Industrial internet of things embedded edge computer system

Abstract

The invention discloses an industrial internet of things embedded edge computer system. The system comprises a data acquisition module which is responsible for acquiring data from various sensors and industrial equipment in real time; the data preprocessing module is responsible for preprocessing the collected original data; the edge calculation module is responsible for performing real-time data processing and analysis on edge equipment; the edge cloud collaboration platform is responsible for processing large-scale computing tasks and data storage requirements; the security protection module is responsible for integrating deep reinforcement learning and a mean field game theory so as to enhance the defense capability of the system to malicious programs and ensure that the industrial Internet of Things can safely and stably run in a complex and changeable environment; according to the invention, the security protection module integrates deep reinforcement learning and average field game theories, and through data interaction with the edge calculation module, the security protection module can monitor the operation state of the system in real time, and discover and cope with potential security threats in time.

Description

Technical Field

[0001] The present invention relates to the field of embedded edge computer technology, and in particular to an industrial Internet of Things embedded edge computer system. Background Art

[0002] The Industrial Internet of Things embedded edge computer system is an advanced computer system that integrates embedded systems and edge computing technologies. It is designed for the Industrial Internet of Things (IIoT) environment to improve data processing efficiency, reduce latency, and enhance the overall performance of the system. The Industrial Internet of Things embedded edge computer system embeds computing and data storage capabilities into the edge devices of the Industrial Internet of Things, which usually include sensors, actuators, controllers, etc. By processing and storing data at the edge level, the system can reduce the amount of data transmission, reduce network load, and improve the real-time and security of data processing.

[0003] In the existing technology, although edge computing improves data security, the distributed computing architecture also brings new security challenges. Issues such as the physical security and privacy protection of edge devices need to be better addressed to prevent malicious attacks and data leakage. Therefore, an industrial Internet of Things embedded edge computer system is proposed. Summary of the invention

[0004] The purpose of the present invention is to solve the shortcomings of the prior art that although edge computing improves data security, the distributed computing architecture also brings new security challenges. Issues such as the physical security and privacy protection of edge devices need to be better solved to prevent malicious attacks and data leakage, and an industrial Internet of Things embedded edge computer system is proposed.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] An industrial Internet of Things embedded edge computer system, comprising:

[0007] Data acquisition module: responsible for real-time data collection from various sensors and industrial equipment, such as temperature, pressure, vibration, etc.;

[0008] Data preprocessing module: responsible for cleaning, filtering, denoising and other preprocessing of the collected raw data to improve data quality;

[0009] Edge computing module: responsible for real-time data processing and analysis on edge devices;

[0010] Edge cloud collaboration platform: responsible for handling large-scale computing tasks and data storage needs;

[0011] Decision-making and control module: responsible for formulating and executing corresponding control strategies based on the analysis results of the edge computing module;

[0012] Intelligent resource scheduler: responsible for dynamically allocating and optimizing computing resources based on system load and computing requirements;

[0013] Security protection module: It integrates deep reinforcement learning and mean field game theory to enhance the system's defense against malicious programs and ensure that the industrial Internet of Things can operate safely and stably in a complex and changing environment;

[0014] Communication and interconnection module: responsible for the communication and interconnection between modules within the system and between the system and external networks;

[0015] The data acquisition module provides the original collected data to the data preprocessing module, and the data preprocessing module provides the preprocessed data to the edge computing module. The edge computing module works closely with the edge cloud collaboration platform to achieve sharing and complementarity of computing resources and storage resources through the cloud-edge collaboration mechanism. The intelligent resource scheduler interacts with the edge computing module to obtain real-time computing load, task queue length, and resource utilization. Based on this information, the intelligent resource scheduler dynamically adjusts the amount of resources allocated to the edge computing module to ensure that key tasks are given priority while avoiding waste of resources. The edge computing module provides analysis results to the decision-making and control module, the edge computing module interacts with the security protection module for data, and the decision-making and control module sends control commands to the device control layer.

[0016] The above technical solution further includes:

[0017] Furthermore, the data acquisition module includes a sensor unit, a data acquisition module, a signal conditioning unit, a data processing unit and a communication interface unit. The sensor unit includes a temperature sensor, a pressure sensor, a vibration sensor, etc., which is used to monitor the operating status and environmental parameters of the equipment. The data acquisition module is responsible for reading data from the sensor and performing preliminary processing and conversion. The signal conditioning unit amplifies, filters, linearizes, etc. the signal output by the sensor to meet the input requirements of the data acquisition module. The data processing unit processes and analyzes the collected data, such as filtering, denoising, data fusion, etc. The communication interface unit provides a standardized communication interface, such as RS-485, CAN bus, Ethernet, etc., to realize communication between data acquisition modules. The sensor unit converts the monitored physical quantity into an electrical signal and outputs it to the data acquisition module through a standardized interface. The data acquisition module reads the signal output by the sensor through the interface and performs preliminary processing and conversion. The data acquisition module transmits the signal after preliminary processing to the signal conditioning unit, the signal conditioning unit transmits the processed signal to the data processing unit, and the data processing unit transmits the processed data to the communication interface unit.

[0018] Furthermore, the data preprocessing module includes a data cleaning unit, a filtering and denoising unit, a data compression unit, a data encoding unit and a feature selection and extraction unit. The data cleaning unit is responsible for data cleaning tasks, including removing duplicate data, filling missing values, processing abnormal values, etc. The filtering and denoising unit applies a filtering algorithm to denoise the data to improve the signal-to-noise ratio of the data. The data compression unit uses a data compression algorithm to compress the data to reduce the consumption of storage space. The data encoding unit encodes the compressed data to facilitate data storage and transmission. The feature selection and extraction unit extracts key features from the original data to prepare for subsequent analysis.

[0019] Furthermore, the edge computing module includes a data processing unit, an algorithm application unit, a decision support unit and a resource management unit. The data processing unit is responsible for performing specific data processing tasks, such as data parsing, format conversion, preliminary analysis, etc. The algorithm application unit integrates artificial intelligence algorithms such as machine learning and deep learning to perform in-depth analysis and mining of data. The decision support unit provides decision support functions based on the analysis results, such as early warning and control instruction generation. The resource management unit is responsible for the scheduling and management of computing resources to ensure the efficient execution of data processing tasks. The data processing unit receives data from the data preprocessing module and performs parsing and format conversion. The data processing unit passes the processed data to the algorithm application unit, and the algorithm application unit passes the analysis results to the decision support unit. The decision support unit sends a resource scheduling request to the resource management unit when necessary, and the resource management unit optimizes the allocation of computing resources according to the request to ensure the smooth progress of the data processing task.

[0020] Furthermore, the edge cloud collaborative platform includes a cloud unit, an edge cloud unit, a data transmission unit, an intelligent scheduling and management unit, and a security control unit. The cloud unit is responsible for large-scale data storage, complex computing task processing, global resource scheduling and management. The edge cloud unit is deployed on the edge node's computing and storage resources, responsible for processing low-latency, high-real-time computing tasks and data storage. The data transmission unit is responsible for data transmission between the cloud and the edge cloud, and between the edge cloud and the terminal device. The intelligent scheduling and management unit is responsible for intelligently scheduling and managing cloud-edge resources according to system load and resource conditions. The security control unit is responsible for establishing and maintaining secure data transmission. and storage mechanism to ensure data security. The cloud unit migrates part of the computing tasks and data to the edge cloud unit to reduce its own load and reduce latency. The edge cloud unit transmits the processing results or data to be processed back to the cloud unit for global analysis and optimization. The data transmission unit is responsible for transmitting the data generated by the terminal device to the edge cloud unit for processing. The data processed by the edge cloud unit is transmitted back to the terminal device or the cloud unit through the data transmission unit. The intelligent scheduling and management unit monitors the resource usage and load of the cloud and edge cloud in real time. According to the monitoring results, the intelligent scheduling and management unit dynamically adjusts resource allocation to ensure efficient operation of the system.

[0021] Furthermore, the decision and control module includes a data analysis unit, a strategy formulation unit, an execution control unit, and a monitoring and feedback unit. The data analysis unit receives the analysis results of the edge computing module, performs data processing and analysis, and provides data support for strategy formulation. The strategy formulation unit formulates a control strategy based on the data provided by the data analysis unit in combination with preset control logic and rules. The execution control unit is responsible for converting the control strategy formulated by the strategy formulation unit into specific control instructions and sending them to the industrial equipment for execution. The monitoring and feedback unit monitors the operating status of the industrial equipment and the execution of the production process in real time, and feeds back the monitoring results to the data analysis unit and the strategy formulation unit for dynamic adjustment and optimization.

[0022] Furthermore, the intelligent resource scheduler includes a resource monitoring unit, an intelligent resource scheduler unit and a container / virtual machine management unit. The resource monitoring unit is responsible for monitoring the resource usage of the edge device in real time and sending the monitoring data to the intelligent resource scheduler. The intelligent resource scheduler unit receives the data sent by the resource monitoring unit and performs resource allocation and optimization according to preset scheduling algorithms and strategies. The container / virtual machine management unit starts, stops or adjusts the number and configuration of containers / virtual machines according to the instructions of the intelligent resource scheduler. The container / virtual machine management unit manages the life cycle of containers / virtual machines to ensure that they can run and expand efficiently. The intelligent resource scheduler unit communicates with the edge computing module in real time to obtain computing load, task queue length and resource utilization. Based on this information, the intelligent resource scheduler unit dynamically adjusts the amount of resources allocated to the edge computing module to ensure that critical tasks are given priority and avoid waste of resources.

[0023] Furthermore, the security protection module includes a data encryption unit, an access control unit, an intrusion detection unit, a threat defense unit, a strategy optimization unit and a game analysis unit. The data encryption unit is responsible for encrypting and decrypting sensitive data. The access control unit implements access control policies and manages user permissions and authentication information. The intrusion detection unit monitors and detects network intrusions and malicious attacks in real time. The threat defense unit executes corresponding defense measures based on the intrusion detection results. The strategy optimization unit continuously optimizes and adjusts security policies based on learning algorithms to improve defense capabilities. The game analysis unit uses mean field game theory to perform strategy game analysis and formulate optimal defense strategies.

[0024] Furthermore, the game analysis unit formulates an optimal defense strategy, specifically the following steps:

[0025] Model establishment: Establish the strategy space of the attacker and the defender. Assume that the strategy space of the attacker is A and the strategy space of the defender is D. Define the payment function of the game. For the attacker, the goal is to maximize its own benefits (such as the benefits after a successful invasion), while the goal of the defender is to minimize the attacker's benefits (that is, to improve its own security). Therefore, set a payment function u(a, d), where a∈A, d∈D, which represents the payment when the attacker chooses strategy a and the defender chooses strategy d;

[0026] Application of mean field game theory: In mean field games, it is assumed that the number of participants is very large, so that the impact of each participant's behavior on other participants is approximately an average value. A probability distribution function p(a) is introduced to represent the probability that the attacker chooses strategy a, and q(d) is introduced to represent the probability that the defender chooses strategy d. According to mean field game theory, the optimal strategy of each participant should maximize its expected payoff:

[0027] Attacker:

[0028] Defender:

[0029] Solving the optimal strategy: By solving the above optimization problem, we can obtain the optimal strategy distribution p of the attacker and the defender. * (a) and q * (d);

[0030] Develop a defensive strategy:

[0031] According to the optimal strategy distribution q obtained by solving * (d) Develop the best defense strategy, which includes adjusting security configuration, updating security patches, strengthening monitoring and other measures.

[0032] The present invention has the following beneficial effects:

[0033] 1. In the present invention, the close collaboration between the edge cloud collaboration platform and the edge computing module realizes the sharing and complementarity of computing resources and storage resources through the cloud-edge collaboration mechanism, effectively improving the resource utilization rate. The intelligent resource scheduler can dynamically adjust the amount of resources allocated to the edge computing module according to the real-time computing load, task queue length and resource utilization rate, ensuring that key tasks are given priority while avoiding waste of resources.

[0034] 2. In the present invention, the security protection module integrates deep reinforcement learning and mean field game theory. Through data interaction with the edge computing module, the security protection module can monitor the operating status of the system in real time, and promptly detect and respond to potential security threats.

[0035] 3. In the present invention, the decision-making and control module can formulate and execute corresponding control strategies according to the analysis results provided by the edge computing module. This decision-making method based on real-time data makes the control strategy more accurate and effective. By sending control commands to the device control layer, precise control of hardware such as industrial equipment and sensors is achieved, thereby improving the overall performance and efficiency of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 This is a system block diagram of an industrial Internet of Things embedded edge computer system proposed by the present invention. DETAILED DESCRIPTION

[0037] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0038] See also Figure 1 As shown, the present invention is an industrial Internet of Things embedded edge computer system, comprising:

[0039] Data acquisition module: responsible for real-time data collection from various sensors and industrial equipment, such as temperature, pressure, vibration, etc.;

[0040] Data preprocessing module: responsible for cleaning, filtering, denoising and other preprocessing of the collected raw data to improve data quality;

[0041] Edge computing module: responsible for real-time data processing and analysis on edge devices;

[0042] Edge cloud collaboration platform: responsible for handling large-scale computing tasks and data storage needs;

[0043] Decision-making and control module: responsible for formulating and executing corresponding control strategies based on the analysis results of the edge computing module;

[0044] Intelligent resource scheduler: responsible for dynamically allocating and optimizing computing resources based on system load and computing requirements;

[0045] Security protection module: It integrates deep reinforcement learning and mean field game theory to enhance the system's defense against malicious programs and ensure that the industrial Internet of Things can operate safely and stably in a complex and changing environment;

[0046] Communication and interconnection module: responsible for the communication and interconnection between modules within the system and between the system and external networks;

[0047] The data acquisition module provides the original collected data to the data preprocessing module, and the data preprocessing module provides the preprocessed data to the edge computing module. The edge computing module works closely with the edge cloud collaboration platform to achieve sharing and complementarity of computing resources and storage resources through the cloud-edge collaboration mechanism. The intelligent resource scheduler interacts with the edge computing module to obtain real-time computing load, task queue length, and resource utilization. Based on this information, the intelligent resource scheduler dynamically adjusts the amount of resources allocated to the edge computing module to ensure that key tasks are given priority while avoiding waste of resources. The edge computing module provides analysis results to the decision-making and control module, and the edge computing module interacts with the security protection module for data. The decision-making and control module sends control commands to the device control layer.

[0048] In one embodiment, for the above-mentioned data acquisition module, the data acquisition module includes a sensor unit, a data acquisition module, a signal conditioning unit, a data processing unit and a communication interface unit. The sensor unit includes a temperature sensor, a pressure sensor, a vibration sensor, etc., which is used to monitor the operating status and environmental parameters of the equipment. The data acquisition module is responsible for reading data from the sensor and performing preliminary processing and conversion. The signal conditioning unit amplifies, filters, linearizes, etc. the signal output by the sensor to meet the input requirements of the data acquisition module. The data processing unit processes and analyzes the collected data, such as filtering, denoising, data fusion, etc. The communication interface unit provides a standardized communication interface, such as RS-485, CAN bus, Ethernet, etc., to realize communication between the data acquisition module and the module. The sensor unit converts the monitored physical quantity into an electrical signal and outputs it to the data acquisition module through a standardized interface. The data acquisition module reads the signal output by the sensor through the interface and performs preliminary processing and conversion. The data acquisition module transmits the signal after preliminary processing to the signal conditioning unit, the signal conditioning unit transmits the processed signal to the data processing unit, and the data processing unit transmits the processed data to the communication interface unit.

[0049] In one embodiment, for the above-mentioned data preprocessing module, the data preprocessing module includes a data cleaning unit, a filtering and denoising unit, a data compression unit, a data encoding unit and a feature selection and extraction unit. The data cleaning unit is responsible for data cleaning tasks, including removing duplicate data, filling missing values, processing abnormal values, etc. The filtering and denoising unit applies a filtering algorithm to denoise the data to improve the signal-to-noise ratio of the data. The data compression unit uses a data compression algorithm to compress the data to reduce the consumption of storage space. The data encoding unit encodes the compressed data to facilitate data storage and transmission. The feature selection and extraction unit extracts key features from the original data to prepare for subsequent analysis.

[0050] In one embodiment, for the above-mentioned edge computing module, the edge computing module includes a data processing unit, an algorithm application unit, a decision support unit and a resource management unit. The data processing unit is responsible for performing specific data processing tasks, such as data parsing, format conversion, preliminary analysis, etc. The algorithm application unit integrates artificial intelligence algorithms such as machine learning and deep learning to conduct in-depth analysis and mining of data. The decision support unit provides decision support functions based on the analysis results, such as early warning, control instruction generation, etc. The resource management unit is responsible for the scheduling and management of computing resources to ensure the efficient execution of data processing tasks. The data processing unit receives data from the data preprocessing module and performs parsing and format conversion. The data processing unit passes the processed data to the algorithm application unit, and the algorithm application unit passes the analysis results to the decision support unit. The decision support unit sends a resource scheduling request to the resource management unit when necessary, and the resource management unit optimizes the allocation of computing resources according to the request to ensure the smooth progress of the data processing task.

[0051] In one embodiment, for the above-mentioned edge cloud collaboration platform, the edge cloud collaboration platform includes a cloud unit, an edge cloud unit, a data transmission unit, an intelligent scheduling and management unit, and a security control unit. The cloud unit is responsible for large-scale data storage, complex computing task processing, global resource scheduling and management. The edge cloud unit is deployed on the edge node computing and storage resources, responsible for processing low-latency, high-real-time computing tasks and data storage. The data transmission unit is responsible for data transmission between the cloud and the edge cloud, and between the edge cloud and the terminal device. The intelligent scheduling and management unit is responsible for intelligently scheduling and managing cloud-edge resources according to the system load and resource conditions. The security control unit is responsible for establishing and maintaining a secure data transmission and storage mechanism to ensure data security. The cloud unit migrates part of the computing tasks and data to the edge cloud unit to reduce its own load and reduce latency. The edge cloud unit transmits the processing results or data to be processed back to the cloud unit for global analysis and optimization. The data transmission unit is responsible for transmitting the data generated by the terminal device to the edge cloud unit for processing. The data processed by the edge cloud unit is transmitted back to the terminal device or the cloud unit through the data transmission unit. The intelligent scheduling and management unit monitors the resource usage and load of the cloud and edge cloud in real time. According to the monitoring results, the intelligent scheduling and management unit dynamically adjusts resource allocation to ensure efficient operation of the system.

[0052] In one embodiment, for the above-mentioned decision and control module, the decision and control module includes a data analysis unit, a strategy formulation unit, an execution control unit, and a monitoring and feedback unit. The data analysis unit receives the analysis results of the edge computing module, performs data processing and analysis, and provides data support for strategy formulation. The strategy formulation unit formulates a control strategy based on the data provided by the data analysis unit and in combination with preset control logic and rules. The execution control unit is responsible for converting the control strategy formulated by the strategy formulation unit into specific control instructions and sending them to the industrial equipment for execution. The monitoring and feedback unit monitors the operating status of the industrial equipment and the execution of the production process in real time, and feeds back the monitoring results to the data analysis unit and the strategy formulation unit for dynamic adjustment and optimization.

[0053] In one embodiment, for the above-mentioned intelligent resource scheduler, the intelligent resource scheduler includes a resource monitoring unit, an intelligent resource scheduler unit and a container / virtual machine management unit. The resource monitoring unit is responsible for monitoring the resource usage of the edge device in real time and sending the monitoring data to the intelligent resource scheduler. The intelligent resource scheduler unit receives the data sent by the resource monitoring unit and allocates and optimizes resources according to preset scheduling algorithms and strategies. The container / virtual machine management unit starts, stops or adjusts the number and configuration of containers / virtual machines according to the instructions of the intelligent resource scheduler. The container / virtual machine management unit manages the life cycle of containers / virtual machines to ensure that they can run and expand efficiently. The intelligent resource scheduler unit communicates with the edge computing module in real time to obtain the computing load, task queue length and resource utilization. Based on this information, the intelligent resource scheduler unit dynamically adjusts the amount of resources allocated to the edge computing module to ensure that critical tasks are given priority and avoid waste of resources.

[0054] In one embodiment, for the above-mentioned security protection module, the security protection module includes a data encryption unit, an access control unit, an intrusion detection unit, a threat defense unit, a policy optimization unit and a game analysis unit. The data encryption unit is responsible for encrypting and decrypting sensitive data. The access control unit implements access control policies and manages user permissions and authentication information. The intrusion detection unit monitors and detects network intrusions and malicious attacks in real time. The threat defense unit executes corresponding defense measures based on the intrusion detection results. The policy optimization unit continuously optimizes and adjusts security policies based on learning algorithms to improve defense capabilities. The game analysis unit uses mean field game theory to perform strategic game analysis and formulate optimal defense strategies.

[0055] In one embodiment, for the game analysis unit, the game analysis unit formulates an optimal defense strategy, specifically, the following steps:

[0056] Model establishment: Establish the strategy space of the attacker and the defender. Assume that the strategy space of the attacker is A and the strategy space of the defender is D. Define the payment function of the game. For the attacker, the goal is to maximize its own benefits (such as the benefits after a successful invasion), while the goal of the defender is to minimize the attacker's benefits (that is, to improve its own security). Therefore, set a payment function u(a, d), where a∈A, d∈D, which represents the payment when the attacker chooses strategy a and the defender chooses strategy d;

[0057] Application of mean field game theory: In mean field games, it is assumed that the number of participants is very large, so that the impact of each participant's behavior on other participants is approximately an average value. A probability distribution function p(a) is introduced to represent the probability that the attacker chooses strategy a, and q(d) is introduced to represent the probability that the defender chooses strategy d. According to mean field game theory, the optimal strategy of each participant should maximize its expected payoff:

[0058] Attacker:

[0059] Defender:

[0060] Solving the optimal strategy: By solving the above optimization problem, we can obtain the optimal strategy distribution p of the attacker and the defender. * (a) and q * (d);

[0061] Develop a defensive strategy:

[0062] According to the optimal strategy distribution q obtained by solving * (d) Develop the best defense strategy, which includes adjusting security configuration, updating security patches, strengthening monitoring, etc.

[0063] Assume that in a simple network security game, the attacker has two strategies: a1 (launch an attack) and a2 (do not launch an attack); the defender also has two strategies: d1 (strengthen protection) and d2 (do not strengthen protection). The payment function is defined as follows:

[0064] u(a,d)=-1(attacker fails, defender succeeds)

[0065] u(a,d)=1(attacker succeeds, defender fails)

[0066] u(a,d)=0 (neither party takes any action and maintains the status quo)

[0067] u(a,d)=0 (neither party takes any action and maintains the status quo)

[0068] Assuming that the probability that both the attacker and the defender choose the strategy is 0.5 (i.e., uniform distribution), the initial expected payoff is:

[0069] By solving the optimization problem, we can obtain the optimal strategy distribution. For example, if the probability of the defender strengthening the defense increases, the expected benefit of the attacker launching an attack will decrease, so the attacker may choose not to launch an attack, and vice versa.

[0070] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An industrial Internet of Things embedded edge computer system, characterized in that: include: Data acquisition module: responsible for real-time data collection from various sensors and industrial equipment; Data preprocessing module: responsible for preprocessing the collected raw data; Edge computing module: responsible for real-time data processing and analysis on edge devices; Edge cloud collaboration platform: responsible for handling large-scale computing tasks and data storage needs; Decision-making and control module: responsible for formulating and executing corresponding control strategies based on the analysis results of the edge computing module; Intelligent resource scheduler: responsible for dynamically allocating and optimizing computing resources based on system load and computing requirements; Security protection module: It integrates deep reinforcement learning and mean field game theory to enhance the system's defense against malicious programs and ensure that the industrial Internet of Things can operate safely and stably in a complex and changing environment; Communication and interconnection module: responsible for the communication and interconnection between modules within the system and between the system and external networks; The data acquisition module provides the original collected data to the data preprocessing module, and the data preprocessing module provides the preprocessed data to the edge computing module. The edge computing module works closely with the edge cloud collaboration platform to achieve sharing and complementarity of computing resources and storage resources through the cloud-edge collaboration mechanism. The intelligent resource scheduler interacts with the edge computing module to obtain real-time computing load, task queue length, and resource utilization. Based on this information, the intelligent resource scheduler dynamically adjusts the amount of resources allocated to the edge computing module to ensure that key tasks are given priority while avoiding waste of resources. The edge computing module provides analysis results to the decision-making and control module, the edge computing module interacts with the security protection module for data, and the decision-making and control module sends control commands to the device control layer.

2. The industrial Internet of Things embedded edge computer system according to claim 1, characterized in that: The data acquisition module includes a sensor unit, a data acquisition module, a signal conditioning unit, a data processing unit and a communication interface unit. The sensor unit is used to monitor the operating status and environmental parameters of the equipment. The data acquisition module is responsible for reading data from the sensor and performing preliminary processing and conversion. The signal conditioning unit processes the signal output by the sensor to meet the input requirements of the data acquisition module. The data processing unit processes and analyzes the collected data. The communication interface unit provides a standardized communication interface to realize communication between data acquisition modules. The sensor unit converts the monitored physical quantity into an electrical signal and outputs it to the data acquisition module through a standardized interface. The data acquisition module reads the signal output by the sensor through the interface and performs preliminary processing and conversion. The data acquisition module transmits the signal after preliminary processing to the signal conditioning unit, and the signal conditioning unit transmits the processed signal to the data processing unit, and the data processing unit transmits the processed data to the communication interface unit.

3. The industrial Internet of Things embedded edge computer system according to claim 2, characterized in that: The data preprocessing module includes a data cleaning unit, a filtering and denoising unit, a data compression unit, a data encoding unit and a feature selection and extraction unit. The data cleaning unit is responsible for data cleaning tasks, the filtering and denoising unit applies a filtering algorithm to denoise the data, the data compression unit uses a data compression algorithm to compress the data, the data encoding unit encodes the compressed data, and the feature selection and extraction unit extracts key features from the original data.

4. The industrial Internet of Things embedded edge computer system according to claim 3, characterized in that: The edge computing module includes a data processing unit, an algorithm application unit, a decision support unit and a resource management unit. The data processing unit is responsible for performing specific data processing tasks. The algorithm application unit integrates artificial intelligence algorithms to perform in-depth analysis and mining of data. The decision support unit provides decision support functions based on the analysis results. The resource management unit is responsible for the scheduling and management of computing resources. The data processing unit receives data from the data preprocessing module, and performs parsing and format conversion. The data processing unit passes the processed data to the algorithm application unit, and the algorithm application unit passes the analysis results to the decision support unit. The decision support unit sends a resource scheduling request to the resource management unit when necessary, and the resource management unit optimizes the allocation of computing resources according to the request.

5. The industrial Internet of Things embedded edge computer system according to claim 4, characterized in that: The edge cloud collaborative platform includes a cloud unit, an edge cloud unit, a data transmission unit, an intelligent scheduling and management unit, and a security control unit. The cloud unit is responsible for large-scale data storage, complex computing task processing, global resource scheduling and management. The edge cloud unit is responsible for processing low-latency, high-real-time computing tasks and data storage. The data transmission unit is responsible for data transmission between the cloud and the edge cloud, and between the edge cloud and the terminal device. The intelligent scheduling and management unit is responsible for intelligently scheduling and managing cloud-edge resources according to system load and resource conditions. The security control unit is responsible for establishing and maintaining a secure data transmission and storage mechanism. The cloud unit migrates part of the computing tasks and data to the edge cloud unit. The edge cloud unit transmits the processing results or data to be processed back to the cloud unit for global analysis and optimization. The data transmission unit is responsible for transmitting the data generated by the terminal device to the edge cloud unit for processing. The data processed by the edge cloud unit is transmitted back to the terminal device or the cloud unit through the data transmission unit. The intelligent scheduling and management unit monitors the resource usage and load conditions of the cloud and edge cloud in real time. According to the monitoring results, the intelligent scheduling and management unit dynamically adjusts resource allocation.

6. The industrial Internet of Things embedded edge computer system according to claim 1, characterized in that: The decision-making and control module includes a data analysis unit, a strategy formulation unit, an execution control unit and a monitoring and feedback unit. The data analysis unit receives the analysis results of the edge computing module and performs data processing and analysis. The strategy formulation unit formulates a control strategy based on the data provided by the data analysis unit in combination with preset control logic and rules. The execution control unit is responsible for converting the control strategy formulated by the strategy formulation unit into specific control instructions and sending them to the industrial equipment for execution. The monitoring and feedback unit monitors the operating status of the industrial equipment and the execution of the production process in real time, and feeds back the monitoring results to the data analysis unit and the strategy formulation unit.

7. The industrial Internet of Things embedded edge computer system according to claim 6, characterized in that: The intelligent resource scheduler includes a resource monitoring unit, an intelligent resource scheduler unit and a container / virtual machine management unit. The resource monitoring unit is responsible for monitoring the resource usage of the edge device in real time and sending the monitoring data to the intelligent resource scheduler. The intelligent resource scheduler unit receives the data sent by the resource monitoring unit and allocates and optimizes resources according to preset scheduling algorithms and strategies. The container / virtual machine management unit starts, stops or adjusts the number and configuration of containers / virtual machines according to the instructions of the intelligent resource scheduler. The container / virtual machine management unit manages the life cycle of containers / virtual machines. The intelligent resource scheduler unit communicates with the edge computing module in real time to obtain computing load, task queue length and resource utilization. Based on this information, the intelligent resource scheduler unit dynamically adjusts the amount of resources allocated to the edge computing module.

8. The industrial Internet of Things embedded edge computer system according to claim 7, characterized in that: The security protection module includes a data encryption unit, an access control unit, an intrusion detection unit, a threat defense unit, a strategy optimization unit and a game analysis unit. The data encryption unit is responsible for encrypting and decrypting sensitive data. The access control unit implements access control strategies and manages user permissions and authentication information. The intrusion detection unit monitors and detects network intrusions and malicious attacks in real time. The threat defense unit executes corresponding defense measures based on the intrusion detection results. The strategy optimization unit continuously optimizes and adjusts security strategies based on learning algorithms to improve defense capabilities. The game analysis unit uses mean field game theory to perform strategy game analysis and formulate optimal defense strategies.

9. The industrial Internet of Things embedded edge computer system according to claim 8, characterized in that: The game analysis unit formulates the optimal defense strategy, specifically the following steps: Model establishment: Establish the strategy space of the attacker and the defender. Assume that the strategy space of the attacker is A and the strategy space of the defender is D. Define the payment function of the game. For the attacker, the goal is to maximize its own benefits, while the goal of the defender is to minimize the attacker's benefits. Therefore, set a payment function u(a, d), where a∈A, d∈D, which represents the payment when the attacker chooses strategy a and the defender chooses strategy d; Application of mean field game theory: In mean field games, it is assumed that the number of participants is very large, so that the impact of each participant's behavior on other participants is approximately an average value. A probability distribution function p(a) is introduced to represent the probability that the attacker chooses strategy a, and q(d) is introduced to represent the probability that the defender chooses strategy d. According to mean field game theory, the optimal strategy of each participant should maximize its expected payoff: Attacker: Defender: Solving the optimal strategy: By solving the above optimization problem, we can obtain the optimal strategy distribution p of the attacker and the defender. * (a) and q * (d); Develop a defensive strategy: According to the optimal strategy distribution q obtained by solving * (d) Develop an optimal defense strategy.

Images