computing optimization based on the target computing node and the cloud center node to obtain an optimization device; and executing the real-time access task with the optimization device.

[0008] In a second aspect, the present application also provides an intelligent high-speed access system based on edge computing, which is used to execute the intelligent high-speed access method based on edge computing as described in the first aspect, wherein the system includes: a computing node establishment module, the computing node establishment module is used to receive the warehouse classification criteria information of the first warehouse system, and establish multiple edge computing nodes corresponding to multiple warehouse types based on the warehouse classification criteria information, wherein the multiple edge computing nodes include preset edge computing devices and preset edge cloud servers, and the multiple edge computing nodes are connected to the cloud center node; a task type identification module, the task type identification module is used to identify the task type through the cloud center The core node receives the real-time access task, identifies the task type of the real-time access task, and generates a task type identification result; a node matching module, the node matching module is used to match the multiple edge computing nodes based on the task type identification result to obtain a target computing node; an edge computing optimization module, the edge computing optimization module is used to perform user security verification on the target computing node, if the security verification passes, the task execution edge computing optimization is performed based on the target computing node and the cloud center node to obtain an optimization device; a task execution module, the task execution module is used to execute the real-time access task with the optimization device.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] Receive the storage classification criteria information of the first storage system, and establish multiple edge computing nodes corresponding to multiple storage types based on the storage classification criteria information, wherein the multiple edge computing nodes include a preset edge computing device and a preset edge cloud server, and the multiple edge computing nodes are connected to the cloud center node; receive the real-time access task through the cloud center node, and identify the task type of the real-time access task to generate a task type identification result; perform node matching on multiple edge computing nodes based on the task type identification result to obtain the target computing node; perform user security verification on the target computing node, and if the security verification passes, perform edge computing optimization for task execution based on the target computing node and the cloud center node to obtain the optimization device; perform the real-time access task with the optimization device. After task type identification, match the target computing node to perform edge computing optimization, so as to achieve the technical effect of improving task response efficiency and reducing power consumption.

[0011] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0013] Figure 1 This is a flow chart of the intelligent high-speed access method based on edge computing of this application;

[0014] Figure 2 This is a schematic diagram of the structure of the intelligent high-speed access system based on edge computing in this application.

[0015] Explanation of the accompanying drawings: computing node establishment module 11, task type identification module 12, node matching module 13, edge computing optimization module 14, task execution module 15. DETAILED DESCRIPTION

[0016] This application solves the technical problem in the prior art that the response speed of tasks is poor due to the large number of storage types and tasks, by providing an intelligent high-speed access method and system based on edge computing. By identifying the task type and matching the target computing node for edge computing optimization, the technical effect of improving task response efficiency and reducing power consumption is achieved.

[0017] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0018] Embodiment 1

[0019] Please refer to the attached Figure 1The present application provides an intelligent high-speed access method based on edge computing, wherein the method is applied to an intelligent high-speed access system based on edge computing, and the method specifically includes the following steps:

[0020] Step 1: receiving storage classification criteria information of a first storage system, and establishing a plurality of edge computing nodes corresponding to a plurality of storage types based on the storage classification criteria information, wherein the plurality of edge computing nodes include a preset edge computing device and a preset edge cloud server, and the plurality of edge computing nodes are connected to a cloud center node;

[0021] Specifically, the present application provides an intelligent high-speed access method based on edge computing, which is applied to an intelligent high-speed access system based on edge computing, and is used to optimize the execution of warehousing tasks when storing goods to improve data response speed. The first warehousing system refers to an existing system platform for managing and controlling warehouse operations. This system usually includes a series of software and hardware components to implement various operations in the warehouse, such as warehousing, outbound, inventory management, order processing, etc. The warehousing classification criteria information is the classification standard when the first warehousing system performs warehousing tasks. For example, different goods are stored in different locations, which needs to be determined in combination with actual conditions. Then, task calculation analysis is performed for different types of access tasks to improve access efficiency, prevent task delays, and cause slow access tasks, and improve task processing efficiency.

[0022] Furthermore, multiple edge computing nodes corresponding to multiple storage types are established based on the storage classification criteria information, that is, each storage type in the storage classification criteria information corresponds to an edge computing node, wherein the multiple edge computing nodes include preset edge computing devices and preset edge cloud servers, the preset edge computing devices are deployed inside or near the corresponding edge computing nodes, and are used to process computing tasks related to warehousing in real time; the preset edge cloud servers refer to computing resources located in the cloud, providing greater computing power and storage resources, and supporting more complex data processing and analysis tasks. The multiple edge computing nodes are connected to the cloud center node, which is responsible for coordinating and managing the work of each edge computing node. In layman's terms, the cloud center node can assist any edge computing node in performing task calculations when multiple edge computing nodes need it.

[0023] Step 2: receiving the real-time access task through the cloud center node, and performing task type identification on the real-time access task to generate a task type identification result;

[0024] Specifically, the cloud center node continuously receives real-time access tasks sent from the first storage system through a network connection. The real-time access tasks include operation requests such as storage, outbound, transfer, and inventory. Upon receiving the real-time access tasks, the type of the tasks is identified. The task type identification is to analyze the information contained in the tasks and determine the storage type to which the tasks belong, which is used as the task type identification result, so as to facilitate subsequent node matching based on the task type.

[0025] Step 3: performing node matching on the multiple edge computing nodes based on the task type identification result to obtain a target computing node;

[0026] Specifically, in step one, multiple edge computing nodes corresponding to multiple storage types are established, thereby obtaining an edge computing node of the storage type corresponding to the real-time access task as a target computing node based on the task type identification result.

[0027] Step 4: Perform user security verification on the target computing node. If the security verification passes, perform edge computing optimization for task execution based on the target computing node and the cloud center node to obtain an optimization device;

[0028] Specifically, the target computing node is obtained, and user security verification is performed to determine whether the user has the authority to perform the corresponding real-time access task. If the user has the authority, the security verification will be deemed to have passed, otherwise it will be deemed to have failed. If the verification fails, the task execution request of the real-time access task is rejected. If the security verification passes, the task execution edge computing optimization is continued between the target computing node and the cloud center node, and the device most suitable for executing the task is determined as the optimization device. The optimization device may include a preset edge computing device and a preset edge cloud server, as well as any device in the cloud center node.

[0029] Step 5: Execute the real-time access task with the optimization device.

[0030] Specifically, the optimization device is used to calculate the real-time access task, thereby completing the real-time access task, improving the task calculation response speed during storage, and reducing the data transmission delay in the network.

[0031] Furthermore, step one of this application also includes:

[0032] The warehouse classification criteria information is parsed according to the warehouse task type to obtain the multiple warehouse types; historical warehouse task execution records are retrieved based on the multiple warehouse types; average task computing power demand and maximum task computing power demand are calculated based on the historical warehouse task execution records; a preset edge computing device is configured based on the average task computing power demand, and a preset edge cloud server is configured based on the maximum task computing power demand.

[0033] Specifically, the method of receiving the storage classification criteria information of the first storage system and establishing multiple edge computing nodes corresponding to multiple storage types based on the storage classification criteria information is as follows:

[0034] First, the storage task type is parsed for the storage classification criteria information, that is, all storage types contained in the storage classification criteria information are extracted, such as different types of storage goods, as multiple storage types, and then the historical storage task execution records are retrieved based on the multiple storage types. The historical storage task execution records refer to the computing resource usage records when executing tasks corresponding to multiple storage types in the past period of time. Based on this, the average value of the computing resource usage records for each task corresponding to each storage type is calculated as the average computing power requirement of the task, and the maximum value in the computing resource usage record is counted as the maximum computing power of the task. Configuring the preset edge computing device based on the average computing power requirement of the task is to ensure that the computing resources of the preset edge computing device can meet the average computing power requirement of the task. At the same time, configuring the preset edge cloud server based on the maximum computing power requirement of the task is to ensure that the total computing resources of the preset edge cloud server and the preset edge computing device can meet the maximum computing power requirement of the task. In this way, the computing resources of multiple edge computing nodes are deployed, laying the foundation for subsequent task execution optimization.

[0035] Furthermore, step 2 of this application also includes:

[0036] A task type identification network layer is constructed based on the warehouse classification criteria information training; the task type identification network layer is communicated with the cloud center node, and the cloud center node receives the real-time access task and sends it to the task type identification network layer; the real-time access task type is identified through the task type identification network layer, and the task type identification result is output.

[0037] Specifically, the method of receiving the real-time access task through the cloud center node and performing task type identification on the real-time access task to generate the task type identification result is as follows:

[0038] First, use the warehouse classification criteria information to train a machine learning model and build a task type identification network layer. Specifically, historical warehouse task data and corresponding historical warehouse types can be retrieved based on the warehouse classification criteria information. Based on the existing machine learning model, such as the neural network model, the historical warehouse task data is input into the neural network model, and the output is supervised and adjusted with the corresponding historical warehouse type. The model trained to convergence is used as the task type identification network layer.

[0039] The task type identification network layer is connected to the cloud center node in communication, and can exchange data with the cloud center node through network requests and responses. When the cloud center node receives the real-time access task, for example, a storage request or a storage request, it sends it to the task type identification network layer, and the task type identification network layer uses its internally trained machine learning model to identify the type of task, and outputs it as the task type identification result. In this way, the identification of the task type is realized, which facilitates the optimization of the allocation of computing nodes based on the task type, improves the response speed of task calculation, and thus improves the efficiency of task processing.

[0040] Furthermore, step 4 of this application also includes:

[0041] Obtain a task request sending device for the real-time access task; determine whether the task request sending device has access authority to the target computing node; if so, perform device security verification on the task request sending device based on the task sending time of the real-time access task to obtain a security verification result.

[0042] Specifically, the method for performing user security verification at the target computing node is: obtaining the task request sending device of the real-time access task, that is, determining the device that sent the real-time access task, which can usually be achieved based on the existing technology by checking the data packet, header information or other related fields of the task request. It is a common technical means for those skilled in the art and will not be elaborated here. Further judging whether the task request sending device has access authority at the target computing node is to verify whether the task request sending device has the right to perform operations on the target computing node. It can be achieved by checking the identity, access control list, token or other authentication mechanism of the task request sending device. It is a common technical means for those skilled in the art and will not be expanded here. If the device does not have access authority, the real-time access task will be rejected. If the device has access authority, the device security verification is performed on the task request sending device based on the task sending time of the real-time access task, that is, the security status of the device is checked. Specifically, the historical behavior records of the task request sending device within a preset time can be collected, such as the historical behavior records within the past hour of the task sending time, and then the historical behavior records are identified to determine whether there is abnormal behavior. Professional and technical personnel in this field can build an abnormal behavior library based on existing technologies, and traverse and compare the historical behavior records in the abnormal behavior library. If the comparison is successful, that is, there is a behavior consistent with the historical behavior record in the abnormal behavior library, the security verification fails, otherwise, the security verification passes, and the security verification result is obtained. Ensure the safe execution of warehousing tasks.

[0043] Furthermore, step 4 of this application also includes:

[0044] The real-time access task includes multiple access tasks; based on the preset edge computing device and the preset edge cloud server of the target computing node, and the cloud center node, the computing resources of the multiple access tasks are allocated to obtain multiple initial allocation schemes; the task execution delay and execution power consumption simulation are performed on the multiple initial allocation schemes, and the task allocation fitness is calculated based on the simulation results to obtain multiple fitnesses; the initial allocation scheme with the largest fitness is used as a temporary optimal scheme, and the multiple initial allocation schemes are updated according to a preset iteration number threshold to generate multiple updated allocation schemes, and multiple updated fitnesses are calculated and obtained; based on the multiple fitnesses and the multiple updated fitnesses, the allocation scheme corresponding to the maximum fitness is selected as the optimal allocation scheme, and the optimization device is generated with the optimal allocation scheme.

[0045] Furthermore, the present application also includes the following steps:

[0046] Collect and obtain the preset edge computing device and the preset edge cloud server of the target computing node, and the sample set of task computing records of the cloud center node; construct a task execution simulator with the sample set of task computing records, wherein the task execution simulator includes a cloud center node simulator, an edge device simulator and an edge cloud simulator; use the task execution simulator to simulate the task execution delay and execution power consumption of the multiple initial allocation schemes to generate the simulation results, wherein the simulation results include task execution delay and execution power consumption; construct a fitness expression, and calculate and obtain the multiple fitnesses based on the simulation results.

[0047] Furthermore, the present application also includes the following steps:

[0048] The fitness expression is:

[0049]

[0050] Among them, F represents fitness; T q is the task execution delay of the qth access task among the multiple access tasks, T max is a preset tolerance delay corresponding to the task type identification result; E q is the task execution power consumption of the qth access task among the multiple access tasks, E max is the preset tolerable power consumption corresponding to the task type identification result; Q is the total number of the multiple access tasks; ω1 and ω2 are weight coefficients.

[0051] Specifically, after the target computing node performs user security verification, if the security verification passes, the task execution edge computing optimization is performed based on the target computing node and the cloud center node to obtain the optimization device. The specific method is described in detail as follows.

[0052] The real-time access task includes multiple access tasks, such as multiple warehousing tasks corresponding to the same storage type. The computing resources of the multiple access tasks are allocated based on the preset edge computing device and the preset edge cloud server of the target computing node, and the cloud center node. That is, the preset edge computing device and the preset edge cloud server, as well as the computing resources in the cloud center node can process and calculate the multiple access tasks. Thus, the computing resources are randomly allocated to the multiple access tasks, and different computing resource allocation schemes are obtained as multiple initial allocation schemes.

[0053] Further, the task execution delay and execution power consumption simulation are performed on the multiple initial allocation schemes, and the simulation results are read. The simulation results include the task execution delay and execution power consumption obtained by simulation. The task allocation fitness is calculated based on the simulation results to obtain multiple fitnesses. The specific method for calculating the fitness is as follows:

[0054] First, the preset edge computing device and the preset edge cloud server of the target computing node, as well as the task computing record sample set of the cloud center node are collected, wherein the task computing record sample set includes task record samples, task delay record samples and task power consumption record samples. Moreover, the preset edge computing device and the preset edge cloud server, as well as the cloud center node respectively correspond to a task computing record sample set. The task execution simulator is constructed with the task computing record sample set, wherein the task execution simulator includes a cloud center node simulator, an edge device simulator and an edge cloud simulator, and the cloud center node simulator, the edge device simulator and the edge cloud simulator are all constructed based on existing machine learning models, such as neural network models, that is, the task record samples in the task computing record sample set are used as input, and the corresponding task delay record samples and task power consumption record samples are used for output supervision and adjustment, and the cloud center node simulator, the edge device simulator and the edge cloud simulator are trained to convergence and then integrated to obtain the task execution simulator.

[0055] Further, the multiple initial allocation schemes are input into the task execution simulator to simulate the task execution delay and execution power consumption, and the simulation results can be output, wherein the simulation results include the task execution delay and execution power consumption, and the fitness expression is constructed:

[0056]

[0057] Among them, F represents fitness; T q is the task execution delay of the qth access task among the multiple access tasks, T maxis the preset tolerance delay corresponding to the task type identification result, that is, the maximum delay expected to occur, which is set by those skilled in the art based on actual needs; E q is the task execution power consumption of the qth access task among the multiple access tasks, E max is the preset tolerable power consumption corresponding to the task type identification result, that is, the expected maximum power consumption, which is set by technical personnel in this field based on actual needs; Q is the total number of tasks of the multiple access tasks, and q is an integer greater than 0 and less than or equal to Q; ω1 and ω2 are weight coefficients, which are set by technical personnel in this field and there is no restriction on this. The sum of ω1 and ω2 is 1.

[0058] Substituting the simulation results into the fitness expression, the multiple fitnesses can be calculated and obtained. This enables the evaluation of multiple initial allocation schemes from the two dimensions of latency and power consumption, provides support for subsequent computational optimization, and facilitates the selection of computing resource allocation schemes with low latency and power consumption, thereby achieving the technical effect of improving task response efficiency and reducing power consumption.

[0059] Based on the multiple fitnesses, the initial allocation scheme with the largest fitness is used as the temporary optimal scheme, and the multiple initial allocation schemes are updated according to the preset iteration number threshold, that is, multiple initial allocation schemes are adjusted iteratively for multiple times, multiple updated allocation schemes are generated, and multiple updated fitnesses are obtained through fitness expression calculation, wherein the preset iteration number threshold is set by technical personnel in this field, such as 50 times, and there is no restriction on this. Then, based on the multiple fitnesses and the multiple updated fitnesses, the allocation scheme corresponding to the maximum fitness is selected as the optimal allocation scheme, and the computing resources allocated to multiple access tasks in the optimal allocation scheme are used as the optimization device. Edge computing optimization is realized to achieve the technical effect of improving task response efficiency and reducing power consumption.

[0060] In summary, the intelligent high-speed access method based on edge computing provided by this application has the following technical effects:

[0061] Receive the storage classification criteria information of the first storage system, and establish multiple edge computing nodes corresponding to multiple storage types based on the storage classification criteria information, wherein the multiple edge computing nodes include a preset edge computing device and a preset edge cloud server, and the multiple edge computing nodes are connected to the cloud center node; receive the real-time access task through the cloud center node, and identify the task type of the real-time access task to generate a task type identification result; perform node matching on multiple edge computing nodes based on the task type identification result to obtain the target computing node; perform user security verification on the target computing node, and if the security verification passes, perform edge computing optimization for task execution based on the target computing node and the cloud center node to obtain the optimization device; perform the real-time access task with the optimization device. After task type identification, match the target computing node to perform edge computing optimization, so as to achieve the technical effect of improving task response efficiency and reducing power consumption.

[0062] Embodiment 2

[0063] Based on the same inventive concept as the intelligent high-speed access method based on edge computing in the aforementioned embodiment, the present application also provides an intelligent high-speed access system based on edge computing, please refer to the attached Figure 2 , the system comprising:

[0064] A computing node establishment module 11, the computing node establishment module 11 is used to receive storage classification criteria information of the first storage system, and establish multiple edge computing nodes corresponding to multiple storage types based on the storage classification criteria information, wherein the multiple edge computing nodes include a preset edge computing device and a preset edge cloud server, and the multiple edge computing nodes are connected to a cloud center node;

[0065] A task type identification module 12, the task type identification module 12 is used to receive the real-time access task through the cloud center node, and perform task type identification on the real-time access task to generate a task type identification result;

[0066] A node matching module 13, wherein the node matching module 13 is used to perform node matching on the plurality of edge computing nodes based on the task type identification result to obtain a target computing node;

[0067] The edge computing optimization module 14 is used to perform user security verification on the target computing node. If the security verification is passed, the task execution edge computing optimization is performed based on the target computing node and the cloud center node to obtain an optimization device;

[0068] The task execution module 15 is used to execute the real-time access task with the optimization device.

[0069] Furthermore, the computing node establishment module 11 in the system is also used for:

[0070] Performing storage task type parsing on the storage classification criterion information to obtain the multiple storage types;

[0071] Retrieving historical storage task execution records based on the multiple storage types;

[0072] Calculate the average computing power requirement and the maximum computing power requirement of the task based on the historical storage task execution records;

[0073] A preset edge computing device is configured based on the average computing power requirement of the task, and a preset edge cloud server is configured based on the maximum computing power requirement of the task.

[0074] Furthermore, the task type identification module 12 in the system is also used for:

[0075] Based on the warehouse classification criteria information training, a task type recognition network layer is constructed;

[0076] The task type identification network layer is in communication connection with the cloud center node, and the cloud center node receives the real-time access task and sends it to the task type identification network layer;

[0077] The task type identification network layer performs real-time access task type identification and outputs the task type identification result.

[0078] Furthermore, the edge computing optimization module 14 in the system is also used for:

[0079] Acquire a task request sending device for the real-time access task;

[0080] Determine whether the task request sending device has access authority to the target computing node;

[0081] If so, a device security verification is performed on the task request sending device based on the task sending time of the real-time access task to obtain a security verification result.

[0082] Furthermore, the edge computing optimization module 14 in the system is also used for:

[0083] The real-time access task includes a plurality of access tasks;

[0084] Based on the preset edge computing device and the preset edge cloud server of the target computing node, and the cloud center node, computing resource allocation of the multiple access tasks is performed to obtain multiple initial allocation schemes;

[0085] Performing task execution delay and execution power consumption simulation on the multiple initial allocation schemes, and calculating task allocation fitness based on the simulation results to obtain multiple fitnesses;

[0086] The initial allocation scheme with the largest fitness is used as a temporary optimal scheme, and the multiple initial allocation schemes are updated according to a preset iteration number threshold to generate multiple updated allocation schemes, and multiple updated fitness are calculated and obtained;

[0087] Based on the multiple fitnesses and the multiple updated fitnesses, an allocation scheme corresponding to the maximum fitness is selected as an optimal allocation scheme, and the optimization device is generated by using the optimal allocation scheme.

[0088] Furthermore, the edge computing optimization module 14 in the system is also used for:

[0089] Collect and obtain a preset edge computing device and a preset edge cloud server of the target computing node, as well as a sample set of task computing records of the cloud center node;

[0090] Constructing a task execution simulator using the task calculation record sample set, wherein the task execution simulator includes a cloud center node simulator, an edge device simulator, and an edge cloud simulator;

[0091] Using the task execution simulator to simulate the task execution delay and execution power consumption of the multiple initial allocation schemes to generate the simulation results, wherein the simulation results include the task execution delay and execution power consumption;

[0092] A fitness expression is constructed, and the multiple fitnesses are calculated based on the simulation results.

[0093] Furthermore, the edge computing optimization module 14 in the system further includes:

[0094] The fitness expression is:

[0095]

[0096] Among them, F represents fitness; T q is the task execution delay of the qth access task among the multiple access tasks, T max is a preset tolerance delay corresponding to the task type identification result; E q is the task execution power consumption of the qth access task among the multiple access tasks, E max is the preset tolerable power consumption corresponding to the task type identification result; Q is the total number of the multiple access tasks; ω1 and ω2 are weight coefficients.

[0097] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. Figure 1 The edge computing-based intelligent high-speed access method and specific examples in the first embodiment are also applicable to the edge computing-based intelligent high-speed access system in this embodiment. Through the above detailed description of the edge computing-based intelligent high-speed access method, those skilled in the art can clearly understand the edge computing-based intelligent high-speed access system in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0098] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0099] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. An intelligent high-speed access method based on edge computing, characterized in that: include: Receive storage classification criteria information of the first storage system, and establish multiple edge computing nodes corresponding to multiple storage types based on the storage classification criteria information, wherein the multiple edge computing nodes include preset edge computing devices and preset edge cloud servers, and the multiple edge computing nodes are connected to a cloud center node; Receiving the real-time access task through the cloud center node, and performing task type identification on the real-time access task to generate a task type identification result; Perform node matching on the multiple edge computing nodes based on the task type identification result to obtain a target computing node; Perform user security verification on the target computing node. If the security verification passes, perform edge computing optimization for task execution based on the target computing node and the cloud center node to obtain an optimization device; Executing the real-time access task with the optimization device; The receiving storage classification criteria information of the first storage system, and establishing a plurality of edge computing nodes corresponding to a plurality of storage types based on the storage classification criteria information, comprises: Performing storage task type parsing on the storage classification criterion information to obtain the multiple storage types; Retrieving historical storage task execution records based on the multiple storage types; Calculate the average computing power requirement and the maximum computing power requirement of the task based on the historical storage task execution records; Configure a preset edge computing device based on the average computing power requirement of the task, and configure a preset edge cloud server based on the maximum computing power requirement of the task; The receiving of the real-time access task through the cloud center node, and performing task type identification on the real-time access task to generate a task type identification result includes: Based on the warehouse classification criteria information training, a task type recognition network layer is constructed; The task type identification network layer is in communication connection with the cloud center node, and the cloud center node receives the real-time access task and sends it to the task type identification network layer; The task type identification network layer performs real-time access task type identification and outputs the task type identification result.

2. The method according to claim 1, characterized in that The performing of user security verification at the target computing node includes: Acquire a task request sending device for the real-time access task; Determine whether the task request sending device has access authority to the target computing node; If so, a device security verification is performed on the task request sending device based on the task sending time of the real-time access task to obtain a security verification result.

3. The method according to claim 1, characterized in that If the security verification is passed, the task execution edge computing optimization is performed based on the target computing node and the cloud center node to obtain the optimization device, including: The real-time access task includes a plurality of access tasks; Based on the preset edge computing device and the preset edge cloud server of the target computing node, and the cloud center node, computing resource allocation of the multiple access tasks is performed to obtain multiple initial allocation schemes; Performing task execution delay and execution power consumption simulation on the multiple initial allocation schemes, and calculating task allocation fitness based on the simulation results to obtain multiple fitnesses; The initial allocation scheme with the largest fitness is used as a temporary optimal scheme, and the multiple initial allocation schemes are updated according to a preset iteration number threshold to generate multiple updated allocation schemes, and multiple updated fitness are calculated and obtained; Based on the multiple fitnesses and the multiple updated fitnesses, an allocation scheme corresponding to the maximum fitness is selected as an optimal allocation scheme, and the optimization device is generated by using the optimal allocation scheme.

4. The method according to claim 3, characterized in that The step of simulating the task execution delay and power consumption of the multiple initial allocation schemes and calculating the task allocation fitness based on the simulation results to obtain multiple fitnesses includes: Collect and obtain a preset edge computing device and a preset edge cloud server of the target computing node, as well as a sample set of task computing records of the cloud center node; Constructing a task execution simulator using the task calculation record sample set, wherein the task execution simulator includes a cloud center node simulator, an edge device simulator, and an edge cloud simulator; Using the task execution simulator to simulate the task execution delay and execution power consumption of the multiple initial allocation schemes to generate the simulation results, wherein the simulation results include the task execution delay and execution power consumption; A fitness expression is constructed, and the multiple fitnesses are calculated based on the simulation results.

5. The method according to claim 4, characterized in that The fitness expression is: Among them, F represents fitness; T q is the task execution delay of the qth access task among the multiple access tasks, T max is a preset tolerance delay corresponding to the task type identification result; E q is the task execution power consumption of the qth access task among the multiple access tasks, E max is the preset tolerable power consumption corresponding to the task type identification result; Q is the total number of the multiple access tasks; ω1 and ω2 are weight coefficients.

6. Intelligent high-speed access system based on edge computing, characterized in that: For implementing the steps of the method according to any one of claims 1 to 5, the system comprises: A computing node establishment module, the computing node establishment module is used to receive storage classification criteria information of the first storage system, and establish multiple edge computing nodes corresponding to multiple storage types based on the storage classification criteria information, wherein the multiple edge computing nodes include a preset edge computing device and a preset edge cloud server, and the multiple edge computing nodes are connected to a cloud center node; A task type identification module, the task type identification module is used to receive the real-time access task through the cloud center node, and perform task type identification on the real-time access task to generate a task type identification result; A node matching module, wherein the node matching module is used to perform node matching on the plurality of edge computing nodes based on the task type identification result to obtain a target computing node; An edge computing optimization module, which is used to perform user security verification on the target computing node. If the security verification passes, the task execution edge computing optimization is performed based on the target computing node and the cloud center node to obtain an optimization device; A task execution module is used to execute the real-time access task with the optimization device.

Images