Internet of Things equipment intelligent management platform based on edge computing

Abstract

The invention relates to an Internet of Things equipment intelligent management platform based on edge computing, and aims to realize efficient and intelligent management of Internet of Things equipment through an edge computing technology. According to the platform, the edge nodes are deployed near the data source, so that local processing and storage of the data are realized, the data transmission delay is remarkably reduced, and the response speed of the system is improved. And the platform is provided with an intelligent management module, so that the equipment state can be monitored in real time, faults can be predicted, repair operation can be automatically executed, and the stability and reliability of the system are enhanced. And a self-adaptive data stream processing algorithm is adopted, and the data stream is dynamically adjusted according to a real-time network state and equipment requirements, so that the high efficiency of data processing is ensured. The secure transmission module protects the data transmission process through an end-to-end encryption technology, and prevents data leakage and tampering. The cloud-side collaborative resource scheduling system realizes optimal allocation of resources, and a user-defined rule engine provides high flexibility and personalized management strategies to meet different user requirements.

Description

Technical Field

[0001] The present invention belongs to the technical field of Internet of Things, and in particular refers to an intelligent management platform integrating edge computing technology. Background Art

[0002] In the traditional Internet of Things (IoT) architecture, data is usually collected by various sensors and devices and then transmitted to a central server or cloud platform for processing and analysis. Although this centralized processing model is effective in some cases, it faces a series of challenges with the exponential growth of IoT devices and the diversification of application scenarios, including network bandwidth limitations, data transmission delays, computing pressure on central servers, and insufficient response to application scenarios with high real-time requirements.

[0003] As data privacy and security awareness increases, sending all data to the cloud for processing may lead to privacy leaks and security risks. Therefore, a new technical architecture is needed that can process data near the source of data generation, reduce dependence on central servers, and improve the efficiency and security of data processing.

[0004] Edge computing technology has emerged as the times require. It deploys computing resources at the edge of the network to make data processing closer to the data source, thereby reducing data transmission delays, improving system response speed, and reducing the load on central servers. However, existing edge computing solutions often lack a unified platform to achieve intelligent management and automated processing of IoT devices, especially in increasingly diverse and complex application scenarios.

[0005] In order to solve the above problems, the present invention proposes an IoT device intelligent management platform based on edge computing, which can not only realize localized data processing, but also provide intelligent equipment management, automated fault prediction and maintenance, and user-defined data processing rules and other functions to meet the needs of modern IoT applications for efficient, secure and intelligent management.

[0006] Technical Solution

[0007] The present invention provides an IoT device intelligent management platform based on edge computing, which aims to solve the shortcomings of the traditional centralized IoT architecture in handling large-scale, high-speed, and low-latency requirements. This platform is implemented through the following technical solutions:

[0008] The edge node deployment is first carefully selected in the near-field environment of the IoT device, such as factory workshops, warehouses, smart buildings and other key areas, to maximize the efficiency and coverage of data collection. Each edge node is equipped with at least a multi-core processor of 2.4GHz or more and a RAM of 16GB or more to support complex data processing tasks, and is equipped with at least 1TB of solid-state drive (SSD) for fast data storage and access. In terms of network connection, we ensure that each node communicates with the IoT device stably and in real time through a wired (such as Ethernet) or wireless (such as Wi-Fi or 4G / 5G) network, and the bandwidth of the network connection is at least 100Mbps to meet the transmission requirements of large amounts of data. At the software level, the edge node is installed with an operating system optimized for edge computing, such as Linux or RTOS, and the necessary drivers and applications are deployed to support data collection, processing and storage. The data collection mechanism communicates with the IoT device through a predefined protocol or API to collect information such as device status, sensor data, etc. These data include but are not limited to environmental parameters such as temperature, humidity, pressure, or the working status and performance indicators of the device. After the data reaches the edge node, preliminary data cleaning and formatting are performed to ensure data consistency and accuracy, and preliminary data analysis is performed, such as calculating average values, detecting outliers, etc., to provide a basis for subsequent in-depth analysis. Through this carefully designed edge node deployment, we can ensure the efficient operation and data processing capabilities of the entire IoT device intelligent management platform, providing a solid foundation for intelligent management and automated decision-making.

[0009] The intelligent management module integrates advanced machine learning algorithms on each edge node, which can analyze the device status in real time and predict potential failures. Specifically, the module realizes real-time monitoring of the device's operating status by continuously monitoring the key performance indicators of the device, such as CPU usage, memory usage, disk I / O performance, and network connection status. Using historical data and real-time data, the intelligent management module can predict possible failures of the device and automatically perform maintenance tasks, such as restarting services, updating system configurations, or restoring the system to a stable state. In addition, the module allows users to customize maintenance strategies based on device types and usage scenarios, and provides viewing functions for device status, maintenance logs, and system notifications through the user interface. At the same time, fault warnings and status updates of maintenance activities are sent to users via email, SMS, or in-app notifications. The results and effects of maintenance activities will be fed back to the machine learning model, forming a continuous optimization cycle to continuously improve the accuracy of fault prediction and the effectiveness of maintenance strategies. Such intelligent management not only improves the stability and reliability of device operation, but also significantly improves the management efficiency of the entire Internet of Things system.

[0010] The adaptive data flow processing is a key technology to ensure data processing efficiency and response speed. This mechanism dynamically adjusts the flow direction and processing strategy of data by monitoring the type, size, priority, and network status (such as bandwidth, delay, and packet loss rate) of data in real time. Specifically, the system first identifies the urgency and importance of data through predefined rules or learning algorithms, and then automatically determines whether the data is processed immediately at the edge node, cached and processed, or transmitted to the central server for in-depth analysis based on these parameters. For example, for high-priority data, the system will prioritize the allocation of more computing resources and bandwidth to ensure its rapid processing; while for low-priority data, delayed processing may be used or transmitted when network conditions are good. In addition, the system will intelligently select the optimal data transmission path and processing method based on the real-time status of the network, such as the current bandwidth [B(t)], delay [L(t)], and packet loss rate [P(t)]. Through this adaptive mechanism, key data can be given priority processing, thereby greatly improving the response speed and operation efficiency of the entire system while ensuring the quality of data processing. This dynamic adjustment strategy not only optimizes the management of data flow, but also improves the efficiency of resource utilization, ensuring the best data processing effect under various network conditions.

[0011] The secure transmission guarantee is achieved by implementing end-to-end data encryption technology to ensure that the data is not intercepted or tampered with during transmission from the source device to the target device or server. Specifically, the data is encrypted by an encryption algorithm when leaving the source device, such as using the AES-256 standard to generate an encryption key [K], which is only shared between the sender and the receiver. During the data transmission process, no intermediate node or potential attacker can read its content, thereby ensuring the confidentiality of the data. After arriving at the target node, the receiver uses the same key [K] to decrypt the data and restore the original data. To further enhance security, the system also implements authentication and access control mechanisms. The authentication mechanism ensures that only authenticated users or devices can initiate data transmission requests, which is usually implemented by username and password, digital certificate or biometric technology. The access control mechanism defines which users or devices have the permission to read, write or execute the data, and is implemented through methods such as access control list (ACL) or role-based access control (RBAC). For example, only users with corresponding permissions can access sensitive data, while ordinary users are restricted from access. The system also regularly updates and manages encryption keys to prevent security risks caused by key leakage. Through these measures, the platform not only ensures the security of data during transmission, but also prevents unauthorized access through identity authentication and access control mechanisms, ensuring the integrity and confidentiality of data, thereby providing a safe and reliable data transmission environment for intelligent management of IoT devices.

[0012] The resource scheduling system monitors the resource usage of edge nodes in real time, such as CPU usage, memory usage, storage space and network bandwidth, and uses machine learning algorithms to dynamically adjust task allocation to optimize the load balancing and energy efficiency of computing tasks. Specifically, the system first summarizes the monitoring data through the formula Resource Usage = {CPU, Memory, Storage, Bandwidth}, and then uses intelligent algorithms such as the Yuchuan algorithm or the Aoqun algorithm to dynamically adjust the task allocation according to the current resource usage and task requirements, and optimizes the objective function Objective = min (Load Imbalance, Energy Consumption), where Load Imbalance represents the load difference between different nodes, and Energy Consumption represents the overall energy consumption. The system can automatically allocate computing-intensive tasks to nodes with low CPU usage and data-intensive tasks to nodes with sufficient storage space, thereby achieving load balancing. At the same time, the system also considers energy consumption and may arrange high-energy consumption tasks during periods of low grid load to reduce electricity costs. In addition, the system can make adaptive adjustments based on real-time feedback, optimize scheduling strategies, and avoid resource overload. Although it mainly relies on automated algorithms, the system also provides an interface for user intervention, allowing users to manually adjust the priority of tasks or specify the execution nodes of tasks according to specific needs, so as to achieve more flexible resource management. Through this comprehensive resource scheduling strategy, the platform can achieve efficient resource utilization, optimize the load balancing of computing tasks, and improve energy efficiency, providing a stable, efficient, and energy-saving operating environment for the intelligent management of IoT devices.

[0013] The user-defined rule engine gives users great flexibility and control. The engine allows users to customize data processing logic and automated tasks according to specific business needs through an intuitive graphical interface or programmatically using an API interface. Specifically, users can define a series of rules and conditions, for example, when the temperature detected by the sensor exceeds the preset threshold Tmax, the system automatically triggers the start of the cooling system; or when the operating status indicator of the equipment drops to a certain level, a maintenance reminder is automatically sent. These rules can include complex logical judgments, data filtering, conversion and aggregation operations, as well as interactions with other systems or services. Users can also set up automated tasks, such as regular data backups, system performance monitoring report generation, or device restarts under specific conditions. These tasks can be executed according to time schedules or event triggers, greatly improving the degree of automation of business processes. To further enhance the user experience, the rule engine also provides a wealth of templates and examples to help users quickly get started and build their own rules and tasks. In addition, the system also provides debugging and testing tools to enable users to verify the correctness and effectiveness of rules and tasks before actual deployment. Through this user-defined rules engine, users can not only achieve personalized business process automation, but also ensure that these automated processes are closely aligned with their business goals and workflows, thereby improving operational efficiency and responsiveness, reducing human errors, and ultimately achieving smarter and more efficient IoT device management.

[0014] The implementation method of the platform includes the following steps:

[0015] s1,Deploy edge nodes near IoT devices to ensure instant data processing and low-latency response.

[0016] s2, develop intelligent management modules, integrate advanced diagnostic tools and maintenance strategies to achieve continuous and healthy operation of equipment.

[0017] s3, design adaptive data stream processing algorithms to achieve intelligent classification, priority sorting and flow control of data.

[0018] s4, implements a security-enhanced data transmission mechanism and adopts end-to-end encryption technology to ensure the security and integrity of data during transmission.

[0019] s5, builds a cloud-edge collaborative resource scheduling system, performs global optimization in the cloud and allocates resources of edge nodes to achieve efficient resource utilization and rapid response to tasks.

[0020] s6, provides a user-defined rule engine, allowing users to define data processing logic through a graphical interface or programming interface to achieve personalized business process automation.

[0021] The edge computing node devices are designed for efficient data processing and instant response. They are equipped with high-performance multi-core processors with a main frequency of at least 2.4GHz to ensure that complex computing tasks can be processed quickly. Each node is equipped with a large-capacity solid-state drive (SSD) of at least 1TB, which not only provides sufficient data storage space, but also significantly improves the data access speed due to its low latency characteristics. In terms of communication, the node device integrates a high-speed Ethernet port, a Wi-Fi module, and a 4G / 5G wireless communication module, supporting a transmission rate of at least 100Mbps, ensuring the stability and flexibility of data transmission. In addition, the device also has a wealth of I / O interfaces, such as USB ports, HDMI interfaces, and serial ports, which are convenient for connection and data exchange with other devices or sensors. In order to improve the reliability and stability of the system, the edge computing node device also has an advanced power management system that supports a wide range of power input and overload protection. At the same time, good heat dissipation design, such as an efficient heat sink and fan system, keeps the processor and other key components working at a suitable temperature to avoid performance degradation or equipment damage caused by overheating. These designs enable edge computing node devices to cope with high-load data processing tasks and achieve high-speed data exchange in various network environments, providing strong hardware support for the intelligent management platform of IoT devices.

[0022] The intelligent management platform software includes an operating system, middleware, application program and user interface optimized for edge computing. The operating system is the foundation of the entire platform, providing underlying resource management and scheduling functions, supporting multiple hardware platforms and communication protocols, and ensuring the stability and compatibility of the system. The middleware layer provides the capabilities of device connection, data exchange and application services, and enables seamless integration and collaboration of different devices and applications through standardized interfaces and protocols. The application layer includes an intelligent management module, an adaptive data stream processing unit, a secure transmission module and a resource scheduling system. These applications use advanced algorithms and strategies to achieve real-time monitoring, fault prediction, data protection and resource optimization of equipment. The user interface layer provides an intuitive and easy-to-use interactive environment that allows users to customize and manage their IoT devices through a graphical interface or API interface, including device configuration, status monitoring, data analysis and automated task setting. In addition, the software also provides rich documentation and development tools, supports secondary development and function expansion, and enables users to customize and expand platform functions according to specific needs. Through this multi-level and modular design, the intelligent management platform software can not only realize all the functions of the present invention, but also adapt to changing business needs and technological developments, providing users with a flexible and scalable IoT device management solution.

[0023] The above technical solution can bring the following three significant technical effects:

[0024] 1. Significantly reduce data processing latency: By deploying edge nodes near the data source, data can be processed and analyzed instantly. This localized processing mechanism reduces the time it takes to transmit data to the central server, thereby significantly reducing data processing latency. Specifically, edge nodes can process data immediately after receiving it, without waiting for the data to be transmitted to the remote server, thereby reducing the response time from hundreds of milliseconds to milliseconds, greatly improving the system's response speed to application scenarios with high real-time requirements.

[0025] 2. Significantly improve system security: End-to-end encryption technology is used to ensure the security of data during transmission. In specific implementation, data is encrypted when it leaves the source device and is only decrypted when it reaches the target edge node or central server. This process not only prevents data from being intercepted and tampered with during transmission, but also ensures that only authorized recipients can access data content through the secure management mechanism of encryption keys. In addition, by implementing a secure transmission module, the system can automatically detect and defend against potential network attacks, thereby enhancing the security protection capabilities of the entire IoT system.

[0026] 3. Optimize resource utilization and energy efficiency: The intelligent resource scheduling system dynamically adjusts task allocation according to the real-time load, optimizing the use of computing resources. During the implementation process, the system is able to monitor the CPU, memory, and storage resource usage of edge nodes in real time, and intelligently allocate resources based on current computing needs and task priorities. For example, when the CPU usage of an edge node exceeds the preset threshold, the system will automatically transfer part of the computing tasks to other nodes to achieve load balancing. This dynamic resource scheduling not only improves the utilization efficiency of resources, but also reduces energy consumption and reduces operating costs. Specific data shows that through intelligent scheduling, resource utilization has increased by at least 30%, while energy consumption has decreased by more than 20%. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 This is a schematic diagram of the intelligent management platform module of the present invention

[0028] Figure 2 This is a step diagram of the management platform implementation method of the present invention DETAILED DESCRIPTION

[0029] The following will be combined with the attached embodiment of the present invention Figure 1 and Figure 2 , the technical solutions in the embodiments of the present invention are clearly and completely described. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. 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.

[0030] The IoT device intelligent management platform of the present invention is implemented through the following specific implementation methods:

[0031] Edge node deployment: Edge nodes are deployed in areas with dense IoT devices. Each node is equipped with at least a 2.4GHz quad-core processor, 16GB DDR4 memory, and 1TB SSD storage. It communicates with the central server via a 100Mbps Ethernet connection or 4G / 5G wireless network to ensure the stability and real-time nature of data transmission.

[0032] Intelligent management module development: Integrate intelligent management software on edge nodes, use random forest algorithm for fault prediction, and set the accuracy target to no less than 85%. Real-time monitoring of device status, such as CPU usage, memory usage, etc., automatically triggers maintenance tasks.

[0033] Adaptive data stream processing unit implementation: Dynamically adjust data flow and processing strategy according to data type, size and priority. Prioritize critical data (such as real-time surveillance video) and postpone non-critical data (such as log files). Real-time monitoring of network status to ensure optimal data transmission.

[0034] Integration of secure transmission module: Data is encrypted using the AES-256 encryption standard during transmission, and the key update cycle is set to once every 24 hours. The security of data transmission is verified through simulated attack tests to ensure that the data leakage rate is less than 0.1%.

[0035] Resource scheduling system construction: The resource scheduling system uses intelligent algorithms to monitor the resource usage of edge nodes, such as CPU usage, memory usage, etc. It dynamically adjusts task allocation according to real-time load and optimizes the objective function.

[0036] The user-defined rule engine provides: a visual programming interface and API interface, allowing users to define data processing logic and automated tasks. After the user-defined rules pass the test, they are automatically deployed to the edge node, and the execution results are fed back to the user interface.

[0037] Implementation steps:

[0038] s1: Deploy edge nodes and test that data transmission latency is reduced to less than 10ms.

[0039] s2: Develop intelligent management modules, integrate fault prediction algorithms, and achieve 85% fault prediction accuracy.

[0040] s3: Design adaptive data stream processing algorithms to optimize data transmission paths and improve data transmission efficiency.

[0041] s4: Implements a security-enhanced data transmission mechanism and ensures data security through AES-256 encryption.

[0042] s5: Build a cloud-edge collaborative resource scheduling system to achieve optimal allocation and scheduling of resources.

[0043] s6: Provides a user-defined rule engine, allowing users to customize data processing processes according to their needs.

[0044] Computer-readable storage medium: Create a storage medium containing a computer program for the above implementation method, such as a USB flash drive, to ensure that the edge node can load and execute the program.

[0045] Edge computing node device: The device includes at least one high-performance processor and large-capacity memory, as well as a communication interface that supports multiple communication protocols to ensure efficient data exchange with IoT devices.

[0046] Intelligent management platform software: The software includes an operating system, middleware, application programs, and a user interface to implement the comprehensive functions of the present invention, and has been tested through actual deployment to verify the stability and reliability of the software.

[0047] Through the above implementation modes, the present invention not only provides an efficient, safe and intelligent IoT device management solution, but also proves its technological advancement and practicality through actual parameter setting and result verification.

[0048] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and descriptions are only preferred examples of the present invention and are not intended to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. An IoT device intelligent management platform based on edge computing, characterized in that: include: Edge nodes, which have high-speed processors and large-capacity memory, are used to realize real-time data processing, analysis and storage of IoT devices; Intelligent management module, integrating machine learning algorithms, for real-time monitoring of equipment status, automatic diagnosis of system anomalies, prediction of equipment failures and execution of preventive maintenance; Adaptive data flow processing unit, using advanced data identification technology to dynamically adjust data flow and processing strategies according to data type, size and priority; The secure transmission module adopts the industry-leading encryption standards to protect the integrity and confidentiality of data during transmission; Resource scheduling system, which optimizes resource allocation through intelligent algorithms to achieve load balancing of computing tasks and optimize energy efficiency; The user-defined rule engine provides a visual programming interface and API interface, allowing users to customize data processing and response rules according to specific needs; specifically, each edge node is equipped with a high-speed processor and a large-capacity memory. These hardware resources provide strong support for real-time data processing, analysis and storage. The intelligent management module integrates machine learning algorithms to monitor the status of equipment in real time, automatically diagnose system anomalies, predict equipment failures, perform preventive maintenance, and ensure the stability and reliability of equipment operation. The adaptive data flow processing unit adopts advanced data recognition technology to dynamically adjust the data flow direction and processing strategy according to the data type, size and priority, and optimize the management and transmission efficiency of data flow. The secure transmission module adopts Industry-leading encryption standards such as AES-256 are used to ensure the integrity and confidentiality of data during transmission and prevent data leakage and tampering. The resource scheduling system uses intelligent algorithms to monitor and analyze the resource usage of edge nodes in real time, optimize resource allocation, achieve load balancing and energy efficiency optimization of computing tasks, and reduce the overall energy consumption of the system. The user-defined rule engine provides a visual programming interface and API interface, allowing users to customize data processing and response rules according to specific needs, increasing the flexibility and scalability of the system. Through this design, edge nodes can not only independently complete local data processing tasks, but also effectively communicate with central servers and other edge nodes to form a complete IoT device intelligent management network.

2. The platform according to claim 1, characterized in that The intelligent management module can analyze the historical operation data and real-time status of the equipment, use statistical models and pattern recognition technology, predict potential failures and automatically perform repair operations, including but not limited to restarting services, updating configurations and restoring backups.

3. The platform according to claim 1, characterized in that: The adaptive data stream processing unit can monitor the network status in real time, including bandwidth, delay and packet loss rate, and intelligently select the optimal data transmission path and processing strategy to ensure efficient processing and stable transmission of data.

4. The platform according to claim 1, characterized in that The secure transmission module not only includes data encryption function, but also has identity authentication, access control and security audit mechanism, forming a comprehensive data security protection system.

5. The platform according to claim 1, characterized in that: The resource scheduling system can monitor the resource usage of edge nodes in real time, including CPU, memory and storage resources, and dynamically adjust task allocation through intelligent algorithms to adapt to different computing needs and optimize resource utilization.

6. The platform according to claim 1, characterized in that: The user-defined rule engine supports complex logic processing, including conditional judgment, loop control and event triggering. Users can flexibly define data processing processes and automated tasks according to business needs.

7. An implementation method based on the platform according to any one of claims 1 to 6, characterized in that: The following steps are involved: s1, deploy edge computing nodes near IoT devices to ensure instant data processing and low-latency response; s2, develop intelligent management modules, integrate advanced diagnostic tools and maintenance strategies to achieve continuous and healthy operation of equipment; s3, design adaptive data stream processing algorithms to achieve intelligent classification, priority sorting and flow control of data; s4, implements a security-enhanced data transmission mechanism, using end-to-end encryption technology to ensure the security and integrity of data during transmission; s5, build a cloud-edge collaborative resource scheduling system, perform global optimization on the cloud and allocate resources to edge nodes to achieve efficient resource utilization and rapid task response; s6, provides a user-defined rule engine, allowing users to define data processing logic through a graphical interface or programming interface to achieve personalized business process automation.

8. A computer-readable storage medium having a computer program stored thereon, the program being configured to execute the implementation method of claim 7, characterized in that: The storage medium may be an optical disk, a hard disk, a solid state disk, a USB flash drive, or other types of storage devices.

9. An edge computing node device, characterized in that: include: At least one high-performance processor for performing complex data processing tasks; at least one high-capacity memory for storing the operating system, applications, and temporary data; At least one high-speed communication interface that supports wired and wireless communication protocols for high-speed data exchange with IoT devices and central servers.

10. A software for an intelligent management platform for Internet of Things devices, characterized in that: It includes a software module for implementing the platform function described in any one of claims 1 to 6, and the software module includes but is not limited to: an operating system for managing and coordinating hardware resources; Middleware, used to implement communication and data exchange between applications; applications, used to perform specific data processing and management tasks; The user interface provides an interactive operating environment that allows users to configure and manage the platform.

Images