Deterministic time delay guarantee method for key data transmission of time-sensitive network

By constructing the data flow shaping model of asynchronous traffic shaping device and adjusting the shaping parameters with fuzzy logic, the shortcomings of multi-dimensional feature integration and dynamic environment adaptability in the existing technology are solved, and the deterministic time delay guarantee of key data flows is achieved, which improves the Real-time and accuracy.

CN118921329AInactive Publication Date: 2024-11-08LINHUAN COAL MINE OF HUAIBEI MINING CO LTD
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411277187.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-12
Publication Date
2024-11-08
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The prior art lacks multi-dimensional feature integration and dynamic environment adaptability when configuring asynchronous traffic shaping strategies, resulting in insufficient detection accuracy and robustness, making it difficult to effectively adjust the shaping parameters in a dynamically changing network environment.

Method used

By analyzing the data flow in the previous cycle, a data flow shaping model of the asynchronous traffic shaping device is constructed, the shaping parameters are optimized to minimize the transmission delay of the data flow, and the shaping parameters are dynamically adjusted using fuzzy logic and historical data to ensure the time of the key data flow Extended protection.

Benefits of technology

It improves the real-time and accuracy of data transmission, shortens the calculation time, overcomes the problem of long processing time in the existing technology, ensures the time-delay guarantee of key data flows, and reduces the adverse consequences caused by untimely data transmission.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118921329A_ABST
    Figure CN118921329A_ABST
Patent Text Reader

Abstract

The invention discloses a deterministic time delay guarantee method for key data transmission of a time-sensitive network, which is used for carrying out parameter optimization on an asynchronous traffic shaper of a TSN (Time Sensitive Network), and comprises the following steps of: 1, extracting and analyzing a previous period of data stream to judge whether a shaping parameter is suitable for the transmission of a next period of data stream or not; 2, respectively dividing the number of data frames, bandwidth occupation and the data flow congestion state value into a plurality of fuzzy subsets, and determining the membership degree of each fuzzy subset, thereby formulating a fuzzy rule, obtaining a data flow congestion state value with the priority of i, constructing a key data flow transmission time delay objective function based on the congestion state value, and obtaining a key data flow transmission time delay objective function; and solving to obtain the optimal parameter of the asynchronous flow shaper, thereby ensuring that the key data flow is preferentially processed and transmitted under various conditions. According to the method, the parameters of the asynchronous traffic shaper are optimized by adopting a fuzzy reasoning method, so that low delay and high reliability of key data stream transmission in a time-sensitive deterministic network can be ensured.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical research direction of the network system field, specifically, is a deterministic delay guarantee method for key data transmission in a time-sensitive network. Background Art

[0002] Real-time communication network technology is a technology used to transmit real-time data and meet strict timing requirements. Among them, Ethernet has achieved low latency and predictability by introducing the mechanism of time-sensitive networking (TSN). The real-time transport protocol (RTP) provides mechanisms such as timestamps and sequence numbers in audio and video transmission to ensure the timing and integrity of data streams. The controller area network (CAN) is suitable for real-time control systems and has low latency, high reliability and anti-interference capabilities. The inter-domain real-time communication protocol (I2C) is used for short-distance communication and supports real-time data transmission and exchange. These technologies play an important role in industrial automation, intelligent transportation, aerospace and other fields, meet real-time requirements, and support real-time control, data acquisition and communication needs.

[0003] TSN is an Ethernet-based network technology that aims to address the challenges faced by current real-time communication network technologies. It solves the problems of low latency, predictability, high reliability and network collaboration in real-time communication by introducing features such as time synchronization, traffic scheduling and priority mechanisms. TSN can provide microsecond-level data transmission delay to ensure timely and consistent data transmission; achieve predictability of real-time data transmission through dynamic scheduling of bandwidth and transmission time; ensure high priority and reliable delivery of real-time data through traffic control and priority mechanisms; at the same time, TSN networks are flexible and scalable, can adapt to networks of different sizes and complexities, and are compatible with existing Ethernet technologies. The application of TSN technology will promote innovation and progress in the field of real-time communication and meet the needs of real-time communication in industrial automation, intelligent transportation, aerospace and other fields.

[0004] The current TSN (Time-Sensitive Networking) network is a set of technologies based on the IEEE 802.1 standard series (the original description of substation design has been replaced with a broader description, but it is equally applicable), which aims to achieve real-time communication with low latency, predictability and high reliability. Asynchronous traffic shaping (ATS) is a network traffic management technology used to control the data transmission rate and priority in the network. Asynchronous traffic shaping can ensure that critical applications or services have higher transmission priority by setting different priorities for different traffic. By properly configuring asynchronous traffic shaping strategies, network performance can be optimized. By limiting traffic rates and managing priorities, network congestion and latency can be reduced, and overall network throughput and response speed can be improved.

[0005] Disadvantages and problems of existing technology:

[0006] 1. Reasonable configuration of asynchronous traffic shaping strategy Lack of multiple feature integration: Real network traffic has multiple dimensions of features, such as traffic size, transmission protocol, source and destination address, packet size distribution, traffic periodicity, etc. However, many existing algorithms often only use some features and lack effective integration and utilization of multiple dimensional features, resulting in insufficient accuracy and robustness of detection algorithms.

[0007] 2. Insufficient adaptability to dynamic network environments: Existing algorithms may have difficulty adapting to dynamically changing network environments, such as fluctuations in business traffic and the emergence of new attacks. Due to the lack of timely perception and adaptive adjustment of changes in the network environment, shaping parameter configuration may affect the accuracy and practicality of detection results. Summary of the invention

[0008] The present invention aims to solve the deficiencies of the above-mentioned prior art and proposes a deterministic delay guarantee method for critical data transmission in a time-sensitive network, so as to act on the shaping parameters of a shaper according to the state information of the real-time data stream, so that the shaper can shape the subsequent data stream to achieve the effect of guaranteeing the delay of the critical data stream.

[0009] In order to achieve the above-mentioned purpose, the present invention adopts the following technical scheme:

[0010] The deterministic delay guarantee method for critical data transmission in a time-sensitive network of the present invention is characterized in that it is performed according to the following steps:

[0011] Step 1: extract and analyze the data flow of the previous cycle to determine whether the shaping parameters are suitable for the transmission of the data flow of the next cycle. If suitable, execute step 2; otherwise, continue to determine the data flow of the next cycle;

[0012] Step 2: For any i-th asynchronous traffic shaper, process the i-th priority data flow, taking the shaping parameter of the i-th asynchronous traffic shaper as a variable, Taking the minimum internal data transmission delay as the goal and the value range of the shaping parameters as the constraint, the data flow shaping model of the i-th asynchronous traffic shaper is constructed and solved to obtain the optimal shaping parameters of the i-th asynchronous traffic shaper, including: the optimal token bucket capacity of the i-th asynchronous traffic shaper , the optimal token filling rate of the token bucket of the i-th asynchronous traffic shaper ;

[0013] Step 3: According to and ,calculate Start with the data flow queued before the i-th asynchronous traffic shaper exist After the start, the transmission delay to reach the target address ;in, express The number of packets transmitted in the cycle that arrive at the queue before the i-th asynchronous traffic shaper data frames, , Indicates the total number of queued data frames; express transmission delay;

[0014] Step 4: If , it means that the i-th asynchronous traffic shaper is transmitting normally Otherwise, discard ;in, express The ideal transmission delay.

[0015] The deterministic delay guarantee method for critical data transmission in a time-sensitive network according to the present invention is also characterized in that step 1 is performed according to the following steps:

[0016] Step 1.1, current Mth transmission cycle Before you begin, get Transmission cycle In this case, the data flow passing through all asynchronous traffic shapers in any switch , and calculate Bit Error Rate ;in, express Middle Priority data flow, and , Indicates Priority data flow Middle The data frames transmitted, Indicates Priority data The number of data frames in , Indicates the maximum priority;

[0017] Step 1.2: Calculate the ratio of the sum of the number of data frames to the sum of the bandwidth occupied using formula (1): :

[0018] (1)

[0019] In formula (1), express Bandwidth usage;

[0020] Step 1.3: Set the bit error rate threshold to , the threshold of the ratio of the sum of the number of frames to the sum of the bandwidth occupied is ;

[0021] Step 1.4: Judgment and Is it true? If so, it means that the shaping parameters of the asynchronous traffic shaper are applicable to the transmission of the next cycle data flow, and go to step 2. Otherwise, wait After the data stream transmission of all asynchronous traffic shapers in the internal switch is completed, M+1 is assigned to M, and the process returns to step 1 for execution.

[0022] Further, the step 2 is performed as follows:

[0023] Step 2.1: Define the Mth transmission cycle of waiting for the i-th asynchronous traffic shaper The opened data stream is the shaping queue, and the data stream waiting to be sent is the scheduling queue. We use formula (2) to construct Objective function of the internal data flow shaping model :

[0024] (2)

[0025] In formula (2), for Neidi The congestion status value of the priority data flow, for The maximum queuing delay before the i-th asynchronous traffic shaper, for The number of switches passed through, is the transmission delay of data through the asynchronous traffic shaper, The receiving storage delay of the switch;

[0026] Step 2.2, calculation ;

[0027] Step 2.3: Use equation (4) to construct the end-to-end minimum transmission delay Expression of

[0028] (4)

[0029] In formula (4), For and priority The number of frames in the shaping queue associated with the scheduling queue. For and priority The dispatch queue associated with A shaping queue, For the Shaping Queue The token bucket capacity of the i-th asynchronous traffic shaper connected, For the Shaping Queue The token filling rate of the connected i-th asynchronous traffic shaper, is the port bandwidth of the switch, for The minimum frame length, for Neidi Priority data flow Maximum frame length;

[0030] Step 2.4: Use formula (5) to construct the token bucket capacity The value constraints of are:

[0031] (5)

[0032] In formula (5), The maximum number of data frames transmitted for the network;

[0033] Step 2.5: Use formula (5) to construct the token filling rate The value constraints of are:

[0034] (6)

[0035] In formula (6), For shaping queues The jth traffic frame length transmitted by the connected shaper, is the maximum frequency deviation between the sending device and the standard clock, The maximum frequency offset between the local clock of the switch and the standard clock;

[0036] Step 2.6: The data flow shaping model is optimized by an interior point optimization algorithm to obtain the optimal shaping parameters of the i-th asynchronous traffic shaper.

[0037] Further, the step 2.2 is performed as follows:

[0038] Step 2.2.1, establish several fuzzy subsets for the number of data frames, bandwidth occupancy, and congestion status values ​​respectively;

[0039] Calculated using Gaussian membership function , Respectively The membership degree of fuzzy subsets , ;

[0040] Step 2.2.2, according to , ,calculate and The trigger weight of rule C in the fuzzy logic control table ;

[0041] Step 2.2.3: Defuzzify the congestion state value according to formula (3) to obtain Congestion status value of the priority data flow :

[0042] (3)

[0043] In formula (3), for The variance of for The variance of is the maximum congestion state value.

[0044] Further, the step 3 is performed as follows:

[0045] Step 3.1, use formula (7) to calculate the number of tokens of the i-th asynchronous traffic shaper sufficient to send Required delay :

[0046] (7)

[0047] Step 3.2: Use equation (8) to calculate whether there are enough tokens in the token bucket of the i-th asynchronous traffic shaper to transmit the data flow. The earliest delay :

[0048] (8)

[0049] In formula (8), Indicates the time when data transmission starts;

[0050] Step 3.3: Calculate using formula (9) The corresponding i-th asynchronous traffic shaper at the most recent token bucket full time :

[0051] (9)

[0052] Step 3.4: Use formula (10) to determine The transmission delay :

[0053] (10).

[0054] Furthermore, if < , then update according to formula (11) , otherwise, update according to formula (12) , return to step 3.2, and continue to determine whether the next data frame queued before arriving at the i-th asynchronous traffic shaper is transmitted normally;

[0055] (11)

[0056] (12).

[0057] An electronic device of the present invention includes a memory and a processor, wherein the memory is used to store a program that supports the processor to execute the deterministic delay guarantee method for critical data transmission in a time-sensitive network, and the processor is configured to execute the program stored in the memory.

[0058] The present invention provides a computer-readable storage medium, and the computer-readable storage medium stores a computer program, wherein the computer program executes the steps of the deterministic delay guarantee method for critical data transmission in a time-sensitive network when the computer program is executed by a processor.

[0059] Compared with the prior art, the present invention has the following beneficial effects:

[0060] 1. The present invention determines the data flow transmission scheme by constructing a key data flow transmission delay minimization function, and uses the fuzzy reasoning method to greatly shorten the calculation time of the transmission, thereby overcoming the long processing time of the prior art and being difficult to apply in the actual situation of the converter station, so that the shaping of the subsequent data flow by the shaper can achieve the effect of ensuring the delay of the key data flow, improve the real-time performance of data transmission, and reduce the adverse consequences caused by untimely data transmission.

[0061] 2. Based on the asynchronous traffic shaping (ATS) mechanism, the present invention proposes an overall architecture of the scheduling method of the shaping parameter configuration module, effectively establishes fuzzy rules, and uses historical data streams to change the shaping parameters in the ATS mechanism from static to dynamic adjustment. The obtained shaping parameters are used to estimate the transmission delay of the currently transmitted data, thereby discarding the data that cannot reach the target address within the specified transmission delay and reordering the data sending order to ensure the transmission delay of the subsequent transmitted data. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 This is the overall architecture diagram of the ATS scheduling mechanism;

[0063] Figure 2 This is the token bucket schematic diagram;

[0064] Figure 3 Provides the overall process of ATS's communication business shaping strategy. DETAILED DESCRIPTION

[0065] In this embodiment, a deterministic delay guarantee method for critical data transmission in a time-sensitive network is provided. Figure 1 As shown in Figure 1, the overall architecture of the ATS scheduling mechanism and the order of processing data are as follows: the flow filter assigns processing priority to the data, the data passes through the flow gating according to the specified flow gating ID, the service data unit discards the identified abnormal traffic, and the internal priority of the data is further assigned through the flow gating, and then the token bucket in the shaper is sorted. Figure 2 The shaping logic shown in the token bucket principle shapes the data, and after shaping, it is passed to the shared queue to wait for sending. In order to ensure the transmission delay of the key data flow, the parameters of the shaper are dynamically adjusted. Specifically, the method includes the following steps:

[0066] Step 1: extract and analyze the data stream of the previous cycle to determine whether the shaping parameters are suitable for the transmission of the data stream of the next cycle;

[0067] Step 1.1, current Mth transmission cycle Before you begin, get Transmission cycle In this case, the data flow passing through all asynchronous traffic shapers in any switch , and calculate Bit Error Rate ;in, express Middle Priority data flow, and , Indicates Priority data flow Middle The data frames transmitted, Indicates Priority data The number of data frames in , Indicates the maximum priority;

[0068] To facilitate subsequent data transmission and calculation, the following introduces the key data flow types and corresponding priority divisions. The initial priority of the GOOSEA message is set to 7; the SV message mainly transmits sampling value information, and its transmission data flow is large, and this type of information has high real-time requirements. The initial priority of the sampling value information SV flow is mapped to the second highest priority and set to 6; the equipment status information is of great significance for the station control layer equipment to grasp the operating status of the process layer equipment, so the initial priority of the GOOSEB message is mapped to 5; the MMS message mainly contains some file transfer information, mainly transmitting daily operation records, fault records and fault log files, etc., which has little impact on primary and secondary equipment, and there is no specific delay requirement for MMS traffic, so the initial priority is set to 4; the initial priority of other messages is set to 0.

[0069] Step 1.2: Calculate the ratio of the sum of the number of data frames to the sum of the bandwidth occupied using formula (1): :

[0070] (1)

[0071] In formula (1), express bandwidth usage.

[0072] Step 1.3: Based on the local actual situation, take the data flow in the low, medium and high incidence period (or several levels) of network storm as samples, calculate the average of the bit error rate threshold of the data flow in each time period, and set it as the bit error rate threshold , calculate the average of the ratio of the sum of the number of frames in each time period to the sum of the bandwidth occupied, and set it as the threshold of the ratio of the sum of the number of frames to the sum of the bandwidth occupied ;

[0073] Step 1.4: Judgment and Is it true? If so, it means that the shaping parameters of the asynchronous traffic shaper are applicable to the transmission of the next cycle data flow, and go to step 2. Otherwise, wait After the data stream transmission of all asynchronous traffic shapers in the internal switch is completed, M+1 is assigned to M, and the process returns to step 1 for execution.

[0074] Step 2: For any i-th asynchronous traffic shaper, process the i-th priority data flow, taking the shaping parameter of the i-th asynchronous traffic shaper as a variable, Taking the minimum internal data transmission delay as the goal and the value range of shaping parameters as the constraint, the data flow shaping model of the i-th asynchronous traffic shaper is constructed and solved, so as to obtain the optimal shaping parameters of the i-th asynchronous traffic shaper;

[0075] Step 2.1: Define the Mth transmission cycle of waiting for the i-th asynchronous traffic shaper The opened data stream is a shaping queue, constructed using formula (2) Objective function of the internal data flow shaping model :

[0076] (2)

[0077] In formula (2), for Neidi The congestion status value of the priority data flow, for The maximum queuing delay before the i-th asynchronous traffic shaper, for The number of switches passed through, is the transmission delay of data through the asynchronous traffic shaper, The receive storage delay of the switch.

[0078] Step 2.2, calculation ;

[0079] Step 2.2.1, establish several fuzzy subsets for the number of data frames, bandwidth occupancy, and congestion status values. For example, , and The anomaly scores are divided into five fuzzy sets {NB, NS, ZE, PS, PB}, where NB means very small, NS means small, ZE means medium, PS means large, and PB means very large;

[0080] Select appropriate membership functions to describe the degree of belonging of relative entropy difference and bandwidth occupancy to each fuzzy set. In traditional logic, an element either completely belongs to a set or does not belong to the set at all. In fuzzy logic, the degree of membership of an element to a set is a continuous value between 0 and 1, indicating the degree of similarity or belonging of the element to the set. In this study, Gaussian membership function is used to calculate , Respectively The membership degree of fuzzy subsets , .

[0081] Step 2.2.2: After fuzzifying the precise parameters, , and output variables The fuzzy logic relationship between them is used to construct a set of rules and stored in the fuzzy rule base. The fuzzy rules are in the form of "If A Then B" and can be expressed as : If (k) is and (k) is , Then y (k) is , i,j = 1,2,··· ,l where, Indicates rules, l represents the total number of rules, according to , ,calculate and Together, the trigger weight of rule C in the fuzzy rule table shown in Table 1 ;

[0082] Table 1 Fuzzy rule table

[0083]

[0084] Step 2.2.3: Defuzzify the congestion state value according to formula (3) to obtain Congestion status value of the priority data flow :

[0085] (3)

[0086] In formula (3), for The variance of for The variance of is the maximum congestion state value.

[0087] Step 2.3: Use equation (4) to construct the end-to-end minimum transmission delay Expression of

[0088] (4)

[0089] In formula (4), the data stream waiting to be sent is called a scheduling queue. For and priority The number of frames in the shaping queue associated with the scheduling queue. For and priority The dispatch queue associated with A shaping queue, For the Shaping Queue The token bucket capacity of the i-th asynchronous traffic shaper connected, For the Shaping Queue The token filling rate of the connected i-th asynchronous traffic shaper, The port bandwidth of the switch is usually supported by the SNMP protocol. The port bandwidth information can be obtained through SNMP query. For example, query the ifSpeed ​​MIB object to obtain the port bandwidth. for The minimum frame length, for Neidi Priority data flow The maximum frame length.

[0090] Step 2.4: Use formula (5) to construct the token bucket capacity The value constraints of are:

[0091] (5)

[0092] In formula (5), The maximum number of data frames transmitted for the network;

[0093] Step 2.5: Use formula (5) to construct the token filling rate The value constraints of are:

[0094] (6)

[0095] In formula (6), For shaping queues The jth traffic frame length transmitted by the connected shaper, is the maximum frequency deviation between the sending device and the standard clock, The maximum frequency offset between the local clock of the switch and the standard clock. You can obtain the frequency deviation information by querying the MIB objects related to clock synchronization through SNMP, for example, querying the ntpSysOffset and ntpSysFreq MIB objects;

[0096] Step 2.6: The data flow shaping model is solved by an interior point optimization algorithm to obtain the optimal shaping parameters of the i-th asynchronous traffic shaper, including: the optimal token bucket capacity of the i-th asynchronous traffic shaper , the optimal token filling rate of the token bucket of the i-th asynchronous traffic shaper .

[0097] Step 3: According to and ,calculate Start with the data flow queued before the i-th asynchronous traffic shaper exist After the start, the transmission delay to reach the target address ;in, express The number of packets transmitted in the cycle that arrive at the queue before the i-th asynchronous traffic shaper data frames, , Indicates the total number of queued data frames; express The transmission delay is calculated based on the token filling rate, token bucket capacity, maximum residence time, frame arrival time, and data frame length to update the state variables such as token bucket empty time. After the zth frame arrives at the shaper, the shaper allocates a transmission qualified delay for the data frame, and the transmission qualified time is calculated through some key time points and time intervals.

[0098] Step 3.1, use formula (7) to calculate the number of tokens of the i-th asynchronous traffic shaper sufficient to send Required delay :

[0099] (7)

[0100] Step 3.2: Use equation (8) to calculate whether there are enough tokens in the token bucket of the i-th asynchronous traffic shaper to transmit the data flow. The earliest delay :

[0101] (8)

[0102] In formula (8), Indicates the time when data transmission starts ;

[0103] Step 3.3: Calculate using formula (9) The corresponding i-th asynchronous traffic shaper at the most recent token bucket full time :

[0104] (9)

[0105] Step 3.4: Use formula (10) to determine The transmission delay :

[0106] (10)

[0107] Step 4: If , it means that the i-th asynchronous traffic shaper is transmitting normally Otherwise, discard ;in, express The ideal transmission delay of

[0108] Step 5: If < , then update according to formula (11) , otherwise, update according to formula (12) , return to step 3.2, and continue to determine whether the next data frame queued before arriving at the i-th asynchronous traffic shaper is transmitted normally;

[0109] (11)

[0110] (12).

[0111] In this embodiment, an electronic device includes a memory and a processor, wherein the memory is used to store a program that supports the processor to execute the above method, and the processor is configured to execute the program stored in the memory.

[0112] In this embodiment, a computer-readable storage medium stores a computer program on the computer-readable storage medium, and the computer program executes the steps of the above method when executed by a processor.

[0113] Figure 2 According to the token bucket principle, the data frame is waited for to arrive and the shaping ID and the outgoing port information in the frame status information table are obtained. When the shaping instance (i.e., the shaping port ID) does not exist or the outgoing port is a discard port, the data frame is discarded. Otherwise, it is determined whether the data frame is empty. When the data frame is empty, the data frame is discarded and the switch shutdown process is executed. When the data frame is not empty and the shaping queue is not full, the data is transferred to the shaping queue. Otherwise, the data frame is discarded.

[0114] like Figure 3 As shown, a deterministic delay guarantee method for critical data transmission in a time-sensitive network is applied to the overall process of the communication service shaping strategy of ATS. First, through the above data analysis and calculation, the shaped service flow enters the corresponding scheduling queue according to the divided priority, and is scheduled based on the strict priority algorithm. The data frames queued in the scheduling queue are arranged in ascending order of the calculated qualified transmission delay and wait for transmission. If the qualified transmission time of the data frame at the head of the scheduling queue is less than the current time, the data frame can be transmitted; otherwise, the data frame in the current queue cannot be sent, and the data frame of the next priority queue is transmitted.

Claims

1. A deterministic delay guarantee method for critical data transmission in a time-sensitive network. It is characterized in that The steps are as follows: Step 1: extract and analyze the data flow of the previous cycle to determine whether the shaping parameters are suitable for the transmission of the data flow of the next cycle. If suitable, execute step 2; otherwise, continue to determine the data flow of the next cycle; Step 2: For any i-th asynchronous traffic shaper, process the i-th priority data flow, taking the shaping parameter of the i-th asynchronous traffic shaper as a variable, Taking the minimum internal data transmission delay as the goal and the value range of the shaping parameters as the constraint, the data flow shaping model of the i-th asynchronous traffic shaper is constructed and solved to obtain the optimal shaping parameters of the i-th asynchronous traffic shaper, including: the optimal token bucket capacity of the i-th asynchronous traffic shaper , the optimal token filling rate of the token bucket of the i-th asynchronous traffic shaper ; Step 3: According to and ,calculate Start with the data flow queued before the i-th asynchronous traffic shaper exist After the start, the transmission delay to reach the target address ;in, express The number of packets transmitted in the cycle that arrive at the queue before the i-th asynchronous traffic shaper data frames, , Indicates the total number of queued data frames; express transmission delay; Step 4: If , it means that the i-th asynchronous traffic shaper is transmitting normally Otherwise, discard ;in, express The ideal transmission delay.

2. According to claim 1, a deterministic delay guarantee method for critical data transmission in a time-sensitive network, It is characterized in that Step 1 is performed as follows: Step 1.1, current Mth transmission cycle Before you begin, get Transmission cycle In this case, the data flow passing through all asynchronous traffic shapers in any switch , and calculate Bit Error Rate ;in, express Middle Priority data flow, and , Indicates Priority data flow Middle The data frames transmitted, Indicates Priority data The number of data frames in , Indicates the maximum priority; Step 1.2: Calculate the ratio of the sum of the number of data frames to the sum of the bandwidth occupied using formula (1): : (1) In formula (1), express Bandwidth usage; Step 1.3: Set the bit error rate threshold to , the threshold of the ratio of the sum of the number of frames to the sum of the bandwidth occupied is ; Step 1.4: Judgment and Is it true? If so, it means that the shaping parameters of the asynchronous traffic shaper are applicable to the transmission of the next cycle data flow, and go to step 2. Otherwise, wait After the data stream transmission of all asynchronous traffic shapers in the internal switch is completed, M+1 is assigned to M, and the process returns to step 1 for execution.

3. According to claim 2, a deterministic delay guarantee method for critical data transmission in a time-sensitive network, It is characterized in that Described step 2 is carried out as follows: Step 2.1: Define the Mth transmission cycle of waiting for the i-th asynchronous traffic shaper The opened data stream is the shaping queue, and the data stream waiting to be sent is the scheduling queue. We use formula (2) to construct Objective function of the internal data flow shaping model : (2) In formula (2), for Neidi The congestion status value of the priority data flow, for The maximum queuing delay before the i-th asynchronous traffic shaper, for The number of switches passed through, is the transmission delay of data through the asynchronous traffic shaper, The receiving storage delay of the switch; Step 2.2, calculation ; Step 2.3: Use equation (4) to construct the end-to-end minimum transmission delay Expression of (4) In formula (4), For and priority The number of frames in the shaping queue associated with the scheduling queue. For and priority The dispatch queue associated with A shaping queue, For the Shaping Queue The token bucket capacity of the i-th asynchronous traffic shaper connected, For the Shaping Queue The token filling rate of the connected i-th asynchronous traffic shaper, is the port bandwidth of the switch, for The minimum frame length, for Neidi Priority data flow Maximum frame length; Step 2.4: Use formula (5) to construct the token bucket capacity The value constraints of are: (5) In formula (5), The maximum number of data frames transmitted for the network; Step 2.5: Use formula (5) to construct the token filling rate The value constraints of are: (6) In formula (6), For shaping queues The jth traffic frame length transmitted by the connected shaper, is the maximum frequency deviation between the sending device and the standard clock, The maximum frequency offset between the local clock of the switch and the standard clock; Step 2.6: The data flow shaping model is optimized by an interior point optimization algorithm to obtain the optimal shaping parameters of the i-th asynchronous traffic shaper.

4. According to claim 3, a deterministic delay guarantee method for critical data transmission in a time-sensitive network, It is characterized in that The step 2.2 is carried out as follows: Step 2.2.1, establish several fuzzy subsets for the number of data frames, bandwidth occupancy, and congestion status values ​​respectively; Calculated using Gaussian membership function , Respectively The membership degree of fuzzy subsets , ; Step 2.2.2, according to , ,calculate and The trigger weight of rule C in the fuzzy logic control table ; Step 2.2.3: Defuzzify the congestion state value according to formula (3) to obtain Congestion status value of the priority data flow : (3) In formula (3), for The variance of for The variance of is the maximum congestion state value.

5. According to claim 4, a deterministic delay guarantee method for critical data transmission in a time-sensitive network, It is characterized in that The step 3 is carried out as follows: Step 3.1, use formula (7) to calculate the number of tokens of the i-th asynchronous traffic shaper that is sufficient to send Required delay : (7) Step 3.2: Use equation (8) to calculate whether there are enough tokens in the token bucket of the i-th asynchronous traffic shaper to transmit the data flow. The earliest delay : (8) In formula (8), Indicates the time when data transmission starts; Step 3.3: Calculate using formula (9) The corresponding i-th asynchronous traffic shaper at the most recent token bucket full time : (9) Step 3.4: Use formula (10) to determine The transmission delay : (10)。 6. A deterministic delay guarantee method for critical data transmission in a time-sensitive network according to claim 5, It is characterized in that like < , then update according to formula (11) , otherwise, update according to formula (12) , return to step 3.2, and continue to determine whether the next data frame queued before arriving at the i-th asynchronous traffic shaper is transmitted normally; (11) (12)。 7. An electronic device comprising a memory and a processor, It is characterized in that The memory is used to store a program that supports the processor to execute the deterministic delay guarantee method for critical data transmission in a time-sensitive network as described in any one of claims 1-6, and the processor is configured to execute the program stored in the memory.

8. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the steps of the deterministic delay guarantee method for critical data transmission in a time-sensitive network described in any one of claims 1 to 6 are executed.

Citation Information

Cited By

  • Cross-layer optimization method and device for video stream exchange delay guarantee, and server

    CN120166077A