Feedback control QOS method, system and device based on chaos test tool and medium

Abstract

The invention discloses a feedback control QOS (Quality of Service) method, system and equipment based on a chaos test tool and a medium, in the chaos test tool, a network feedback mechanism is monitored in real time, and network service quality is adjusted, and the method comprises the following steps of: aiming at network topology change and flow change, realizing dynamic load balancing through a dynamic load balancing algorithm; according to the real-time flow demand condition, bandwidth allocation is dynamically adjusted through an elastic bandwidth adjustment algorithm, and it is ensured that the bandwidth demand of the key application is met; and an intelligent fault detection and recovery mechanism is introduced, so that the system can process faults in time. According to the method, the network service quality is monitored and adjusted in real time through a network feedback mechanism so as to adapt to network topology change and flow change.

Description

Technical Field

[0001] The present invention relates to the field of QOS technology, and in particular to a feedback control QOS method, system, device and medium based on chaos testing tool. Background Art

[0002] With the continuous development and application of the Internet, people have higher and higher requirements for network service quality. However, the data traffic in the network is very complex and diverse, and different types of applications and services have different requirements for the network, which brings great challenges to the guarantee of network service quality. Therefore, QOS technology came into being.

[0003] QOS (Quality of Service) management technology is a network management technology that ensures that specific services or applications on the network can obtain the required bandwidth and priority to achieve a higher performance level. It can prioritize and schedule network resources according to different application requirements to meet the performance requirements of applications. QOS technology can not only improve the quality of network services, but also reduce network congestion, improve network utilization, and improve user satisfaction, which is conducive to promoting the development and innovation of network applications. QOS technology mainly involves three aspects: traffic classification and marking, traffic control and congestion management. Traffic classification and marking is to distinguish and mark different types of network traffic for subsequent traffic control and congestion management. Traffic control is to control the transmission of network traffic by adjusting network bandwidth and traffic priority to ensure that important data traffic can be transmitted first. Congestion management is to take measures against network congestion, such as dropping data packets, adjusting bandwidth, etc., to avoid network collapse and service quality degradation.

[0004] QOS technology is widely used, including multimedia transmission, real-time communication, online games, video conferencing and other application scenarios that require network service quality assurance. QOS technology also plays an important role in video live broadcast, online education, cloud computing and other fields. With the continuous development and innovation of network applications, QOS technology is also constantly improving and upgrading. Modern QOS technology not only covers traditional network service quality assurance mechanisms, but also includes higher-level network management technologies such as network slicing and software-defined networks. These technologies will further improve the reliability, flexibility and intelligence of network service quality, and are expected to bring better experience and development opportunities to network applications.

[0005] QOS technology can effectively improve the quality of network services, but it still has the following defects and shortcomings: it is highly complex and requires complex configuration and management; it is easily affected by changes in network topology and traffic emergencies, resulting in reduced service quality; it requires in-depth analysis and control of network traffic, which increases network overhead and latency. Summary of the invention

[0006] The purpose of the present invention is to provide a feedback control QOS method, system, device and medium based on chaos testing tools, which monitors and adjusts the network service quality in real time through a network feedback mechanism to adapt to changes in network topology and traffic.

[0007] To achieve the above purpose, the technical solution provided by the present invention is:

[0008] The first aspect of the present application provides a feedback control QOS method based on a chaos test tool. In the chaos test tool, a network feedback mechanism is monitored in real time to adjust the network service quality, including the following steps:

[0009] Dynamic load balancing is achieved through dynamic load balancing algorithms in response to changes in network topology and traffic;

[0010] Based on real-time traffic demand, the elastic bandwidth adjustment algorithm dynamically adjusts bandwidth allocation to ensure that the bandwidth requirements of key applications are met.

[0011] Introducing intelligent fault detection and recovery mechanisms enables the system to handle faults in a timely manner.

[0012] To optimize the above technical solutions, the specific measures taken also include:

[0013] Furthermore, the real-time monitoring network feedback mechanism includes data collection: using performance monitoring tools to monitor the key performance indicators of each virtual machine, and obtaining the load and network traffic data of the virtual machine. The key performance indicators of the virtual machine include CPU usage, memory usage and network bandwidth usage.

[0014] Furthermore, the real-time monitoring network feedback mechanism includes data analysis: using graphical tools for visual display, defining load balancing strategies and thresholds, and determining under what circumstances network traffic needs to be redistributed.

[0015] Furthermore, the real-time monitoring network feedback mechanism includes feedback control: through a continuous feedback mechanism, the network quality is monitored and adjusted to meet different application requirements and network topology changes.

[0016] Specifically, the dynamic load balancing algorithm is used to implement dynamic load balancing in response to changes in network topology and traffic flow, including:

[0017] The load of each virtual machine is monitored through a dynamic load balancing algorithm. If the load of a virtual machine is found to be too high, the dynamic load balancing algorithm will dynamically adjust the distribution of network traffic and transfer part of the load to the virtual machine with lower load, making the load distribution of the entire system more balanced.

[0018] Specifically, the method dynamically adjusts bandwidth allocation according to real-time traffic demand through an elastic bandwidth adjustment algorithm to ensure that bandwidth requirements of key applications are met, including:

[0019] Dynamically adjust bandwidth allocation based on real-time traffic demand. If the traffic demand of a virtual machine increases, the elastic bandwidth adjustment algorithm automatically adjusts the bandwidth allocation of the virtual machine to ensure that the bandwidth demand of its key applications is met. At the same time, for other virtual machines with lower bandwidth demand, the elastic bandwidth adjustment algorithm reduces their bandwidth allocation to avoid waste of resources and improve system resource utilization.

[0020] Specifically, the introduction of intelligent fault detection and recovery mechanism enables the system to handle faults in a timely manner, including:

[0021] By monitoring faults in the network, timely detecting and restoring faults, the impact of faults on system performance and service quality can be avoided, ensuring stable system operation.

[0022] The second aspect of the present application provides a feedback control QOS system based on a chaos testing tool, comprising:

[0023] Dynamic load balancing module, used to achieve dynamic load balancing through dynamic load balancing algorithm according to changes in network topology and traffic;

[0024] The elastic bandwidth adjustment module is used to dynamically adjust bandwidth allocation based on real-time traffic demand through an elastic bandwidth adjustment algorithm to ensure that the bandwidth requirements of key applications are met;

[0025] The fault handling module enables the system to handle faults in a timely manner by introducing intelligent fault detection and recovery mechanisms.

[0026] The third aspect of the present application provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the feedback control QOS method based on the chaos testing tool as described in the first aspect of the present application is implemented.

[0027] The fourth aspect of the present application provides a computer-readable storage medium storing a computer program, wherein the computer program enables a computer to execute the feedback control QOS method based on the chaos testing tool as described in the first aspect of the present application.

[0028] Compared with the prior art, the present invention has the following beneficial effects:

[0029] Traditional QOS configuration methods usually use a static pre-configuration method to allocate network resources, which lacks flexibility and cannot adapt to changes in network topology and traffic. The feedback control QOS method of the present invention can monitor and adjust the network service quality in real time through a network feedback mechanism to adapt to changes in network topology and traffic. It has higher flexibility and adaptability and can provide better network service quality assurance in different network environments and application scenarios.

[0030] The algorithm of the present invention has lower complexity and latency. Compared with the traditional static QOS configuration method, it does not need to pre-configure a large number of QOS rules. Instead, it realizes the optimal configuration of network resources through a dynamic feedback mechanism, which can better avoid the decline of network service quality and traffic congestion, and improve network utilization and user satisfaction.

[0031] The feedback control QOS technology based on chaos testing tools adopts the feedback control QOS method, which has lower complexity and latency, and is more flexible and intelligent. Compared with the traditional static QOS configuration method, it can better adapt to network topology changes and traffic changes, and improve network service quality and user satisfaction.

[0032] The present invention adopts dynamic adaptive feedback control QOS technology and utilizes network feedback mechanism to monitor and adjust network service quality in real time to adapt to changes in network topology and traffic. It has low complexity and latency and can adapt to different network environments and application scenarios. Network slicing technology can be used to improve the reliability and flexibility of QOS, and network resources can be cut into multiple virtual networks. Each virtual network can be configured with different service qualities as needed, thereby achieving better network service quality assurance. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 : Flow chart of the feedback control QOS method based on chaos testing tool of the present invention.

[0034] Figure 2 : A schematic diagram of the process of real-time monitoring of the network feedback mechanism to adjust the network service quality of the present invention.

[0035] Figure 3 : A structural diagram of the feedback control QOS system based on the chaos testing tool of the present invention. DETAILED DESCRIPTION

[0036] The above contents of the present invention are further described in detail below in the form of embodiments, but this should not be understood as the scope of the above subject matter of the present invention being limited to the following embodiments, and all technologies realized based on the above contents of the present invention belong to the scope of the present invention.

[0037] Some of the terms in the present invention are explained as follows:

[0038] virtual_machines variable: This variable is used to store a list of identifiers of virtual machine instances.

[0039] bandwidth_allocation variable: This variable is a dictionary that records the bandwidth allocation of the virtual machine instance.

[0040] network_topology variable: This variable is a dictionary that stores virtual machine instances and corresponding network topology information, that is, the available bandwidth of the virtual machine instances.

[0041] add_virtual_machine method: This method is used to add a virtual machine instance to the virtualization platform, where the vm_id parameter represents the identifier of the virtual machine instance.

[0042] remove_virtual_machine method: This method is used to remove a virtual machine instance from the virtualization platform, where the vm_id parameter represents the identifier of the virtual machine instance.

[0043] update_network_topology method: This method is used to update the network topology information. The topology parameter is a dictionary that represents the virtual machine instance and the corresponding available bandwidth.

[0044] monitor_virtual_machine_load method: This method is used to monitor the load of a virtual machine instance and returns a dictionary containing the virtual machine instance and the corresponding load value.

[0045] adjust_network_traffic method: This method dynamically adjusts network traffic distribution according to the load of the virtual machine instance, that is, calculates the bandwidth allocation of each virtual machine instance based on the load value and network topology information.

[0046] elastic_bandwidth_adjustment method: This method dynamically adjusts the bandwidth allocation of virtual machine instances according to traffic demand, that is, adjusts the bandwidth allocation of each virtual machine instance according to the bandwidth allocation value.

[0047] fault_detection_and_recovery method: This method is used to implement intelligent fault detection and recovery functions, and to process and recover based on the monitored network fault conditions.

[0048] The above classes and variable functions describe the key elements in the code implementation to achieve the goals of dynamic load balancing, elastic bandwidth adjustment, and intelligent fault detection and recovery.

[0049] The purpose of the present invention is to provide a feedback control QOS method, system, device and medium based on chaos testing tools, such as Figure 1 As shown, the network service quality is monitored and adjusted in real time through the network feedback mechanism to adapt to changes in network topology and traffic.

[0050] In the traditional static QoS configuration method, the network quality of service (QoS) is usually a pre-configured fixed value, which cannot be adjusted according to the real-time network environment and traffic changes. This static configuration method has some limitations, which may lead to a decline in network service quality and traffic congestion. At the same time, it cannot fully utilize network resources, reducing network utilization and user satisfaction. In contrast, the feedback control QoS method can better solve these problems and improve network utilization and user satisfaction.

[0051] This application can monitor and adjust the quality of network services in real time, has low complexity and latency, can adapt to different network environments and application scenarios, has technical flexibility and adaptability, and can reduce network overhead and latency.

[0052] In one embodiment, the present invention proposes a feedback control QOS method based on a chaos test tool. In the chaos test tool, the network feedback mechanism is monitored in real time to adjust the network service quality, such as Figure 2 As shown, the following steps are included:

[0053] Dynamic load balancing is achieved through dynamic load balancing algorithms in response to changes in network topology and traffic;

[0054] Based on real-time traffic demand, the elastic bandwidth adjustment algorithm dynamically adjusts bandwidth allocation to ensure that the bandwidth requirements of key applications are met.

[0055] Introducing intelligent fault detection and recovery mechanisms enables the system to handle faults in a timely manner.

[0056] The real-time monitoring network feedback mechanism includes data collection: using performance monitoring tools to monitor the key performance indicators of each virtual machine and obtain the load and network traffic data of the virtual machine. The key performance indicators of the virtual machine include CPU utilization, memory utilization, and network bandwidth utilization.

[0057] Real-time monitoring of network feedback mechanisms includes data analysis: using graphical tools for visual display, defining load balancing strategies and thresholds, and determining when network traffic needs to be redistributed.

[0058] Real-time monitoring of network feedback mechanisms includes feedback control: through continuous feedback mechanisms, network quality is monitored and adjusted to meet different application requirements and network topology changes.

[0059] In response to changes in network topology and traffic, dynamic load balancing is achieved through a dynamic load balancing algorithm, specifically:

[0060] The load of each virtual machine is monitored through a dynamic load balancing algorithm. If the load of a virtual machine is found to be too high, the dynamic load balancing algorithm will dynamically adjust the distribution of network traffic and transfer part of the load to the virtual machine with lower load, making the load distribution of the entire system more balanced.

[0061] Based on the real-time traffic demand, the elastic bandwidth adjustment algorithm dynamically adjusts the bandwidth allocation to ensure that the bandwidth requirements of key applications are met. Specifically:

[0062] Dynamically adjust bandwidth allocation based on real-time traffic demand. If the traffic demand of a virtual machine increases, the elastic bandwidth adjustment algorithm automatically adjusts the bandwidth allocation of the virtual machine to ensure that the bandwidth demand of its key applications is met. At the same time, for other virtual machines with lower bandwidth demand, the elastic bandwidth adjustment algorithm reduces their bandwidth allocation to avoid waste of resources and improve system resource utilization.

[0063] Introduce intelligent fault detection and recovery mechanisms to enable the system to handle faults in a timely manner, specifically:

[0064] By monitoring faults in the network, timely detecting and restoring faults, the impact of faults on system performance and service quality can be avoided, ensuring stable system operation.

[0065] The present invention is further described in detail below in conjunction with specific embodiments:

[0066] Real-time monitoring and adjustment of network service quality:

[0067] The feedback control QOS method of the present application is a technology that can monitor and adjust the quality of network services in real time. It uses the network feedback mechanism to adapt to changes in network topology and traffic. The core idea is to monitor and adjust the network quality through a continuous feedback mechanism to meet different application requirements and network topology changes. The implementation of this technology involves many key technologies, such as data collection, data analysis, and feedback control.

[0068] In response to the changes in network topology and traffic in the chaos testing tool, dynamic load balancing is achieved through improved algorithms; the load of virtual machine instances is monitored, and the distribution of network traffic is dynamically adjusted to make the load distribution of the entire system more balanced, improving the performance and stability of the system; in order to adapt to traffic changes, elastic bandwidth adjustment is achieved through improved algorithms; according to real-time traffic demand conditions, the bandwidth allocation of virtual machine instances is dynamically adjusted to ensure that the bandwidth requirements of key applications are met, while avoiding resource waste and improving system resource utilization.

[0069] In order to improve the reliability and security of the system, an intelligent fault detection and recovery mechanism is introduced; by monitoring the fault conditions in the network, faults are detected and restored in a timely manner to avoid the impact of faults on system performance and service quality, thus ensuring the stable operation of the system.

[0070] In chaos testing tools, dynamic load balancing, elastic bandwidth adjustment, and intelligent fault detection and recovery are three important improvement directions, aiming to improve the performance, stability, and security of the system.

[0071] The following is a specific example to illustrate the value and role of these improvements:

[0072] Assume that there are three virtual machines (VM1, VM2, VM3) in the chaos test tool, and different bandwidth resources are allocated to them. As time goes by, the network topology and traffic in the system change, which may cause some virtual machines to be overloaded while other virtual machines are underloaded. The unbalanced load distribution will reduce the performance and stability of the system. To solve this problem, a dynamic load balancing algorithm can be introduced.

[0073] The dynamic load balancing algorithm monitors the load of each virtual machine, including CPU usage, memory usage and other indicators; if it is found that the load of a virtual machine is too high, the algorithm will dynamically adjust the distribution of network traffic and transfer part of the load to the virtual machine with lower load, so that the load distribution of the entire system is more balanced. For example, if the load of VM1 is too high, the algorithm can transfer part of the traffic from VM1 to VM2 and VM3 to improve the performance and stability of the system; the traffic is constantly changing in the chaos test tool, and there may be sudden increases or decreases in traffic. In order to adapt to this traffic change, the algorithm can be improved to achieve elastic bandwidth adjustment.

[0074] The elastic bandwidth adjustment algorithm will dynamically adjust bandwidth allocation according to real-time traffic demand. If the traffic demand of a virtual machine increases, the algorithm will automatically adjust the bandwidth allocation of the virtual machine to ensure that the bandwidth demand of its key applications is met. At the same time, for other virtual machines with lower bandwidth demand, the algorithm will moderately reduce their bandwidth allocation to avoid waste of resources and improve the resource utilization of the system. Through elastic bandwidth adjustment, the system can flexibly adjust bandwidth allocation according to traffic changes, thereby improving the adaptability and performance of the system.

[0075] In the chaos testing tool, dynamic load balancing, elastic bandwidth adjustment and intelligent fault detection and recovery are key improvement directions that can improve the performance, stability and security of the system. Through dynamic load balancing, the distribution of network traffic is adjusted in real time to maintain load balance; through elastic bandwidth adjustment, bandwidth resources are reasonably allocated according to traffic changes; through intelligent fault detection and recovery, faults are handled in a timely manner to ensure system reliability.

[0076] Lower complexity and latency:

[0077] The feedback control QOS method has lower complexity and delay. Compared with the traditional static QOS configuration method, it can better avoid the decline of network service quality and traffic congestion, and improve network utilization and user satisfaction.

[0078] In the traditional static QoS configuration method, the network quality of service (QoS) is usually a pre-configured fixed value, which cannot be adjusted according to the real-time network environment and traffic changes. This static configuration method has some limitations, which may lead to a decline in network service quality and traffic congestion. At the same time, it cannot fully utilize network resources, reducing network utilization and user satisfaction. In contrast, the feedback control QoS method can better solve these problems and improve network utilization and user satisfaction.

[0079] In a chaos testing tool, multiple virtual machines run simultaneously and share network resources. At a certain moment, the traffic demand of a virtual machine suddenly increases, while the traffic demand of other virtual machines remains unchanged. In the traditional static QoS configuration method, the network service quality is pre-allocated and cannot be dynamically adjusted according to this traffic change. The result may be that the traffic of the virtual machine cannot be met, resulting in its performance degradation or even traffic congestion, affecting the normal operation of other virtual machines.

[0080] However, the feedback control QOS method of the present application can better adapt to this scenario. The algorithm collects feedback information by real-time monitoring of the network environment and traffic changes, and dynamically adjusts the network service quality. When an increase in the traffic demand of a virtual machine is detected, the algorithm can adjust the bandwidth allocation of the virtual machine in real time to meet its demand while avoiding performance degradation of other virtual machines. Dynamic adjustment can avoid degradation of network service quality and traffic congestion, and improve network utilization and user satisfaction.

[0081] In addition, the feedback control QOS method is also adaptive and flexible. It can adjust the network service quality in real time according to different network environments and application scenarios to adapt to changes in network topology and traffic. For example, when the network topology changes, the algorithm can automatically recalculate and adjust bandwidth allocation to adapt to the new network structure. Adaptability and flexibility can better cope with unpredictable network changes and improve system performance and stability.

[0082] In summary, compared with the traditional static QoS configuration method, the feedback control QOS method has obvious advantages in avoiding network service quality degradation and traffic congestion, improving network utilization and user satisfaction. It can dynamically adjust the network service quality according to the real-time network environment and traffic changes, improve the system's adaptability, performance and user experience; use the feedback mechanism to achieve real-time monitoring and adjustment, so as to better adapt to the ever-changing network environment and application requirements, and provide more efficient, stable and satisfactory services for chaos testing tools.

[0083] The present application is a technology that can monitor and adjust the network service quality in real time, and adapt to changes in network topology and traffic by utilizing a network feedback mechanism. Through a continuous feedback mechanism, the network quality is monitored and adjusted to meet different application requirements and network topology changes.

[0084] In this technical solution, the load and network traffic of virtual machine instances are monitored, and performance monitoring tools such as Nagios are used to monitor key performance indicators such as CPU usage, memory usage, and network bandwidth usage of each virtual machine instance; data is collected in real time and visualized using graphical tools such as Grafana; load balancing strategies and thresholds are defined to determine under what circumstances network traffic needs to be redistributed. For example, when the CPU or network bandwidth usage of a virtual machine exceeds a set threshold (such as 80%), adjustments are required; formulate bandwidth guarantee strategies for key applications to ensure that the traffic needs of important services are met first; implement a dynamic network traffic adjustment mechanism and use software-defined network (SDN) technologies, such as OpenFlow, to achieve dynamic adjustment of network traffic; dynamically adjust routing strategies and bandwidth allocation through the SDN controller based on monitored data and defined policies; fault detection and recovery implement real-time fault detection mechanisms for networks and services, such as using Heartbeat for heartbeat detection; once a fault is detected, immediately start the preset recovery process, such as automatic failover or fast rerouting; performance and security evaluation, regularly evaluate system performance, check the response time and service availability of key applications; implement network security strategies, including intrusion detection systems (IDS) and network segmentation to improve system security.

[0085] CPU and memory usage: Keep the CPU and memory usage of the virtual machine below the safety threshold (for example, below 80%) to avoid overload.

[0086] Network bandwidth utilization: Dynamically adjusts to ensure that network bandwidth needs of critical services are met while avoiding over-allocation.

[0087] Service response time: Monitor the response time of key applications to ensure that user experience is not affected after dynamic adjustments to network traffic.

[0088] System stability indicators: such as fault recovery time (MTTR), system availability (Uptime), etc., are used to measure the stability and reliability of the system.

[0089] Resource utilization: Improve overall resource utilization and reduce costs by optimizing resource allocation.

[0090] Through the above implementation steps and continuous data indicator monitoring, it can ensure that network traffic in the virtualized environment is effectively managed, improve system performance and stability, and improve resource utilization efficiency and security.

[0091] Use load balancing algorithms, such as weighted round-robin, to evenly distribute traffic to each virtual machine. Dynamically adjust the bandwidth allocation of virtual machine instances based on real-time traffic demand. By monitoring traffic conditions, adaptive bandwidth allocation strategies can be adopted, such as dynamically adjusting bandwidth quotas or using traffic regulation algorithms to ensure that the bandwidth requirements of key applications are met. By monitoring network faults, such as link interruptions and virtual machine failures, faults can be detected and recovered in a timely manner. Fault detection algorithms, such as heartbeat detection and link status monitoring, can be used in combination with fault recovery strategies, such as switching to backup links and rescheduling virtual machines, to achieve intelligent fault detection and recovery.

[0092] There is a service consisting of 3 virtual machine instances. The performance indicators and initial weights of each instance are as follows:

[0093] VM1: CPU = 8 cores, memory = 16GB, initial weight = 3;

[0094] VM2: CPU = 4 cores, memory = 8GB, initial weight = 2;

[0095] VM3: CPU = 2 cores, memory = 4GB, initial weight = 1.

[0096] By comparing the traffic distribution before and after load balancing, the consistency of the traffic distribution ratio of each virtual machine and the expected weight is calculated. Ideally, the proportion of traffic handled by each virtual machine should be proportional to its weight. After dynamically adjusting the bandwidth quota, monitor the match between the actual bandwidth used by each virtual machine and the allocated bandwidth quota. Bandwidth utilization = actual bandwidth used / total allocated bandwidth. The ideal utilization is close to 100%. The short average time from the occurrence of a fault to the full recovery of the system indicates that the system has efficient fault detection and recovery capabilities. The proportion of time that the system can provide services within a certain period of time can be calculated by subtracting (total fault time / total time) from 100%.

[0097] By implementing these steps and monitoring the corresponding data indicators, you can ensure that network traffic in the virtualized environment is effectively managed, improve overall performance and stability, while optimizing resource utilization and improving system reliability.

[0098] The feedback control QOS method of this application optimizes resource utilization and traffic allocation in the chaos test tool through dynamic load balancing and elastic bandwidth adjustment, improves system performance and stability; adjusts resource allocation according to real-time needs to provide better service quality and user experience. Through elastic bandwidth adjustment, bandwidth resources are reasonably allocated to avoid resource waste; bandwidth is dynamically allocated according to actual needs to improve the utilization efficiency of bandwidth resources. Through intelligent fault detection and recovery, faults in the network are discovered and handled in a timely manner to ensure the reliability and security of the system; faults are automatically detected and recovered to reduce the impact on user services.

[0099] Compared with the traditional static QoS configuration method, this solution has higher flexibility and adaptability, and can adapt to different network environments and application scenarios. By real-time monitoring and adjusting the network service quality, it can avoid network service quality degradation and traffic congestion, and improve network utilization and user satisfaction. At the same time, the solution introduces improvement measures such as dynamic load balancing, elastic bandwidth adjustment, and intelligent fault detection and recovery, which enhances the performance, stability and security of the system, and brings better service and user experience to chaos testing tools.

[0100] For the data separation problem of the improved feedback control QOS method of the present application applied to the chaos test tool, the following mathematical derivation formula can be used:

[0101] QoS=R h -R s -R n

[0102] Among them, QoS represents the quality of network service; R h Indicates the bandwidth allocated to the virtual machine; R s Indicates the actual bandwidth used by the virtual machine; R nIndicates the bandwidth usage of other virtual machines in the network.

[0103] Specifically, the formula expresses the relationship between QoS and bandwidth allocation, bandwidth usage, and bandwidth usage of other virtual machines on the network. h Greater than the actual bandwidth Rs and the bandwidth used by other virtual machines on the network R n , the QoS value will increase accordingly, indicating that the network service quality is guaranteed. On the contrary, if the actual bandwidth Rs used by the virtual machine is equal to the bandwidth used by other virtual machines in the network, R n Exceeds its allocated bandwidth R h , the QoS value will decrease accordingly, indicating that the quality of network service has decreased.

[0104] Security and stability improvements:

[0105] In order to solve the security and stability problems of data separation in the cloud platform, the above formula can be improved by introducing security and stability indicators to evaluate the performance of QoS. The improved formula is:

[0106] QoS = α(R h -R s -R n )-β(R s -R avg )-γ(R h -R max )

[0107] Among them, QoS represents the quality of network service; R h Indicates the bandwidth allocated to the virtual machine; R s Indicates the actual bandwidth used by the virtual machine; R n Indicates the bandwidth usage of other virtual machines in the network; α, β, γ are weight coefficients used to balance the impact between different indicators; R avg Indicates the average bandwidth usage of other virtual machines in the network; R max Indicates the maximum bandwidth usage of other virtual machines in the network.

[0108] The formula introduces stability and security indicators to more comprehensively evaluate QoS performance. The first item represents bandwidth allocation and usage, which is the main factor in improving QoS; the second item represents the difference between the bandwidth usage of the current virtual machine and the average bandwidth usage of the network, which is used to evaluate the stability of the virtual machine's bandwidth usage; the third item represents the difference between the bandwidth allocated to the virtual machine and the maximum bandwidth usage of other virtual machines in the network, which is used to evaluate the security of the network. The weight coefficients α, β, and γ can be adjusted according to the specific application scenario to achieve the optimal QoS performance.

[0109] The improvement of this formula can improve the security and stability of data separation while ensuring the quality of network services. By introducing stability and security indicators, the quality of network services can be evaluated more comprehensively and the reliability and security of the system can be improved.

[0110] Improvements to adaptive capabilities:

[0111] To address the adaptive performance issues of data separation in the cloud platform, the above formula can be improved by introducing adaptive indicators to evaluate QoS performance. The improved formula is:

[0112] QoS = α(R h -R s -R n )-β(R s -R avg )-γ(R h -R max )+δ(R h -R s -R avg )

[0113] Among them, QoS represents the quality of network service; R h Indicates the bandwidth allocated to the virtual machine; R s Indicates the actual bandwidth used by the virtual machine; R n Indicates the bandwidth usage of other virtual machines in the network; α, β, γ, δ are weight coefficients used to balance the impact between different indicators; R avg Indicates the average bandwidth usage of other virtual machines in the network; R max Indicates the maximum bandwidth usage of other virtual machines in the network.

[0114] Based on the above formula, the adaptive index is introduced, that is, the fourth term δ(R h -R s -R avg ), which is used to evaluate the adaptability of virtual machine bandwidth usage; when the actual bandwidth used by the virtual machine is lower than the average bandwidth usage of the network, this indicator will increase, and the QoS value will be increased to promote the improvement of bandwidth utilization; when the actual bandwidth used by the virtual machine is higher than the average bandwidth usage of the network, this indicator will decrease, and the QoS value will be reduced to avoid bandwidth congestion and service quality degradation; the weight coefficients α, β, γ, and δ can be adjusted according to the specific application scenario to achieve the optimal QoS performance.

[0115] By introducing adaptive indicators, we can better adapt to changes in network topology and traffic, improve network service quality and bandwidth utilization. At the same time, the security and stability of data separation are guaranteed. The specific derivation process is given below:

[0116] According to the above formula, the following derivation process can be obtained:

[0117] QoS = α(R h -R s -R n )-β(R s -R avg )-γ(R h -R max )+δ(R h -R s -R avg )

[0118] QoS=αR h -αRs-αR n -βR s +βR avg -γR h +γR max +δR h -δR s -δR avg

[0119] QoS=R h (α-γ+δ)-R s (α+β+δ)-R n (α)+βR avg -γR max -δR avg

[0120] Among them, the weight coefficients α, β, γ, and δ are used to balance the impact between different indicators. At the same time, the adaptive performance of the algorithm can be adjusted by adjusting the weight coefficients. According to the formula, QoS can be regarded as a weighted sum, in which each item represents an aspect of QoS. The values ​​of the weight coefficients α, β, and γ can be adjusted according to the actual application scenario to achieve the optimal QoS performance.

[0121] In order to further improve the performance of QoS, the formula can be combined with a feedback control algorithm to achieve dynamic adaptive QOS; specifically, the feedback control algorithm can be used to monitor and adjust the network service quality in real time to adapt to changes in network topology and traffic; at the same time, the QoS value is calculated according to the above formula, and the bandwidth allocation is adjusted according to the QoS value to optimize the stability and security of network service quality and data separation.

[0122] When the QoS value decreases, the bandwidth allocated to the virtual machine can be appropriately reduced to avoid network congestion and data leakage; on the contrary, when the QoS value increases, the bandwidth allocated to the virtual machine can be appropriately increased to improve network utilization and user satisfaction; at the same time, according to the stability and security indicators, the ratio of the bandwidth usage of the virtual machine to the bandwidth usage of other virtual machines in the network can be adjusted to improve the stability and security of data separation.

[0123] The performance, stability and security of the system are improved through improved formulas and algorithms; by introducing a mechanism for QoS calculation and adjustment of bandwidth allocation, bandwidth allocation can be dynamically adjusted according to real-time network usage and QoS values ​​to adapt to changes in network topology and traffic; at the same time, bandwidth allocation is adjusted according to stability and security indicators to improve the stability and security of data separation.

[0124] Compared with the original technology, the improvement lies in the introduction of QoS calculation and bandwidth allocation adjustment mechanism, as well as the consideration of stability and security indicators. By comprehensively considering factors such as network load, bandwidth allocation, stability and security, it can more intelligently implement dynamic adaptive QoS control and improve system performance, stability and security.

[0125] Adapt to different network environments and application scenarios:

[0126] The feedback control QOS method can adapt to different network environments and application scenarios, thereby providing better network service quality assurance.

[0127] The feedback control QOS method of the present application is a technology that can adapt to different network environments and application scenarios. It monitors and adjusts the network service quality in real time to meet the needs of different applications and adapt to changes in network topology and traffic. The following is a specific example to illustrate the adaptability of this technology in different scenarios.

[0128] Consider a multi-tenant chaos testing tool, where multiple tenants use network resources at the same time. Each tenant may have different application types and service requirements. For example, tenant A may be an online game provider that requires low-latency and high-bandwidth network services; tenant B may be an online video streaming platform that requires high throughput and stable network connections; tenant C may be an enterprise office application provider that has high requirements for network reliability and security.

[0129] In the traditional static QoS configuration method, it is often necessary to pre-allocate certain bandwidth and service quality for different tenants, but this configuration is difficult to adapt to the changing needs of different tenants and changes in the network environment. For example, when the number of users of tenant A suddenly increases, resulting in an increase in bandwidth demand, other tenants may be affected, resulting in performance degradation or traffic congestion.

[0130] However, by adopting the feedback control QOS method of the present application, it is possible to better adapt to different network environments and application scenarios. In this example, the technology can dynamically adjust the allocation of network resources according to the real-time monitored network load and user needs to meet the needs of different tenants.

[0131] For tenant A, when the number of its users increases, the system can automatically increase the bandwidth quota of the tenant and provide higher bandwidth and low-latency services to meet the requirements of online games. For tenant B, the system can dynamically adjust bandwidth allocation and traffic scheduling strategies according to real-time streaming needs to ensure smooth video playback and high-quality viewing experience. For tenant C, the system can provide reliable network connection and secure data transmission, and detect and restore faults in a timely manner by real-time monitoring of network security status and fault conditions, to ensure the stable operation of enterprise office applications.

[0132] This example illustrates the adaptability of the feedback control QOS method of this application in different scenarios. It can dynamically adjust the allocation of network resources according to the needs of different tenants and real-time network conditions to provide better service quality and user experience. Whether it is for delay-sensitive applications, high-throughput applications, or applications that require stability and security, this technology can be flexibly adjusted according to actual needs to achieve better network service quality assurance. By improving the performance, stability, and security of the system, this technology brings higher flexibility and adaptability to chaos testing tools, improving user satisfaction and system resource utilization efficiency.

[0133] Flexibility and adaptability:

[0134] The algorithm has higher flexibility and adaptability, and can provide better network service quality assurance in different network environments and application scenarios.

[0135] The feedback control QOS method of the present application is flexible and adaptable, and can be dynamically adjusted according to different network environments and application scenarios to provide better network service quality. The following is a specific example to illustrate the flexibility and adaptability of the technology in practical applications.

[0136] Consider an enterprise-level chaos testing tool, which hosts business applications of multiple enterprises. Different enterprises may have different network requirements and service level agreements (SLAs). For example, enterprise A may be a financial institution with high requirements for network security and stability; enterprise B may be a technology innovation enterprise with high requirements for network bandwidth and latency; enterprise C may be a traditional manufacturing enterprise with high requirements for network stability and reliability.

[0137] In traditional static QoS configuration methods, it is often necessary to pre-allocate fixed network resources and service quality for different enterprises. However, since the business needs and network environment of different enterprises may change, static configuration is difficult to meet the changing needs.

[0138] By adopting the feedback control QOS method of the present application, different network environments and application scenarios can be better adapted. In this example, the technology can dynamically adjust the allocation of network resources according to the real-time monitored network quality and the needs of the enterprise to meet the needs of different enterprises.

[0139] For institution A, this technology can dynamically adjust security policies and traffic management rules based on real-time network security conditions, provide stronger network security protection, and prevent potential network attacks and data leaks.

[0140] For enterprise B, this technology can dynamically adjust bandwidth allocation and latency management strategies based on real-time network load conditions to ensure high-bandwidth and low-latency network connections to meet the needs of large-scale data transmission and real-time applications.

[0141] For the manufacturing industry C, this technology can dynamically adjust fault detection and recovery strategies based on real-time network reliability conditions to ensure the stability and availability of network connections and avoid production interruptions and data loss.

[0142] This example illustrates the flexibility and adaptability of the feedback control QOS method of this application in different enterprise scenarios. It can dynamically adjust the allocation of network resources according to the needs of different enterprises and real-time network conditions, and provide customized network service quality to meet the business needs of enterprises. By providing flexible and adaptable solutions, this technology can meet the specific needs of different enterprises, improve network performance, stability and reliability, and thus provide enterprise users with a better service experience.

[0143] Reduce network overhead and latency:

[0144] Compared with traditional QOS technology, the feedback control QOS method does not require in-depth analysis and control of network traffic, thereby reducing network overhead and latency.

[0145] The feedback control QOS method of the present application has significant advantages in reducing network overhead and delay. The following is a specific example to illustrate the ability of the technology to reduce network overhead and delay in practical applications.

[0146] Consider a large-scale chaos testing tool that hosts a large number of virtual machine instances and applications. On this platform, different virtual machine instances may generate different network traffic, and network overhead and latency may become a bottleneck for system performance.

[0147] In traditional static QoS configuration methods, it is often necessary to pre-allocate a fixed network bandwidth for each virtual machine instance, which may lead to resource waste and network congestion. For example, some virtual machine instances may only require low bandwidth, while other virtual machine instances may require higher bandwidth. Due to the limitations of static configuration, resources may be wasted on low-bandwidth virtual machines, while high-bandwidth virtual machines may not meet their needs, resulting in latency and performance issues.

[0148] By adopting the feedback control QOS method of the present application, the network bandwidth allocation can be dynamically adjusted to reduce network overhead and delay. In this example, the technology can dynamically allocate bandwidth resources according to the real-time network load and traffic demand to optimize network performance and reduce delay.

[0149] For example, suppose a certain virtual machine instance generates a large amount of network traffic at a certain moment, while other virtual machine instances have a lower network load. Traditional static configuration methods may limit the bandwidth of each virtual machine instance, resulting in increased latency and network congestion. However, through the feedback control QOS method of this application, the system can monitor traffic changes in real time and automatically adjust the bandwidth allocation of virtual machine instances; in this case, the system can allocate more bandwidth resources to high-traffic virtual machine instances to meet their needs, while reducing the bandwidth allocation of low-traffic virtual machines to avoid resource waste.

[0150] By dynamically adjusting bandwidth allocation, this technology can reduce network overhead and latency, improve system performance and user experience; the system can optimize bandwidth allocation strategies based on real-time network load conditions, make more efficient use of network resources, avoid bandwidth waste and congestion, and thus reduce network overhead and latency.

[0151] This example illustrates the advantages of the feedback control QOS method of the present application in reducing network overhead and latency; by real-time monitoring and dynamic adjustment of network bandwidth allocation, the technology can provide more efficient network resource utilization, reduce resource waste and congestion problems, thereby reducing network overhead and latency, and improving system performance and user experience.

[0152] In another embodiment, the present invention proposes a feedback control QOS system based on a chaos testing tool, such as Figure 3 As shown, including:

[0153] Dynamic load balancing module, used to achieve dynamic load balancing through dynamic load balancing algorithm according to changes in network topology and traffic;

[0154] The elastic bandwidth adjustment module is used to dynamically adjust bandwidth allocation based on real-time traffic demand through an elastic bandwidth adjustment algorithm to ensure that the bandwidth requirements of key applications are met;

[0155] The fault handling module enables the system to handle faults in a timely manner by introducing intelligent fault detection and recovery mechanisms.

[0156] In another embodiment, the present invention proposes an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the feedback control QOS method based on the chaos testing tool is implemented.

[0157] In another embodiment, the present invention provides a computer-readable storage medium storing a computer program, wherein the computer program enables a computer to execute the above feedback control QOS method based on the chaos testing tool.

[0158] In response to the problems existing in the existing QOS technology, the present application proposes a QOS method based on feedback control, and optimizes it in combination with a chaos testing tool; the method monitors and adjusts the network service quality in real time, and is implemented through a network feedback mechanism, and can adapt to changes in network topology and traffic, thereby improving network utilization and user satisfaction; the method has low complexity and latency, avoids in-depth analysis and control of network traffic, and reduces network overhead and latency; the method is flexible and adaptable, and can adapt to different network environments and application scenarios, providing better network service quality assurance; the method reduces network overhead and latency, improves network utilization and user satisfaction, and has broad commercial application prospects, and is expected to become an important technical means for ensuring network service quality in the future.

[0159] This application mainly aims at improving the quality of network services, solves the impact of network topology changes and traffic emergencies on QOS, and provides better network service quality assurance; network slicing technology can be used to improve the reliability and flexibility of QOS, and network resources can be cut into multiple virtual networks. Each virtual network can be configured with different service qualities as needed, thereby achieving better network service quality assurance; this technology is suitable for various business scenarios, such as live video streaming, cloud gaming, remote office, etc., and can effectively improve user experience and satisfaction.

[0160] The feedback control QOS technology based on the chaos test tool of this application can be applied to various network fields such as cloud computing, Internet of Things, 5G, etc. In cloud computing, it can improve the bandwidth utilization and service quality of virtual machines, and enhance the reliability and security of cloud computing; in the Internet of Things, it can improve the service quality of sensor networks, enhance the real-time and stability of the Internet of Things; in 5G, it can improve the quality of network services and enhance the high speed, low latency and other characteristics of 5G.

[0161] The commercial value of this application lies mainly in improving the quality of network services, enhancing user experience and satisfaction, thereby improving the competitiveness and market share of enterprises; by improving service quality, enterprises can attract more users and customers, improve user retention and loyalty, and thus increase corporate revenue and profits; in addition, this technology can reduce the company's network overhead and latency, improve network utilization and efficiency, further reduce the company's costs and increase profits.

[0162] In the embodiments disclosed in the present application, the computer storage medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. The computer storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the above. More specific examples of computer storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above.

[0163] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in any form. Any technician familiar with the profession, without departing from the scope of the technical solution of the present invention and based on the technical essence of the present invention, may make any simple modifications, equivalent substitutions and improvements to the above embodiments, which are still within the protection scope of the technical solution of the present invention.

Claims

1. A feedback control QOS method based on chaos testing tool, characterized by: In the chaos testing tool, real-time monitoring of the network feedback mechanism and adjustment of network service quality include the following steps: Dynamic load balancing is achieved through dynamic load balancing algorithms in response to changes in network topology and traffic; Based on real-time traffic demand, the elastic bandwidth adjustment algorithm dynamically adjusts bandwidth allocation to ensure that the bandwidth requirements of key applications are met. Introducing intelligent fault detection and recovery mechanisms enables the system to handle faults in a timely manner.

2. The feedback control QOS method based on chaos testing tool according to claim 1 is characterized in that: The real-time monitoring network feedback mechanism includes data collection: using performance monitoring tools to monitor the key performance indicators of each virtual machine, and obtaining the load and network traffic data of the virtual machine. The key performance indicators of the virtual machine include CPU usage, memory usage and network bandwidth usage.

3. The feedback control QOS method based on chaos testing tool according to claim 1 is characterized in that: The real-time monitoring network feedback mechanism includes data analysis: using graphical tools for visual display, defining load balancing strategies and thresholds, and determining under what circumstances network traffic needs to be redistributed.

4. The feedback control QOS method based on chaos testing tool according to claim 1 is characterized in that: The real-time monitoring network feedback mechanism includes feedback control: through a continuous feedback mechanism, the network quality is monitored and adjusted to meet different application requirements and network topology changes.

5. The feedback control QOS method based on chaos testing tool according to claim 1 is characterized in that: The dynamic load balancing algorithm is used to achieve dynamic load balancing in response to changes in network topology and traffic flow. Specifically, The load of each virtual machine is monitored through a dynamic load balancing algorithm. If the load of a virtual machine is found to be too high, the dynamic load balancing algorithm will dynamically adjust the distribution of network traffic and transfer part of the load to the virtual machine with lower load, making the load distribution of the entire system more balanced.

6. The feedback control QOS method based on chaos testing tool according to claim 1 is characterized in that: According to the real-time traffic demand, the bandwidth allocation is dynamically adjusted through the elastic bandwidth adjustment algorithm to ensure that the bandwidth demand of key applications is met. Specifically: Dynamically adjust bandwidth allocation based on real-time traffic demand. If the traffic demand of a virtual machine increases, the elastic bandwidth adjustment algorithm automatically adjusts the bandwidth allocation of the virtual machine to ensure that the bandwidth demand of its key applications is met. At the same time, for other virtual machines with lower bandwidth demand, the elastic bandwidth adjustment algorithm reduces their bandwidth allocation to avoid waste of resources and improve system resource utilization.

7. The feedback control QOS method based on chaos testing tool according to claim 1 is characterized in that: The introduction of intelligent fault detection and recovery mechanism enables the system to handle faults in a timely manner, specifically: By monitoring faults in the network, timely detecting and restoring faults, the impact of faults on system performance and service quality can be avoided, ensuring stable system operation.

8. A feedback-controlled QOS system based on a chaos testing tool, characterized in that: include: Dynamic load balancing module, used to achieve dynamic load balancing through dynamic load balancing algorithm according to changes in network topology and traffic; The elastic bandwidth adjustment module is used to dynamically adjust bandwidth allocation based on real-time traffic demand through an elastic bandwidth adjustment algorithm to ensure that the bandwidth requirements of key applications are met; The fault handling module enables the system to handle faults in a timely manner by introducing intelligent fault detection and recovery mechanisms.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the feedback control QOS method based on the chaos testing tool as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, wherein the computer program enables a computer to execute the feedback control QOS method based on a chaos testing tool as described in any one of claims 1 to 7.

Images