Internet of Things service quality management method and system based on adaptive flow optimization

Abstract

The invention relates to an internet of things quality of service (QoS) management method and system, and aims to solve the problem that the internet of things quality of service is unstable through a self-adaptive flow optimization technology. The system comprises a device identification module, a flow analysis module, a flow prediction module, a resource allocation module, a congestion control module, a safety guarantee module, a user feedback module and the like, predicts a flow trend by using a machine learning algorithm, dynamically adjusts resource allocation, and improves network efficiency and user experience. The method is suitable for various scales of Internet of Things environments, and is of great significance for promoting the development of the Internet of Things technology.

Description

Technical Field

[0001] The present invention relates to the field of Internet of Things (IoT) technology, and in particular to technologies and methods for IoT Quality of Service (QoS) management. Specifically, the present invention relates to an IoT QoS management method and system based on adaptive traffic optimization, which aims to improve the service stability and reliability of IoT devices and applications in a changing network environment through intelligent traffic analysis and resource allocation. The present invention is suitable for IoT environments where data transmission quality and efficiency need to be ensured, including various application scenarios such as smart homes, industrial automation, smart cities, and remote medical monitoring. By implementing the present invention, the problem of network congestion caused by the increase in the number of IoT devices can be effectively solved, the use of network resources can be optimized, the overall network performance can be improved, and the smooth operation of key services can be ensured. Background Art

[0002] With the rapid development of the Internet of Things (IoT), an increasing number of smart devices and sensors are being integrated into various networks, forming a vast and complex interconnected system. These devices are widely used in a variety of fields, including data collection, remote control, automated operation, and intelligent analysis, significantly enhancing the intelligence of our lives and work. However, the increasing diversity and number of IoT devices also pose unprecedented challenges to network management and quality of service (QoS). Traditional network QoS management methods typically employ static traffic control and resource allocation strategies. These strategies often lack the necessary flexibility and adaptability to the dynamically changing network traffic and diverse service demands of IoT environments. For example, services with high real-time requirements (such as video surveillance and remote control) have strict requirements on network latency and bandwidth, while large amounts of low-priority data transmission can consume valuable network resources, degrading the performance of critical services. Furthermore, network conditions in IoT environments are constantly changing, such as device mobility, network congestion, and wireless signal interference, all of which can affect service quality. Therefore, existing QoS management technologies need to be further improved to adapt to the unique requirements of IoT environments. There is a need for a QoS management method and system that can adaptively optimize network resource allocation, effectively handle different business traffic, ensure the quality of key business services, and improve the overall efficiency of the network. Summary of the Invention

[0003] In order to ensure the stability and reliability of service quality in the Internet of Things environment, the present invention proposes an Internet of Things Quality of Service (QoS) management method and system based on adaptive traffic optimization.

[0004] Device Identification and Classification: 1. Automatic Detection: Deploy intelligent detection scripts or programs at the network access layer to automatically identify new devices connecting to the network. 2. Device Classification: Based on information such as the device's MAC address, IP address, and port number, combined with a predefined device database, devices are classified as sensors, cameras, actuators, and so on. 3. Service Requirements Analysis: Analyze the data packets sent by devices to identify service types, such as real-time monitoring, data collection, or remote control, and define different QoS requirements for each service type. 4. QoS Parameter Allocation: Based on device type and service requirements, QoS parameters such as priority, bandwidth, and latency are dynamically allocated to each device and service type using pre-defined QoS parameter templates.

[0005] Traffic Characterization Analysis: 1. Traffic Monitoring: Deploy traffic monitoring tools such as NetFlow or sFlow to capture network traffic data in real time. 2. Feature Extraction: Analyze traffic data and extract key features, including packet size, transmission frequency, and protocol type. 3. Traffic Classification: Based on the extracted features, utilize a multi-dimensional traffic classification algorithm to classify traffic into high-priority traffic (such as VoIP and video streaming) and low-priority traffic (such as regular data transmission).

[0006] Adaptive Traffic Forecasting: 1. Historical Data Analysis: Collect and store historical traffic data to build a traffic forecasting model. 2. Model Building: Use time series analysis and machine learning algorithms, such as ARIMA or neural networks, to build a traffic forecasting model. 3. Real-Time Forecasting: Input the current network status and historical data into the forecasting model to output a forecast of traffic trends for a period of time. 4. Policy Adjustment: Based on the forecast results, adjust the existing QoS policy, such as increasing the reserved bandwidth for critical services, to adapt to expected traffic changes.

[0007] Dynamic Resource Allocation: 1. Resource Status Monitoring: Real-time monitoring of network resource status, including bandwidth utilization and node load. 2. Resource Allocation Algorithms: Develop and deploy dynamic resource allocation algorithms, such as genetic algorithms or ant colony algorithms, to dynamically adjust bandwidth allocation based on traffic forecasts and resource availability. 3. Priority Adjustment: Ensure sufficient bandwidth and low latency for critical business traffic; schedule non-critical business traffic appropriately based on resource availability.

[0008] Congestion Control and Optimization: 1. Congestion Monitoring: Deploy congestion monitoring mechanisms at key network nodes to monitor congestion indicators such as queue length and packet loss rate in real time. 2. Congestion Control Strategy: When potential congestion is detected, implement congestion control strategies such as RED or WRED by adjusting packet transmission paths and priorities. 3. Congestion Avoidance Algorithm: Utilize advanced congestion avoidance algorithms, such as the PI controller, to dynamically adjust congestion control parameters to reduce network latency and packet loss.

[0009] Security Assurance: 1. Data Encryption: End-to-end encryption is implemented for all transmitted data packets, using encryption standards such as AES to ensure data transmission security. 2. Authentication: Each device is assigned a unique security certificate and security protocols such as TLS or SSL are implemented for authentication and data encryption. 3. Security Policy Updates: Security policies and encryption algorithms are regularly updated to address new security threats and vulnerabilities.

[0010] User experience feedback: 1. Feedback collection: Design and implement user satisfaction surveys to collect user feedback on services through mobile applications or web pages. 2. Performance indicator analysis: Collect business performance indicators, such as application response time, data integrity, connection stability, etc., as a reference for QoS optimization. 3. Policy adjustment: Based on user feedback and performance indicators, use data analysis techniques, such as regression analysis, to adjust QoS parameters and service policies to improve user satisfaction. Through the above implementation steps and management methods, the present invention can effectively manage and optimize the service quality in the Internet of Things environment, ensure the stable operation of key businesses, improve the utilization efficiency of network resources, and continuously improve the user's service experience. BRIEF DESCRIPTION OF THE DRAWINGS Figure 1 Flowchart of the Internet of Things Service Quality Management Method for Adaptive Traffic Optimization of the Present Invention Figure 2 This is the adaptive traffic prediction flow chart of the present invention Figure 3 This is a flow chart of the prediction engine of the present invention.

Claims

1. A method for managing quality of service (QoS) of the Internet of Things based on adaptive traffic optimization, characterized in that: The following steps are involved: a) Device identification and classification: IoT network access points automatically detect connected devices, classify them according to their type and service requirements, and assign corresponding QoS parameters to each type of device; b) Traffic characteristic analysis: Monitor network traffic in real time and analyze traffic characteristics, including packet size, transmission frequency, and latency requirements, and classify traffic based on the analysis results; c) Adaptive traffic prediction: Using machine learning algorithms, combined with historical traffic data and current network status, it predicts future traffic trends and demand to facilitate resource allocation decisions. d) Dynamic resource allocation: Based on traffic forecast results, network resource allocation is dynamically adjusted, including but not limited to bandwidth, cache, and processing power, to prioritize the QoS requirements of critical services. e) Congestion control and optimization: When the possibility of network congestion is detected, the congestion control mechanism is automatically triggered to optimize network traffic by adjusting the transmission path and priority of data packets, reducing delays and packet loss; f) Security: Implement encryption and authentication mechanisms for data transmission to ensure the security of IoT devices and services and prevent unauthorized access and data tampering; g) User experience feedback: Collect user service experience feedback and business performance indicators to adjust and optimize QoS management strategies to improve user satisfaction and service quality.

2. The Internet of Things QoS management method according to claim 1, wherein the adaptive traffic prediction further comprises: a) Collect and store historical traffic data; b) Building a prediction model using classified device and traffic characteristics; c) regularly update the prediction model to adapt to changes in network conditions; d) Apply forecasting models to predict short-term and long-term traffic trends.

3. The Internet of Things QoS management method according to claim 1 or 2, wherein the dynamic resource allocation further comprises: a) Determine the resource requirements for each type of service based on the service's QoS requirements and traffic forecast results; b) Dynamically adjust bandwidth allocation for various services based on resource requirements and current network resource conditions; c) Ensure the quality of service for critical services through traffic shaping and priority adjustment when resources are limited; d) When resources are sufficient, optimize resource usage for non-critical services to improve the overall efficiency of the network.

4. The Internet of Things QoS management method according to claim 1, wherein the congestion control and optimization further comprises: a) Real-time monitoring of the queue length and processing capacity of network nodes; b) When the queue length exceeds the preset threshold, the congestion control mechanism is triggered; c) Actively discard low-priority traffic through Random Early Detection (RED) or Weighted Random Early Detection (WRED) algorithms; d) According to the network congestion, adjust the data packet transmission path to achieve load balancing.

5. The Internet of Things QoS management method according to claim 1, wherein the security guarantee further comprises: a) Encrypt all transmitted data packets; b) Authentication of devices accessing the network; c) Regularly update encryption and authentication mechanisms to prevent security breaches.

6. The Internet of Things QoS management method according to claim 1, wherein the user experience feedback further comprises: a) Design and implement user satisfaction surveys; b) Collect service performance indicators such as response time, data integrity, and connection stability; c) Adjust QoS parameters and resource allocation strategies based on feedback results; d) Optimize service quality through user feedback loops.

7. An Internet of Things QoS management system, used to implement the Internet of Things QoS management method according to any one of claims 1 to 6, characterized in that: include: a) Device identification module, used to automatically identify and classify IoT devices in the network; b) Traffic analysis module, used to monitor and analyze network traffic characteristics in real time; c) Prediction engine, used for traffic prediction based on machine learning algorithms; d) a resource allocation module, used to dynamically allocate network resources based on the prediction results; e) Congestion control module, used to optimize traffic flow when the network is congested; f) Security module, used to implement encryption and authentication of data transmission; g) Feedback processing module, used to collect user experience feedback and optimize QoS management strategies.

8. The Internet of Things QoS management system according to claim 7, wherein the device identification module further comprises: a) Device detection submodule, used to detect newly connected devices; b) Equipment classification submodule, used to classify equipment according to type and business requirements; c) QoS parameter allocation submodule, used to allocate corresponding QoS parameters to the classified devices.

9. The Internet of Things QoS management system according to claim 7, wherein the traffic analysis module further comprises: a) Traffic monitoring submodule, used to monitor network traffic in real time; b) Traffic feature extraction submodule, used to analyze traffic features; c) Traffic classification submodule, which is used to classify traffic into different categories based on characteristics.

10. The Internet of Things QoS management system according to claim 7, wherein the prediction engine further comprises: a) Data collection submodule, used to collect historical traffic data; b) Prediction model building submodule, used to build traffic prediction model; c) Model update submodule, used to regularly update the prediction model; d) Trend prediction submodule, used to apply the model to predict traffic trends.

11. The Internet of Things QoS management system according to claim 7, wherein the resource allocation module further comprises: a) Resource requirement determination submodule, used to determine the resource requirements of various services; b) Resource adjustment submodule, used to dynamically adjust the bandwidth allocation of services; c) Priority management submodule, used to adjust priorities when resources are tight.

12. The Internet of Things QoS management system according to claim 7, wherein the congestion control module further comprises: a) Node monitoring submodule, used to monitor the queue length and processing capacity of network nodes; b) Congestion control strategy submodule, used to implement congestion control algorithm; c) Load balancing submodule, used to adjust the transmission path of data packets.

13. The Internet of Things QoS management system according to claim 7, wherein the security module further comprises: a) Encryption submodule, used to encrypt data packets; b) Authentication submodule, used to authenticate the device accessing the network; c) Security update submodule, used to regularly update encryption and authentication mechanisms.

14. The Internet of Things QoS management system according to claim 7, wherein the feedback processing module further comprises: a) Survey design submodule, used to design user satisfaction surveys; b) Performance indicator collection submodule, used to collect business performance indicators; c) Policy optimization submodule, used to adjust the QoS policy based on the feedback results.

15. The Internet of Things QoS management system according to any one of claims 7 to 14, characterized in that: The system is compatible with existing IoT network infrastructure and can be seamlessly integrated into IoT applications.

Images