Closed-loop bandwidth adjustment method and system based on model-free adaptive control

Abstract

The invention discloses a closed-loop bandwidth adjustment method and system based on model-free adaptive control, belongs to the technical field of communication operation and maintenance, and aims to solve the technical problem of how to dynamically adjust bandwidth and realize closed-loop control based on model-free adaptive control. Comprising a data acquisition module used for acquiring operation and maintenance data of a target network and sending the operation and maintenance data to a model-free adaptive controller; the model-free adaptive controller is used for carrying out network bandwidth allocation strategy adjustment on the target network through a model-free adaptive algorithm based on the operation and maintenance data; the bandwidth adjustment execution module is used for adjusting the network bandwidth of the target network based on the adjusted network bandwidth; the performance evaluation feedback module is used for performing performance evaluation on the adjusted target network; and the model-free adaptive controller is used for optimizing a current model-free adaptive algorithm and a network bandwidth allocation strategy based on the operation and maintenance data and the evaluation result.

Description

Technical Field

[0001] The present invention relates to the field of communication operation and maintenance technology, and in particular to a closed-loop bandwidth adjustment method and system based on model-free adaptive control. Background Art

[0002] With the increasing complexity and diversity of communication networks, network operation and maintenance management faces many challenges, including how to efficiently use network resources, how to quickly respond to changes in network status, and how to ensure stable network performance. In addition, the communication environment is often complex and changeable, with unfavorable factors such as large time delays and strong interference, which seriously affect the stability and reliability of the communication system. Traditional operation and maintenance management methods often rely on static rules or empirical judgments, and it is difficult to respond to the variability and complexity of network status in real time and accurately. Therefore, an intelligent operation and maintenance optimization system that can analyze network status in real time and automatically adjust operation and maintenance strategies is needed. As an emerging control technology, model-free adaptive control does not require precise modeling of the controlled object and only relies on input and output data for control, which has unique advantages.

[0003] Model-Free Adaptive Control (MFAC) is an adaptive control method that does not require the establishment of a process model. This method observes the input and output data of the system and uses a certain algorithm to learn and update the control strategy of the system online to adapt to the dynamic changes of the system. The basic principle of model-free adaptive control is to observe the input and output data of the system and use a certain algorithm to learn and update the control strategy of the system online. The controller compares the actual output of the system with the expected output to obtain an error signal, and then uses this error signal to update the control strategy of the system to minimize the system error.

[0004] In communication operation and maintenance, effective management and dynamic adjustment of bandwidth resources are the key to ensuring the quality of network communication. Model-free adaptive control can achieve closed-loop control by monitoring the utilization of network bandwidth in real time and dynamically adjusting the bandwidth allocation strategy according to the preset target bandwidth utilization or network performance indicators.

[0005] How to dynamically adjust the bandwidth and achieve closed-loop control based on model-free adaptive control is a technical problem that needs to be solved. Summary of the invention

[0006] The technical task of the present invention is to address the above shortcomings and provide a closed-loop bandwidth adjustment method and system based on model-free adaptive control to solve the technical problem of how to dynamically adjust the bandwidth based on model-free adaptive control and realize closed-loop control.

[0007] In a first aspect, the present invention provides a closed-loop bandwidth adjustment system based on model-free adaptive control, comprising a data acquisition module, a model-free adaptive controller, a bandwidth adjustment execution module, and a performance evaluation feedback module;

[0008] The data acquisition module is used to monitor the target network in real time, collect operation and maintenance data of the target network and send the operation and maintenance data to the model-free adaptive controller, wherein the operation and maintenance data includes bandwidth utilization and service bandwidth of the target network;

[0009] The model-free adaptive controller is configured with a model-free adaptive algorithm with a hysteresis time constraint, which is used to adjust the network bandwidth allocation strategy of the target network based on the operation and maintenance data through the model-free adaptive algorithm, output the adjusted service bandwidth, and send the adjusted network bandwidth to the bandwidth adjustment execution module;

[0010] The bandwidth adjustment execution module is used to adjust the network bandwidth of the target network based on the adjusted network bandwidth, and increase or decrease the bandwidth resources of a specific link in the target network through the network bandwidth adjustment;

[0011] The performance evaluation feedback module is used to obtain the operation and maintenance data of the adjusted target network from the data acquisition module, perform performance evaluation on the adjusted target network based on the operation and maintenance data, and feed back the obtained evaluation results to the model-free adaptive controller; correspondingly, the model-free adaptive controller is used to receive the operation and maintenance data of the adjusted target network from the data acquisition module, and optimize the current model-free adaptive algorithm and network bandwidth allocation strategy based on the operation and maintenance data and the evaluation results.

[0012] Preferably, the performance evaluation feedback module evaluates the improvement of bandwidth utilization and network congestion in the target network through performance evaluation to obtain an evaluation result.

[0013] Preferably, the model-free adaptive controller is used to perform the following network bandwidth allocation strategy adjustment on the target network:

[0014] Based on project experience or experimental methods, obtain the best bandwidth utilization under different bandwidths;

[0015] When the network load changes more than the predetermined frequency, the service bandwidth is adjusted based on a model-free adaptive control algorithm with hysteresis time constraints, so that the bandwidth utilization rate can stably and quickly track the optimal bandwidth utilization rate.

[0016] Preferably, for the model-free adaptive control algorithm with lag time constraint, its input direction and output direction are set, and the input items include the actual bandwidth utilization y(k) at time k, the actual bandwidth utilization y(k-1) at time k-1, the service bandwidth u(k-1) at time k-1, the service bandwidth u(k-2) at time k-2, the service bandwidth u(k-1-τ) at time k-1-τ, the service bandwidth u(k-2-τ) at time k-2-τ, and the optimal bandwidth utilization y at time k+1 * (k+1), where τ represents the lag time constant, and the output term is the service bandwidth u(k) at time k. The calculation formula of the service bandwidth u(k) at time k is as follows:

[0017]

[0018] Where T represents the sampling time, ρ, η and λ represent weight coefficients, ρ∈(0,1), η∈(0,10), λ∈(0,100),

[0019]

[0020] Among them, ξ and μ represent weight coefficients, ξ∈(0,2), μ∈(0,10);

[0021] When the bandwidth strategy is adjusted, the service bandwidth at time k is obtained as output through the model-free adaptive control algorithm with lag time constraint. When the service bandwidth size is adjusted based on the model-free adaptive control algorithm with lag time constraint, the characteristic parameters can be obtained by each iteration of the calculation process only by the measurement data of the closed-loop test. Then a control signal u(k) is generated.

[0022] In a second aspect, the present invention provides a closed-loop bandwidth adjustment method based on model-free adaptive control, wherein the closed-loop bandwidth adjustment is implemented by a closed-loop bandwidth adjustment system based on model-free adaptive control as described in any one of the first aspects, and the method comprises the following steps:

[0023] The target network is monitored in real time through the data acquisition module, operation and maintenance data of the target network is collected and sent to the model-free adaptive controller, wherein the operation and maintenance data includes bandwidth utilization and service bandwidth of the target network;

[0024] Based on the operation and maintenance data, the network bandwidth allocation strategy of the target network is adjusted by a model-free adaptive algorithm configured in the model-free adaptive controller, the adjusted service bandwidth is output, and the adjusted network bandwidth is sent to the bandwidth adjustment execution module;

[0025] Adjust the network bandwidth of the target network based on the adjusted network bandwidth, and increase or decrease the bandwidth resources of a specific link in the target network through the network bandwidth adjustment;

[0026] The operation and maintenance data of the adjusted target network is obtained from the data acquisition module, and the performance of the adjusted target network is evaluated based on the operation and maintenance data, and the evaluation results are fed back to the model-free adaptive controller; correspondingly, the operation and maintenance data of the adjusted target network is received from the data acquisition module through the model-free adaptive controller, and the current model-free adaptive algorithm and network bandwidth allocation strategy are optimized based on the operation and maintenance data and the evaluation results.

[0027] Preferably, the improvement of bandwidth utilization and the improvement of network congestion in the target network are evaluated through performance evaluation to obtain an evaluation result.

[0028] Preferably, the network bandwidth allocation strategy of the target network is adjusted by the model-free adaptive controller as follows:

[0029] Based on project experience or experimental methods, obtain the best bandwidth utilization under different bandwidths;

[0030] When the network load changes more than the predetermined frequency, the service bandwidth is adjusted based on a model-free adaptive control algorithm with hysteresis time constraints, so that the bandwidth utilization rate can stably and quickly track the optimal bandwidth utilization rate.

[0031] Preferably, for the model-free adaptive control algorithm with lag time constraint, its input direction and output direction are set, and the input items include the actual bandwidth utilization y(k) at time k, the actual bandwidth utilization y(k-1) at time k-1, the service bandwidth u(k-1) at time k-1, the service bandwidth u(k-2) at time k-2, the service bandwidth u(k-1-τ) at time k-1-τ, the service bandwidth u(k-2-τ) at time k-2-τ, and the optimal bandwidth utilization y at time k+1 * (k+1), where τ represents the lag time constant, and the output term is the service bandwidth u(k) at time k. The calculation formula of the service bandwidth u(k) at time k is as follows:

[0032]

[0033] Where T represents the sampling time, ρ, η and λ represent weight coefficients, ρ∈(0,1), η∈(0,10), λ∈(0,100),

[0034]

[0035] Among them, ξ and μ represent weight coefficients, ξ∈(0,2), μ∈(0,10);

[0036] When the bandwidth strategy is adjusted, the service bandwidth at time k is obtained as output through the model-free adaptive control algorithm with lag time constraint. When the service bandwidth size is adjusted based on the model-free adaptive control algorithm with lag time constraint, the characteristic parameters can be obtained by each iteration of the calculation process only by the measurement data of the closed-loop test. Then a control signal u(k) is generated.

[0037] The closed-loop bandwidth adjustment system and method based on model-free adaptive control of the present invention have the following advantages: it can monitor the network bandwidth utilization in real time, analyze the operation and maintenance data through the model-free adaptive control algorithm, automatically adjust the bandwidth allocation strategy, and realize the closed-loop optimization control of bandwidth resources, so as to improve the operation and maintenance quality in the following aspects: dynamically adjust the bandwidth resource allocation to improve the overall utilization of the network bandwidth; timely discover and solve the network bottleneck problem, alleviate the network congestion phenomenon, improve the communication quality, and enhance the user satisfaction and loyalty; the automated bandwidth adjustment strategy can reduce manual intervention, improve the operation and maintenance efficiency, and reduce the operation and maintenance cost; the model-free adaptive control can realize the rapid response and adaptive adjustment to the change of network status, and enhance the network stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0039] The present invention is further described below in conjunction with the accompanying drawings.

[0040] Figure 1 This is a flowchart of a closed-loop bandwidth adjustment method based on model-free adaptive control in Example 2. DETAILED DESCRIPTION

[0041] The present invention is further described below in conjunction with the accompanying drawings and specific embodiments so that those skilled in the art can better understand the present invention and implement it. However, the embodiments are not intended to limit the present invention. In the absence of conflict, the embodiments of the present invention and the technical features in the embodiments may be combined with each other.

[0042] The embodiments of the present invention provide a closed-loop bandwidth adjustment system and method based on model-free adaptive control, which are used to solve the technical problem of how to dynamically adjust the bandwidth based on model-free adaptive control and realize closed-loop control.

[0043] Embodiment 1:

[0044] The invention discloses a closed-loop bandwidth adjustment system based on model-free adaptive control, comprising a data acquisition module, a model-free adaptive controller, a bandwidth adjustment execution module and a performance evaluation feedback module.

[0045] The data acquisition module is used to monitor the target network in real time, collect the operation and maintenance data of the target network and send the operation and maintenance data to the model-free adaptive controller, wherein the operation and maintenance data includes the bandwidth utilization and service bandwidth of the target network.

[0046] The model-free adaptive controller is configured with a model-free adaptive algorithm with a lag time constraint, which is used to adjust the network bandwidth allocation strategy of the target network based on operation and maintenance data through the model-free adaptive algorithm, output the adjusted service bandwidth, and send the adjusted network bandwidth to the bandwidth adjustment execution module.

[0047] As a specific implementation of the model-free adaptive controller, the controller is used to perform the following network bandwidth allocation policy adjustment on the target network:

[0048] (1) Based on project experience or experimental methods, obtain the optimal bandwidth utilization under different bandwidths;

[0049] (2) When the network load changes more than the predetermined frequency, the service bandwidth is adjusted based on a model-free adaptive control algorithm with a hysteresis time constraint, so that the bandwidth utilization rate can stably and quickly track the optimal bandwidth utilization rate.

[0050] For the model-free adaptive control algorithm with lag time constraint disclosed in this embodiment, its input direction and output direction are set, and the input items include the actual bandwidth utilization y(k) at time k, the actual bandwidth utilization y(k-1) at time k-1, the service bandwidth u(k-1) at time k-1, the service bandwidth u(k-2) at time k-2, the service bandwidth u(k-1-τ) at time k-1-τ, the service bandwidth u(k-2-τ) at time k-2-τ, and the optimal bandwidth utilization y at time k+1 * (k+1), where τ represents the lag time constant, and the output term is the service bandwidth u(k) at time k. The calculation formula of the service bandwidth u(k) at time k is as follows:

[0051]

[0052] Where T represents the sampling time, ρ, η and λ represent weight coefficients, ρ∈(0,1), η∈(0,10), λ∈(0,100),

[0053]

[0054] Among them, ξ and μ represent weight coefficients, ξ∈(0,2), μ∈(0,10);

[0055] In this embodiment, the loop control of the model-free adaptive algorithm controller is described as follows: The characteristic parameter at time k is obtained by equation (2) through the service bandwidth at time k-1 and time k-2-τ, the actual bandwidth utilization rate fed back by the acquisition module at time k and time k-1, and the characteristic parameter at time k-1. Formula (1) is used to calculate the control input at this moment, i.e., the service bandwidth u(k) at the current moment, through the service bandwidth at time k-1 and time k-1-τ, the actual bandwidth utilization rate fed back by the data acquisition module at time k, the characteristic parameter at time k, and the expected output at time k+1, i.e., the setting value of the optimal bandwidth utilization rate. u(k) will be passed to the bandwidth adjustment execution module to dynamically adjust the bandwidth value. The acquisition module will collect the actual bandwidth utilization rate after bandwidth adjustment and obtain the output of the controlled system, i.e., the actual bandwidth utilization rate y(k+1). The obtained data is used as the input data of the model-free adaptive algorithm controller in the next cycle of the control loop.

[0056] When adjusting the bandwidth strategy, the service bandwidth at time k is obtained as output through the model-free adaptive control algorithm with lag time constraint. When adjusting the service bandwidth size based on the model-free adaptive control algorithm with lag time constraint, the characteristic parameters can be obtained by each iteration of the calculation process with only the measurement data of the closed-loop test. Then a control signal u(k) is generated.

[0057] The bandwidth adjustment execution module is used to adjust the network bandwidth of the target network based on the adjusted network bandwidth, and increase or decrease the bandwidth resources of a specific link in the target network through the network bandwidth adjustment.

[0058] The performance evaluation feedback module is used to obtain the operation and maintenance data of the adjusted target network from the data acquisition module, perform performance evaluation on the adjusted target network based on the operation and maintenance data, and feed back the obtained evaluation results to the model-free adaptive controller; correspondingly, the model-free adaptive controller is used to receive the operation and maintenance data of the adjusted target network from the data acquisition module, and optimize the current model-free adaptive algorithm and network bandwidth allocation strategy based on the operation and maintenance data and the evaluation results.

[0059] In this embodiment, the performance evaluation feedback module evaluates the improvement of bandwidth utilization and network congestion in the target network through performance evaluation to obtain an evaluation result.

[0060] The closed-loop bandwidth adjustment system disclosed in this embodiment has the following working process:

[0061] Data collection: Real-time acquisition of operation and maintenance data such as network bandwidth utilization.

[0062] (1) Data analysis: The model-free adaptive controller uses the collected data to analyze and identify bottlenecks and redundancies in network bandwidth.

[0063] (2) Strategy generation: Based on the analysis results, the model-free adaptive controller generates targeted bandwidth adjustment strategies.

[0064] (3) Policy execution: The bandwidth adjustment execution module adjusts bandwidth resources according to the generated policy.

[0065] (4) Performance evaluation: Evaluate the performance of the adjusted network, paying particular attention to the improvement in bandwidth utilization and the improvement in network congestion.

[0066] (5) Feedback adjustment: The evaluation results are fed back to the model-free adaptive controller, and the control algorithm and bandwidth allocation strategy are adjusted according to the feedback results to form a closed-loop control.

[0067] Embodiment 2:

[0068] The present invention provides a closed-loop bandwidth adjustment method based on model-free adaptive control, which implements closed-loop bandwidth adjustment through the system disclosed in Example 1. The method includes the following steps:

[0069] Step S100: monitor the target network in real time through the data acquisition module, collect operation and maintenance data of the target network and send the operation and maintenance data to the model-free adaptive controller, wherein the operation and maintenance data includes bandwidth utilization and service bandwidth of the target network;

[0070] Step S200: Based on the operation and maintenance data, the network bandwidth allocation strategy of the target network is adjusted by a model-free adaptive algorithm configured in the model-free adaptive controller, and the adjusted service bandwidth is output and sent to the bandwidth adjustment execution module;

[0071] Step S300: adjusting the network bandwidth of the target network based on the adjusted network bandwidth, and increasing or decreasing the bandwidth resources of a specific link in the target network through the network bandwidth adjustment;

[0072] Step S400: obtain the operation and maintenance data of the adjusted target network from the data acquisition module, perform performance evaluation on the adjusted target network based on the operation and maintenance data, and feed back the obtained evaluation results to the model-free adaptive controller; correspondingly, receive the operation and maintenance data of the adjusted target network from the data acquisition module through the model-free adaptive controller, and optimize the current model-free adaptive algorithm and network bandwidth allocation strategy based on the operation and maintenance data and the evaluation results.

[0073] As a specific implementation of step S200, the following is performed to adjust the network bandwidth allocation strategy of the target network:

[0074] (1) Based on project experience or experimental methods, obtain the optimal bandwidth utilization under different bandwidths;

[0075] (2) When the network load changes more than the predetermined frequency, the service bandwidth is adjusted based on a model-free adaptive control algorithm with a hysteresis time constraint, so that the bandwidth utilization rate can stably and quickly track the optimal bandwidth utilization rate.

[0076] For the model-free adaptive control algorithm with lag time constraint disclosed in this embodiment, its input direction and output direction are set, and the input items include the actual bandwidth utilization y(k) at time k, the actual bandwidth utilization y(k-1) at time k-1, the service bandwidth u(k-1) at time k-1, the service bandwidth u(k-2) at time k-2, the service bandwidth u(k-1-τ) at time k-1-τ, the service bandwidth u(k-2-τ) at time k-2-τ, and the optimal bandwidth utilization y at time k+1 * (k+1), where τ represents the lag time constant, and the output term is the service bandwidth u(k) at time k. The calculation formula of the service bandwidth u(k) at time k is as follows:

[0077]

[0078] Where T represents the sampling time, ρ, η and λ represent weight coefficients, ρ∈(0,1), η∈(0,10), λ∈(0,100),

[0079]

[0080] Among them, ξ and μ represent weight coefficients, ξ∈(0,2), μ∈(0,10);

[0081] In this embodiment, the loop control of the model-free adaptive algorithm controller is described as follows: The characteristic parameter at time k is obtained by equation (2) through the service bandwidth at time k-1 and time k-2-τ, the actual bandwidth utilization rate fed back by the acquisition module at time k and time k-1, and the characteristic parameter at time k-1. Formula (1) is used to calculate the control input at this moment, i.e., the service bandwidth u(k) at the current moment, through the service bandwidth at time k-1 and time k-1-τ, the actual bandwidth utilization rate fed back by the data acquisition module at time k, the characteristic parameter at time k, and the expected output at time k+1, i.e., the setting value of the optimal bandwidth utilization rate. u(k) will be passed to the bandwidth adjustment execution module to dynamically adjust the bandwidth value. The acquisition module will collect the actual bandwidth utilization rate after bandwidth adjustment and obtain the output of the controlled system, i.e., the actual bandwidth utilization rate y(k+1). The obtained data is used as the input data of the model-free adaptive algorithm controller in the next cycle of the control loop.

[0082] When adjusting the bandwidth strategy, the service bandwidth at time k is obtained as output through the model-free adaptive control algorithm with lag time constraint. When adjusting the service bandwidth size based on the model-free adaptive control algorithm with lag time constraint, the characteristic parameters can be obtained by each iteration of the calculation process with only the measurement data of the closed-loop test. Then a control signal u(k) is generated.

[0083] In this embodiment, the improvement of bandwidth utilization and the improvement of network congestion in the target network are evaluated through performance evaluation to obtain evaluation results.

[0084] The closed-loop bandwidth adjustment system and method based on model-free adaptive control provided by the present invention are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method and core idea of ​​the present invention. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A closed-loop bandwidth adjustment system based on model-free adaptive control, characterized in that: It includes a data acquisition module, a model-free adaptive controller, a bandwidth adjustment execution module, and a performance evaluation feedback module; The data acquisition module is used to monitor the target network in real time, collect operation and maintenance data of the target network and send the operation and maintenance data to the model-free adaptive controller, wherein the operation and maintenance data includes bandwidth utilization and service bandwidth of the target network; The model-free adaptive controller is configured with a model-free adaptive algorithm with a hysteresis time constraint, which is used to adjust the network bandwidth allocation strategy of the target network based on the operation and maintenance data through the model-free adaptive algorithm, output the adjusted service bandwidth, and send the adjusted network bandwidth to the bandwidth adjustment execution module; The bandwidth adjustment execution module is used to adjust the network bandwidth of the target network based on the adjusted network bandwidth, and increase or decrease the bandwidth resources of a specific link in the target network through the network bandwidth adjustment; The performance evaluation feedback module is used to obtain the operation and maintenance data of the adjusted target network from the data acquisition module, perform performance evaluation on the adjusted target network based on the operation and maintenance data, and feed back the obtained evaluation results to the model-free adaptive controller; correspondingly, the model-free adaptive controller is used to receive the operation and maintenance data of the adjusted target network from the data acquisition module, and optimize the current model-free adaptive algorithm and network bandwidth allocation strategy based on the operation and maintenance data and the evaluation results.

2. The closed-loop bandwidth adjustment system based on model-free adaptive control according to claim 1, characterized in that: The performance evaluation feedback module evaluates the improvement of bandwidth utilization and network congestion in the target network through performance evaluation to obtain evaluation results.

3. The closed-loop bandwidth adjustment system based on model-free adaptive control according to claim 1 or 2, characterized in that: The model-free adaptive controller is used to perform the following network bandwidth allocation strategy adjustment on the target network: Based on project experience or experimental methods, obtain the best bandwidth utilization under different bandwidths; When the network load changes more than the predetermined frequency, the service bandwidth is adjusted based on a model-free adaptive control algorithm with hysteresis time constraints, so that the bandwidth utilization rate can stably and quickly track the optimal bandwidth utilization rate.

4. The closed-loop bandwidth adjustment system based on model-free adaptive control according to claim 3, characterized in that: For the model-free adaptive control algorithm with lag time constraint, its input direction and output direction are set, and the input items include the actual bandwidth utilization y(k) at time k, the actual bandwidth utilization y(k-1) at time k-1, the service bandwidth u(k-1) at time k-1, the service bandwidth u(k-2) at time k-2, the service bandwidth u(k-1-τ) at time k-1-τ, the service bandwidth u(k-2-τ) at time k-2-τ, and the optimal bandwidth utilization y at time k+1 * (k+1), where τ represents the lag time constant, and the output term is the service bandwidth u(k) at time k. The calculation formula of the service bandwidth u(k) at time k is as follows: Where T represents the sampling time, ρ, η and λ represent weight coefficients, ρ∈(0,1), η∈(0,10), λ∈(0,100), Among them, ξ and μ represent weight coefficients, ξ∈(0,2), μ∈(0,10); When the bandwidth strategy is adjusted, the service bandwidth at time k is obtained as output through the model-free adaptive control algorithm with lag time constraint. When the service bandwidth size is adjusted based on the model-free adaptive control algorithm with lag time constraint, the characteristic parameters can be obtained by each iteration of the calculation process only by the measurement data of the closed-loop test. Then a control signal u(k) is generated.

5. A closed-loop bandwidth adjustment method based on model-free adaptive control, characterized in that: The closed-loop bandwidth adjustment is implemented by a closed-loop bandwidth adjustment system based on model-free adaptive control as claimed in any one of claims 1 to 4, the method comprising the following steps: The target network is monitored in real time through the data acquisition module, operation and maintenance data of the target network is collected and sent to the model-free adaptive controller, wherein the operation and maintenance data includes bandwidth utilization and service bandwidth of the target network; Based on the operation and maintenance data, the network bandwidth allocation strategy of the target network is adjusted by a model-free adaptive algorithm configured in the model-free adaptive controller, the adjusted service bandwidth is output, and the adjusted network bandwidth is sent to the bandwidth adjustment execution module; Adjust the network bandwidth of the target network based on the adjusted network bandwidth, and increase or decrease the bandwidth resources of a specific link in the target network through the network bandwidth adjustment; The operation and maintenance data of the adjusted target network is obtained from the data acquisition module, and the performance of the adjusted target network is evaluated based on the operation and maintenance data, and the evaluation results are fed back to the model-free adaptive controller; correspondingly, the operation and maintenance data of the adjusted target network is received from the data acquisition module through the model-free adaptive controller, and the current model-free adaptive algorithm and network bandwidth allocation strategy are optimized based on the operation and maintenance data and the evaluation results.

6. The closed-loop bandwidth adjustment method based on model-free adaptive control according to claim 5, characterized in that: The improvement of bandwidth utilization and network congestion in the target network are evaluated through performance evaluation to obtain evaluation results.

7. The closed-loop bandwidth adjustment method based on model-free adaptive control according to claim 5 or 6, characterized in that: The network bandwidth allocation strategy of the target network is adjusted by the model-free adaptive controller as follows: Based on project experience or experimental methods, obtain the best bandwidth utilization under different bandwidths; When the network load changes more than the predetermined frequency, the service bandwidth is adjusted based on a model-free adaptive control algorithm with hysteresis time constraints, so that the bandwidth utilization rate can stably and quickly track the optimal bandwidth utilization rate.

8. The closed-loop bandwidth adjustment method based on model-free adaptive control according to claim 7, characterized in that: For the model-free adaptive control algorithm with lag time constraint, its input direction and output direction are set, and the input items include the actual bandwidth utilization y(k) at time k, the actual bandwidth utilization y(k-1) at time k-1, the service bandwidth u(k-1) at time k-1, the service bandwidth u(k-2) at time k-2, the service bandwidth u(k-1-τ) at time k-1-τ, the service bandwidth u(k-2-τ) at time k-2-τ, and the optimal bandwidth utilization y at time k+1 * (k+1), where τ represents the lag time constant, and the output term is the service bandwidth u(k) at time k. The calculation formula of the service bandwidth u(k) at time k is as follows: Where T represents the sampling time, ρ, η and λ represent weight coefficients, ρ∈(0,1), η∈(0,10), λ∈(0,100), Among them, ξ and μ represent weight coefficients, ξ∈(0,2), μ∈(0,10); When the bandwidth strategy is adjusted, the service bandwidth at time k is obtained as output through the model-free adaptive control algorithm with lag time constraint. When the service bandwidth size is adjusted based on the model-free adaptive control algorithm with lag time constraint, the characteristic parameters can be obtained by each iteration of the calculation process only by the measurement data of the closed-loop test. Then a control signal u(k) is generated.

Images