Industrial Internet of Things Task Scheduling System

Abstract

The present invention provides an industrial Internet of Things task scheduling system, wherein: the Internet of Things sensor device layer is used to collect and generate data, and a variety of actuators are used to send instructions from the upper layer to the Internet of Things devices for execution; the edge processing layer is used to receive the data uploaded by the Internet of Things sensor device layer and perform preliminary processing on the data; multiple node devices in the fog computing layer receive the preliminarily processed data and further process it; the cloud computing layer is used to receive the processed result data of the fog computing layer, analyze or process the data, and provide the processing results to users in the form of FaaS; the middleware layer is arranged between the cloud computing layer and the data solidification layer, and a database or a file system is arranged in the data solidification layer to realize the persistent storage of the Internet of Things data.

Description

Technical Field

[0001] The technical solution of the present disclosure relates to the field of computers, and specifically relates to the field of task allocation methods and Internet of Things technologies. Background Art

[0002] The Internet of Things is a network formed by connections between various objective objects, where information interaction and communication between objects are achieved through various information sensors, sensors, scanners and other devices and technologies such as radio frequency identification. Edge computing, fog computing, and cloud computing technologies are all used to support the development of Internet of Things applications. However, the heterogeneity of the Internet of Things and the demand for collaboration reliability pose challenges to the development of related technologies.

[0003] Another requirement for Internet of Things applications is low latency and low response time. Since the application functions of traditional cloud computing technologies are all deployed in the cloud, the process of obtaining Internet of Things data from the bottom layer and handing it over to the cloud for processing is long and time-consuming. Therefore, a way to deploy application algorithms closer to the cloud is needed to reduce latency losses.

[0004] Compared with traditional Internet of Things, industrial Internet of Things puts forward higher requirements for configurability and scalability, and further increases the demand for low latency. Especially in the industrial Internet of Things application environment of processing production lines, high configurability and low latency mean higher production efficiency and product quality. Summary of the Invention

[0005] Based on the traditional Internet of Things sensor device layer and cloud computing layer, the present invention respectively sets a fog computing layer and an edge processing layer from top to bottom, performs computing and processing on the data uploaded from the bottom layer at the edge processing layer closer to the cloud, and further receives the data that has been processed by the edge processing layer through the fog computing layer, so that key and time-sensitive information can be quickly processed at a lower level, reducing the response time. At the same time, such a structure also enables data to be processed closer to its source, and only relatively less data needs to enter the cloud computing layer and be solidified, which can further reduce the bandwidth overhead in the communication link and the cost of data storage.

[0006] The present invention provides a task processing method, characterized in that:

[0007] Define data acquisition tasks, data standardization tasks, data filtering tasks and data aggregation tasks;

[0008] Among them, data acquisition tasks and data standardization tasks run on multiple data acquisition nodes, data filtering tasks run on multiple data filtering nodes, and data aggregation tasks run on multiple data aggregation nodes, and the nodes are data processing devices with computing capabilities;

[0009] Obtain the latency times of multiple data acquisition nodes, and select the data acquisition node with the minimum latency time, where the latency time is the sum of the network transmission time and the computing processing time;

[0010] Take the selected data acquisition node with the minimum latency time as the first node, and compare the computing processing time of each remaining data acquisition node with the latency time of the first node:

[0011] If the latency time of the first node is less than the computing processing time of the data acquisition node being compared, assign the data filtering task to the first node;

[0012] If the latency time of the first node is greater than the computing processing time of the data acquisition node, assign the data filtering task to the data acquisition node according to the locality assignment principle, where the locality assignment principle refers to assigning the task to a location close to its data input source;

[0013] Iteratively repeat the above steps until all tasks in this stage are assigned or a termination exit condition is given.

[0014] The task processing method further includes:

[0015] Obtain the load of each data filtering node;

[0016] In the case where the load is greater than a first threshold, assign the data filtering task on the data filtering node to an adjacent node, where the adjacent node is a data acquisition node whose network transmission time and computing processing time are both less than those of the data filtering node to which the task to be assigned, and is close to the data source in the data filtering task;

[0017] Iteratively repeat the above steps until all data filtering tasks in this stage are assigned or a termination exit condition is given.

[0018] The task processing method further includes:

[0019] Group the nodes that process the data filtering tasks, where nodes with adjacent positions are grouped into the same group;

[0020] Select the node with the minimum latency time in each group of nodes, and assign the data aggregation task from the data aggregation node with a load greater than a second threshold to the node with the minimum latency time;

[0021] Iteratively repeat the above steps until all data aggregation tasks in this stage are assigned or a termination exit condition is given.

[0022] The present invention also provides a task processing method, characterized in that:

[0023] The edge management node measures the total latency of the task data stream on each edge computing node according to the sampling period;

[0024] The total latency is the sum of the following latencies: contention latency on the sensor device, transmission latency from the sensor to the edge computing node, processing latency of the edge computing node, processing latency of the edge management node, and transmission latency from the edge computing node to the actuator;

[0025] Judge the magnitude relationship between the total latency and a third threshold and a fourth threshold, where the third threshold is less than the fourth threshold:

[0026] In the case where the total latency is less than the third threshold, maintain the task data stream of the existing edge nodes;

[0027] In the case where the total latency is greater than or equal to the third threshold and less than the fourth threshold, perform a task data stream selection operation;

[0028] In the case where the total latency is greater than or equal to the fourth threshold, perform a reset operation on the edge node;

[0029] Iteratively repeat the above steps until the total latency returns to the normal range.

[0030] The task processing method further includes:

[0031] The performing the task data stream selection operation includes obtaining the task priority of the task data stream and the resource consumption situation of the edge node in processing the task data stream;

[0032] Calculate the total priority of the task data stream, where the total priority is the weighted sum of the task priority and the resource consumption situation of the task data stream;

[0033] The edge computing node checks the total priorities of different received task data streams and preferentially processes the task data stream with the higher total priority;

[0034] If the total priorities of multiple task data streams are the same or the difference is less than a certain threshold, the task data streams are processed according to the first-come, first-served principle.

[0035] The task processing method further includes:

[0036] The reset operation of the edge node includes: the edge management node obtains the function priorities of different functions used by the edge computing node for reset, and the edge management node sends a reset request to the edge computing node to be reset according to the highest-ranked function priority;

[0037] When the edge management node receives the reset completion confirmation message returned by the edge computing node, it proves that the edge node reset is successful;

[0038] When the edge management node receives the rejection reset message returned by the edge computing node, it obtains the function with the next function priority ranking and continues to send the reset request;

[0039] When the edge management node does not receive any message returned by the edge node within the preset time, it sends a reset request to the edge computing node again according to the function indicated by the current highest function priority.

[0040] The present invention also provides an Internet of Things system, characterized in that:

[0041] It includes an Internet of Things sensor device layer, an edge processing layer, a fog computing layer, a cloud computing layer, a middleware layer, and a data solidification layer;

[0042] The Internet of Things sensor device layer is specifically a wireless sensor network, including multiple sensors of various types and quantities, for autonomously collecting and generating data, and also including multiple actuators of various types and quantities, for sending instructions from the upper layer to the Internet of Things devices for execution;

[0043] The edge processing layer is used to receive the data uploaded by the Internet of Things sensor device layer and perform preliminary processing on the data;

[0044] Multiple node devices in the fog computing layer receive the data preliminarily processed by the edge processing layer and further perform computational processing on the data;

[0045] The cloud computing layer is used to receive the processed result data of the fog computing layer, perform data analysis on the processed result or further process it according to the functional requirements of the user, and provide the processed result to the user in the form of FaaS;

[0046] The middleware layer is arranged between the cloud computing layer and the data solidification layer, and realizes the access of the devices in the cloud computing layer to the data stored in the data solidification layer by setting up a task queue and a corresponding message queue;

[0047] A database or a file system is set in the data solidification layer to realize the persistent storage of the Internet of Things data.

[0048] The task processing method further includes:

[0049] The edge processing layer further includes multiple edge computing nodes and multiple edge management nodes not exceeding the number of edge computing nodes;

[0050] The edge computing node directly receives the task data stream from the sensor through the gateway, and is resetable and has the function of executing multiple tasks;

[0051] The edge management node coordinates the overall network architecture of the edge computing layer and the flow direction of the task data stream.

[0052] The task processing method further includes:

[0053] The system is used to execute the task processing method described above.

[0054] The present invention also provides a computer program product, characterized in that:

[0055] The computer program product is stored in a non-volatile computer-readable storage medium and includes machine-executable program instructions;

[0056] When the machine-executable program instructions run on the device, the device is caused to execute the task processing method described above. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 It is the overall system architecture diagram of the Internet of Things of the present invention.

[0058] Figure 2 It is a schematic diagram of the edge processing node and the edge management node of the present invention.

[0059] Figure 3 It is a flowchart of the first task allocation method provided by the present invention.

[0060] Figure 4 It is a flowchart of the second task allocation method provided by the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0061] The technical solutions of the present invention will be described in detail below with reference to the accompanying drawings. Although the preferred embodiments disclosed herein are described, it should be understood that the specific implementation manners of various forms of the technical solutions should not be limited by the preferred embodiments. The terms "a possible implementation manner" used in the specification and claims of the present invention mean "at least one embodiment"; "first", "second", etc. are used to distinguish different objects themselves and do not necessarily represent a logical front-back or progressive relationship.

[0062] Figure 1 An Internet of Things system architecture is given, which is particularly suitable for industrial production environments, including an Internet of Things sensor device layer, an edge processing layer, a fog computing layer, a cloud computing layer, a middleware layer, and a data solidification layer, wherein:

[0063] Internet of Things sensor device layer:

[0064] In a specific embodiment, the Internet of Things (IoT) sensor device layer can specifically be an industrial wireless sensor network; the industrial wireless sensor network includes multiple sensors of various types, which are used to autonomously collect and generate data, and the sensor nodes are composed of devices that are difficult to perform complex data processing or have limited resources.

[0065] In an alternative embodiment, the sensor device is powered by a battery or a low-voltage power supply, has low power consumption, supports the IEEE 802.15.4 standard, uses IPv6 as the network layer protocol, and selects UDP as the transport layer protocol. However, as known to those skilled in the art, any protocol and standard suitable for use in a specific scenario fall within the scope of the disclosure of this architecture.

[0066] The IoT sensor device layer is also provided with multiple actuators of various types, which are used to send instructions from the upper layer to the IoT devices for execution; the instructions include sensor and device switch instructions, sensor and device switching instructions, sensor and device frequency conversion instructions, product rejection instructions, etc.

[0067] Edge processing layer:

[0068] The edge processing layer is used to receive the data uploaded by the IoT sensor device layer and perform preliminary processing on the data. Considering the possible diversity and differentiation of sensor devices, the data collected and generated by the edge processing layer needs to be processed on the edge side to make quick decisions, and such quick decisions can reduce the response time and improve the data throughput.

[0069] In a possible embodiment, the edge processing layer can handle the task of judging qualified products. The devices in the edge processing layer can quickly screen the data reported by the sensors and classify and mark the abnormal data when reporting the data to the upper-layer computing device; for example, in a machining production line, the data reported by the sensors can be directly calculated and judged; such as product size, light reflectivity, elongation rate, etc., and based on this, it can be directly judged whether the product is qualified; when it is judged that the product is unqualified, the data stream can be directly sent back to the IoT sensor device layer, so that the actuator in it can quickly reject the unqualified product.

[0070] In another possible embodiment, the devices in the edge processing layer can perform sampling tasks on the data reported by the sensors, including basic simple finite deduplication or merging; for example, if the data acquisition frequency of a certain sensor is once per second, and the data in the next acquisition cycle does not change, then the data in the next acquisition cycle can be deduplicated.

[0071] The edge processing layer implements the first filtering of the data uploaded by IoT sensor devices and data verification including integrity. At the same time, sampling the data first and then reporting it can reduce the size of the transmitted data, reduce latency and response time.

[0072] The edge processing layer includes multiple edge computing nodes and multiple edge management nodes not exceeding the number of edge computing nodes; the edge computing nodes directly receive task data streams from sensors through gateways, and are resetable and have the function of executing multiple tasks. The edge management nodes coordinate the overall network architecture of the edge computing layer and the direction of task data streams.

[0073] Fog computing layer:

[0074] Multiple node devices in the fog computing layer receive the data preliminarily processed by the edge processing layer and further perform computing processing on the data; the computing processing includes data filtering algorithms, data conversion algorithms, and data aggregation algorithms.

[0075] The data filtering algorithm can filter out data that is not very useful for the data analysis process or the user's production, or can filter out data that has not changed within a certain period of time; the data conversion algorithm can be a process of standardizing data from different sources, that is, a process of running a data standardization algorithm; the data aggregation algorithm can include grouping aggregation, metric aggregation, and pipeline aggregation, etc. Metric aggregation can be, for example, calculating the average value or correlation coefficient of a certain group of data, and pipeline aggregation can be further aggregating based on the results of other aggregation algorithms.

[0076] The data processing in the fog computing layer can also be quickly processed in this layer; for example, in the case of finding a production line fault in the processed data, quickly report it to the on-site personnel to achieve rapid response and handling of the fault; the production line fault can include electrical or mechanical faults, etc.

[0077] The fog computing layer can further perform a second data filtering and various forms of data verification on the basis of the first data sampling and filtering. It should be noted that the fault alarm of the fog computing layer can be an abnormal alarm at a higher level than the error alarm level of the edge processing layer; for example, the edge processing layer can only judge whether each product is qualified, while the fog computing layer can further analyze the aggregated data, discover patterns, and thus discover the abnormal operation of a certain entire production line within a certain period of time.

[0078] Cloud computing layer:

[0079] The cloud computing layer is used to receive the processed result data from the fog computing layer, perform data analysis on the processed results or further process them according to the functional requirements of users, and provide the processed results to users in the form of FaaS. This function-as-a-service method can realize the construction of loosely coupled application programs and solve the differential characteristics of Internet of Things data.

[0080] These functions can include simple queries for data visualization, such as the output of a certain production line during a certain period; they can also include predictions for the future, such as the prediction of the future output of a certain production line; the above examples are only for illustration and not exhaustive.

[0081] At the same time, the cloud computing layer can receive instructions sent by users to the underlying layer and send the instructions to the fog computing layer, the edge processing layer, and the Internet of Things sensor device layer in sequence, or directly send the instructions to the edge processing layer when resource conditions permit; the situation where resource conditions permit can include that at least one device in the edge processing layer is in an idle state, and the idle state includes the case where one or more metrics among the processor utilization rate, memory utilization rate, and IO throughput are lower than the threshold.

[0082] Based on this design, the user instructions received by the cloud computing layer can reach the underlying Internet of Things sensor devices in a way with less latency; the instructions can specifically include switch instructions or control instructions for sensors, and the control instructions can switch the data acquisition objects or data acquisition content of specific one or more sensors. In addition, further analysis of the acquired data is also carried out in the cloud computing layer, and various artificial intelligence technologies such as neural networks can be used in this step to achieve intelligent analysis and processing of industrial data.

[0083] Middleware layer:

[0084] The middleware layer is set between the cloud computing layer and the data solidification layer. By setting up a task queue and a corresponding message queue, it realizes the access of devices in the cloud computing layer to the data stored in the data solidification layer, and the access includes the control of specific data access policies; for example, after the device in the cloud computing layer sends a request message for obtaining or storing data, the middleware layer can pre-check the request message, and the check can include identity security verification, timeout detection, route query, etc. These functions can decouple the devices in the cloud computing layer from the data solidification storage devices.

[0085] In some embodiments, the timeout detection in the above manner can be performed before the request reaches the final destination, and the timeout request can be terminated before reaching the final destination, which not only saves the thread and bandwidth resources of the cloud computing layer devices, but also avoids the waste of resources of the data solidification layer devices, and improves the data processing ability. For the routing query function, on the one hand, it includes the routing query of a single data solidification device, and on the other hand, it also includes obtaining data node information at different locations more quickly in the case of distributed storage implemented in the data solidification layer.

[0086] Data solidification layer:

[0087] In the data solidification layer, a database or a file system is set up to achieve the persistent storage of Internet of Things data.

[0088] In one embodiment, the database of the data solidification layer uses the distributed database OceanBase, or HBase can also be used; in some other embodiments, traditional relational databases and non-relational databases can also be configured and used alone, in multiple, or in combination according to the actual situation. As known to those skilled in the art, any data storage paradigm suitable for a specific scenario falls within the scope of the disclosure of this architecture, and the possibility of further improvement and expansion of data storage in this architecture is reserved.

[0089] Based on the above architecture design, by pushing resources to the network edge through the fog computing layer and buffering the data solidification layer and the cloud computing layer in the middleware layer, the problems of high latency, high data storage cost, and security and privacy in traditional Internet of Things cloud computing scenarios can be properly overcome. Although the computing power of the fog computing layer devices is likely to be inferior to that of the cloud computing layer devices, moving the computing closer to the data source can significantly reduce the transmission delay and improve the throughput response ability of the data, providing architectural support for rapid decision-making in the Internet of Things.

[0090] In this embodiment, a first task allocation method is provided, which is as follows:

[0091] In the fog computing layer, data acquisition tasks, data standardization tasks, data filtering tasks, and data aggregation tasks are defined; among them, the data acquisition tasks and data standardization tasks run on multiple data acquisition nodes, the data filtering tasks run on multiple data filtering nodes, and the data aggregation tasks run on multiple data aggregation nodes; the nodes are data processing devices with computing capabilities.

[0092] Due to the limitations and heterogeneity of resources in the fog computing layer, if only the network conditions are considered to adjust the task priorities, it will cause multiple tasks to be assigned to a few processing nodes within a short period of time, which may trigger an avalanche-like network delay. Therefore, while considering reducing the network delay, it is also necessary to consider reducing the processing time.

[0093] The task allocation method for the fog computing layer includes:

[0094] S101: Calculate the computing latency time among multiple data acquisition nodes in the fog computing layer, and select the data acquisition node with the minimum latency time; where the latency time is the sum of the network transmission time and the computing processing time.

[0095] S102: Take the selected data acquisition node with the minimum latency time as the first node, and compare the computing processing time of each remaining data acquisition node with the latency time of the first node.

[0096] S103: If the latency time of the first node is less than the computing processing time of the data acquisition node being compared, allocate the data filtering task to the first node; if the latency time of the first node is greater than the computing processing time of the data acquisition node, allocate the data filtering task to the data acquisition node according to the locality allocation principle; the locality allocation principle refers to allocating the task to a position close to its data input source. If a situation where the latency time is equal to the computing processing time occurs, those skilled in the art can arbitrarily select the data filtering task allocation method according to experience.

[0097] S104: Iteratively repeat steps S101 - S103 until all data filtering tasks in this stage are allocated or a termination exit condition is given; in one embodiment, the termination exit condition can be a program interruption exit caused by an exception, etc. Generally speaking, the number of data filtering nodes is less than that of data acquisition nodes. Therefore, transferring the data filtering tasks on the data filtering nodes to the data acquisition nodes for execution can effectively reduce the load on the data filtering nodes. Here, the load calculation of the data filtering nodes can be temporarily not considered because the number of data filtering nodes is small and it is easier to cause a backlog of data filtering tasks, and calculating the load of the data filtering nodes itself is also a consumption of node resources.

[0098] S105: Obtain the load of each data filtering node; the load can include one or more metrics such as processor utilization rate, memory utilization rate, and IO throughput. For the improvement of the foregoing steps, at this time, consider the load of the data filtering nodes. If, after the allocation in steps S101 - S103, the load of the data filtering nodes still cannot be adjusted to an appropriate range, when the load of the data filtering nodes is still too high, allocate the data filtering tasks to the data acquisition nodes by directly obtaining the load value for adjustment, and in this way, the data processing efficiency can be more accurately improved and the latency can be reduced.

[0099] S106: When the load is greater than the first threshold, assign the data filtering task on the data filtering node to an adjacent node; the adjacent node is a data filtering node whose network transmission time and computing processing time are both less than those of the task to be assigned, and is a data acquisition node close to the data source in the data filtering task. The threshold can be given based on experience or calculated according to various algorithms. After the data filtering task assignment is completed, perform the data aggregation task assignment.

[0100] S107: Group the nodes that process the data filtering tasks, where the adjacent nodes in position are grouped into the same group; the adjacent nodes in position refer to the nodes directly connected through network communication.

[0101] S108: Select the node with the minimum delay time in each group of nodes, and assign the data aggregation task from the data aggregation node with a load greater than the second threshold to the node with the minimum delay time.

[0102] S109: Iteratively repeat steps S107 - S108 until the data aggregation tasks in this stage are all assigned or a termination and exit condition is given.

[0103] S110: Iteratively repeat steps S101 - S109.

[0104] According to the above first assignment method, by minimizing network and processing delays, reduce the operation time of data tasks, and assign the data tasks to positions close to their sources, which can reduce network delays by reducing communication distances and data transmission volumes, and reduce task processing time by evacuating overloaded nodes; according to the task assignment method proposed above, the data processing efficiency in the Internet of Things environment can be effectively improved.

[0105] Although this assignment method is applied to fog computing in this embodiment, however, when nodes run corresponding data processing tasks, it can also be applied to cloud computing or edge computing.

[0106] Although the embodiment is applied to the industrial Internet of Things environment, it is equally applicable to other environments involving the Internet of Things.

[0107] In this embodiment, a second task assignment method is provided, which is as follows:

[0108] To further improve the processing efficiency of the Internet of Things system, on the basis of considering task assignment optimization from the fog computing layer as described above, further consider the task processing problem of the edge computing layer from top to bottom. As described in the architecture above, due to the diversity and differentiation of sensors, the amount and types of data collected by them are not the same. This heterogeneous characteristic makes it difficult for resource - limited edge device nodes to exert their maximum efficiency.

[0109] Therefore, on the one hand, it is necessary to consider how to select edge nodes so that they are suitable for processing data streams of different tasks. On the other hand, edge nodes are designed to support reconfiguration to meet the running requirements of various tasks. As is known to those skilled in the art, edge nodes at least include edge management nodes and edge computing nodes.

[0110] S201: The edge management node measures the total delay of the task data stream on each edge computing node according to the sampling period; the total delay is the sum of the following delays: contention delay on the sensor device, transmission delay from the sensor to the edge computing node, processing delay of the edge computing node, processing delay of the edge management node, and transmission delay from the edge computing node to the actuator. The contention delay refers to the delay caused by the channel contention situation when multiple sensor nodes send data to the same or a few edge computing nodes.

[0111] S202: Judge the magnitude relationship between the total delay and the third threshold and the fourth threshold, where the third threshold is less than the fourth threshold.

[0112] S203: When the total delay is less than the third threshold, maintain the task data stream of the existing edge nodes.

[0113] S204: When the total delay is greater than or equal to the third threshold and less than the fourth threshold, perform the task data stream selection operation.

[0114] S205: When the total delay is greater than or equal to the fourth threshold, perform the reset operation of the edge node; reset means reconfiguring the function of the node to a new function different from the previous function. The reset process is mainly completed through software configuration, and when necessary, it can also be achieved by changing the hardware physical structure or logical structure.

[0115] S206: Iteratively repeat steps S201 - S205 until the total delay returns to the normal range; the normal range can be the situation where the total delay is less than the third threshold, or it can be dynamically configured according to the system status.

[0116] The step S204 further includes:

[0117] S2041: Obtain the task priority of the task data stream and the resource consumption situation of processing the task data stream on the edge node; among them, different task data streams have different priorities, and the priorities are predefined according to different sensor acquisition devices and the acquired data; for example, in a certain machining production line, the primary qualified condition of a workpiece is that its size meets certain standards, and the secondary condition is that its light reflectivity meets certain standards, then the task data stream priority of the size data is greater than the task data stream priority of the light reflectivity data.

[0118] S2042: Calculate the total priority of the task data stream; the total priority is the weighted sum of the task priority and the resource consumption of the task data stream, and the total priority = α × task priority + (1 - α) × resource consumption priority; where α is a weight value, which is a constant between 0 and 1, and the influencing factor of the resource consumption priority is the resource consumption. When a task data stream has a large consumption of processor, memory or network resources, the resource consumption priority is low, and vice versa, the resource consumption priority is high.

[0119] S2043: The edge computing node checks the total priorities of different received task data streams and preferentially processes the task data stream with a higher total priority; if the total priorities of multiple task data streams are the same or the difference is less than a certain threshold, the task data streams are processed according to the first-come, first-served principle.

[0120] S2044: Return to step S2041.

[0121] The step S205 further includes:

[0122] S2051: The edge management node obtains the function priorities of different functions used by the edge computing node for resetting; among them, the different function priorities can be set according to the usage frequency of different functions, the size of the transmitted data volume corresponding to different functions, the resource consumption load corresponding to different functions, etc., and the function priorities can change dynamically; for example, if the usage frequency of a certain function increases significantly within a period of time, its priority will also increase accordingly.

[0123] S2052: The edge management node sends a reset request to the edge computing node to be reset according to the highest-ranked function priority, and the reset request may also carry the configuration file required for resetting.

[0124] S2053: When the edge management node receives the reset completion confirmation message returned by the edge computing node, it proves that the edge node reset is successful.

[0125] S2054: When the edge management node receives the reject reset message returned by the edge computing node, it obtains the function with the next highest function priority ranking and continues to send the reset request; the situation where the edge computing node rejects the reset may include that the edge computing node has a heavy load and is currently in a busy state, or the existing resources cannot meet the reset requirements, etc.

[0126] S2055: When the edge management node does not receive any message returned by the edge node within the preset time, it again sends a reset request to the edge computing node according to the function indicated by the current highest function priority; in this embodiment, the sending of the reset request is tried a limited number of times again. If the edge computing node still does not respond, there may be exceptions such as network failures or node offline, and this reconfiguration process can be skipped.

[0127] S2056: Return to step S2051.

[0128] By judging the total delay, when the total delay is small, the existing task processing method can be maintained unchanged. When the total delay is large, the task data stream with a higher priority is selected for execution. When the total delay is even larger, resetting the edge node that processes the task data stream can enable the edge processing layer to give priority to processing high-priority tasks. This is because the process of channel contention and the process of security authentication when data enters the node cause obvious delays to it. In the case where the delay is further amplified, it indicates that the adaptability between the edge node and the task data stream is further reduced. Therefore, by resetting the edge node to reduce the contention delay and more specifically process the task data stream, the delay waiting time can be effectively reduced, ensuring the overall task data processing efficiency of the system.

[0129] The embodiment of the present application also provides a computer program product; the computer program product is stored in a non-volatile computer-readable storage medium and includes machine-executable program instructions. When the machine-executable program instructions run on the device, the device is enabled to execute each method process of task allocation in the above embodiment, and is also used to support the construction of the system architecture in the above embodiment, and can achieve the same technical effect. The non-volatile computer-readable storage medium includes magnetic tapes, hard disks, optical discs, mobile hard disks, USB flash drives, read-only memory ROM, random access memory RAM, etc.

[0130] The above specific implementation manners are preferred specific application examples of the present invention. The above examples are illustrative rather than exhaustive, and do not constitute a limitation on the principle of the solution of the embodiment itself; without departing from the scope and spirit of the disclosed embodiments, obvious simple changes and substitutions made by those skilled in the art without creative efforts all fall within the scope of the disclosure of the above embodiments.

Claims

1. An Internet of Things system, characterized in that: It includes IoT sensor device layer, edge processing layer, fog computing layer, cloud computing layer, middleware layer, and data solidification layer; The IoT sensor device layer is specifically a wireless sensor network, including multiple numbers and types of sensor nodes for autonomously collecting and generating data, and multiple numbers and types of actuators for sending instructions from the upper layer to the IoT devices for execution; The edge processing layer is used to receive data uploaded by the IoT sensor device layer and perform preliminary processing on the data; Multiple node devices in the fog computing layer receive the data initially processed by the edge processing layer and further perform computation on the data; The cloud computing layer is used to receive the processing result data of the fog computing layer, and perform data analysis on the processing result data or further process it according to the functional requirements of the user, and provide the processing result data to the user in the form of FaaS; The middleware layer is set between the cloud computing layer and the data hardening layer. By setting task queues and corresponding message queues, the devices in the cloud computing layer can access the data stored in the data hardening layer. A database or file system is set up in the data curing layer to achieve persistent storage of IoT data; The Internet of Things system is used to perform the following task processing method: Define data acquisition tasks, data standardization tasks, data filtering tasks, and data aggregation tasks; The data acquisition task and the data standardization task are run on multiple data acquisition nodes, the data filtering task is run on multiple data filtering nodes, and the data aggregation task is run on multiple data aggregation nodes. The data acquisition nodes, data filtering nodes, and data aggregation nodes are all data processing devices with computing capabilities. Obtaining delay times of the plurality of data acquisition nodes, and selecting a data acquisition node with the smallest delay time, wherein the delay time is the sum of the network transmission time and the calculation processing time; The selected data acquisition node with the smallest delay time is used as the first node, and the calculation processing time of each remaining data acquisition node is compared with the delay time of the first node: If the delay time of the first node is less than the calculation processing time of the data acquisition node for comparison, the data filtering task is assigned to the first node; if the delay time of the first node is greater than the calculation processing time of the data acquisition node for comparison, the data filtering task is assigned to the data acquisition node for comparison according to the locality allocation principle, and the locality allocation principle refers to assigning tasks to locations close to their data input sources; The above task processing method is repeated iteratively until all tasks in this stage are assigned or a termination exit condition is given.

2. The Internet of Things system according to claim 1, characterized in that: The edge processing layer further includes a plurality of edge computing nodes, and a plurality of edge management nodes not exceeding the number of edge computing nodes; The edge computing node directly receives task data streams from sensors through the gateway, is reconfigurable, and has the function of executing multiple tasks; The edge management node coordinates the overall network architecture of the edge computing layer and the direction of task data flow.

3. An Internet of Things system, characterized in that: It includes IoT sensor device layer, edge processing layer, fog computing layer, cloud computing layer, middleware layer, and data solidification layer; The IoT sensor device layer is specifically a wireless sensor network, including multiple numbers and types of sensor nodes for autonomously collecting and generating data, and multiple numbers and types of actuators for sending instructions from the upper layer to the IoT devices for execution; The edge processing layer is used to receive data uploaded by the IoT sensor device layer and perform preliminary processing on the data; Multiple node devices in the fog computing layer receive the data initially processed by the edge processing layer and further perform computation on the data; The cloud computing layer is used to receive the processing result data of the fog computing layer, and perform data analysis on the processing result data or further process it according to the functional requirements of the user, and provide the processing result data to the user in the form of FaaS; The middleware layer is set between the cloud computing layer and the data hardening layer. By setting task queues and corresponding message queues, the devices in the cloud computing layer can access the data stored in the data hardening layer. A database or file system is set up in the data curing layer to achieve persistent storage of IoT data; The Internet of Things system is used to perform the following task processing method: The edge management node measures the total delay of the task data flow on each edge computing node according to the sampling period; The total delay is the sum of the following delays: contention delay on the sensor device, transmission delay from the sensor to the edge computing node, processing delay of the edge computing node, processing delay of the edge management node, and transmission delay from the edge computing node to the actuator; Determine the relationship between the total delay and the third threshold and the fourth threshold, the third threshold being less than the fourth threshold: When the total delay is less than the third threshold, maintaining the task data flow of the existing edge computing node; When the total delay is greater than or equal to the third threshold and less than a fourth threshold, performing a task data stream selection operation; When the total delay is greater than or equal to the fourth threshold, performing a reset operation of the edge computing node; The above task processing method is iterated and repeated until the total delay returns to the normal range.

4. The Internet of Things system according to claim 3, characterized in that: The edge processing layer further includes a plurality of edge computing nodes, and a plurality of edge management nodes not exceeding the number of edge computing nodes; The edge computing node directly receives task data streams from sensors through the gateway, is reconfigurable, and has the function of executing multiple tasks; The edge management node coordinates the overall network architecture of the edge computing layer and the direction of task data flow.

Images