Edge gateway system and data processing method of edge gateway system

By adopting edge computing technology that coordinates the work of central processing unit and auxiliary computing processor in the edge gateway system, combining data perception and edge cloud collaboration strategies, the problem of low efficiency of massive data processing in smart cities is solved, and efficient local data is achieved Processing and cloud load reduction.

CN118972433APending Publication Date: 2024-11-15DEMING COMM SHANGHAI CO LTD
View PDF 0 Cites 4 Cited by

Patent Information

Application Number
CN202411047264.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-01
Publication Date
2024-11-15

AI Technical Summary

Technical Problem

In the construction of smart cities, the number of edge gateways and the scale of data is large, resulting in massive data transmission to the cloud for calculation and processing, resulting in redundancy of data in the cloud and heavy computing burden, affecting data processing efficiency.

Method used

Design an edge gateway system, including multi-protocol access unit, edge computing processing unit and external interface unit, uses a central processor and an auxiliary computing processor to work together, and classify and process data through data perception module and storage module, and use pre- Suppose the neural network model is analyzed and the model is updated through edge cloud collaborative strategy to realize local data processing and reduce dependence on the cloud.

Benefits of technology

It improves the data processing efficiency and business processing capabilities of edge gateway systems, reduces the load on the cloud, realizes fast response and efficient data processing, and reduces the burden of cloud computing.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118972433A_ABST
    Figure CN118972433A_ABST
Patent Text Reader

Abstract

The invention provides an edge gateway system and a data processing method of the edge gateway system. The system comprises at least one edge gateway device, and the edge gateway device comprises a multi-protocol access unit, an edge computing processing unit and an external interface unit. The external interface unit is used for being connected with terminal equipment, and the multi-protocol access unit is used for being connected with cloud equipment; the edge calculation processing unit comprises a central processing unit and an auxiliary calculation processor used for carrying out auxiliary calculation on original business data, and the auxiliary calculation processor is connected with the central processing unit; the central processing unit is connected with the external interface unit so as to be in communication connection with terminal equipment through the external interface unit; and the central processing unit is connected with the multi-protocol access unit so as to be in communication connection with cloud equipment through the multi-protocol access unit. According to the system, the cloud load can be reduced, the data processing efficiency of the edge gateway system can be improved, and the service processing capability of the edge gateway equipment can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of edge computing technology, and more specifically to an edge gateway system and a data processing method for the edge gateway system. Background Art

[0002] Edge Gateway is an important component of the Internet of Things (IoT) and the Industrial Internet. It is a bridge between the cloud and the device. Edge Gateway is usually located at the edge of the network between physical devices and cloud servers to process, analyze and transmit data.

[0003] In related technologies, edge gateways are usually only able to perform simple data analysis tasks. For data that requires complex calculations, it is usually necessary to transfer the data to the cloud for calculation and processing. In the construction of smart cities, the new generation of basic network facilities is complex, the number of edge gateways is large, the data scale is large, and massive data is transferred to the cloud for calculation and processing, resulting in redundant cloud data and heavy calculation burden, which seriously affects the data processing efficiency.

[0004] In view of this, this application is hereby filed. Summary of the invention

[0005] The present application is proposed in view of the above problems. According to one aspect of the present application, an edge gateway system is provided, including at least one edge gateway device, the edge gateway device includes a multi-protocol access unit, an edge computing processing unit and an external interface unit; the external interface unit is used to connect to a terminal device, and the multi-protocol access unit is used to connect to a cloud device; the edge computing processing unit includes a central processing unit and an auxiliary computing processor for auxiliary computing of original business data, and the auxiliary computing processor is connected to the central processing unit; the central processing unit is connected to the external interface unit to communicate with the terminal device through the external interface unit; the central processing unit is connected to the multi-protocol access unit to communicate with the cloud device through the multi-protocol access unit.

[0006] Exemplarily, the edge computing processing unit also includes a data perception module for classifying data, and the data perception module is connected to the auxiliary computing processor.

[0007] Exemplarily, the edge computing processing unit also includes a storage module, which is connected to the central processing unit.

[0008] Exemplarily, there are multiple edge gateway devices, and the multiple edge gateway devices are communicatively connected.

[0009] Exemplarily, the multi-protocol access unit includes a multi-mode communication module and a radio frequency module, the multi-mode communication module is connected to the radio frequency module, the radio frequency module is used to communicate with the cloud device, and the multi-mode communication module is connected to the central processing unit.

[0010] Exemplarily, the multi-protocol access unit includes a fiber optic interface for connecting to a cloud device, and the central processor is connected to the fiber optic interface.

[0011] Exemplarily, the external interface unit includes a wired access submodule and / or a wireless access submodule.

[0012] Exemplarily, the external interface module includes a wired access submodule, and the wired access submodule includes at least one of the following interfaces: a USB interface, an Ethernet interface, a CAN bus interface, and an RS232 / RS485 interface.

[0013] Exemplarily, the external interface module includes a wireless access submodule, and the wireless access submodule includes at least one of the following communication modules: a Wifi module, a Bluetooth module, a Zigbee module, and a LoRa module.

[0014] Exemplarily, the central processing unit adopts the OPENWRT operating system.

[0015] According to another aspect of the present application, a data processing method of an edge gateway system is provided, which is applied to the edge gateway system; the edge gateway system includes at least one edge gateway device, the edge gateway device includes a multi-protocol access unit, an edge computing processing unit and an external interface unit; the external interface unit is used to connect to a terminal device, and the multi-protocol access unit is used to connect to a cloud device; the edge computing processing unit includes a central processing unit and an auxiliary computing processor for performing auxiliary computing on original business data, and the auxiliary computing processor is connected to the central processing unit; the central processing unit is connected to the external interface unit to communicate with the terminal device through the external interface unit; the central processing unit is connected to the multi-protocol access unit to communicate with the cloud device through the multi-protocol access unit; the method includes: when receiving original business data sent by the terminal device, determining the type of the original business data to be processed; when the type of the original business data to be processed is a first type of data, analyzing the original business data; when the type of the original business data to be processed is a second type of data, sending the original business data to the auxiliary computing processor, so that the auxiliary computing processor analyzes the original business data; after obtaining the analysis result obtained by analyzing the original business data, sending the analysis result to the corresponding terminal device, so that the terminal device performs a corresponding operation according to the analysis result.

[0016] Exemplarily, the edge computing processing unit also includes a data perception module and a storage module, and the method also includes: after the auxiliary computing processor analyzes the original business data to obtain an analysis result, sending the analysis data in the auxiliary computing processor to the data perception module, so that the data perception module classifies the analysis data, the analysis data includes the original business data and the analysis results corresponding to the original business data; according to the classification result obtained by classifying the analysis data by the data perception module, the original business data in the analysis data is saved in the storage module according to the type of the original business data; wherein the classification result includes the data type of the corresponding data, and the data type includes text data, video data and picture data.

[0017] Exemplarily, there are multiple edge gateway devices, and when the type of original business data to be processed is the second type of data, the method also includes: performing a gateway processing capability evaluation operation to determine whether the processing capability of the current edge gateway device is sufficient to execute the tasks to be processed corresponding to the original business data, the current edge gateway device being an edge gateway device among multiple edge gateway devices that receives the original business data; when the processing capability of the current edge gateway device is insufficient, executing an edge-to-edge collaboration strategy to utilize other edge gateway devices to collaborate with the current edge gateway device to execute the tasks to be processed.

[0018] Exemplarily, the auxiliary computing processor uses a preset neural network model to analyze the original business data; the method also includes: updating the preset neural network model using an edge-cloud collaborative strategy.

[0019] By setting up a central processor and an auxiliary computing processor, the above technical solution can use the central processor to determine the data type of the currently received data in advance to determine whether the central processor can directly process the data. When the central processor cannot process the data, the data can be transmitted to the auxiliary computing processor for calculation. As a result, the edge gateway device can respond quickly to local events without sending data to the cloud for processing, which helps to reduce the cloud load, and helps to improve the data processing efficiency of the edge gateway system and improve the business processing capabilities of the edge gateway device.

[0020] 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 in accordance with the contents of the specification. 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 listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0022] Figure 1 A schematic block diagram of an edge gateway system according to an embodiment of the present application is shown;

[0023] Figure 2 A schematic flow chart of a data processing method according to an embodiment of the present application is shown.

[0024] In the figure, 1. multi-protocol access unit; 101. multi-mode communication module; 102. radio frequency module; 103. optical fiber interface; 2. edge computing processing unit; 201. internal flash memory module; 202. external storage module; 203. central processing unit; 204. auxiliary computing processor; 205. data perception module; 3. external interface unit; 301. wired access submodule; 3011. USB interface; 3012. Ethernet interface; 3013. CAN bus interface; 3014. RS232 / RS485 interface; 302. wireless access submodule; 3021. Wifi module; 3022. Bluetooth module; 3023. Zigbee module; 3024. LoRa module. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solutions and advantages of the present application more obvious, the example embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and 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 described in the present application, all other embodiments obtained by those skilled in the art without creative work should fall within the scope of protection of the present application.

[0026] According to one aspect of an embodiment of the present application, an edge gateway system is provided. Figure 1 FIG. 1 is a schematic block diagram of an edge gateway system according to an embodiment of the present application. Figure 1 As shown, the edge gateway system includes at least one edge gateway device, and the edge gateway device includes a multi-protocol access unit 1, an edge computing processing unit 2 and an external interface unit 3; the external interface unit 3 is used to connect to the terminal device, and the multi-protocol access unit 1 is used to connect to the cloud device.

[0027] Continue reading Figure 1The edge computing processing unit 2 includes a central processing unit 203 and an auxiliary computing processor 204 for performing auxiliary computing on the original business data, and the auxiliary computing processor 204 is connected to the central processing unit 203; the central processing unit 203 is connected to the external interface unit 3 to communicate with the terminal device through the external interface unit 3; the central processing unit 203 is connected to the multi-protocol access unit 1 to communicate with the cloud device through the multi-protocol access unit 1.

[0028] In the scheme of this embodiment, the terminal device can transmit data (which can be called original business data) to the central processor 203 through the external interface unit 3, and the central processor 203 can be used at least to determine the type of the original business data to be processed. The auxiliary calculation processor 204 can be specifically used to analyze the data classified as the second type of data (i.e., auxiliary calculation), and send the result to the central processor 203. The central processor 203 can also be used to analyze the original business data classified as the first type of data. After obtaining the analysis result obtained by analyzing the original business data, the central processor 203 can send the above analysis result to the corresponding terminal device, so that the corresponding terminal device performs the corresponding operation according to the analysis result. Among them, the type to be processed may include the first type of data and the second type of data. The first type of data is data that does not exceed the processing capacity of the central processor 203, and the second type of data is data that exceeds the processing capacity of the central processor 203.

[0029] As mentioned above, in the related art, the edge gateway device is usually only able to perform simple data analysis tasks (i.e., processing data that does not exceed the processing capacity of the central processor 203). For data that requires complex calculations (i.e., data that exceeds the processing capacity of the central processor 203), it is usually necessary to transmit the data to the cloud for calculation and processing. When the number of edge gateways is large, a large amount of data is transmitted to the cloud for calculation and processing, resulting in unstable network conditions, high transmission delay, redundant cloud data, heavy calculation burden, and the inability to process the data in a timely manner, affecting the data processing efficiency. The scheme of this embodiment can use the central processor 203 to determine the data type of the currently received data in advance by setting the central processor 203 and the auxiliary calculation processor 204 to determine whether the central processor 203 can directly process the data. When the central processor 203 cannot process the data, the data can be transmitted to the auxiliary calculation processor 204 for calculation. As a result, the edge gateway device can respond quickly to local events without sending the data to the cloud for processing, which helps to reduce the cloud load and helps to improve the data processing efficiency of the edge gateway system and improve the business processing capabilities of the edge gateway device.

[0030] Continue reading Figure 1In some embodiments of the present application, the edge computing processing unit 2 also includes a data perception module 205 for classifying data, and the data perception module 205 is connected to the auxiliary computing processor 204. In the scheme of this embodiment, the auxiliary computing processor 204 can send the original business data classified as the second type of data and the corresponding analysis results to the data perception module 205, and the data perception module 205 can be used to determine the data type of the above-mentioned analysis data (i.e., classify the data), and the data type includes but is not limited to text data, video data, picture data, etc. By setting the data perception module 205, the scheme can use the data perception module 205 to classify the data, thereby determining the data type of the data, which can provide a reliable basis for subsequent data processing operations. For example, the central processing unit 203 can allocate corresponding bandwidth according to the data type of the data when transmitting the above-mentioned data to the cloud for backup. For another example, data can be stored according to the data type, which is conducive to optimizing storage efficiency.

[0031] Continue reading Figure 1 In some embodiments of the present application, the edge computing processing unit 2 further includes a storage module, and the storage module is connected to the central processor 203. Figure 1 In the embodiment shown, the storage module includes an internal flash memory (DDR) module 201 and an external memory module 202. In the solution of this embodiment, the central processor 203 can store the original business data in the storage module for user call, which helps to improve the user experience.

[0032] Continue reading Figure 1 In some embodiments of the present application, there are multiple edge gateway devices, and the multiple edge gateway devices are connected in communication. Specifically, the multiple edge gateway devices can establish communication connections through wired connections such as optical fibers, or through wireless connections such as Bluetooth, local area networks, etc.

[0033] Continue reading Figure 1 In some embodiments of the present application, the multi-protocol access unit 1 includes a multi-mode communication module 101 and a radio frequency module 102, the multi-mode communication module 101 is connected to the radio frequency module 102, the radio frequency module 102 is used to communicate with the cloud device, and the multi-mode communication module 101 is connected to the central processor 203. By setting the multi-mode communication module 101 and the radio frequency module 102 in the multi-protocol access unit 1, the solution can enable the edge gateway device to support a variety of different wireless network protocols, thereby helping to improve the applicability of the edge gateway device so that it can be applied to a wider range of application scenarios.

[0034] Continue reading Figure 1In some embodiments of the present application, the multi-protocol access unit 1 includes an optical fiber interface 103 for connecting to a cloud device, and the central processor 203 is connected to the optical fiber interface 103. In the solution of this embodiment, the central processor 203 can establish a communication connection with the cloud device and / or the central processor 203 in other edge gateway devices through the optical fiber interface 103.

[0035] Continue reading Figure 1 In some embodiments of the present application, the external interface unit 3 includes a wired access submodule 301 and / or a wireless access submodule 302. In this embodiment, the terminal device can be connected through the wired access submodule 301 and / or the wireless access submodule 302, which helps to improve the connection flexibility between the edge gateway device and the terminal device.

[0036] Continue reading Figure 1 In some embodiments of the present application, the external interface module includes a wired access submodule 301, and the wired access submodule 301 includes at least one of the following interfaces: a USB interface 3011, an Ethernet interface 3012, a CAN bus interface 3013, and an RS232 / RS485 interface 3014. Figure 1 In the solution shown, the wired access submodule 301 includes a USB interface 3011, an Ethernet interface 3012, a CAN bus interface 3013, and an RS232 / RS485 interface 3014. This solution can adapt to different terminal devices by providing a variety of wired access interfaces, which is conducive to expanding the application scope of edge gateway devices.

[0037] Continue reading Figure 1 In some embodiments of the present application, the external interface module includes a wireless access submodule 302, and the wireless access submodule 302 includes at least one of the following communication modules: a Wifi module 3021, a Bluetooth module 3022, a Zigbee module 3023, and a LoRa module 3024. Figure 1 In the solution, the wireless access submodule 302 includes a Wifi module 3021, a Bluetooth module 3022, a Zigbee module 3023 and a LoRa module 3024. The solution can be adapted to different terminal devices by setting a variety of wireless modules, which is conducive to expanding the application range of edge gateway devices.

[0038] Continue reading Figure 1In some embodiments of the present application, the central processor 203 uses the OPENWRT operating system. In some embodiments, the OPENWRT operating system can be used to build a secondary development platform to achieve the perception access interface layer. The operating system can support the secondary development platform, support the secondary development of the Python system and business modules, realize customized applications, and easily adapt peripheral devices to adapt to different application scenarios and environments.

[0039] According to another aspect of an embodiment of the present application, a data processing method for an edge gateway system is provided, which is applied to the edge gateway system; the edge gateway system includes at least one edge gateway device, the edge gateway device includes a multi-protocol access unit, an edge computing processing unit and an external interface unit; the external interface unit is used to connect to a terminal device, and the multi-protocol access unit is used to connect to a cloud device.

[0040] The edge computing processing unit includes a central processing unit and an auxiliary computing processor for performing auxiliary computing on the original business data, and the auxiliary computing processor is connected to the central processing unit; the central processing unit is connected to the external interface unit to communicate with the terminal device through the external interface unit; the central processing unit is connected to the multi-protocol access unit to communicate with the cloud device through the multi-protocol access unit.

[0041] Figure 2 FIG. 1 is a schematic flow chart of a data processing method according to an embodiment of the present application. Figure 2 As shown, the method 200 may include the following steps S210, S220, S230 and S240.

[0042] In step S210, when the original service data sent by the terminal device is received, the type of the original service data to be processed is determined.

[0043] In step S220, when the type of the original business data to be processed is the first type of data, the original business data is analyzed.

[0044] In step S230, when the type of the original business data to be processed is the second type of data, the original business data is sent to the auxiliary computing processor so that the auxiliary computing processor analyzes the original business data.

[0045] In step S240, after obtaining the analysis result obtained by analyzing the original business data, the analysis result is sent to the corresponding terminal device, so that the terminal device performs a corresponding operation according to the analysis result.

[0046] The above method may be executed by a central processing unit.

[0047] The above method is explained below through a specific embodiment. In one embodiment, when the original business data sent by the terminal device is received, the type of the original business data to be processed can be determined first. Specifically, the user can determine the type of the original business data to be processed in advance according to the calculation complexity of each type of original business data. For example, real-time monitoring data (such as temperature data, humidity data, etc.) may be used for real-time monitoring of the production environment. When calculating this type of data, it is usually only necessary to compare it with the standard threshold to obtain the analysis result. The calculation is simple, and it can be classified as the first type of data. For data that requires complex analysis (such as vibration data, image data, fingerprint data, etc.), these data may require more powerful computing power to run the fault prediction algorithm. In this case, this type of data can be classified as the second type of data, and the auxiliary computing processor can analyze and process it.

[0048] After obtaining the analysis result, step S240 may be executed to send the analysis result to the corresponding terminal device. After receiving the analysis result, the terminal device may perform corresponding operations according to the analysis result. For example, if the analysis result is that the current fingerprint does not match, an alarm process may be performed (e.g., flashing an alarm light, playing an alarm message through a speaker, etc.).

[0049] The above technical solution can allocate and analyze the original business data according to the type of original business data to be processed. This resource scheduling strategy can ensure the processing efficiency and processing effect of the original business data. The original business data in this solution does not need to be uploaded to the cloud for analysis and calculation, which can not only reduce the cloud computing burden, but also help improve the data processing efficiency of the edge gateway system and improve the business processing capabilities of the edge gateway device. In short, by changing the traditional cloud computing method to the local computing method, this solution can not only reduce the cloud load, but also improve the response speed to local events and improve the efficiency of system implementation.

[0050] In some embodiments of the present application, the edge computing processing unit also includes a data perception module and a storage module, and the method 200 may also include the following steps S250 and S260.

[0051] In step S250, after the auxiliary computing processor analyzes the original business data and obtains the analysis results, the analysis data in the auxiliary computing processor is sent to the data perception module so that the data perception module classifies the analysis data, and the analysis data includes the original business data and the analysis results corresponding to the original business data.

[0052] In step S260, the analysis data is classified according to the classification result obtained by the data perception module, and the original business data in the analysis data is saved in the storage module according to the type of the original business data; wherein the classification result includes the data type of the corresponding data, and the data type includes text data, video data and picture data.

[0053] In the solution of this example, the data perception module can classify the analysis data, and after the classification is completed, the classification results can be sent to the central processing unit via the auxiliary computing processor. The central processing unit can execute step S260 to store the original business data in the storage module according to its data type for future use. In other embodiments, the central processing unit can also synchronize the analysis results of each original business data to the cloud and other collaborative edge gateway devices according to the data type corresponding to the analysis results. Specifically, it can reasonably allocate the bandwidth when synchronizing data according to the data type of the analysis results to improve network resource utilization.

[0054] In the above technical solution, the analysis data can be classified according to the classification results obtained by the data perception module, and the original business data in the analysis data can be saved in the storage module according to the type of the original business data, which helps to optimize storage efficiency and improve computing resource utilization.

[0055] In some embodiments of the present application, there are multiple edge gateway devices. When the type of original business data to be processed is the second type of data, method 200 may further include the following steps S270 and S280.

[0056] Step S270, performing a gateway processing capability evaluation operation to determine whether the processing capability of the current edge gateway device is sufficient to execute the to-be-processed task corresponding to the original business data, the current edge gateway device being the edge gateway device that receives the original business data among the multiple edge gateway devices;

[0057] In step S280, when the processing capacity of the current edge gateway device is insufficient, an edge-to-edge collaboration strategy is executed to utilize other edge gateway devices to collaborate with the current edge gateway device to execute tasks to be processed.

[0058] In the solution of this embodiment, when the processing capacity of the current edge gateway device is insufficient, the edge-to-edge collaboration strategy can be used to use other edge gateway devices to collaborate with the current edge gateway device to execute the task to be processed. For example, the task to be processed can be divided into multiple subtasks, each edge gateway device processes one of the subtasks respectively, and the current edge gateway device summarizes the processing results of all subtasks to obtain the analysis results corresponding to the original business data.

[0059] In some implementations of this embodiment, the gateway processing capacity evaluation operation may include: analyzing and evaluating the type, size and urgency of the task to be processed to determine whether the task to be processed exceeds the processing capacity of the current edge gateway device. Specifically, it is possible to determine whether the task to be processed is a complex or large task based on the type, size and urgency of the task to be processed. If the task to be processed is a complex or large task, it may exceed the processing capacity of the current edge gateway device and needs to be allocated to other edge gateway devices for joint processing.

[0060] In some implementations of this embodiment, the gateway processing capacity evaluation operation may include: analyzing the current resource usage of the current edge gateway device, which may include but is not limited to the usage of the central processing unit (CPU), memory, storage, and network bandwidth. If the current resource usage of the current edge gateway device indicates that the resources are close to saturation, the current edge gateway device may not be able to independently process the pending tasks, that is, the pending tasks exceed the processing capacity of the current edge gateway device, and at this time, they need to be allocated to other edge gateway devices for joint processing.

[0061] In some implementations of this embodiment, the gateway processing capacity evaluation operation may include: determining the service level that the current edge gateway device must meet according to the SLA signed with the customer. If the service level of the current edge gateway device cannot meet the SLA requirements, it can be determined that the task to be processed exceeds the processing capacity of the current edge gateway device, and at this time it needs to be allocated to other edge gateway devices for joint processing.

[0062] In some implementations of this embodiment, the gateway processing capacity evaluation operation may include: analyzing historical data to identify the performance of the current edge gateway device under similar load conditions. If the historical data shows that the current edge gateway device is prone to bottlenecks under high load, it can be determined that the task to be processed exceeds the processing capacity of the current edge gateway device, and it needs to be allocated to other edge gateway devices for joint processing.

[0063] In some implementations of this embodiment, the gateway processing capacity evaluation operation may include: using a prediction model to estimate the resource usage of the current edge gateway device in the future. If the prediction shows that the resources of the current edge gateway device will reach a saturation point, it can be predetermined that the tasks to be processed exceed the processing capacity of the current edge gateway device, and at this time, they need to be allocated to other edge gateway devices for joint processing.

[0064] Optionally, the edge collaboration strategy may include the following steps: determining other edge gateway devices for collaborating with the current edge gateway device; dividing the task to be processed to obtain multiple sub-tasks to be processed, wherein the number of sub-tasks to be processed is the same as the sum of the number of the current edge gateway device and other edge gateway devices for collaborating with the current edge gateway device; for any edge gateway device among the other edge gateway devices, assigning the sub-task to be processed to the edge gateway device, wherein the edge gateway device, after receiving the assistance request, uses the assistance processing operation to process the sub-task to be processed; receiving the processing results obtained by other edge gateway devices for processing the sub-task to be processed; performing data fusion operations on the processing results corresponding to all sub-tasks to be processed to obtain fused data; and determining the analysis results based on the fused data.

[0065] Optionally, the strategy for other edge gateway devices that cooperate with the current edge gateway device can adopt the strategy of learning task allocation from the process. In a specific embodiment, the resource usage status and the number of tasks of the edge gateway device can be used as the state set s, the task processing of the edge gateway device is used as the action a, and the selected strategy set is Q(s,a). The process of batch task processing is regarded as a continuous process, the smooth execution of the task is regarded as the reward r, and the strategy of task allocation is learned from the process. The specific process is as follows:

[0066] a) Initialize the target network Q(s,a) and state s

[0067] b) Select action a according to state s

[0068] c) Execute action a and get reward r

[0069] d) Update strategy Q.

[0070] For example:

[0071] In step a), the target network Q(s,a) and state s are initialized. In this step, it is assumed that there are three edge gateway devices A, B and C (hereinafter referred to as gateway A, gateway B and gateway C), and their resource usage and task numbers are:

[0072] Gateway A: CPU usage 80%, memory usage 70%, task queue length 5;

[0073] Gateway B: CPU usage 50%, memory usage 60%, task queue length 3;

[0074] Gateway C: CPU usage 90%, memory usage 80%, task queue length 4;

[0075] The initial state s can be expressed as:

[0076] s=[80,70,5;50,60,3;90,80,4]

[0077] The target network Q(s,a) can be initialized as a zero matrix:

[0078] Q(s,a)=[0,0,0;0,0,0;0,0,0]

[0079] In step b), action a is selected according to state s. In this step, it is assumed that the central processor of gateway A decides to assign a batch task (ie, a part of the tasks to be processed) to gateway B according to the current state s.

[0080] In step c), action a is executed to obtain reward r. In this step, after gateway B executes the task, it successfully processes all tasks without any failure, and the central processor gives reward r. Among them, reward r is a combined score of the success rate and processing speed of task processing.

[0081] In step d), update the strategy Q. When updating the strategy Q, the central processor of gateway A adjusts the Q value according to the actual reward r and the selected action a.

[0082] Assume that the update formula is Q(s,a)=Q(s,a)+α[rQ(s,a)], where α is the learning rate.

[0083] Assume that the updated Q value is as follows:

[0084] Q(s,a)=[0,0+α[r],0;0,0,0;0,0,0]

[0085] Continuing the learning process, the CPU will continue to select action a according to the new Q value and the current state s, and continuously learn and optimize the task allocation strategy, thereby more reasonably selecting other edge gateway devices to cooperate with the current edge gateway device to process the tasks to be processed.

[0086] Optionally, before the tasks to be processed are divided, the edge-to-edge collaboration strategy may also include: determining the resource status of each edge gateway device in other edge gateway devices; wherein, when the tasks to be processed are divided, the tasks to be processed are divided according to the resource status of each edge gateway device. In a specific embodiment, an assistance request may be first sent to other edge gateway devices, and the assistance request may include the content of the request, the required resources, and the processing requirements. For any edge gateway device in other edge gateway devices (which may be referred to as an auxiliary edge gateway device), when the auxiliary edge gateway device receives an assistance request sent from the current edge gateway device, the received assistance request may be first parsed to understand the content of the assistance request, the required resources, and the processing requirements. Then, the auxiliary edge gateway device may check its own resource status, including CPU usage, memory usage, storage space, network bandwidth, etc., to determine whether there are sufficient resources to process the tasks corresponding to the assistance request. At the same time, the auxiliary edge gateway device may evaluate whether the subtasks to be processed corresponding to the received assistance request are in line with its own processing capabilities and business scope. When the auxiliary edge gateway device has sufficient resources and is able to process the tasks corresponding to the assistance request, the auxiliary edge gateway device may send a response to the current edge gateway device agreeing to process, and send the resource status to the current edge gateway device. Otherwise, the auxiliary edge gateway device can send a response to the current edge gateway device to reject the processing and explain the reason. This division method can ensure that the assigned subtasks to be processed do not exceed the processing capacity of the corresponding edge gateway device, thereby ensuring the processing efficiency of the subtasks to be processed.

[0087] Optionally, the assisting processing operation may include the following steps: performing corresponding processing according to the characteristics of the subtask to be processed, such as data calculation, storage operation, network communication, etc. During the task processing process, the auxiliary edge gateway device may regularly send progress feedback to the current edge gateway device, including the amount of work completed, the problems encountered, etc. After the task processing is completed, the auxiliary edge gateway device will return the processing results to the current edge gateway device. At the same time, after the task processing is completed, the auxiliary edge gateway device can release the occupied resources to facilitate the processing of subsequent tasks. In addition, the auxiliary edge gateway device can record a detailed log of the assisting processing, including the process of request processing, the problems encountered and the solutions, etc., for subsequent analysis and auditing.

[0088] Optionally, performing a data fusion operation on the processing results corresponding to all the subtasks to be processed to obtain fused data may include the following steps:

[0089] (1) Through the clock synchronization protocol, ensure that the data sent by all edge gateway devices are synchronized, that is, the timestamps and event sequences they represent are consistent.

[0090] (2) Perform data cleaning on the received processing results. The data cleaning process includes but is not limited to removing duplicate data, correcting erroneous data, and filling missing values. This process can ensure the quality of the data and provide a reliable foundation for subsequent data fusion.

[0091] (3) After data cleaning is completed, the data format of each processing result is converted, the measurement unit is unified, and the normalization is performed so that the processing results can be compared and merged under the same standards.

[0092] (4) Merging the processing results from multiple sources into a single data set. This merging process can include simple numerical addition or more complex statistical analysis, such as mean, median, mode, etc. In some cases, data merging can also include the merging of spatial data, such as the integration of point, line, and surface data in a geographic information system (GIS).

[0093] (5) Perform data relationship analysis through correlation coefficient calculation, regression analysis, grayscale analysis, etc. to identify the dependency relationship between data.

[0094] (6) Select an appropriate data fusion algorithm based on the characteristics of the data and the purpose of analysis. The data fusion algorithm can include machine learning algorithms such as weighted average, Bayesian reasoning, neural network, etc., or it can be implemented using a deep learning model.

[0095] (7) Use historical data to train the data fusion algorithm to improve the accuracy of data fusion. During the training process, the data fusion algorithm will learn how to extract useful information from multiple data sources, thereby improving the accuracy of the final analysis results.

[0096] (8) Verify the fused data to ensure its accuracy and reliability. This process may include comparing it with known real data or using techniques such as cross-validation to evaluate the generalization ability of the above algorithm.

[0097] (9) After obtaining the fused data, the fused data can be used for further analysis, such as decision support, prediction model establishment, etc. At the same time, these data can also be used as the basis for real-time monitoring and control.

[0098] The implementation process of the edge-to-edge coordination strategy is described below with a specific embodiment: In this embodiment, the edge gateway system can be used for intelligent transportation. In this case, the edge gateway system can include edge gateway devices set up at various intersections. At this time, the edge gateway devices can be used to monitor traffic flow and vehicle status to optimize traffic signal control. When traffic congestion occurs, the current edge gateway device can coordinate with nearby edge gateway devices to jointly process data to find the best signal timing solution.

[0099] In this embodiment, data collection can be performed first. For example, if the edge gateway device at intersection A detects traffic congestion, data such as the number of vehicles and speed can be collected. If the edge gateway devices at intersections B and C also detect similar situations, they start collecting data at the same time.

[0100] Then, other gateway devices for assisting the current edge gateway device may be determined. For example, when the task to be processed corresponding to the raw service data collected by the edge gateway device at intersection A is how to optimize signal timing, an assistance request may be sent to the edge gateway devices at intersections B and C.

[0101] Next, task allocation can be performed, that is, the task to be processed can be divided into multiple subtasks. For example, the computing resources (i.e., resource status) of the edge gateway devices at intersections B and C can be determined respectively, and the processing capacity can be fed back to the edge gateway device at intersection A.

[0102] After obtaining the resource status of each edge gateway device, the current edge gateway device can allocate tasks (i.e., split the tasks to be processed) according to the feedback results, and send the split subtasks to be processed to other edge gateway devices. For example, the subtasks to be processed can be sent to the edge gateway devices at intersections B and C to assist the edge gateway device at intersection A in data processing.

[0103] Then, the edge gateway devices at intersections B and C can start processing their own collected data according to the assigned subtasks to be processed, and exchange some data with each other to assist in processing. Through collaborative processing, intersections B and C can more accurately understand the traffic conditions of the entire area.

[0104] After the edge gateway devices at intersections B and C complete the processing, they send the results to the current edge gateway device. After receiving all the results, the current edge gateway device performs integrated analysis and calculates the optimal signal timing plan based on the integrated data. The signal timing plan can include the green light duration and red light duration of each intersection.

[0105] After obtaining the signal timing plan, the current edge gateway device can send the optimal plan to the edge gateway devices at intersections B and C. The edge gateway device can adjust the traffic lights (i.e., terminal devices) according to the new signal timing plan. As a result, over time, the current edge gateway device can continuously optimize the signal timing plan according to actual traffic conditions.

[0106] The technical solution of the above-mentioned embodiment can comprehensively utilize the resources of multiple edge gateway devices to process the tasks to be processed, thereby breaking through the limitation of limited gateway resources, realizing efficient utilization of resources, and helping to improve processing efficiency.

[0107] In some embodiments of the present application, the auxiliary computing processor analyzes the original business data using a preset neural network model; the method also includes: updating the preset neural network model using an edge-cloud collaborative strategy. The preset neural network model can be a lightweight model obtained through processing methods such as knowledge distillation, which helps to reduce the resource usage of the model itself. In a further modified embodiment, the preset neural network model can be inferred in the cloud device, and the updated parameters obtained by inference are sent to the auxiliary computing processor to update the preset neural network model. This edge-cloud collaborative strategy helps to ensure the accuracy of the preset neural network model.

[0108] A person skilled in the art can easily understand the implementation structure, working principle and beneficial effects of the sensitivity testing system, electronic device and computer-readable storage medium by reading the above sensitivity testing method. For the sake of brevity, no further description is given here.

[0109] Although example embodiments have been described herein with reference to the accompanying drawings, it should be understood that the above example embodiments are merely exemplary and are not intended to limit the scope of the present application to this. Those of ordinary skill in the art may make various changes and modifications therein without departing from the scope and spirit of the present application. All these changes and modifications are intended to be included within the scope of the present application as required by the appended claims.

[0110] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0111] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of 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.

[0112] In the description provided herein, a large number of specific details are described. However, it is understood that the embodiments of the present application can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0113] Similarly, it should be understood that in order to streamline the present application and help understand one or more of the various application aspects, in the description of the exemplary embodiments of the present application, the various features of the present application are sometimes grouped together into a single embodiment, figure, or description thereof. However, the method of the present application should not be interpreted as reflecting the following intention: the claimed application requires more features than the features clearly stated in each claim. More specifically, as reflected in the corresponding claims, the application point is that the corresponding technical problem can be solved with less than all the features of a single disclosed embodiment. Therefore, the claims following the specific embodiment are hereby explicitly incorporated into the specific embodiment, wherein each claim itself serves as a separate embodiment of the present application.

[0114] It will be understood by those skilled in the art that, except for mutually exclusive features, all features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed in this specification may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature that provides the same, equivalent or similar purpose.

[0115] In addition, those skilled in the art will appreciate that, although some embodiments described herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present application and form different embodiments. For example, in the claims, any one of the claimed embodiments can be used in any combination.

[0116] The various component embodiments of the present application can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or digital signal processor (DSP) can be used in practice to implement some or all functions of some modules in the sensitivity test system and electronic equipment according to the embodiment of the present application. The application can also be implemented as a device program (for example, a computer program and a computer program product) for executing a part or all of the methods described herein. Such a program implementing the present application can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0117] It should be noted that the above embodiments illustrate the present application rather than limit the present application, and that those skilled in the art may design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets should not be constructed as a limitation to the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of multiple such elements. The present application may be implemented by means of hardware including several different elements and by means of a suitably programmed computer. In a unit claim that lists several devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc. does not indicate any order. These words may be interpreted as names.

[0118] The above is only a specific implementation or description of a specific implementation of the present application, and the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. The protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. An edge gateway system, characterized in that: It includes at least one edge gateway device, and the edge gateway device includes a multi-protocol access unit, an edge computing processing unit and an external interface unit; the external interface unit is used to connect to a terminal device, and the multi-protocol access unit is used to connect to a cloud device; The edge computing processing unit includes a central processing unit and an auxiliary computing processor for performing auxiliary computing on original business data, wherein the auxiliary computing processor is connected to the central processing unit; the central processing unit is connected to the external interface unit to communicate with the terminal device through the external interface unit; the central processing unit is connected to the multi-protocol access unit to communicate with the cloud device through the multi-protocol access unit.

2. The edge gateway system according to claim 1, characterized in that: The edge computing processing unit also includes a data perception module for classifying data, and the data perception module is connected to the auxiliary computing processor.

3. The edge gateway system according to claim 1, characterized in that: The edge computing processing unit also includes a storage module, which is connected to the central processing unit.

4. The edge gateway system according to claim 1, characterized in that: There are multiple edge gateway devices, and the multiple edge gateway devices are communicatively connected.

5. The edge gateway system according to claim 1, characterized in that: The multi-protocol access unit includes a multi-mode communication module and a radio frequency module, the multi-mode communication module is connected to the radio frequency module, the radio frequency module is used to communicate with the cloud device, and the multi-mode communication module is connected to the central processor; Preferably, the multi-protocol access unit includes a fiber optic interface for connecting to a cloud device, and the central processor is connected to the fiber optic interface.

6. The edge gateway system according to claim 1, characterized in that: The external interface unit includes a wired access submodule and / or a wireless access submodule; Preferably, the external interface module includes a wired access submodule, and the wired access submodule includes at least one of the following interfaces: a USB interface, an Ethernet interface, a CAN bus interface, and an RS232 / RS485 interface; Preferably, the external interface module includes a wireless access submodule, and the wireless access submodule includes at least one of the following communication modules: a Wifi module, a Bluetooth module, a Zigbee module, and a LoRa module.

7. A data processing method for an edge gateway system, characterized in that: Applied to an edge gateway system; the edge gateway system includes at least one edge gateway device, the edge gateway device includes a multi-protocol access unit, an edge computing processing unit and an external interface unit; the external interface unit is used to connect to a terminal device, and the multi-protocol access unit is used to connect to a cloud device; The edge computing processing unit includes a central processor and an auxiliary computing processor for performing auxiliary computing on the original business data, wherein the auxiliary computing processor is connected to the central processor; the central processor is connected to the external interface unit to communicate with the terminal device through the external interface unit; The central processor is connected to the multi-protocol access unit to communicate with the cloud device through the multi-protocol access unit; The method comprises: When receiving the original service data sent by the terminal device, determining the type of the original service data to be processed; When the type of the original business data to be processed is the first type of data, analyzing the original business data; When the type of the original business data to be processed is the second type of data, sending the original business data to the auxiliary computing processor so that the auxiliary computing processor analyzes the original business data; After obtaining the analysis result obtained by analyzing the original business data, the analysis result is sent to the corresponding terminal device, so that the terminal device performs a corresponding operation according to the analysis result.

8. The method according to claim 7, characterized in that The edge computing processing unit further includes a data sensing module and a storage module, and the method further includes: After the auxiliary computing processor analyzes the original business data to obtain an analysis result, the analysis data in the auxiliary computing processor is sent to the data perception module so that the data perception module classifies the analysis data, the analysis data including the original business data and the analysis result corresponding to the original business data; According to the classification result obtained by classifying the analysis data by the data perception module, the original business data in the analysis data is saved in the storage module according to the type of the original business data; The classification result includes the data type of the corresponding data, and the data type includes text data, video data and picture data.

9. The method according to claim 7, characterized in that: The number of the edge gateway devices is multiple, and when the type of the original business data to be processed is the second type of data, the method further includes: Performing a gateway processing capability evaluation operation to determine whether the processing capability of a current edge gateway device is sufficient to execute a to-be-processed task corresponding to the original service data, the current edge gateway device being an edge gateway device among the plurality of edge gateway devices that receives the original service data; When the processing capability of the current edge gateway device is insufficient, an edge-to-edge collaboration strategy is executed to utilize other edge gateway devices to collaborate with the current edge gateway device to execute the task to be processed.

10. The method according to claim 7, characterized in that The auxiliary computing processor uses a preset neural network model to analyze the original business data; the method also includes: updating the preset neural network model using an edge-cloud collaborative strategy.

Citation Information

Cited By

  • Resource allocation method and system based on cloud edge collaboration

    CN119676185A

  • A resource allocation method and system based on cloud-edge collaboration

    CN119676185B

  • Edge gateway system for AI visual identification processing based on large model scene application

    CN119741694A

  • Edge Gateway System for AI Visual Recognition Processing Based on Large Model Scenario Application

    CN119741694B