5G and star flash short-range fusion industrial wireless network system

Abstract

The application provides a 5G and star flash short distance fusion industrial wireless network system, the system comprises an end side, a side and a cloud side, wherein: the end side comprises a plurality of industrial devices and a plurality of 5G communication units, each industrial device is configured with a star flash short distance module, and part of the industrial devices are further configured with a 5G communication component; the side comprises a 5G CU unit and an edge computing server, wherein the 5G CU unit is used for receiving the data of the end side and the cloud side, and forwarding the data transmitted by the cloud side and the end side; the edge computing server is used for executing an edge computing task based on the data received by the 5G CU unit; the cloud side comprises a cloud platform or a data center, wherein the cloud platform or the data center is used for receiving and storing the data transmitted by the end side and the side, and executing data analysis based on the received data. The application combines the characteristics of 5G wide area coverage and star flash short distance communication, and realizes comprehensive wireless connection of industrial devices.

Description

Technical Field

[0001] This invention relates to wireless communication networks, more specifically to short-range satellite technology in wireless communication networks, and more specifically to an industrial wireless network system that integrates 5G and short-range satellite technology. Background Technology

[0002] In the era of Industry 4.0, the digitalization, networking, and intelligentization of industrial manufacturing systems are highly dependent on the upgrading and construction of industrial networks. Industrial communication networks are evolving from fieldbus to industrial Ethernet and industrial wireless networks. Wired networks face insurmountable difficulties in terms of installation accessibility, coverage, flexibility, and maintainability, resulting in ineffective data collection and transfer within industrial field networks. Moreover, the physical connection method of wired connections limits the dynamic changes in network topology. To meet the demands of flexible production and intelligent warehousing and logistics in future intelligent manufacturing, cableless solutions represent a crucial development direction for industrial networks.

[0003] The demand for wireless connectivity in industrial networks is constantly growing. However, existing traditional wireless networks such as WiFi, Bluetooth, and Zigbee exhibit problems such as limited coverage, poor network stability, and insufficient terminal connectivity. The 5G standard, led by the 3rd Generation Partnership Project (3GPP), can support peak data rates of 10-20Gbps, 1ms air interface latency, 99.999% reliability, and millions of device connections per square kilometer.

[0004] Programmable logic controllers (PLCs) are a typical example of modern industrial control systems. However, local PLCs have limited capacity and computing power, and different PLCs are incompatible with each other's protocols, making it difficult to meet the production demands of large-scale, flexible, intelligent, and collaborative control in future complex industrial networks. 5G-based cloud-based PLC technology can decouple the physical binding between network and control, flexibly orchestrate the connection relationship between the network and control, and quickly adapt to the needs of flexible production adjustments. Simultaneously, by integrating software-defined networking, artificial intelligence, cloud computing, and edge computing capabilities, it can improve the intelligence and wide-area collaborative capabilities of industrial production. "5G + cloud-based PLC" is currently a research hotspot in industrial networks and is leading the intelligent transformation of industrial control systems.

[0005] To address the wireless connectivity requirements of industrial networks, existing technologies have proposed a partially centralized PLC industrial network architecture based on a two-level PLC system. The master PLC is centrally deployed on a mobile edge computing (MEC) server via virtualization. The master PLC and slave PLCs are connected via a 5G wireless link, while the slave PLCs are connected to input / output (I / O) drivers using a traditional wired distributed approach. This partially centralized architecture enables collaborative control between master PLCs and flexible connections between them. Simultaneously, existing technologies have also proposed a novel centralized PLC industrial networking architecture based on 5G full connectivity. In this architecture, all PLC functions are integrated and deployed on a 5G MEC via virtualization. The virtualized PLCs and I / O drivers are wirelessly connected. This fully connected centralized architecture enables efficient collaboration among globally centralized virtualized PLCs.

[0006] While existing industrial network architectures can address the wireless connectivity needs of industrial networks, they all have shortcomings. For a partially centralized PLC industrial network architecture based on two-level PLCs, this partially centralized architecture can achieve collaborative control between master PLCs and flexible connections between master and slave PLCs, but local slave PLCs still use wired fixed connections to I / O drivers. For a new industrial networking architecture based on fully connected 5G PLCs, this architecture can achieve efficient collaboration of globally centralized virtualized PLCs; however, this architecture requires all device I / O drivers to connect to the virtualized PLCs via 5G wireless communication, which is very costly, with a single 5G terminal module costing several thousand RMB. Furthermore, considering the access capacity of base stations, multiple 5G base stations need to be deployed within the factory according to equipment connectivity requirements, with each base station costing hundreds of thousands of RMB. Achieving full 5G coverage in the factory requires a huge financial investment. Summary of the Invention

[0007] Therefore, the purpose of this invention is to overcome the shortcomings of the prior art and provide an industrial wireless network system that integrates 5G and StarScan short-range technology and a method for executing computing tasks.

[0008] The objective of this invention is achieved through the following technical solutions.

[0009] According to a first aspect of the present invention, an industrial wireless network system integrating 5G and StarShortRay is provided. The system includes an end-side, an edge-side, and a cloud-side, wherein: the end-side includes multiple industrial devices and multiple 5G communication units, each industrial device is equipped with a StarShortRay module, and some industrial devices are also equipped with 5G communication components; wherein, industrial devices equipped with 5G communication components and StarShortRay modules connect to the 5G communication units through the 5G communication components, or connect to other industrial devices equipped with 5G communication components and StarShortRay modules through the StarShortRay modules to achieve connection with the 5G communication units; industrial devices equipped only with StarShortRay modules connect to other industrial devices equipped with 5G communication components and StarShortRay modules through the StarShortRay modules to achieve connection with the 5G communication units; each 5G communication unit is used to realize communication between the industrial device it is connected to and the edge-side or cloud-side; the edge-side includes a 5G CU unit and an edge computing server, wherein the 5G... The CU unit is used to receive data from the edge and cloud sides, and to forward data transmitted from itself and the cloud side to the edge side; the edge computing server is used to perform edge computing tasks based on the data received by the 5G CU unit; the cloud side includes a cloud platform or data center, wherein the cloud platform or data center is used to receive and store data transmitted from the edge and cloud sides, and to perform data analysis based on the received data.

[0010] In some embodiments of the present invention, the plurality of 5G communication units include a plurality of 5G base station distributed units and / or a plurality of active antenna units.

[0011] In some embodiments of the present invention, the edge computing server and 5G CU unit in the edge are deployed in a centralized manner, wherein the centralized deployment means that the edge computing server and 5G CU unit share computing resources in the edge.

[0012] In some embodiments of the present invention, the edge computing server and 5G CU unit in the edge are deployed in a distributed manner, wherein the distributed deployment means that the edge computing server and 5G CU unit are each configured with corresponding computing resources in the edge.

[0013] In some embodiments of the present invention, the industrial wireless network system coordinates the execution of computing tasks on the end side, edge side, and cloud side in a compute offloading manner.

[0014] In some embodiments of the present invention, the computation offloading method is as follows: based on the characteristics of the computation task, the task is divided into local computation task, edge computation task and / or cloud-side computation task, and the local computation task after task division is assigned to the end side for execution, the edge computation task is assigned to the edge side for execution, and the cloud-side computation task is assigned to the cloud side for execution.

[0015] In some embodiments of the present invention, the terminal side also includes multiple industrial devices configured only with 5G communication components.

[0016] According to a second aspect of the present invention, a method for executing a computational task is provided, the method comprising: step S1, obtaining a computational task to be executed; and step S2, executing the computational task using the system described in the first aspect of the present invention to obtain a task execution result.

[0017] Compared with the prior art, the advantages of the present invention are: (1) Combining the characteristics of 5G wide-area coverage and Star Flash short-range communication, it realizes comprehensive wireless connection of industrial equipment; (2) Introducing industrial equipment equipped with Star Flash short-range module and 5G communication components, it can realize the integration of 5G and Star Flash networks, and realize low-cost large-scale wireless connection of industrial field equipment. Attached Figure Description

[0018] The embodiments of the present invention will be further described below with reference to the accompanying drawings, wherein:

[0019] Figure 1 This is a schematic diagram of an industrial wireless network system structure that integrates 5G and StarScan short-range technology according to an embodiment of the present invention;

[0020] Figure 2 This is a schematic diagram illustrating an example of an industrial wireless network system according to an embodiment of the present invention;

[0021] Figure 3 This is a schematic diagram of an example industrial wireless network system according to an embodiment of the present invention. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are merely illustrative and are not intended to limit the invention.

[0023] As mentioned in the background section, although existing industrial network architectures can meet the wireless connectivity requirements of industrial networks, they all have shortcomings. For a partially centralized PLC industrial network architecture based on two-level PLCs, this partially centralized architecture can achieve collaborative control between master PLCs and flexible connections between master and slave PLCs, but wired fixed connections are still used between local slave PLCs and I / O drivers. For a new industrial networking architecture based on 5G full connectivity and centralized PLCs, this architecture can achieve efficient collaboration of globally centralized virtualized PLCs; however, this architecture requires all device I / O drivers to connect to the virtualized PLCs via 5G wireless communication, which is very costly, with a single 5G terminal module costing several thousand RMB. Furthermore, considering the access capacity of base stations, multiple 5G base stations need to be deployed within the factory according to equipment connectivity requirements, with each base station costing hundreds of thousands of RMB. Achieving full 5G coverage in the factory requires a huge financial investment.

[0024] To address the aforementioned issues, the inventors proposed integrating 5G and StarSpark short-range wireless communication to achieve wireless deployment and resolve the high capital investment problem. Simply put, within 5G cellular coverage areas, industrial equipment equipped with StarSpark short-range modules can extend 5G services, thereby achieving fully wireless connectivity while reducing the need for 5G base station deployment. The next-generation StarSpark short-range wireless communication standard supports transmission rates of 900Mbps, 20 microseconds of one-way latency, 1 microsecond of synchronization accuracy, 99.999% reliability, and 80 concurrent communication nodes within milliseconds. This demonstrates that StarSpark short-range communication technology meets the requirements of low latency, ultra-reliability, massive connectivity, and high bandwidth. Furthermore, compared to 5G terminal modules, StarSpark short-range modules are much cheaper, costing only tens to hundreds of RMB, allowing for large-scale deployment in short-range communication scenarios.

[0025] In summary, such as Figure 1As shown, this invention provides an industrial wireless network system integrating 5G and StarShort-Ray technology. The system includes an end-side, an edge-side, and a cloud-side. The end-side includes multiple industrial devices and multiple 5G communication units. Each industrial device is equipped with a StarShort-Ray module, and some industrial devices also have 5G communication components. Industrial devices equipped with both 5G communication components and StarShort-Ray modules connect to the 5G communication units via the 5G communication components, or connect to other industrial devices equipped with both 5G communication components and StarShort-Ray modules via the StarShort-Ray modules to achieve connection with the 5G communication units. Industrial devices equipped only with StarShort-Ray modules connect to other industrial devices equipped with both 5G communication components and StarShort-Ray modules via the StarShort-Ray modules to achieve connection with the 5G communication units. Each 5G communication unit is used to enable communication between the connected industrial device and the edge-side or cloud-side. The edge-side includes 5G... The 5G CU unit is used to receive data from the edge and cloud sides, and to forward data transmitted from itself and the cloud side to the edge side; the edge computing server is used to perform edge computing tasks based on the data received by the 5G CU unit; the cloud side includes a cloud platform or data center, wherein the cloud platform or data center is used to receive and store data transmitted from the edge and cloud sides, and to perform data analysis based on the received data.

[0026] To better understand the present invention, each component of the industrial wireless network system will be described in detail below with reference to specific embodiments.

[0027] I. End side

[0028] The edge side includes multiple industrial devices and multiple 5G communication units. Each industrial device is equipped with a star-flash short-range module, and some industrial devices are also equipped with 5G communication components. Industrial devices equipped with both 5G communication components and star-flash short-range modules connect to the 5G communication unit via the 5G communication components, or connect to other industrial devices equipped with both 5G communication components and star-flash short-range modules via the star-flash short-range module to achieve connection with the 5G communication unit. Industrial devices equipped only with star-flash short-range modules connect to other industrial devices equipped with both 5G communication components and star-flash short-range modules via the star-flash short-range module to achieve connection with the 5G communication unit. Each 5G communication unit is used to enable communication between the connected industrial device and the edge side or cloud side.

[0029] According to one embodiment of the present invention, the end side also includes a plurality of industrial devices configured only with 5G communication components.

[0030] According to one embodiment of the present invention, the plurality of 5G communication units include a plurality of 5G base station distributed units and / or a plurality of active antenna units.

[0031] Based on the above embodiments, it can be seen that the terminal side can consist of multiple industrial devices equipped only with a short-range strobe module, multiple industrial devices equipped with a short-range strobe module and 5G communication components, and multiple 5G communication units; or it can consist of multiple industrial devices equipped only with a short-range strobe module, multiple industrial devices equipped with a short-range strobe module and 5G communication components, multiple industrial devices equipped only with 5G communication components, and multiple 5G communication units. It should be noted that the integration of 5G and short-range strobe technology can provide wide-area / regional connectivity, and short-range strobe technology can further extend 5G services, extending short-range communication down to the last ten to tens of meters of core industrial production processes, such as short-range communication inside enclosed metal bodies or robotic arms.

[0032] To better understand how various industrial devices on the terminal side communicate with the edge or cloud side, the communication methods of each industrial device are explained below.

[0033] When an industrial device equipped only with a short-range telescope module communicates with the edge, it connects its own short-range telescope module to another industrial device equipped with both a short-range telescope module and a 5G communication component. This allows the device to connect to the edge's 5G communication unit via the 5G communication component on the edge device, and then communicate with the edge via the 5G communication unit. Similarly, when an industrial device equipped only with a short-range telescope module communicates with the cloud, it connects its own short-range telescope module to another industrial device equipped with both a short-range telescope module and a 5G communication component. This allows the device to connect to the edge's 5G communication unit via the 5G communication component on the edge device, and then communicate with the cloud via the 5G communication unit.

[0034] When industrial equipment equipped with a 5G short-range telescope module and 5G communication components communicates with the edge, it connects to the 5G communication unit on the terminal side through its own 5G communication component and communicates with the edge through the 5G communication unit; or it connects to other industrial equipment equipped with 5G communication components and 5G short-range telescope modules through the 5G short-range telescope module to connect to the 5G communication unit and communicate with the edge through the 5G communication unit. Similarly, when industrial equipment equipped with a 5G short-range telescope module and 5G communication components communicates with the cloud side, it connects to the 5G communication unit on the terminal side through its own 5G communication component and communicates with the cloud through the 5G communication unit; or it connects to other industrial equipment equipped with 5G communication components and 5G short-range telescope modules through the 5G short-range telescope module to connect to the 5G communication unit and communicates with the cloud through the 5G communication unit. It should be noted that industrial equipment equipped with a StarScan short-range module and 5G communication components can randomly choose a connection method to connect to the 5G communication unit to achieve communication with the edge or cloud side; alternatively, the connection method can be determined based on data transmission requirements. For example, for short-distance transmission, it can connect to the 5G communication unit through other industrial equipment equipped with StarScan short-range modules and 5G communication components; for long-distance transmission, it can connect directly to the 5G communication unit. It should also be noted that industrial equipment equipped with StarScan short-range modules and 5G communication components can achieve the convergence of 5G and StarScan networks upstream, and enable low-cost, large-scale connectivity of industrial field devices downstream.

[0035] When an industrial device equipped with only 5G communication components communicates with the edge, it connects to the 5G communication unit on the terminal side through its own 5G communication components, and then communicates with the edge via the 5G communication unit. Similarly, when an industrial device equipped with only 5G communication components communicates with the cloud side, it connects to the 5G communication unit on the terminal side through its own 5G communication components, and then communicates with the cloud via the 5G communication unit.

[0036] II. Side

[0037] The edge side includes a 5G CU unit and an edge computing server. The 5G CU unit is used to receive data from the terminal side and the cloud side, and to forward data transmitted from itself and the cloud side to the terminal side. The edge computing server is used to perform edge computing tasks based on the data received by the 5G CU unit.

[0038] According to one embodiment of the present invention, the edge computing server and 5G CU unit in the edge are deployed in a centralized manner, wherein the centralized deployment means that the edge computing server and 5G CU unit share computing resources in the edge.

[0039] According to one embodiment of the present invention, the edge computing server and 5G CU unit in the edge side are deployed in a distributed manner, wherein the distributed deployment means that the edge computing server and 5G CU unit are each configured with corresponding computing resources in the edge side.

[0040] III. Cloud Side

[0041] The cloud side includes a cloud platform or a data center, wherein the cloud platform or data center is used to receive and store data transmitted from the end side and the edge side, and to perform data analysis based on the received data.

[0042] According to one embodiment of the present invention, the industrial wireless network system coordinates the execution of computing tasks on the end side, edge side, and cloud side in a computing offload manner.

[0043] According to one embodiment of the present invention, the computation offloading method is as follows: the task is divided into local computing tasks, edge computing tasks and / or cloud computing tasks based on the characteristics of the computing task, and the local computing tasks after task division are assigned to the edge side for execution, the edge computing tasks are assigned to the edge side for execution, and the cloud computing tasks are assigned to the cloud side for execution.

[0044] It should be noted that computation offloading is usually based on the characteristics of the computation task itself to achieve task partitioning. For example, computation tasks with high latency requirements can be assigned to the edge or terminal side for execution; while computation tasks with low latency requirements can be assigned to the cloud side for execution. Another example is distributed model training tasks. Considering that the data collected by various industrial devices may be different, each industrial device can use its own configured computing resources to perform local training to obtain its own local model. Then, the local model parameters of each industrial device are passed to the edge or cloud side to aggregate the parameters and obtain the final global model.

[0045] It should also be noted that there is no fixed standard for task partitioning in the computation offloading method. Task partitioning needs to be based on the actual characteristics of the computation tasks, and this invention does not impose any special restrictions. Furthermore, when partitioning tasks based on the characteristics of the computation tasks, the computing resources on the edge, device, and cloud can be considered for better task partitioning. For example, if each industrial device on the edge can execute the computation task according to its own configured computing resources, no task partitioning is required; conversely, if each industrial device on the edge cannot execute the computation task according to its own configured computing resources, task partitioning is required. When partitioning tasks, priority should be given to allocating time-sensitive (high latency requirements) computation tasks to the industrial devices on the edge for processing, while time-insensitive computation tasks should be allocated to the edge or cloud. If the computing resources configured on the industrial devices on the edge cannot meet the needs of time-sensitive computation tasks, then the time-sensitive computation tasks are allocated to the edge. Similarly, for time-insensitive computation tasks, if the computing resources configured on the edge cannot meet the needs of the time-insensitive computation tasks, then the time-insensitive computation tasks are allocated to the cloud.

[0046] To better understand this invention, the following will be used... Figure 2 and Figure 3 The industrial wireless network system shown is used as an example for illustration.

[0047] exist Figure 2 The mid-end includes multiple industrial devices equipped only with short-range star-flash modules, multiple industrial CPE devices (customer premise equipment), and multiple 5G base station distributed units (5G DU) or multiple active antenna units (5G AAU); the edge includes edge computing servers (MEC servers) and 5G CU units; the cloud includes multiple factory cloud platforms or data centers. The following sections will discuss these in detail. Figure 2 The end side, edge side, and cloud side shown in the figure are explained.

[0048] Depend on Figure 2 As can be seen, the device on the left side of the terminal is an industrial CPE, the device on the right side is an industrial device equipped only with a star flash short-range module, and the device on top is a 5G DU or 5G AAU.

[0049] The industrial CPE device is equipped with a stroboscopic short-range module and a 5G communication component. It can connect to a 5G DU or 5G AAU via its own 5G communication component to achieve communication with the edge and cloud sides. Furthermore, because the industrial CPE device integrates gateway functionality, it can convert between 5G and stroboscopic short-range protocols. Therefore, the industrial CPE device can also act as a management node to connect to industrial devices equipped only with stroboscopic short-range modules, enabling communication between these devices and the edge and cloud sides via its own 5G communication component. In addition, the industrial CPE device can also act as a management node to connect to other industrial CPE devices, enabling communication between these other industrial CPE devices and the edge and cloud sides via its own 5G communication component. It should be noted that industrial CPE devices, based on data acquisition, integrate technologies such as mobile edge computing and artificial intelligence. This enables PLC virtualization and edge computing on the industrial CPE device, allowing for location sensing and edge computing capabilities on industrial field equipment. Furthermore, the deployment of the PLC further enhances low-latency and high-reliability transmission services. Simultaneously, by integrating PLC virtualization and edge computing, the industrial CPE device can completely decouple the hard connection between the PLC and I / O drivers through PLC virtualization, supporting flexible connections and device mobility. It should also be noted that, in addition to PLC virtualization and edge computing, industrial CPE devices can be configured with other functions. The specific supported functions can be determined by actual needs, and this invention does not impose any special limitations.

[0050] Industrial equipment equipped only with a star-shaped short-range module cannot directly connect to a 5G DU or 5G AAU. It requires protocol conversion via an industrial CPE device to connect to the 5G DU or 5G AAU and then communicate with the edge and cloud sides. This industrial equipment with only a star-shaped short-range module can support functions such as I / O drive conversion, information acquisition, sensing and positioning, and edge computing. Similar to industrial CPE devices, industrial equipment equipped only with a star-shaped short-range module can also support other functions. The specific supported functions can be determined by actual needs, and this invention does not impose any special limitations.

[0051] 5G DU or 5G AAU is a front-end radio frequency transmission and reception unit decoupled from the base station's centralized unit (CU). It can be deployed on the edge as needed. Combining the characteristics of 5G and satellite-based short-range, low-latency, high-reliability, large-scale connectivity, and high bandwidth, it can achieve low-latency, high-reliability distribution of control signals, and the collection and transmission of massive amounts of field data. Simultaneously, using wireless transmission, it can support node mobility and seamless, rapid handover based on signal strength and task connection relationships.

[0052] Depend on Figure 2 It can be seen that the side includes MEC servers and 5G CU units, and in Figure 2 In the industrial wireless network system example shown, the MEC server and 5G CU unit are deployed centrally. When the MEC server and 5G CU unit are centrally deployed, shared computing resources enable edge-based centralized processing of communication protocols, cloud-based deployment of the main PLC, deployment of various industrial application apps, and edge computing. These industrial application apps include cloud-based AGVs, visual inspection, data acquisition, intelligent control, and inference decision-making.

[0053] Depend on Figure 2 It is understood that the cloud side consists of multiple factory cloud platforms or data centers. This allows various business systems that were originally deployed in a decentralized manner, such as Manufacturing Execution System (MES), Enterprise Resource Planning (ERP), and Customer Relationship Management (CRM), to be centrally deployed on the factory cloud platform or data center. Consequently, data generated by various networked devices and business processes can be aggregated in real time to the factory cloud platform / data center for analysis and decision-making.

[0054] Depend on Figure 3 As can be seen, from left to right on the terminal side, there are industrial equipment equipped only with 5G communication components, industrial CPE equipment, and industrial equipment equipped only with a star-flash short-range module. The top component is a 5G DU or 5G AAU. Among these, the industrial equipment equipped only with 5G communication components can support functions such as I / O drive conversion, information acquisition, sensing and positioning, and terminal-side computing, similar to the industrial CPE equipment. The specific functions supported can be determined by actual needs, and this invention does not impose any special limitations. The side side includes an MEC server and a 5G CU unit, and in... Figure 3 In the industrial wireless network system example shown, the MEC server and 5G CU unit are deployed in a distributed manner. In this distributed deployment, the MEC server and 5G CU unit are each allocated computing resources. The MEC's ​​computing resources enable cloud-based deployment of the main PLC, deployment of various industrial application apps, and edge computing; the 5G CU unit's computing resources handle communication protocol processing (UPF, GW-U, and virtualized BBU). The cloud side consists of multiple factory cloud platforms or data centers.

[0055] based on Figure 2 and Figure 3As demonstrated by the industrial wireless network system examples, both systems integrate communication, computing, sensing, and control capabilities, enabling technologies such as edge-cloud collaboration and distributed training and decision-making. They provide services such as ubiquitous access, sensing computing, and intelligent control decision-making, promoting the wider application of industrial large models and expert systems in the field of industrial control and achieving intelligent upgrades in industrial control.

[0056] In this context, edge-cloud collaboration refers to the ability of computing tasks in an industrial wireless network system to be collaboratively performed by the edge, device, and cloud sides through computation offloading. For example, an autonomous vehicle on the edge needs to collect information from its onboard cameras, determine if there are obstacles ahead, and then plan its path. This process can be considered a computing task. Due to the limited computing power of industrial equipment, this task needs to be divided. Some of the computing tasks are performed on the industrial equipment or edge side, while others are performed on the edge or cloud side. For path planning, operations such as emergency stops and braking related to obstacle detection can be assigned to the industrial equipment or edge side. Computations involving overall path planning, which require scheduling the paths of multiple vehicles from a global perspective, should be assigned to the cloud side.

[0057] Distributed training and decision-making indicate that industrial wireless network systems can deploy training or decision-making tasks on a relatively centralized node, and then distribute them to multiple nodes within its coverage area to perform distributed decision-making training using local data. For example, training or decision-making tasks can be deployed on an edge-side MEC server, with unmanned vehicles and CPE devices within its coverage area (edge ​​side) performing distributed training and decision-making. For instance, in obstacle recognition by unmanned vehicles, the recognition algorithm is based on machine learning, requiring neural network training first. However, the information collected by a single unmanned vehicle (industrial equipment) is limited. Therefore, multiple vehicles can collaborate on distributed training, and then the local model parameters trained on each unmanned vehicle are uploaded to the 5G CU for aggregation. The 5G CU then aggregates the data and distributes the complete neural network model back to the unmanned vehicles.

[0058] Based on the aforementioned industrial network system, this invention also provides a method for executing computational tasks, the method comprising: step S1, obtaining a computational task to be executed; and step S2, executing the computational task using the system described in the foregoing embodiments to obtain the task execution result. It should be noted that the industrial network system can customize computational tasks according to actual needs, such as data acquisition tasks, path planning tasks, obstacle recognition tasks, temperature monitoring tasks, etc., and this invention does not impose any special limitations.

[0059] The beneficial effects of the present invention are: (1) Combining the characteristics of 5G wide-area coverage and Star Flash short-range communication, comprehensive wireless connection of industrial equipment is realized; (2) By introducing industrial equipment equipped with Star Flash short-range module and 5G communication components, the integration of 5G and Star Flash networks can be realized at the top, and large-scale wireless connection of industrial field equipment can be realized at low cost at the bottom.

[0060] It should be noted that although the steps are described in a specific order above, it does not mean that the steps must be executed in the above specific order. In fact, some of these steps can be executed concurrently, or even in a different order, as long as the required function can be achieved.

[0061] This invention can be a system, method, and / or computer program product. A computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for causing a processor to implement various aspects of the invention.

[0062] Computer-readable storage media can be tangible devices that hold and store instructions for use by an instruction execution device. Computer-readable storage media can be, for example, including but not limited to, electrical storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or recessed protrusions storing instructions thereon, and any suitable combination thereof.

[0063] The various embodiments of the present invention have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or technical improvements to the embodiments in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. An industrial wireless network system integrating 5G and Starlink short-range technology, characterized in that, The system includes end-side, edge-side, and cloud-side components, wherein: The edge side includes multiple industrial devices and multiple 5G communication units. Each industrial device is equipped with a StarSignal short-range module, and some industrial devices are also equipped with 5G communication components. Industrial devices equipped with both 5G communication components and StarSignal short-range modules connect to the 5G communication unit via the 5G communication components, or connect to other industrial devices equipped with both 5G communication components and StarSignal short-range modules via the StarSignal short-range module to achieve connection with the 5G communication unit. Industrial devices equipped only with StarSignal short-range modules connect to other industrial devices equipped with both 5G communication components and StarSignal short-range modules via the StarSignal short-range module to achieve connection with the 5G communication unit. Each 5G communication unit is used to enable communication between the connected industrial device and the edge side or cloud side. The edge side includes a 5G CU unit and an edge computing server. The 5G CU unit is used to receive data from the terminal side and the cloud side, and to forward data transmitted from itself and the cloud side to the terminal side. The edge computing server is used to perform edge computing tasks based on the data received by the 5G CU unit. The cloud side includes a cloud platform or a data center, wherein the cloud platform or data center is used to receive and store data transmitted from the end side and the edge side, and to perform data analysis based on the received data; The industrial wireless network system coordinates the execution of computing tasks on the end side, edge side, and cloud side in a computing offloading manner. The computing offloading manner is as follows: based on the characteristics of the computing task, the task is divided into local computing task, edge computing task, and / or cloud computing task, and the local computing task after task division is assigned to the end side for execution, the edge computing task is assigned to the edge side for execution, and the cloud computing task is assigned to the cloud side for execution.

2. The system according to claim 1, characterized in that, Multiple 5G communication units include multiple 5G base station distributed units and / or multiple active antenna units.

3. The system according to claim 2, characterized in that, The edge computing servers and 5G CU units in the edge are deployed in a centralized manner, which means that the edge computing servers and 5G CU units share computing resources in the edge.

4. The system according to claim 2, characterized in that, The edge computing servers and 5G CU units in the edge are deployed in a distributed manner, wherein the distributed deployment means that the edge computing servers and 5G CU units are each configured with corresponding computing resources in the edge.

5. The system according to claim 3 or 4, characterized in that, The terminal side also includes multiple industrial devices equipped only with 5G communication components.

6. A method for executing a computational task, characterized in that, The method includes: Step S1: Obtain the computation task to be executed; Step S2: Execute the task to be calculated using the system described in any one of claims 1-5 to obtain the task execution result.

7. A computer-readable storage medium, characterized in that, It stores a computer program that can be executed by a processor to implement the steps of the method of claim 6.

8. An electronic device, characterized in that, include: One or more processors, and Memory, wherein the memory is used to store executable instructions; The one or more processors are configured to implement the steps of the method of claim 6 by executing the executable instructions.

Images