Intelligent Control Method and System for Data Traffic in Docks

Abstract

This invention relates to the field of traffic control technology, specifically to an intelligent data traffic control method and system for docking stations. The method includes the following steps: obtaining the throughput and timestamp of each interface per unit time; determining slope reversal and abrupt changes to generate task switching boundaries; constructing a difference sequence to determine rate stability changes and generate a strategy switching identifier; calculating a control coefficient based on service level and request frequency to correct the bandwidth ratio; differentiating task types to adjust the cycle and rate level; and constructing a scheduling structure to generate a control instruction set. In this invention, by constructing a bandwidth utilization change sequence of port running data and combining slope reversal and change magnitude determination, accurate identification of task change nodes is achieved. Bandwidth control is performed based on service level tags and port request frequency, making bandwidth resource allocation more aligned with task importance and actual request frequency. Simultaneously, the window length and rate level are dynamically configured based on task interactivity and cycle stability to suppress bandwidth waste and unnecessary transmission delays.

Description

Technical Field

[0001] This invention relates to the field of traffic control technology, and in particular to a method and system for intelligent control of data traffic in a docking station. Background Technology

[0002] The field of traffic control technology primarily involves the intelligent management and allocation of data traffic during multi-channel data transmission to ensure data transmission efficiency, channel resource utilization, and system stability. This field encompasses several core technologies, including network communication interfaces, bus architecture, I / O control strategies, multi-protocol support mechanisms, load balancing algorithms, and traffic priority determination mechanisms. Its main objective is to dynamically assess the load status of various data streams on different transmission paths, and to rationally schedule and optimize data streams on each channel to avoid congestion, reduce latency, and improve transmission bandwidth utilization. Furthermore, this field also involves specific solutions for identifying and classifying real-time and non-real-time data streams, designing queue management mechanisms, and setting buffer allocation strategies to achieve a high-throughput, low-blocking traffic control system architecture.

[0003] The intelligent data traffic control method for expansion docks primarily addresses issues such as data flow conflicts, uneven bandwidth resources, and sudden increases in latency when multiple external interfaces in an expansion dock transmit data in parallel. It proposes an intelligent control method based on a combination of data type identification, port load monitoring, and scheduling control strategies. This method can be widely applied to computing platforms equipped with expansion docks, such as laptops, all-in-one devices, and mobile workstations. By sensing the status and prioritizing data flows from multiple interfaces, it enables priority scheduling and resource allocation for critical data flows, improving overall data transmission efficiency and user experience.

[0004] Traditional control methods rely on basic data type identification and port load detection for scheduling. However, they fail to analyze the slope of dynamic changes in bandwidth utilization and cannot effectively detect sudden data flow changes. This leads to delayed scheduling responses, and changes in task transmission status within the sliding window are not promptly identified, easily causing control strategies to fail. Traditional methods often rely on fixed priority presets for control strategies. In scenarios with high-frequency data requests or changes in task level labels, the lack of real-time optimization mechanisms can cause congestion or increased latency in critical tasks. For example, interactive data may be frequently requested during transmission, but the bandwidth allocation remains fixed, failing to adapt to fluctuations in actual demand. This results in decreased transmission efficiency and inconsistent user experience under high load conditions. Summary of the Invention

[0005] The purpose of this invention is to address the shortcomings of existing technologies by proposing an intelligent data traffic control method and system for expansion docks.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: a method for intelligent control of data traffic in a docking station, comprising the following steps:

[0007] S1: Obtain the operating data of each interface of the expansion dock within the current control cycle, construct the bandwidth utilization change sequence over time, locate the port task change signal point, and generate window task switching boundary position information;

[0008] S2: Call the time period identified by the window task switching boundary position information, compare the unit time effective payload transmission rate of the same port in the two sliding windows before and after, determine whether the rate stability state of the current window has changed, identify the port that needs to be adjusted, and generate a control strategy switching trigger identifier.

[0009] S3: According to the control strategy, switch the port marked as needing adjustment in the trigger identifier, read the current maximum bandwidth allocation value, combine the DiffServ service level code point tag corresponding to the task and the number of port requests in the current unit time, calculate the bandwidth control priority coefficient, adjust the original bandwidth allocation ratio, and generate the port bandwidth allocation control result.

[0010] S4: Call the port number in the port bandwidth allocation and control result, read the current sliding window period and the rate level configuration under the IEEE 802.3 standard, distinguish between interactive and throughput tasks, adjust the window period and channel rate, and generate window control period and rate level configuration information.

[0011] As a further embodiment of the present invention, the window task switching boundary position information includes a jump time identifier, a port number record, a control cycle index number, and a data mutation type label; the control strategy switching trigger identifier includes a window rate change status, a priority adjustment signal, a channel scheduling flag, and a strategy update identifier code; the port bandwidth allocation control result includes a bandwidth allocation ratio parameter, a port priority level index, a traffic scheduling control factor, and a port flow limiting status bit; and the window control cycle and rate level configuration information includes a sliding cycle setting value, a rate level, a port task category label, and a control trigger identifier index.

[0012] As a further aspect of the present invention, the step of obtaining the window task switching boundary position information specifically includes:

[0013] S101: Obtain the operating data of each interface of the docking station in the current control cycle. The operating data includes the data throughput per unit time and the corresponding timestamp of the USB 3.0 port, HDMI 2.1 interface and RJ45 Ethernet interface. Based on the sampling period, construct the throughput sequence of each port in ascending order of time to generate a multi-interface data throughput time series.

[0014] S102: Normalize the time interval based on the throughput values ​​corresponding to each group of adjacent time points in the multi-interface data throughput time series, and use the normalization result as the denominator to calculate the ratio of the throughput difference of each group, calculate the quotient of the throughput change value to the time difference, determine whether there is a continuous reversal in the direction of change, and obtain the interface bandwidth utilization change slope sequence; S103: Call the slope value corresponding to the time point in the interface bandwidth utilization change slope sequence to compare the slope change direction between two adjacent time points, calculate the slope change amplitude of the reversal point, filter the time points with the change amplitude greater than the rate change detection threshold as candidate nodes for task status change, aggregate the port number and timestamp information corresponding to the node, and generate window task switching boundary position information.

[0015] As a further aspect of the present invention, the step of obtaining the control strategy switching trigger identifier specifically includes:

[0016] S201: Call the start and end timestamps identified in the window task switching boundary position information, retrieve the unit time effective payload transmission rate recorded by each port within the time period, form a continuous data sequence of the transmission rates in the time window according to the time order, calculate the difference between the average transmission rates of the same ports in two adjacent sliding windows, obtain the rate change amplitude of the port in the current boundary segment, and generate a port sliding rate difference sequence.

[0017] S202: Based on each value in the port sliding rate difference sequence, compare it with the preset burst traffic tolerance benchmark threshold, determine whether the difference value exceeds the burst traffic tolerance benchmark threshold, and record the ports that exceed the threshold by numbering, mark the corresponding sliding window as a rate state abnormality, extract the port number, time index and rate fluctuation status corresponding to the marked window to obtain the port rate abnormality identification parameter set.

[0018] S203: Call the port number and time index information in the port rate anomaly identification parameter set, match the scheduling priority label of the task within the time period, compare the label level with the level corresponding to the current control strategy table, if there is a policy inconsistency between the two, mark the port as needing to be updated in the control state, and combine the port number, window number and status change field that meet the conditions to generate a control strategy switching trigger identifier.

[0019] As a further aspect of the present invention, the burst traffic tolerance benchmark value is the sum of the average value and standard deviation of the transmission rate differences of all ports;

[0020] The step of numbering and recording the ports that exceed the limit includes associating the port number with the corresponding sliding window timestamp and marking the window as having an abnormal rate status.

[0021] As a further aspect of the present invention, the step of obtaining the port bandwidth allocation and control result specifically includes:

[0022] S301: Call the control strategy to switch the port marked as needing adjustment in the trigger identifier, obtain the maximum bandwidth allocation value of the current port, combine the DiffServ service level code point tag of the task corresponding to the port, read the number of requests of the port in the current unit time, normalize the number of requests and the DiffServ service level value, and generate port request normalization parameters.

[0023] S302: Calculate the bandwidth control priority coefficient based on the port request normalization parameter, and adjust the original bandwidth allocation ratio by correcting the bandwidth control priority coefficient, thereby adjusting the maximum bandwidth allocation value of the port and generating the port bandwidth allocation control result.

[0024] As a further aspect of the present invention, the step of obtaining the window adjustment period and rate level configuration information specifically includes:

[0025] S401: Call the port number in the port bandwidth allocation control result, obtain the current sliding window period of the port, and in combination with the rate level configuration under the IEEE 802.3 standard, read the rate configuration of the port in the current control period and generate a port rate level configuration record.

[0026] S402: Based on the port task type in the port rate setting configuration record, identify whether the task is an interactive task or a throughput task. If the task is an interactive task and there are frequent requests in a short period of time, mark the port task status as needing adjustment and generate the task type and frequent request identifier.

[0027] S403: Based on the task type and frequent request identifier, determine whether the current port meets the conditions for shortening the window period and increasing the rate level. If it does, modify the window period and increase the rate level, and generate window control period and rate level configuration information.

[0028] As a further aspect of the present invention, the method further includes the following steps:

[0029] S5: Based on the port parameters recorded in the window control cycle and rate level configuration information, extract the corresponding port type, available bandwidth limit, allocation cycle and priority level, combine them to form three scheduling control fields, construct a scheduling execution structure, bind the structure with the current scheduling cycle number, and generate a multi-channel data flow control instruction set;

[0030] The multi-channel data flow control instruction set includes port scheduling number, flow control parameter set, window allocation instruction field and priority rate mapping structure.

[0031] As a further aspect of the present invention, the step of acquiring the multi-channel data stream control instruction set specifically includes:

[0032] S501: Based on the port number recorded in the window control cycle and rate level configuration information, extract the port type, available bandwidth limit, allocation cycle and priority level of the corresponding port, convert the parameters into scheduling control fields according to the scheduling rules, and combine the fields to obtain the port scheduling control field combination.

[0033] S502: Based on the port scheduling control field combination and the current scheduling cycle number, bind the scheduling control field with the scheduling cycle number to construct a scheduling execution structure. Apply the scheduling execution structure to the docking station data flow control to adjust the port bandwidth allocation and scheduling cycle, and generate a multi-channel data flow control instruction set.

[0034] A docking station data traffic intelligent control system, wherein the docking station data traffic intelligent control system is used to implement the above-mentioned docking station data traffic intelligent control method, the system comprising;

[0035] The window switching recognition module acquires the operating data of each interface of the expansion dock in the current control cycle, constructs a sequence of bandwidth utilization changes over time, locates port task change signal points, and generates window task switching boundary location information.

[0036] The control switching trigger module calls the time period identified by the window task switching boundary position information, compares the unit time effective payload transmission rate of the same port in the two sliding windows before and after, determines whether the rate stability state of the current window has changed, identifies the port that needs to be adjusted, and generates a control strategy switching trigger identifier.

[0037] The port bandwidth control module switches the ports marked as needing adjustment in the switching trigger identifier according to the control strategy, reads the current maximum bandwidth allocation value, combines the DiffServ service level code point tag corresponding to the task and the number of port requests per unit time, calculates the bandwidth control priority coefficient, adjusts the original bandwidth allocation ratio, and generates the port bandwidth allocation control result.

[0038] The periodic rate adjustment module calls the port number in the port bandwidth allocation control result, reads the current sliding window period and the rate level configuration under the IEEE 802.3 standard, distinguishes between interactive and throughput tasks, adjusts the window period and channel rate, and generates window control period and rate level configuration information.

[0039] The data flow control module extracts the corresponding port type, available bandwidth limit, allocation period and priority level from the port parameters recorded in the window control period and rate level configuration information, combines them to form three scheduling control fields, constructs a scheduling execution structure, binds the structure to the current scheduling period number, and generates a multi-channel data flow control instruction set.

[0040] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0041] In this invention, by constructing a bandwidth utilization change sequence of port operation data and combining slope reversal and change amplitude determination, the invention achieves accurate identification of task change nodes. Based on the sliding window difference sequence and rate stability discrimination method, it forms a sensitive response capability to burst data streams. By combining service level tags and port request frequency for bandwidth regulation, the bandwidth resource allocation is more in line with the task importance and actual request frequency. At the same time, the invention dynamically configures the window length and rate level according to the task interactivity and periodic stability, so that short-term high-frequency fluctuating data can obtain higher scheduling priority. While ensuring the continuity of critical task transmission, it suppresses bandwidth waste and unnecessary transmission delays. By periodically constructing scheduling execution structures and channel instruction sets, it achieves consistency and efficiency in resource coordination and scheduling execution among multiple data channels, improving the stability of data scheduling and the accuracy of control direction in parallel transmission environments. Attached Figure Description

[0042] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0043] Figure 1 This is a schematic diagram of the workflow of the present invention;

[0044] Figure 2 This is a detailed flowchart of S1 of the present invention;

[0045] Figure 3 This is a detailed flowchart of the S2 process of the present invention;

[0046] Figure 4 This is a detailed flowchart of the S3 process of the present invention;

[0047] Figure 5 This is a detailed flowchart of the S4 process of the present invention;

[0048] Figure 6 This is a detailed flowchart of S5 of the present invention;

[0049] Figure 7This is a system flowchart of the present invention. Detailed Implementation

[0050] The technical solution of the present invention will now be described with reference to the accompanying drawings.

[0051] In embodiments of the present invention, words such as "exemplarily," "for example," etc., are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" in the present invention should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the word "exemplary" is intended to present the concept in a concrete manner. Furthermore, in embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one.

[0052] In the embodiments of this invention, the terms "image" and "picture" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning. Similarly, the terms "of," "corresponding (relevant)," and "corresponding" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning.

[0053] In this embodiment of the invention, sometimes a subscript such as W1 may be written in a non-subscript form such as W1. When the difference is not emphasized, the meaning they express is the same.

[0054] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0055] Please see Figure 1 This invention provides a technical solution: a method for intelligent control of data traffic in a docking station, comprising the following steps:

[0056] S1: Obtain the operating data of each interface of the docking station in the current control cycle. The operating data includes the data throughput per unit time and the corresponding timestamp of the USB 3.0 port, HDMI 2.1 interface and RJ45 Ethernet interface. Construct a sequence of bandwidth utilization changes over time, calculate the slope of bandwidth utilization change between adjacent time points and determine whether the slope direction of two consecutive time points is reversed and the change amplitude is greater than the rate change detection threshold. If the condition is met, locate the port task change signal point and generate window task switching boundary position information.

[0057] The slope of bandwidth utilization change refers to the trend of the rate of change of data throughput per unit time.

[0058] S2: Call the time period marked by the window task switching boundary position information, compare the unit time effective payload transmission rate of the same port in the two sliding windows before and after, construct a sliding difference sequence, compare each item in the sliding difference sequence with the burst traffic tolerance benchmark value, and determine whether the rate stability state of the current window has changed based on whether the difference exceeds the set fluctuation benchmark. Combine the position of the task in the scheduling priority label to perform strategy status analysis, identify the port that needs to be adjusted, and generate the control strategy switching trigger identifier.

[0059] Payload transmission rate refers to the actual amount of data transmitted per unit time after removing protocol control information; the sliding difference sequence is the set of rate differences between two consecutive sliding windows, used to detect rate abrupt changes.

[0060] S3: Based on the control strategy, switch the port marked as needing adjustment in the trigger identifier, read the current maximum bandwidth allocation value, combine the DiffServ service level code point label corresponding to the task and the number of port requests in the current unit time, normalize the DiffServ service level value and the number of port requests, calculate the bandwidth control priority coefficient, and correct the original bandwidth allocation ratio according to the bandwidth control priority coefficient to generate the port bandwidth allocation control result.

[0061] DiffServ service level codes are widely used in QoS control to identify the priority of different types of data streams; common levels include EF (voice stream) and AF41 / AF21 (video / normal data).

[0062] S4: Call the port number in the port bandwidth allocation and control result, read the current sliding window period and the rate level configuration under the IEEE 802.3 standard, and distinguish between interactive and throughput tasks. If the task has frequent requests in a short period of time but the transmission period is unstable, shorten the window period and increase the channel rate level to generate window control period and rate level configuration information.

[0063] The IEEE 802.3 standard rate gradations define the rate classification in Ethernet transmission and are often used in control devices to adapt to different interface load capabilities.

[0064] S5: Based on the port parameters recorded in the window control cycle and rate level configuration information, extract the corresponding port type, available bandwidth limit, allocation cycle and priority level, combine them to form three scheduling control fields, construct a scheduling execution structure, bind the structure with the current scheduling cycle number, and generate a multi-channel data flow control instruction set;

[0065] The window task switching boundary location information includes the jump time identifier, port number record, control cycle index number, and data mutation type label. The control strategy switching trigger identifier includes the window rate change status, priority adjustment signal, channel scheduling mark, and policy update identifier code. The port bandwidth allocation control result includes the bandwidth allocation ratio parameter, port priority level index, traffic scheduling control factor, and port flow limiting status bit. The window control cycle and rate level configuration information includes the sliding cycle setting value, rate level, port task category label, and control trigger identifier index. The multi-channel data flow control instruction set includes the port scheduling number, traffic control parameter set, window allocation instruction field, and priority rate mapping structure.

[0066] Please see Figure 2 The specific steps for obtaining window task switching boundary position information are as follows:

[0067] S101: Obtain the operating data of each interface of the docking station in the current control cycle. The operating data includes the data throughput per unit time and the corresponding timestamp of the USB 3.0 port, HDMI 2.1 interface and RJ45 Ethernet interface. Based on the sampling period, construct the throughput sequence of each port in ascending order of time to generate a multi-interface data throughput time series.

[0068] The raw data packet counts and timestamps from the USB 3.0 port, HDMI 2.1 interface, and RJ45 Ethernet interface are extracted from the internal data bus monitoring module of the expansion dock. With a sampling period of 100 milliseconds, data is collected 10 times for each port within a 1000-millisecond control cycle. The collected data is the total number of bytes passing through the port within that 100-millisecond cycle. Dividing the number of bytes by the cycle length of 0.1 seconds converts to the data throughput per unit time, expressed in bytes per second (B / s). For example, if the USB 3.0 port transmits 12,500,000 bytes of data within that sampling cycle at timestamp of 100 milliseconds, its throughput is calculated as follows: ,Right now Each calculated throughput is associated with its corresponding timestamp to form a data pair, for example... For the RJ45 interface, at timestamp 200 milliseconds, 1,125,000 bytes of data were detected being transmitted, with a throughput of 11,250,000 bytes / s, or 11.25 MB / s. For the HDMI 2.1 interface, at timestamp 300 milliseconds, 400,000,000 bytes of data were detected being transmitted, with a throughput of 4,000,000,000 bytes / s, or 4000 MB / s, or 4 GB / s. All data points collected within a complete control cycle are sorted in ascending order by timestamp, generating an independent throughput sequence for each port. For example, the sequence for the USB 3.0 port is (100ms, 125 MB / s), (200ms, 126 MB / s), ..., (1000ms, 124 MB / s). The throughput sequences of all ports are aggregated to generate a multi-interface data throughput time series.

[0069] Table 1. Data Throughput Acquisition Table for Multiple Interfaces:

[0070] ;

[0071] As shown in Table 1, this table records the data throughput of the three interfaces at ten sampling points during a complete control cycle. All data are arranged in chronological order and constitute the basic data for subsequent analysis.

[0072] S102: Normalize the time interval based on the throughput value corresponding to each group of adjacent time points in the multi-interface data throughput time series, and use the normalization result as the denominator to calculate the ratio of the throughput difference of each group, calculate the quotient of the throughput change value to the time difference, determine whether there is a continuous reversal in the direction of change, and obtain the interface bandwidth utilization change slope sequence.

[0073] The throughput of the RJ45 Ethernet interface at timestamps of 300 ms and 400 ms is extracted, which are 11.30 MB / s and 10.50 MB / s respectively. The corresponding timestamp difference is 400 - 300 = 100 ms, or 0.1 seconds. Since the sampling period is fixed at 100 ms, the result of the time interval normalization is always 1. That is, the time difference of 100 ms is divided by the base period of 100 ms to obtain the normalized time interval of 1. Using this normalized result as the denominator, the ratio of the throughput difference to the normalized time interval is calculated. The throughput difference is 10.50 - 11.30 = -0.80 MB / s. The calculated quotient is... This value represents the slope of the throughput change within that time period. This calculation is performed on the entire sequence of the RJ45 interface, resulting in a slope sequence. For example, the slope for the period from timestamp 200 milliseconds to 300 milliseconds is... Between 300 milliseconds and milliseconds, the slope is Between 400 and 500 milliseconds, the slope is Between 500 and 600 milliseconds, the slope is Next, it is determined whether there is a continuous reversal in the direction of change. This is achieved by checking whether the signs of consecutive terms in the slope sequence are opposite. At time point 500 milliseconds, the slope sign of the previous interval is negative (from 400 milliseconds to 500 milliseconds), and the slope sign of the next interval is positive (from 500 milliseconds to 600 milliseconds), showing a reversal from negative to positive. At time point 400 milliseconds, the slope sign of the previous interval is positive (the slope from 300 milliseconds to 400 milliseconds is -0.80, which is corrected here to the previously calculated +0.05 to -0.80, showing a reversal from positive to negative), and the slope sign of the next interval is negative (from 400 milliseconds to 500 milliseconds), also showing a reversal. This judgment is performed on all time points of all ports to obtain the interface bandwidth utilization change slope sequence.

[0074] S103: Compare the slope values ​​corresponding to the time points in the bandwidth utilization change slope sequence of the call interface with the slope change direction between two adjacent time points, calculate the slope change amplitude of the reversal point, and select time points with change amplitude greater than the rate change detection threshold as candidate nodes for task status change. Aggregate the port number and timestamp information corresponding to the node to generate window task switching boundary position information.

[0075] Taking the slope change of the RJ45 interface at time point 500 milliseconds as an example, the slope value of the interval preceding this time point is... The slope value of the next interval is The slope change at the reversal point is calculated by determining the absolute value of the difference between the slope of the subsequent interval and the slope of the preceding interval. Then, the magnitude of this change is compared with the rate mutation detection threshold. This threshold is calculated based on a historical dataset of the slope changes of all ports within a full hour of stable operation of the docking station. The 90th percentile of this dataset is used as the threshold. Assuming that the calculated rate mutation detection threshold for the RJ45 port is obtained through analysis of tens of thousands of data points, the threshold is... Due to the calculated range of change Greater than this threshold Therefore, time point 500 milliseconds was selected as a candidate node for task state change. Next, the HDMI 2.1 interface was analyzed at time point 300 milliseconds. The slope of the preceding interval (from 200 milliseconds to 300 milliseconds) was... The slope of the second interval (from 300 milliseconds to milliseconds) is Since the slope signs are all positive and no inversion has occurred, no further calculations are performed. All selected candidate nodes, such as nodes with RJ45 ports at timestamp 500 milliseconds, are aggregated with their corresponding port numbers (e.g., port 3 for RJ45) and timestamp information (500ms) to generate window task switching boundary position information.

[0076] Please see Figure 3 The specific steps for obtaining the trigger identifier for switching control strategies are as follows:

[0077] S201: Call the start and end timestamps identified in the window task switching boundary position information, retrieve the unit time effective payload transmission rate recorded for each port within the time period, form a continuous data sequence of transmission rates in the time window according to the time order, calculate the difference between the average transmission rates of the same ports in two adjacent sliding windows, obtain the rate change amplitude of the port in the current boundary segment, and generate a port sliding rate difference sequence.

[0078] Taking the boundary location information of the RJ45 port at 500 milliseconds as an example, a time window centered on this boundary is defined, with a total window duration of 400 milliseconds. Therefore, the start and end timestamps are from 500-200=300 milliseconds to 500+200=700 milliseconds. A sliding window is set with a width of 200 milliseconds and a step size of 200 milliseconds. The first sliding window covers 300 milliseconds to 500 milliseconds, and the second sliding window covers 500 milliseconds to 700 milliseconds. The effective payload transmission rate per unit time recorded by the RJ45 port during this time period, i.e., the throughput, is retrieved. The rate values ​​are extracted from Table 1. The data in the first window are 10.50 MB / s at timestamp 400 milliseconds and 8.20 MB / s at timestamp 500 milliseconds. The second... The data within the window is 11.25 MB / s at timestamp 600 milliseconds and 11.35 MB / s at timestamp 700 milliseconds. The transmission rates in each sliding window are arranged into a continuous data sequence in chronological order, and their average values ​​are calculated. The average rate of the first window is (10.50 + 8.20) / 2 = 9.35 MB / s, and the average rate of the second window is (11.25 + 11.35) / 2 = 11.30 MB / s. The difference between the average transmission rates of the same port in these two adjacent sliding windows is calculated to obtain the rate change amplitude of the port within the current boundary segment. The calculation result is 11.30 - 9.35 = 1.95 MB / s. This process is repeated for all identified boundary position information to generate a port sliding rate difference sequence.

[0079] S202: Based on each value in the port sliding rate difference sequence, compare it with the preset burst traffic tolerance benchmark threshold, determine whether the difference value exceeds the burst traffic tolerance benchmark threshold, and record the ports that exceed the threshold by numbering, mark the corresponding sliding window as a rate status abnormality, extract the port number, time index and rate fluctuation status corresponding to the marked window to obtain the port rate abnormality identification parameter set.

[0080] The burst traffic tolerance baseline is the sum of the average and standard deviation of the transmission rate differences across all ports;

[0081] The process of numbering and recording ports exceeding the limit includes associating the port number with the corresponding sliding window timestamp and marking the window as having an abnormal rate status.

[0082] Taking a rate variation of 1.95 MB / s at the RJ45 port as an example, this is compared with a preset burst traffic tolerance threshold. This burst traffic tolerance threshold is set based on the statistical characteristics of all sliding rate differences calculated for all ports (USB 3.0, HDMI 2.1, RJ45) within the current control cycle. Specifically, it is the sum of the average and standard deviation of these difference data. Assuming that the rate difference for the USB 3.0 port is -125.75 MB / s within the current cycle (based on...),... The throughput drop at 800 milliseconds is calculated as follows: the rate difference for the HDMI 2.1 port is 0.025 GB / s (i.e., 25 MB / s, calculated based on the change at 300 milliseconds), and the difference for the RJ45 port is 1.95 MB / s. Therefore, the set of differences is -125.75, 25, and 1.95, with an average of (-125.75 + 25 + 1.95) / 3 = -32.93 MB / s and a standard deviation of 87.35 MB / s. Thus, the burst traffic tolerance baseline threshold is... Since the RJ45 port's rate change of 1.95MB / s did not exceed the threshold of 120.28MB / s, its rate status was normal. However, the absolute value of the change in the USB 3.0 port was 125.75MB / s, which exceeded the threshold of 120.28MB / s. Therefore, the USB 3.0 port was numbered and recorded, and its port number (e.g., port 1) was associated with the corresponding sliding window timestamp (center point is 800 milliseconds). The window was marked as having an abnormal rate status. The port number, time index, and rate fluctuation status corresponding to the marked window were extracted to obtain the port rate abnormality identification parameter set.

[0083] S203: Call the port number and time index information in the port rate anomaly identification parameter set, match the scheduling priority label of the task within the time period, compare the label level with the level corresponding to the current control strategy table, if there is a policy inconsistency between the two, mark the port as needing to be updated in the control state, and combine the port number, window number and status change field that meet the conditions to generate a control strategy switching trigger identifier.

[0084] Taking the abnormal speed of the identified USB 3.0 port (port 1) at time index 800 milliseconds as an example, the application active on this port during that time period was queried and it was found that it was performing a large file backup task. The scheduling priority label assigned to this task by the operation unit was "background transmission", with a low level. Subsequently, the current control policy table was read. This table specifies the bandwidth guarantee policy corresponding to different priority levels of tasks. The bandwidth policy corresponding to the "background transmission" level is set to "limited opportunity type", that is, it is available when the network is not congested. However, it was found that because it was processing the high-definition video stream from the HDMI port and the video conferencing stream from the RJ45 port, the overall bandwidth policy had been adjusted to "real-time priority". Under this policy, the bandwidth of the port of the "background transmission" task should be strictly limited. At present, the USB 3.0 port still occupied a high bandwidth before the speed abnormality occurred, which shows an inconsistency in the policy. Therefore, the USB 3.0 port was marked as needing to update the control status. The port number "1" that meets the conditions, the window number (e.g., the window sequence number "4" determined according to the timestamp 800 milliseconds), and the status change field "need to be downgraded" are combined to generate a control policy switching trigger identifier.

[0085] Please see Figure 4 The specific steps for obtaining the port bandwidth allocation control result are as follows: S301: Call the control strategy to switch the port marked as needing adjustment in the trigger identifier, obtain the maximum bandwidth allocation value of the current port, combine the DiffServ service level code point tag of the task corresponding to the port, read the number of requests of the port in the current unit time, normalize the number of requests and the DiffServ service level value, and generate port request normalization parameters.

[0086] Call the USB 3.0 port (port 1) to obtain the current maximum bandwidth allocation value of the port, assuming it is 150MB / s. Combine this with the DiffServ Service Level Code Point (DSCP) tag of the task corresponding to the port. File backup tasks are usually marked as AssuredForwarding category, such as AF11, with a decimal value of 10. Read the number of requests to the port in the current unit of time (e.g., the past second), which is 50. To perform normalization, it is necessary to obtain the average and maximum number of historical requests to the port, as well as the maximum DSCP value. Assuming that based on statistics from the past hour, the historical average number of requests to the USB 3.0 port is 30 and the maximum number is 200, and the maximum DSCP value is defined as the decimal value of the highest priority ExpeditedForwarding (EF), which is 46, the request count is normalized by subtracting the absolute value of the historical average of 30 from the current request count of 50, and then dividing by the maximum request count of 200. The DSCP service level value is normalized by dividing the current port's DSCP value of 10 by the maximum DSCP value of 46. Generate port request normalization parameters.

[0087] S302: Calculate the bandwidth control priority coefficient based on the port request normalization parameter, and adjust the original bandwidth allocation ratio by correcting the bandwidth control priority coefficient, thereby adjusting the maximum bandwidth allocation value of the port and generating the port bandwidth allocation control result.

[0088] The specific formula for calculating the bandwidth control priority coefficient is as follows: ;

[0089] in, Represents the bandwidth control priority coefficient. This represents the number of requests made to the port within the current unit of time. This represents the average number of historical requests to the port. This represents the maximum number of requests made to the port. The DiffServ service level code dot label representing the port. This represents the maximum value of the DiffServ service level. The average request duration for port-based tasks;

[0090] Calculate the bandwidth control priority coefficient based on the port request normalization parameters. The formula is as follows: ;

[0091] The meaning and calculation logic of each parameter are as follows: It is a bandwidth control priority coefficient, used to quantify and adjust the priority of bandwidth allocation. Part of the calculation measures the deviation of the current port request frequency from its historical behavior, and normalizes it. The absolute value operation ensures that fluctuations, whether above or below the average, are considered changes. Dividing by the maximum value constrains the result to within a certain range. Within the interval, Part of the calculation measures the relative position of a task's service quality level within the entire service system; a higher ratio indicates a higher task priority. The process also incorporates the impact of task request duration. By taking the square root of the average request duration, the impact of duration is reflected while smoothing out its intensity, preventing excessively long tasks from receiving overly high weights. Multiplying these three factors together integrates the real-time changes in task behavior, the preset static priority, and the continuous nature of the task. Now, we substitute the values ​​obtained in the previous steps into the calculation. This represents the number of requests made to the port within the current unit of time, and its value is 50. This represents the average number of historical requests to the port, with a value of 30. This is the maximum number of requests allowed to the port, and its value is 200. The DiffServ service level code dot label for the port has a quantization value of 10. This is the maximum value for the DiffServ service level, which is 46. Let be the average request duration for port tasks. Monitoring shows the average request duration for this file backup task is 0.04 seconds. Substituting these values ​​into the formula:

[0092] This result indicates that the bandwidth control priority factor for USB 3.0 ports is a relatively low value. This priority factor can be used to correct the original bandwidth allocation ratio; for example, the correction rule could be: The adjusted maximum bandwidth allocation value for the port is... This generates port bandwidth allocation and control results.

[0093] The advantage of the formula is that it can capture the real-time fluctuations of port requests. Static priority of service quality and the duration characteristics of the task The combination of these three elements enables dynamic and multi-dimensional precise quantification of bandwidth allocation priorities.

[0094] Please see Figure 5 The specific steps for obtaining window control period and rate level configuration information are as follows: S401: Call the port number in the port bandwidth allocation control result, obtain the current sliding window period of the port, and combine it with the rate level configuration under the IEEE 802.3 standard to read the rate configuration of the port in the current control period and generate the port rate level configuration record.

[0095] Taking an RJ45 port (port 3) requiring increased bandwidth as an example, this port is currently handling a high-priority video conferencing task. The recommended bandwidth allocation is to increase the maximum bandwidth from 10MB / s to 15MB / s. The current sliding window period for this port is obtained and set to 100 milliseconds. Combined with the rate tier configuration under the IEEE 802.3 standard, the rate configuration of this Ethernet port within the current adjustment period is read. This docking station supports... Multiple speed settings are currently configured as follows: That is, the theoretical maximum throughput is The current actual bandwidth allocation is far lower than this value, so a port speed tier configuration record is generated.

[0096] S402: Based on the port task type in the port rate tier configuration record, identify whether the task is an interactive task or a throughput task. If the task is an interactive task and there are frequent requests in a short period of time, mark the port task status as needing adjustment and generate the task type and frequent request identifier.

[0097] The video conferencing task on the RJ45 port is identified as an interactive task, while the file transfer task on the USB 3.0 port is identified as a throughput task. Next, the interactive task is monitored for frequent requests in the short term. The "short term" is set to 500 milliseconds. The criterion for "frequent requests" is that the number of requests exceeds a dynamic threshold. This threshold is set to 1.5 times the average number of requests of the same type of task in the same historical time period on this port. Assuming that the video conferencing task initiated 120 data requests in the past 500 milliseconds, while the historical average is 70 times, the threshold is 70 x 1.5 = 105 times. Since 120 > 105, the task is determined to have frequent requests in the short term. The task status of port 3 is marked as needing adjustment, and the task type and frequent request identifier are generated.

[0098] S403: Based on the task type and frequent request identifier, determine whether the current port meets the conditions for shortening the window period and increasing the rate level. If it does, modify the window period and increase the rate level, and generate window control period and rate level configuration information.

[0099] The system determines whether port 3 meets the conditions for shortening the window period and increasing the rate level. The conditions are: the task is interactive, involves frequent requests, and there is room for improvement in the current rate level. The video conferencing task meets all these conditions. Therefore, the control window period for this port is shortened from 100 milliseconds to 50 milliseconds, and its rate level is increased. The physical rate tiers are not saturated, but the "rate tier upgrade" here refers to the upgrade of logical rate allocation, that is, the bandwidth guarantee level at the software level, which is upgraded from "standard guarantee" to "priority guarantee". This will give it a higher dequeue priority in the traffic scheduling queue and generate window adjustment period and rate level configuration information.

[0100] Please see Figure 6 The specific steps for obtaining the multi-channel data stream control instruction set are as follows:

[0101] S501: Based on the port number recorded in the window control cycle and rate level configuration information, extract the port type, available bandwidth limit, allocation cycle and priority level of the corresponding port, convert the parameters into scheduling control fields according to the scheduling rules, and combine the fields to obtain the port scheduling control field combination.

[0102] Extract the detailed parameters of port 3 (RJ45). The port type is "RJ45 Ethernet", the available bandwidth limit is the updated 15MB / s, the allocation period is the shortened 50 milliseconds, and the priority level is the upgraded "priority guarantee". Convert the parameters into scheduling control fields according to the preset scheduling rules. For example, convert the port type to binary code 0011, convert the bandwidth limit of 15MB / s to a 16-bit unsigned integer 15000 (unit KB / s), convert the allocation period of 50 milliseconds to an 8-bit integer 50, and map the priority level "priority guarantee" to the value 3. Then combine these fields in the order of [port type]-[bandwidth limit]-[allocation period]-[priority level] to obtain the scheduling control field combination 0011-15000-50-3 for port 3.

[0103] S502: Based on the combination of port scheduling control fields and the current scheduling cycle number, the scheduling control fields are bound to the scheduling cycle number to construct a scheduling execution structure. The scheduling execution structure is then applied to the docking station data flow control to adjust the port bandwidth allocation and scheduling cycle, and generate a multi-channel data flow control instruction set.

[0104] Taking the field combination 0011-15000-50-3 for port 3 as an example, combined with the current scheduling cycle number, assuming that the current time is the 1024th scheduling cycle after the dock starts, the scheduling control field is bound to the scheduling cycle number 1024 to construct a structured scheduling execution body. This structure contains the cycle number and control field, and its form is {cycle_id: 1024, control_field: '0011-15000-50-3'}. At the same time, for other ports that need to be regulated, such as USB 3.0 ports that need to be downgraded, corresponding scheduling execution bodies are also generated, such as {cycle_id: 1024, control_field: '0001-149350-100-1'}. The scheduling execution structures of all ports are collected together and applied to the underlying data flow control hardware or software module of the dock. This module parses the information in the structure, adjusts the bandwidth allocation limit and scheduling response cycle of each port in real time, and generates a multi-channel data flow control instruction set.

[0105] Please see Figure 7 A docking station data traffic intelligent control system is used to execute the above-mentioned docking station data traffic intelligent control method. The system includes:

[0106] The window switching recognition module acquires the operating data of each interface of the expansion dock in the current control cycle, constructs a sequence of bandwidth utilization changes over time, locates port task change signal points, and generates window task switching boundary location information.

[0107] The control switching trigger module calls the time period marked by the window task switching boundary position information, compares the unit time effective payload transmission rate of the same port in the two sliding windows before and after, determines whether the rate stability state of the current window has changed, identifies the port that needs to be adjusted, and generates a control strategy switching trigger identifier.

[0108] The port bandwidth control module switches the ports marked as needing adjustment according to the control strategy, reads the current maximum bandwidth allocation value, combines the DiffServ service level code point tag corresponding to the task and the number of port requests per unit time, calculates the bandwidth control priority coefficient, adjusts the original bandwidth allocation ratio, and generates the port bandwidth allocation control result.

[0109] The periodic rate adjustment module calls the port number in the port bandwidth allocation control result, reads the current sliding window period and the rate level configuration under the IEEE 802.3 standard, distinguishes between interactive and throughput tasks, adjusts the window period and channel rate, and generates window control period and rate level configuration information.

[0110] The data flow control module extracts the corresponding port type, available bandwidth limit, allocation period and priority level from the port parameters recorded in the window control period and rate level configuration information, combines them to form three scheduling control fields, constructs a scheduling execution structure, binds the structure to the current scheduling period number, and generates a multi-channel data flow control instruction set.

[0111] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0112] In this invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be a single item or multiple items.

[0113] It should be understood that, in various embodiments of the present invention, the order of the above-mentioned process numbers does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0114] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0115] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the devices, apparatuses, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0116] In the several embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0117] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0118] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0119] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0120] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for intelligent control of data traffic in a docking station, characterized in that, Includes the following steps: S1: Obtain the operating data of each interface of the expansion dock within the current control cycle, construct the bandwidth utilization change sequence over time, locate the port task change signal point, and generate window task switching boundary position information; S2: Call the time period identified by the window task switching boundary position information, compare the unit time effective payload transmission rate of the same port in the two sliding windows before and after, determine whether the rate stability state of the current window has changed, identify the port that needs to be adjusted, and generate a control strategy switching trigger identifier. S3: According to the control strategy, switch the port marked as needing adjustment in the trigger identifier, read the current maximum bandwidth allocation value, combine the DiffServ service level code point tag corresponding to the task and the number of port requests in the current unit time, calculate the bandwidth control priority coefficient, adjust the original bandwidth allocation ratio, and generate the port bandwidth allocation control result. S4: Call the port number in the port bandwidth allocation and control result, read the current sliding window period and the rate level configuration under the IEEE 802.3 standard, distinguish between interactive and throughput tasks, adjust the window period and channel rate, and generate window control period and rate level configuration information.

2. The intelligent data traffic control method for expansion docks according to claim 1, characterized in that, The window task switching boundary location information includes a jump time identifier, port number record, control cycle index number, and data mutation type label. The control strategy switching trigger identifier includes window rate change status, priority adjustment signal, channel scheduling flag, and policy update identifier code. The port bandwidth allocation control result includes bandwidth allocation ratio parameter, port priority level index, traffic scheduling control factor, and port flow limiting status bit. The window control cycle and rate level configuration information includes sliding cycle setting value, rate level, port task category label, and control trigger identifier index.

3. The intelligent data traffic control method for expansion docks according to claim 2, characterized in that, The specific steps for obtaining the window task switching boundary position information are as follows: S101: Obtain the operating data of each interface of the docking station in the current control cycle. The operating data includes the data throughput per unit time and the corresponding timestamp of the USB 3.0 port, HDMI 2.1 interface and RJ45 Ethernet interface. Based on the sampling period, construct the throughput sequence of each port in ascending order of time to generate a multi-interface data throughput time series. S102: Normalize the time interval according to the throughput value corresponding to each group of adjacent time points in the multi-interface data throughput time series, and use the normalization result as the denominator to calculate the ratio of each group of throughput difference, calculate the quotient of throughput change value to time difference, determine whether the change direction is continuously reversed, and obtain the interface bandwidth utilization change slope sequence. S103: The slope values ​​corresponding to the time points in the interface bandwidth utilization change slope sequence are called to compare the slope change direction between two adjacent time points, and the slope change amplitude of the reversal point is calculated. Time points with change amplitude greater than the rate change detection threshold are selected as candidate nodes for task state change. The port number and timestamp information corresponding to the node are aggregated to generate window task switching boundary position information.

4. The intelligent data traffic control method for expansion docks according to claim 3, characterized in that, The specific steps for obtaining the control strategy switching trigger identifier are as follows: S201: Call the start and end timestamps identified in the window task switching boundary position information, retrieve the unit time effective payload transmission rate recorded by each port within the time period, form a continuous data sequence of the transmission rates in the time window according to the time order, calculate the difference between the average transmission rates of the same ports in two adjacent sliding windows, obtain the rate change amplitude of the port in the current boundary segment, and generate a port sliding rate difference sequence. S202: Based on each value in the port sliding rate difference sequence, compare it with the preset burst traffic tolerance benchmark threshold, determine whether the difference value exceeds the burst traffic tolerance benchmark threshold, and record the ports that exceed the threshold by numbering, mark the corresponding sliding window as a rate state abnormality, extract the port number, time index and rate fluctuation status corresponding to the marked window to obtain the port rate abnormality identification parameter set. S203: Call the port number and time index information in the port rate anomaly identification parameter set, match the scheduling priority label of the task within the time period, compare the label level with the level corresponding to the current control strategy table, if there is a policy inconsistency between the two, mark the port as needing to be updated in the control state, and combine the port number, window number and status change field that meet the conditions to generate a control strategy switching trigger identifier.

5. The intelligent data traffic control method for expansion docks according to claim 4, characterized in that, The burst traffic tolerance baseline value is the sum of the average value and standard deviation of the transmission rate differences across all ports; The step of numbering and recording the ports that exceed the limit includes associating the port number with the corresponding sliding window timestamp and marking the window as having an abnormal rate status.

6. The intelligent data traffic control method for expansion docks according to claim 5, characterized in that, The specific steps for obtaining the port bandwidth allocation and control results are as follows: S301: Call the control strategy to switch the port marked as needing adjustment in the trigger identifier, obtain the maximum bandwidth allocation value of the current port, combine the DiffServ service level code point tag of the task corresponding to the port, read the number of requests of the port in the current unit time, normalize the number of requests and the DiffServ service level value, and generate port request normalization parameters. S302: Calculate the bandwidth control priority coefficient based on the port request normalization parameter, and adjust the original bandwidth allocation ratio by correcting the bandwidth control priority coefficient, thereby adjusting the maximum bandwidth allocation value of the port and generating the port bandwidth allocation control result.

7. The intelligent data traffic control method for expansion docks according to claim 6, characterized in that, The specific steps for obtaining the window control cycle and rate level configuration information are as follows: S401: Call the port number in the port bandwidth allocation control result, obtain the current sliding window period of the port, and in combination with the rate level configuration under the IEEE 802.3 standard, read the rate configuration of the port in the current control period and generate a port rate level configuration record. S402: Based on the port task type in the port rate setting configuration record, identify whether the task is an interactive task or a throughput task. If the task is an interactive task and there are frequent requests in a short period of time, mark the port task status as needing adjustment and generate the task type and frequent request identifier. S403: Based on the task type and frequent request identifier, determine whether the current port meets the conditions for shortening the window period and increasing the rate level. If it does, modify the window period and increase the rate level, and generate window control period and rate level configuration information.

8. The intelligent data traffic control method for expansion docks according to claim 7, characterized in that, The method further includes the following steps: S5: Based on the port parameters recorded in the window control cycle and rate level configuration information, extract the corresponding port type, available bandwidth limit, allocation cycle and priority level, combine them to form three scheduling control fields, construct a scheduling execution structure, bind the structure with the current scheduling cycle number, and generate a multi-channel data flow control instruction set; The multi-channel data flow control instruction set includes port scheduling number, flow control parameter set, window allocation instruction field and priority rate mapping structure.

9. The intelligent data traffic control method for expansion docks according to claim 8, characterized in that, The specific steps for obtaining the multi-channel data stream control instruction set are as follows: S501: Based on the port number recorded in the window control cycle and rate level configuration information, extract the port type, available bandwidth limit, allocation cycle and priority level of the corresponding port, convert the parameters into scheduling control fields according to the scheduling rules, and combine the fields to obtain the port scheduling control field combination. S502: Based on the port scheduling control field combination and the current scheduling cycle number, bind the scheduling control field with the scheduling cycle number to construct a scheduling execution structure. Apply the scheduling execution structure to the docking station data flow control to adjust the port bandwidth allocation and scheduling cycle, and generate a multi-channel data flow control instruction set.

10. An intelligent data traffic control system for expansion docks, characterized in that, The system is used to implement the intelligent data traffic control method for the expansion dock as described in any one of claims 1-9, and the system includes: The window switching recognition module acquires the operating data of each interface of the expansion dock in the current control cycle, constructs a sequence of bandwidth utilization changes over time, locates port task change signal points, and generates window task switching boundary location information. The control switching trigger module calls the time period identified by the window task switching boundary position information, compares the unit time effective payload transmission rate of the same port in the two sliding windows before and after, determines whether the rate stability state of the current window has changed, identifies the port that needs to be adjusted, and generates a control strategy switching trigger identifier. The port bandwidth control module switches the ports marked as needing adjustment in the switching trigger identifier according to the control strategy, reads the current maximum bandwidth allocation value, combines the DiffServ service level code point tag corresponding to the task and the number of port requests per unit time, calculates the bandwidth control priority coefficient, adjusts the original bandwidth allocation ratio, and generates the port bandwidth allocation control result. The periodic rate adjustment module calls the port number in the port bandwidth allocation control result, reads the current sliding window period and the rate level configuration under the IEEE 802.3 standard, distinguishes between interactive and throughput tasks, adjusts the window period and channel rate, and generates window control period and rate level configuration information. The data flow control module extracts the corresponding port type, available bandwidth limit, allocation period and priority level from the port parameters recorded in the window control period and rate level configuration information, combines them to form three scheduling control fields, constructs a scheduling execution structure, binds the structure to the current scheduling period number, and generates a multi-channel data flow control instruction set.

Images