Hybrid congestion control method and system based on dynamic adjustment of monitoring time period

Abstract

The invention provides a hybrid congestion control method and system based on dynamic adjustment of a monitoring time period, and relates to the technical field of communication, and the method comprises the steps: obtaining a real-time network state, and calculating a round-trip delay change according to the network state to obtain network state data; performing normalization processing on the network state data to standardize the network state data, comparing the standardized network state data with a preset threshold to classify the network state data after normalization processing, and calculating a monitoring time period value according to a classification result to dynamically adjust the monitoring time period value; judging whether the current time reaches a monitoring time period value or not; and if yes, switching the current congestion window to a congestion window which is generated based on deep reinforcement learning and is adjusted by an optimal action according to the monitoring time period value. Compared with a traditional fixed monitoring time period scheme, the method not only has higher environment generalization ability, but also can quickly adapt to network condition changes through real-time state classification.

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and in particular to a hybrid congestion control method and system based on dynamic adjustment of monitoring time period. Background Art

[0002] Congestion control algorithms are core mechanisms used in network protocols (such as the Transmission Control Protocol (TCP)) to avoid or alleviate network congestion. TCP includes a variety of heuristic congestion control algorithms. When network traffic exceeds the processing capacity of links, routers, or switches, congestion symptoms such as increased round-trip delay, increased packet loss, and decreased throughput can result. Congestion control algorithms dynamically adjust the sender's transmission rate or window size to balance network load and ensure stable and efficient data transmission.

[0003] The core of the congestion control algorithm is to dynamically adjust the sender's congestion window (cwnd), or sending rate, by sensing network status (such as packet loss, round-trip delay variations, and throughput). The congestion window represents the maximum number of packets that a sender can continuously send before receiving an acknowledgment (ACK). It reflects the network's carrying capacity and is the most commonly used control metric. Common network status signals include packet loss, round-trip time (RTT), and throughput. Packet loss is often considered a direct indicator of congestion (e.g., due to router buffer overflows). An increase in RTT may indicate a backlog in a link or router queue, signaling potential congestion. Throughput represents the difference between the actual transmission rate and the bottleneck link bandwidth, reflecting resource utilization efficiency.

[0004] Currently, traditional congestion control algorithms (such as TCP, CUBIC, and BBR) rely on fixed rules to adjust the congestion window, making them difficult to adapt to dynamic network environments. Deep reinforcement learning (DRL)-based congestion control algorithms (such as Aurora), while highly adaptable, suffer from high computational overhead and limited stability. Existing hybrid approaches (such as Orca and Spine) combine heuristic and DRL-based congestion control algorithms. These methods switch between the heuristic and DRL-based congestion control algorithms using a fixed monitoring period. However, these approaches have limitations. For example, when the monitoring period is too long, the heuristic congestion control algorithm dominates, potentially leading to increased latency and packet loss. Conversely, when the monitoring period is too short, the DRL-based congestion control algorithm plays a more prominent role, resulting in initial instability and higher CPU utilization. Summary of the Invention

[0005] Based on this, the purpose of the present invention is to provide a hybrid congestion control method and system based on dynamically adjusting the monitoring time period, so as to solve the limitation problem caused by the hybrid method in the prior art adopting a fixed monitoring time period.

[0006] In one aspect, the present invention provides a hybrid congestion control method based on dynamically adjusting a monitoring time period, the method comprising: Acquire real-time network status, and calculate round-trip delay change based on the network status to obtain network status data, the network status data including round-trip delay, round-trip delay change rate, and packet loss rate; performing normalization processing on the network status data to standardize the network status data, the standardized network status data including a standardized round-trip delay and a standardized round-trip delay change rate, comparing the standardized network status data with a preset threshold to classify the normalized network status data, and calculating a monitoring time period value based on the classification result to dynamically adjust the monitoring time period value; Determine whether the current time reaches the monitoring time period value; If so, the current congestion window is switched to the congestion window adjusted based on the optimal action generated by deep reinforcement learning according to the monitoring time period value.

[0007] This hybrid congestion control method, based on dynamically adjusting the monitoring period, effectively identifies congestion noise data in diverse network environments, including random packet loss and delay jitter, significantly improving transmission control accuracy. Compared to traditional fixed-period monitoring schemes, this dynamic adjustment method, which combines a deep reinforcement learning-based congestion control algorithm with a heuristic congestion control algorithm, not only exhibits stronger generalization capabilities but also rapidly adapts to changing network conditions through real-time state classification.

[0008] In addition, the hybrid congestion control method based on dynamic adjustment of the monitoring time period according to the present invention may also have the following additional technical features: Furthermore, the calculation formula for the normalized round-trip delay is: ; Where, Represents normalized round-trip time; RTT t Indicates the RTT value at the current time t, RTT min is the minimum observed RTT; where RTT represents the round-trip time; The formula for calculating the normalized round-trip delay variation rate is: ; Where, Indicates the normalized round-trip delay change rate, RTT t-1 Indicates the RTT value at time t-1; The packet loss rate calculation formula is: ; Where Loss_pck t Indicates the number of packet losses, Send_pck t Indicates the number of packets sent.

[0009] Furthermore, in the step of comparing the normalized network status data with preset thresholds to classify the normalized network status data, the preset threshold for the normalized round-trip delay is a first threshold, the preset threshold for the normalized round-trip delay variation rate is a second threshold, and the preset threshold for the packet loss rate is a third threshold; the method further includes: When the normalized round-trip delay is not greater than the first threshold, the normalized round-trip delay change rate is less than the second threshold, and the packet loss rate is less than the third threshold, the network state of the bottleneck link is stable and non-congested. In this case, the monitoring period is increased to prioritize the use of the heuristic congestion control algorithm for sending rate decisions. The calculation formula for the monitoring time period is: ; Where, MTP n Indicates the current monitoring time period; MTP n-1 Indicates the last monitoring time period; S(x) represents the Sigmoid function, , where x represents a random sample selected from the normal distribution of the inverse of the round-trip delay.

[0010] Furthermore, in the step of comparing the normalized network status data with preset thresholds to classify the normalized network status data, the preset threshold for the normalized round-trip delay is a first threshold, the preset threshold for the normalized round-trip delay variation rate is a second threshold, and the preset threshold for the packet loss rate is a third threshold; the method further includes: When the normalized round-trip delay is no greater than a first threshold, the normalized round-trip delay change rate is no less than a second threshold, and the packet loss rate is less than a third threshold, the network state of the bottleneck link is close to congestion. The monitoring period is reduced to determine the sending rate using a congestion control algorithm based on deep reinforcement learning. The calculation formula for the monitoring time period is: ; Where, MTP n Indicates the current monitoring time period; MTP n-1Indicates the last monitoring time period; Indicates that the monitoring period is dynamically reduced at an exponential rate based on the degree of increase in normalized round-trip delay.

[0011] Furthermore, in the step of comparing the normalized network status data with preset thresholds to classify the normalized network status data, the preset threshold for the normalized round-trip delay is a first threshold, the preset threshold for the normalized round-trip delay variation rate is a second threshold, and the preset threshold for the packet loss rate is a third threshold; the method further includes: When the normalized round-trip delay is no greater than a first threshold and the packet loss rate is no less than a third threshold, the network status of the bottleneck link is not congested, but packet loss occurs. In this case, the congestion window is switched to a window adjusted by deep reinforcement learning. The conversion formula for converting actions into congestion windows is: ; Where, cwnd represents the congestion window, Represents the optimal action a generated based on deep reinforcement learning at time t t Adjusted congestion window; Represents the optimal action a generated based on deep reinforcement learning at time t-1 t-1 Adjusted congestion window.

[0012] Furthermore, in the step of comparing the normalized network status data with preset thresholds to classify the normalized network status data, the preset threshold for the normalized round-trip delay is a first threshold, the preset threshold for the normalized round-trip delay variation rate is a second threshold, and the preset threshold for the packet loss rate is a third threshold; the method further includes: When the normalized round trip delay is greater than the first threshold, the network can no longer bear the additional data packets, and the monitoring time period is reduced.

[0013] The calculation formula for the monitoring time period is: ; Where, MTP n Indicates the current monitoring time period; MTP n-1 Indicates the last monitoring time period; Indicates that the monitoring period is dynamically reduced at an exponential rate based on the degree of increase in normalized round-trip delay.

[0014] Another aspect of the present invention provides a hybrid congestion control system based on dynamically adjusting a monitoring time period, the system comprising: An acquisition module is used to obtain real-time network status and calculate the round-trip delay change based on the network status to obtain network status data, the network status data including round-trip delay, round-trip delay change rate and packet loss rate; a classification module, configured to perform normalization processing on the network status data to standardize the network status data, the standardized network status data including a standardized round-trip delay and a standardized round-trip delay change rate, compare the standardized network status data with a preset threshold to classify the normalized network status data, and calculate a monitoring time period value based on the classification result to dynamically adjust the monitoring time period value; A judgment module is used to judge whether the current time reaches the monitoring time period value; The first execution module is used to switch the current congestion window to the congestion window adjusted by the optimal action generated based on deep reinforcement learning according to the monitoring time period value if the current time reaches the monitoring time period value.

[0015] Another aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the hybrid congestion control method based on dynamically adjusting the monitoring time period as described above.

[0016] On the other hand, the present invention also provides a data processing device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the hybrid congestion control method based on dynamically adjusting the monitoring time period as described above is implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 Flowchart of a hybrid congestion control method based on dynamic adjustment of monitoring time period in an embodiment of the present invention; Figure 2 Schematic diagram of the principle of dynamic switching mechanism of monitoring time period in an embodiment of the present invention; The following specific embodiments will further illustrate the present invention in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION

[0018] To facilitate understanding of the present invention, the present invention will be described more fully below with reference to the accompanying drawings. The drawings illustrate several embodiments of the present invention. However, the present invention may be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and comprehensive understanding of the present invention.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one skilled in the art to which this invention pertains. The terms used in this specification of the present invention are for the purpose of describing specific embodiments only and are not intended to limit the present invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0020] To address the limitations of fixed monitoring time periods in existing congestion control algorithms that combine a heuristic congestion control algorithm with a reinforcement learning-based congestion control algorithm, the present application provides a hybrid congestion control method and system based on dynamically adjusted monitoring time periods. Specifically, the technical solution adopted by the present application collects network status and further calculates delay changes; then normalizes the obtained network status data to obtain normalized network status data; then uses a status analyzer to analyze the normalized network status data and compare it with a preset threshold, classifying it into one of four predefined situations based on the comparison and calculating an appropriate monitoring time period value; finally, a judgment is made based on the dynamically adjusted monitoring time period value. If the monitoring time period value is not reached at this time, the heuristic congestion control algorithm continues to be used to calculate the congestion window; if the monitoring time period value is reached, the congestion control algorithm based on deep reinforcement learning is switched to generate the optimal action to adjust the congestion window.

[0021] A hybrid congestion control mechanism that dynamically adjusts the monitoring period can effectively identify congestion noise data in different network environments, including random packet loss and delay jitter, significantly improving transmission control accuracy. Compared to traditional fixed monitoring period schemes, this dynamic adjustment method, which combines a congestion control algorithm based on deep reinforcement learning with a heuristic congestion control algorithm, not only has stronger environmental generalization capabilities but also can quickly adapt to changing network conditions through real-time status classification.

[0022] To facilitate understanding of the present invention, several embodiments of the present invention are provided below. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and comprehensive disclosure of the present invention.

[0023] Example 1 See also Figure 1 , which shows a hybrid congestion control method based on dynamic adjustment of monitoring time period in a first embodiment of the present invention, the method includes steps S101 to S106: S101: Acquire real-time network status, and calculate round-trip delay changes based on the network status to obtain network status data.

[0024] As a specific example, real-time network status is obtained from confirmed data packets based on the round-trip delay as a period, and the delay change is calculated based on the network status to obtain network status data. In this embodiment, the network status data includes the round-trip delay, the round-trip delay change rate, and the packet loss rate.

[0025] S102: Perform normalization processing on the network status data to standardize the network status data.

[0026] Specifically, the standardized network status data includes the standardized round-trip delay and the standardized round-trip delay change rate. The calculation formula for the standardized round-trip delay is: ; Where, Represents normalized round-trip time; RTT t Indicates the RTT value at the current time t, RTT min is the minimum observed RTT; where RTT represents the round-trip time.

[0027] Furthermore, the calculation formula for the normalized round-trip delay change rate is: ; Where, Indicates the normalized round-trip delay change rate, RTT t-1 Indicates the RTT value at time t-1; Furthermore, the packet loss rate calculation formula is: ; Where, Loss t Indicates the packet loss rate; Loss_pck t Indicates the number of packet losses, Send_pck t Indicates the number of packets sent.

[0028] S103 : Compare the normalized network status data with a preset threshold to classify the normalized network status data, and calculate a monitoring time period value according to the classification result to dynamically adjust the monitoring time period value.

[0029] Specifically, the preset threshold value of the normalized round-trip delay is the first threshold value, the preset threshold value of the normalized round-trip delay change rate is the second threshold value, and the preset threshold value of the packet loss rate is the third threshold value. In this embodiment, the first threshold value is 1.5, the second threshold value is 0, and the third threshold value is 0.2. Furthermore, the network status of the bottleneck link can be divided into four situations, specifically: (1) When the normalized round-trip delay is ≤1.5, the normalized round-trip delay variation rate is <0, and the packet loss rate is <0.2, it means that the network state of the bottleneck link is stable and non-congested, and more data packets can be transmitted. In this case, it is necessary to increase the monitoring time period to give priority to the heuristic congestion control algorithm for sending rate decision. At this time, the calculation formula of the monitoring time period is: ; Where, MTP n Indicates the current monitoring time period; MTP n-1 Indicates the last monitoring time period; S(x) represents the Sigmoid function, , where x represents a random sample selected from the normal distribution of the inverse of the round-trip delay.

[0030] (2) When the normalized round-trip delay is ≤1.5, the normalized round-trip delay variation rate is ≥0, and the packet loss rate is <0.2, it means that the network state of the bottleneck link is close to the congested state. Although it is in a non-congested state, the number of packets queued in the cache of the switch on the bottleneck link increases. At this time, it is necessary to slowly reduce the monitoring time period to maximize the transmission rate, so as to determine the sending rate with the help of the congestion control algorithm based on deep reinforcement learning. At this time, the calculation formula of the monitoring time period is: ; Where, Indicates that the monitoring period is dynamically reduced at an exponential rate based on the degree of increase in normalized round-trip delay.

[0031] (3) When the normalized round-trip delay is ≤1.5 and the packet loss rate is ≥0.2, the bottleneck link is not congested, but packet loss still occurs. This indicates that the loss is mainly due to random factors, specifically channel errors or interference. When encountering this random packet loss, it is necessary to switch to a conservative deep reinforcement learning-based solution; at this time, the conversion formula between action and congestion window is: ; Where, cwnd represents the congestion window, Represents the optimal action a generated based on deep reinforcement learning at time t t Adjusted congestion window; Represents the optimal action a generated based on deep reinforcement learning at time t-1 t-1 Adjusted congestion window.

[0032] (4) When the normalized round-trip delay is greater than 1.5, that is, the normalized delay exceeds the threshold, it means that the network can no longer withstand additional data packets. In this case, no distinction is made between delay packet loss and random packet loss. There are two reasons for this: first, the probability of congestion packet loss is much higher than random packet loss; second, a more conservative method is used, namely the method based on deep reinforcement learning, that is, the sending rate control strategy output by the deep reinforcement learning control module, which is applicable to both types of packet loss. At this time, the monitoring time period needs to be reduced. Specifically, the calculation formula for the monitoring time period is: ; MTP n Indicates the current monitoring time period; MTP n-1 Indicates the last monitoring time period; Indicates that the monitoring period is dynamically reduced at an exponential rate based on the degree of increase in normalized round-trip delay. S104: Determine whether the current time reaches the monitoring time period value.

[0033] As a specific example, the current time is the time elapsed since the last monitoring time period, i.e., the time elapsed since the last selection of a Deep Reinforcement Learning (DRL) output. Specifically, if the current time has not reached the monitoring time period, step S105 is executed; if the current time has reached the monitoring time period, step S106 is executed.

[0034] S105: Calculate the congestion window using a heuristic congestion control algorithm.

[0035] S106. Switch the current congestion window to a congestion window adjusted based on the optimal action generated by deep reinforcement learning according to the monitoring time period value.

[0036] Specifically, the MTP controller chooses to use a heuristic congestion window or a congestion window based on deep reinforcement learning according to the current MTP value. What is switched is the calculation of the window, that is, switching to a heuristic window or a window adjusted by action based on deep reinforcement learning.

[0037] Monitoring time period dynamic switching mechanism such as Figure 2 As shown, intervals of different lengths represent continuous monitoring time periods, specifically, MTP n-1 Indicates the last monitoring time period, MTP n Indicates the current monitoring time period, MTP n+1Indicates the next monitoring time period. During each monitoring time period, the monitoring time period value is dynamically adjusted according to the network status. If the monitoring time period threshold is not reached at this time, the heuristic congestion control algorithm represented by the orange arrow (such as TCP'scwnd, that is, the congestion window based on the heuristic congestion control algorithm) is used to control the sending rate; when the monitoring time period threshold is reached, the congestion window based on deep reinforcement learning (i.e., DRL's cwnd) represented by the purple arrow is enabled. at , a congestion window based on deep reinforcement learning. The algorithm demonstrates how it dynamically adapts heuristics and deep reinforcement learning methods over time, balancing performance and overhead to address varying network conditions.

[0038] The monitoring time period value is calculated based on the current network status for judgment. If the monitoring time period threshold is not reached at this time, the heuristic congestion control algorithm is continued to be used to calculate the congestion window; if the monitoring time period threshold is reached, the congestion control algorithm based on deep reinforcement learning is switched to according to the network status S collected at time t. t , the Actor-Critic algorithm is used to train the agent, where the agent is an entity that learns to make decisions by interacting with the environment, and the policy network is based on the currently collected network state S t The generated policy decision selects the optimal action. The action represents the ratio of sending rates between consecutive time steps. The action is converted to a congestion window using the action-congestion window conversion formula. A reward function is also designed as a feedback signal to guide network performance optimization, where the network performance optimization objectives are maximum throughput, minimum round-trip delay, and packet loss rate. Finally, a value network evaluates the value function and feedbacks the action quality to guide policy optimization.

[0039] Among them, the reward function is: ; Where R represents the reward of deep reinforcement learning; thr represents the current actual throughput; ζ is the coefficient, ζ=5; loss represents the packet loss rate; thr max Indicates maximum throughput; RTT indicates round-trip time; RTT min Indicates the minimum round-trip delay.

[0040] In summary, the hybrid congestion control method based on dynamically adjusted monitoring time periods in the above-mentioned embodiments of the present invention, through its hybrid congestion control mechanism with dynamically adjusted monitoring time periods, can effectively identify congestion noise data in different network environments, including random packet loss and delay jitter, significantly improving the accuracy of transmission control. Compared to traditional fixed monitoring time period schemes, the dynamic adjustment method, which integrates a congestion control algorithm based on deep reinforcement learning with a heuristic congestion control algorithm, not only has stronger environmental generalization capabilities but also can quickly adapt to changing network conditions through real-time status classification.

[0041] Example 2 The hybrid congestion control system based on dynamically adjusting the monitoring time period in the second embodiment of the present invention includes: An acquisition module is used to obtain real-time network status and calculate the round-trip delay change based on the network status to obtain network status data, the network status data including round-trip delay, round-trip delay change rate and packet loss rate; a classification module, configured to perform normalization processing on the network status data to standardize the network status data, the standardized network status data including a standardized round-trip delay and a standardized round-trip delay change rate, compare the standardized network status data with a preset threshold to classify the normalized network status data, and calculate a monitoring time period value based on the classification result to dynamically adjust the monitoring time period value; A judgment module is used to judge whether the current time reaches the monitoring time period value; The first execution module is used to switch the current congestion window to the congestion window adjusted by the optimal action generated based on deep reinforcement learning according to the monitoring time period value if the current time reaches the monitoring time period value.

[0042] In summary, the hybrid congestion control system based on dynamically adjusted monitoring time periods in the above-mentioned embodiments of the present invention, through its hybrid congestion control mechanism with dynamically adjusted monitoring time periods, can effectively identify congestion noise data in different network environments, including random packet loss and delay jitter, significantly improving the accuracy of transmission control. Compared to traditional fixed monitoring time period schemes, the dynamic adjustment method that integrates a congestion control algorithm based on deep reinforcement learning with a heuristic congestion control algorithm not only has stronger environmental generalization capabilities, but also can quickly adapt to changing network conditions through real-time state classification.

[0043] In addition, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the method in the above embodiment when the program is executed by a processor.

[0044] In addition, an embodiment of the present invention further provides a data processing device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method in the above embodiment when executing the program.

[0045] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0046] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting, or processing it in another suitable manner as necessary, and then storing it in a computer memory.

[0047] It should be understood that various components of the present invention may be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods may be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof may be used: a discrete logic circuit having logic gate circuits for implementing logic functions on data signals, an application-specific integrated circuit having suitable combinational logic gate circuits, a programmable gate array (PGA), a field-programmable gate array (FPGA), etc.

[0048] Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "examples," "specific examples," or "some examples" means that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0049] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to the embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the claims and their equivalents.

Claims

1. A hybrid congestion control method based on dynamic adjustment of monitoring time period, characterized in that: Methods include: Acquire real-time network status, and calculate round-trip delay change based on the network status to obtain network status data, the network status data including round-trip delay, round-trip delay change rate, and packet loss rate; performing normalization processing on the network status data to standardize the network status data, the standardized network status data including a standardized round-trip delay and a standardized round-trip delay change rate, comparing the standardized network status data with a preset threshold to classify the normalized network status data, and calculating a monitoring time period value based on the classification result to dynamically adjust the monitoring time period value; Determine whether the current time reaches the monitoring time period value; If so, the current congestion window is switched to the congestion window adjusted based on the optimal action generated by deep reinforcement learning according to the monitoring time period value.

2. The hybrid congestion control method based on dynamic adjustment of monitoring time period according to claim 1, characterized in that: The formula for calculating the normalized round-trip delay is: ； Where, represents the normalized round-trip delay; RTT t Indicates the RTT value at the current time t, RTT min is the minimum observed RTT; where RTT represents the round-trip time; The calculation formula for the normalized round-trip delay variation rate is: ； Where, Indicates the normalized round-trip delay change rate, RTT t-1 Indicates the RTT value at time t-1; The packet loss rate calculation formula is: ； Where Loss_pck t Indicates the number of packet losses, Send_pck t Indicates the number of packets sent.

3. The hybrid congestion control method based on dynamic adjustment of monitoring time period according to claim 1, characterized in that: In the step of comparing the normalized network status data with preset thresholds to classify the normalized network status data, the preset threshold for the normalized round-trip delay is a first threshold, the preset threshold for the normalized round-trip delay variation rate is a second threshold, and the preset threshold for the packet loss rate is a third threshold; the method further includes: When the normalized round-trip delay is not greater than the first threshold, the normalized round-trip delay change rate is less than the second threshold, and the packet loss rate is less than the third threshold, the network state of the bottleneck link is stable and non-congested. In this case, the monitoring period is increased to prioritize the use of the heuristic congestion control algorithm for sending rate decisions. The calculation formula for the monitoring time period is: ； Where, MTP n Indicates the current monitoring time period; MTP n-1 Indicates the last monitoring time period; S(x) represents the Sigmoid function, , where x represents a random sample selected from the normal distribution of the inverse of the round-trip delay.

4. The hybrid congestion control method based on dynamic adjustment of monitoring time period according to claim 1, characterized in that: In the step of comparing the normalized network status data with preset thresholds to classify the normalized network status data, the preset threshold for the normalized round-trip delay is a first threshold, the preset threshold for the normalized round-trip delay variation rate is a second threshold, and the preset threshold for the packet loss rate is a third threshold; the method further includes: When the normalized round-trip delay is no greater than a first threshold, the normalized round-trip delay change rate is no less than a second threshold, and the packet loss rate is less than a third threshold, the network state of the bottleneck link is close to congestion. The monitoring period is reduced to determine the sending rate using a congestion control algorithm based on deep reinforcement learning. The calculation formula for the monitoring time period is: ； Where, MTP n Indicates the current monitoring time period; MTP n-1 Indicates the last monitoring time period; Indicates that the monitoring period is dynamically reduced at an exponential rate based on the degree of increase in normalized round-trip delay.

5. The hybrid congestion control method based on dynamic adjustment of monitoring time period according to claim 1, characterized in that: In the step of comparing the normalized network status data with preset thresholds to classify the normalized network status data, the preset threshold for the normalized round-trip delay is a first threshold, the preset threshold for the normalized round-trip delay variation rate is a second threshold, and the preset threshold for the packet loss rate is a third threshold; the method further includes: When the normalized round-trip delay is no greater than a first threshold and the packet loss rate is no less than a third threshold, the network status of the bottleneck link is not congested, but packet loss occurs. In this case, the congestion window is switched to a window adjusted by deep reinforcement learning. The conversion formula for converting actions into congestion windows is: ； Where, cwnd represents the congestion window, Represents the optimal action a generated based on deep reinforcement learning at time t t Adjusted congestion window; Represents the optimal action a generated based on deep reinforcement learning at time t-1 t-1 Adjusted congestion window.

6. The hybrid congestion control method based on dynamic adjustment of monitoring time period according to claim 1, characterized in that: In the step of comparing the normalized network status data with preset thresholds to classify the normalized network status data, the preset threshold for the normalized round-trip delay is a first threshold, the preset threshold for the normalized round-trip delay variation rate is a second threshold, and the preset threshold for the packet loss rate is a third threshold; the method further includes: When the normalized round trip delay is greater than the first threshold, the network can no longer bear the additional data packets, and the monitoring time period is reduced. The calculation formula for the monitoring time period is: ； Where, MTP n Indicates the current monitoring time period; MTP n-1 Indicates the last monitoring time period; Indicates that the monitoring period is dynamically reduced at an exponential rate based on the degree of increase in normalized round-trip delay.

7. A hybrid congestion control system based on dynamic adjustment of monitoring time period, characterized in that: The system comprises: An acquisition module is used to obtain real-time network status and calculate the round-trip delay change based on the network status to obtain network status data, the network status data including round-trip delay, round-trip delay change rate and packet loss rate; a classification module, configured to perform normalization processing on the network status data to standardize the network status data, the standardized network status data including a standardized round-trip delay and a standardized round-trip delay change rate, compare the standardized network status data with a preset threshold to classify the normalized network status data, and calculate a monitoring time period value based on the classification result to dynamically adjust the monitoring time period value; A judgment module is used to judge whether the current time reaches the monitoring time period value; The first execution module is used to switch the current congestion window to the congestion window adjusted by the optimal action generated based on deep reinforcement learning according to the monitoring time period value if the current time reaches the monitoring time period value.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the hybrid congestion control method based on dynamic adjustment of the monitoring time period as claimed in any one of claims 1 to 6 is implemented.

9. A data processing device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the hybrid congestion control method based on dynamic adjustment of the monitoring time period according to any one of claims 1 to 6 is implemented.

Images