Stability control method, device, medium and product of adaptive cruise control system based on time sensitive network

Abstract

The application discloses a stability control method, device, medium and product of an adaptive cruise control system based on a time-sensitive network, relates to the field of adaptive cruise control, and comprises the following steps: determining an optimization target; determining a gate list; obtaining a solution vector and decoding the solution vector into a window length and a window offset; fine-tuning the decoded solution vector; solving the optimization target based on the decoded and fine-tuned solution vector, obtaining a worst end-to-end delay of a flow; solving the optimization target based on the worst end-to-end delay of the flow and a genetic algorithm, obtaining a scheduling scheme with the lowest delay; constructing a closed-loop system matrix considering the delay based on the scheduling scheme with the lowest delay; the eigenvalue of the closed-loop system matrix considering the delay is located within a unit circle; and controlling the adaptive cruise control system based on the closed-loop system matrix considering the delay. The application can effectively evaluate the stability of the adaptive cruise control system to the time-sensitive network (TSN) and output a scheduling scheme ensuring the stability.

Description

Technical Field

[0001] This application relates to the field of adaptive cruise control, and in particular to a stability control method, device, medium, and product for an adaptive cruise control system based on a time-sensitive network. Background Technology

[0002] In the wave of vehicle intelligence, vehicles are equipped with an increasing number of intelligent sensors, controllers, and actuators. This trend has driven the evolution of electronic and electrical architecture from distributed to centralized, giving rise to central computing platforms and regional controllers with higher computing power, as well as vehicle backbone networks with greater bandwidth. For safety and control stability considerations, in-vehicle communication systems must possess determinism and real-time performance. Time-Sensitive Networking (TSN), an extension of Ethernet, achieves deterministic low-latency communication through mechanisms such as clock synchronization and Time-Aware Scheduling (TAS), and is considered the most promising solution for next-generation in-vehicle networks. Numerous studies have demonstrated that TSN can significantly reduce the latency and jitter of time-triggered streams, exhibiting a clear communication advantage compared to traditional CAN and Ethernet. However, the specific impact of this communication advantage on common vehicle controls (such as adaptive cruise control, ACC) still lacks sufficient discussion. Therefore, in the context of TSN, how to design ACC control stability becomes a noteworthy issue. Summary of the Invention

[0003] The purpose of this application is to provide a stability control method, device, medium, and product for an adaptive cruise control system based on time-sensitive networks, which can achieve communication optimization design through information flow scheduling to realize ACC stability control under complex communication loads.

[0004] To achieve the above objectives, this application provides the following solution:

[0005] Firstly, this application provides a stability control method for an adaptive cruise control system based on a time-sensitive network, the stability control method for the adaptive cruise control system based on a time-sensitive network comprising:

[0006] Define the optimization objective;

[0007] Determine the gate list; the gate list includes: gate list periodic constraints, window opening length constraints for each priority level, and window opening offset constraints;

[0008] Obtain the solution vector; the solution vector includes a set of real numbers;

[0009] Each real number in the solution vector is decoded into the window length and window offset;

[0010] The decoded solution vector is fine-tuned so that the window length and window offset of each real number in the decoded solution vector satisfy the window length constraint and window offset constraint of each priority.

[0011] The optimization objective is solved based on the decoded and fine-tuned solution vector to obtain the worst end-to-end delay of the flow;

[0012] The optimization objective is solved based on the worst-case end-to-end delay of the flow and a genetic algorithm to obtain the scheduling scheme with the lowest delay.

[0013] Based on the scheduling scheme with the lowest latency, a closed-loop system matrix considering latency is constructed; the eigenvalues ​​of the closed-loop system matrix considering latency are located inside the unit circle.

[0014] The adaptive cruise control system is controlled based on the closed-loop system matrix that takes time delay into account.

[0015] Optionally, the expression for the optimization objective is as follows:

[0016]

[0017] Where J is the optimization objective, f i Let i be a stream, F be the set of streams, and D be the stream i. fi The worst-case end-to-end delay for the flow.

[0018] Optionally, the expressions for the gated list periodic constraint, the window length constraint for each priority level, and the window offset constraint are as follows:

[0019] T GCL ≤min({f i .D|f i ∈F})

[0020]

[0021] HPmodT GCL =0

[0022] Among them, T GCL Indicates the period of the gated list, f i .D is the deadline for solving the flow, f i Let i be a stream, F be the set of streams, and P be the stream i. m Let m be the priority, and P be the set of all priorities. It is port P. m Priority window length, O is the set of all ports, HP is the timeout;

[0023]

[0024] in, It is the window opening length, f i .size is the size of the stream, f i T is the period of the flow. This indicates that the transmission priority through port o is P. m The set of flows, where B is the network bandwidth. For the length of the protective belt;

[0025]

[0026] Among them, P o It is the sum of priorities on o. It is the window length of the BE stream at port o. It is a collection of BE streams transmitted through port o;

[0027]

[0028]

[0029]

[0030]

[0031]

[0032] in, P is the windowing time offset of the window with priority m on port o. n It is priority n. It is the windowing time offset of the window with priority n on port o. It is the window length of the window with priority n on port o.

[0033] Optionally, the length of the solution vector is:

[0034]

[0035] Where O represents the set of all ports, o represents the current port, and P o This represents the sum of priorities on o.

[0036] Optionally, the following formula is used to decode each real number in the solution vector into the window length and window offset:

[0037]

[0038]

[0039] in, and These are the corresponding o-ports P in the solution vector.m The window's length and offset are real numbers.

[0040] Optionally, the optimization objective is solved based on the decoded and fine-tuned solution vector to obtain the worst-case end-to-end delay of the flow, specifically using the following formula:

[0041]

[0042] Among them, D fi This represents the worst-case end-to-end delay, where O represents the set of all ports, and o represents the current port. t represents the queuing and transmission delay of a flow with priority m at port o. prop Indicates the propagation delay, t proc This indicates a processing delay.

[0043] The control delay and transmission delay of the preceding condition ACC are represented as D. ACC =(Υ+ν)·t s , where t s To control the cycle,

[0044] Optionally, the expression for the closed-loop system matrix considering time delay is as follows:

[0045]

[0046] in, All represent the discrete coefficient matrix of the ACC state-space equations, Δ i,k The matrix representing the uncertainty coefficients introduced by random time-varying delay can be processed using the matrix multicell description method. i = 1, ..., γ, K represents the optimal control matrix calculated by the linear quadratic regulator (LQR) based on the state-space equation without considering the delay.

[0047] In a second aspect, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the stability control method of the adaptive cruise control system based on time-sensitive networks as described above.

[0048] Thirdly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the stability control method for the time-sensitive network-based adaptive cruise control system described above.

[0049] Fourthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the stability control method for an adaptive cruise control system based on a time-sensitive network as described above.

[0050] According to the specific embodiments provided in this application, the following technical effects are disclosed:

[0051] This application provides a stability control method, device, medium, and product for an adaptive cruise control system based on time-sensitive networks (TSN). Traditional Ethernet experiences a significant increase in critical control link latency as the load increases. Under the same BE flow load, the TSN latency is much smaller than the Ethernet latency. The scheduling method in this application reduces interference between flows through reasonable window partitioning, providing real-time and deterministic transmission for the TT flow. Under high load, Ethernet exhibits points where eigenvalues ​​are not within the unit circle as latency increases; therefore, simple LQR control cannot achieve system stability. This situation requires more complex robust control design. The TSN latency in this application is optimized through scheduling. The eigenvalues ​​are all distributed within the unit circle, enabling stable control through LQR even under high BE flow loads. In addition, many eigenvalues ​​of Ethernet delay have large imaginary parts, which can lead to significant oscillations in the system response. In contrast, the eigenvalues ​​of TSN delay are distributed around the real axis, avoiding significant oscillations and promoting a smoother system response. Control stability no longer requires complex control methods to guarantee. The low latency of the TSN mechanism provides better control stability in complex load environments. The introduction of TSN can further simplify the design of control systems, allowing the implementation of functions that previously required robust control strategies to be achieved using simpler control strategies. Attached Figure Description

[0052] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0053] Figure 1 This is a schematic diagram of the stability control method framework for an adaptive cruise control system based on a time-sensitive network according to one embodiment of this application;

[0054] Figure 2 This is a flowchart illustrating a stability control method for an adaptive cruise control system based on a time-sensitive network, according to one embodiment of this application.

[0055] Figure 3This is a schematic diagram of the encoding and decoding process in one embodiment of this application;

[0056] Figure 4 This is a schematic diagram of information transmission in a network and control flow according to an embodiment of this application;

[0057] Figure 5 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0058] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0059] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0060] This application provides a stability control method for an adaptive cruise control system based on time-sensitive networks. The framework of this method is as follows: Figure 1 As shown, it mainly consists of two parts. The first part is a scheduling method based on the worst-case delay analysis theory of flexible window, and the second part is the stability analysis theory of ACC system based on the worst-case control link delay of TSN. The output delay of the first part of the scheduling method is used to determine the stability of the system in the second part of the stability analysis. If the determination fails, the system is re-scheduled until it is stable.

[0061] See Figure 2 The detailed steps of the stability control method for the adaptive cruise control system based on time-sensitive networks in this application are as follows:

[0062] Part 1: Network Scheduling Based on Flexible Window Worst Delay Analysis Theory

[0063] The basic scheduling process involves mapping the scheduling solution to a gated list scheme. This process evaluates the scheme using worst-case delay analysis theory and iteratively searches for scheduling solutions based on the evaluation results. The solution process of genetic algorithms is very compatible with the scheduling method in this application. The delay analysis process can be regarded as the fitness function solution process, and the iterative search process can be implemented through crossover and compilation.

[0064] Step 101: Determine the optimization objective.

[0065] To simplify the design process, this application stipulates the following: First, all ports use the same GCL period, and different priority windows on the same port are not allowed to overlap. Although some existing methods provide analysis methods for overlapping different periods and windows, this application believes that these methods are unnecessary in the design, because this not only increases the difficulty of analysis, but also the occupation of high priority may have an adverse effect on the latency of low priority. Second, after reserving sufficient bandwidth for the best-effort flow (BE flow), the time-sensitive flow occupies all the remaining bandwidth. This is because the in-vehicle network scenario is relatively stable and there will not be a large amount of unpredictable traffic, so occupying all bandwidth can effectively reduce bandwidth waste and reduce scheduling latency. Finally, this invention does not only focus on the ACC-related information flow during scheduling, but also on the overall TT flow transmission effect. Therefore, the scheduling optimization objective is to minimize the latency of all TT flows, as shown in Equation (1).

[0066]

[0067] Where J is the optimization objective, and D fi The worst-case end-to-end delay for the flow.

[0068] Step 102: Determine the gate list; the gate list includes: gate list periodic constraints, window opening length constraints for each priority level, and window opening offset constraints.

[0069] Once the network environment is determined, the gating list for an output port can be determined by the gating list period T. GCL Window length for each priority level and window offset This needs to be determined. The appropriate selection of the gating list period is crucial for successful scheduling. To meet the flow's deadline constraints, T... GCL It must not exceed the minimum of the cutoff times of all flows, as shown in equation (2). Meanwhile, T GCL It needs to be long enough to accommodate all priority windows, therefore it must be no less than the sum of the lengths of all priority windows for each output port, as shown in Equation (3), where O represents the set of all output ports. In addition, for ease of deployment, T... GCL It needs to be a divisor of the superperiod, as shown in equation (4).

[0070] T GCL ≤min({f i .D|f i ∈F})(2)

[0071]

[0072] HPmodT GCL =0(4)

[0073] Among them, f i D is the deadline for solving the flow, F is the set of flows, and P is the solution deadline. m Let m be the priority, and P be the set of all priorities. It is port P. m Priority window length, O is the set of all ports, and HP is the timeout.

[0074] definition and P of port o respectively m Priority window opening length and window offset. To ensure the window has sufficient bandwidth for transmission, The constraints defined in equation (5) need to be satisfied.

[0075]

[0076] Among them, f i .size is the size of the stream, f i T is the period of the flow. This indicates that the transmission priority through port o is P. m The set of flows, where B is the network bandwidth. The length of the protective belt is shown in equation (6).

[0077]

[0078] MTU is the maximum transmission unit, with a size of 1500B. Since the BE stream does not need to guarantee its transmission delay, this application only reserves sufficient transmission bandwidth for the BE stream, and its window length is shown in equation (7).

[0079]

[0080] The previous definition stated that time-sensitive streams occupy all bandwidth except for BE streams, therefore It also needs to satisfy the following constraint (8).

[0081]

[0082] Window offset It is the window relative to T GCL The start time of the window opening. To ensure all window opening periods fall within the cycle. The constraints shown in equation (9) need to be satisfied.

[0083]

[0084]

[0085]

[0086] Because this invention also defines that windows of different priorities are not allowed to overlap, therefore and It is also necessary to satisfy the constraints shown in equation (10).

[0087]

[0088] Step 103: Obtain the solution vector; the solution vector includes a set of real numbers.

[0089] Step 104: Decode each real number in the solution vector into window length and window offset.

[0090] Step 105: Fine-tune the decoded solution vector so that the window length and window offset of each real number in the decoded solution vector satisfy the window length constraint and window offset constraint of each priority.

[0091] The scheduling method proposed in this application uses real number encoding to represent a solution, that is, a solution vector consists of a set of real numbers, the length (L) of which is shown in equation (11), where the first L / 2 bits represent the window length of each priority of each transmitting port. The last L / 2 bits represent the window offset, respectively. Each real number takes values ​​in the range [1, 1000]. The process of mapping the solution vector to a gated list scheme for each port is called decoding.

[0092]

[0093] The following is through Figure 3 Taking the topology shown as an example, the encoding and decoding process is described in detail. In this topology, three priority streams are transmitted from terminal 1 to terminal 2 and terminal 3, with a total of three output ports, which have 3, 1, and 2 priority windows respectively. Therefore, L = 2 × (3 + 1 + 2) = 12. In the example solution vector shown in the figure, the first 6 bits of the first 6 bits correspond to the window lengths of the three priorities of o1, the fourth bit corresponds to the window length of the one priority of o2, and the fifth and sixth bits correspond to the window lengths of the two priorities of o3. The last six bits are similar to the first six bits, corresponding to the window opening offsets respectively. Using equations (12) and (13), each real number can be decoded into the window opening length and offset.

[0094]

[0095] in, and These are the corresponding o-ports P in the solution vector. m The window's length and offset are real numbers.

[0096] Based on this, fine-tuning is performed to satisfy the constraints represented by equations (5), (8), (9), and (10), thereby obtaining all parameters for worst-case delay analysis. Then, the fitness of the solution vector can be obtained using the worst-case delay analysis method based on flexible windows.

[0097] Step 106: Solve the optimization objective based on the decoded and fine-tuned solution vector to obtain the worst end-to-end delay of the flow.

[0098] The fitness of this application is the optimization objective shown in formula (1). This application uses the worst-case delay analysis theory of flexible window GCL to solve for the delay based on the GCL window length and bias obtained from decoding. The priority is P. m flow f i The worst-case delay at port o can be calculated using formula (14).

[0099]

[0100] in, and P m The arrival curve and service curve of the window, h(·) represents the maximum horizontal distance between the two curves. Based on formula (15), f is further obtained. i The end-to-end transmission delay is shown in (15).

[0101]

[0102] Among them, O(f) i ) is f i The set of sending ports traversed by the route, |O(f i )| represents the number of sending ports in the set, t prop , t proc These represent propagation delay and processing delay, respectively. Since the transmission distance of the in-vehicle network is short and the switch chip has high performance, this application ignores these two delays. and The specific calculation method can refer to the existing TSN analysis method based on network calculus. No specific restrictions or definitions are made in this application.

[0103] Step 107: Solve the optimization objective based on the worst end-to-end delay of the flow and the genetic algorithm to obtain the scheduling scheme with the lowest delay.

[0104] This application uses a genetic algorithm to solve the problem. An initial population is generated by real number encoding. After crossover and mutation, the optimal solution is continuously searched. The search stops after the specified solution time is reached, and the optimal solution is output as the scheduling result.

[0105] Part Two: Stability Analysis of the ACC System Based on Worst-Case Control Link Delay of TSN

[0106] Step 108: Construct a closed-loop system matrix that takes into account the delay based on the scheduling scheme with the lowest delay; the eigenvalues ​​of the closed-loop system matrix that takes into account the delay are located inside the unit circle.

[0107] The scheduling method proposed above can calculate the worst-case delay of the ACC control link flow, which can be further expressed as D. ACC =(Υ+ν)·t s Among them, t s Let be the controller cycle. The ACC closed-loop state-space equation, neglecting control delay, is shown in equation (16).

[0108]

[0109] Since the ZCU executes the latest received control command according to the event-triggered mode, the control commands that may take effect on the system during the time period from k to k+1 include u k ,u k-1 ,...u k-Υ-1 The system state equation (16) considering the time delay can be rewritten as equation (17).

[0110]

[0111] Where, Δ i,k It is the uncertainty coefficient matrix introduced by the random time-varying delay. According to state feedback control, it can be known that... Therefore, equation (17) can be further written as the closed-loop system equation formula (18).

[0112]

[0113] In this application, K is obtained by controlling the solution of equation (16) based on LQR control.

[0114] Define a new state vector Equation (18) can be written as equation (19).

[0115] X k+1 =ΦX k +Θr k (19)

[0116] in, The value in the lower right corner indicates the dimension of the matrix. Thus, the closed-loop system matrix Φ is constructed.

[0117] Step 109: Control the adaptive cruise control system based on the closed-loop system matrix that takes time delay into account.

[0118] According to the stability criterion for discrete control systems, as long as all eigenvalues ​​of Φ lie within the unit circle, the asymptotic stability of the system can be guaranteed. Therefore, the stability of the time-delayed ACC control system is proven.

[0119] The scope of application of the above-mentioned scheme in this application is as follows:

[0120] (1) Vehicle network: This solution is applicable to centralized electronic and electrical architectures and requires sensors, area controllers and high-performance computing units. At the same time, the vehicle communication needs to support time-sensitive network protocols, including IEEE 802.1AS and IEEE 802.Qbv protocols.

[0121] (2) Control Flow: After the sensors collect data in real time, the signals are transmitted to the high-performance computing unit via Ethernet through the area controller. Upon receiving the latest signal, the high-performance computing unit processes it and then sends the control signal to the relevant area controller for execution. A schematic diagram of the applicable network and control flow information transmission is shown below. Figure 4 As shown.

[0122] (3) ACC control method: The hierarchical ACC method, in which the upper controller is the acceleration planning layer and the lower controller is the acceleration tracking layer. The upper layer usually decides the desired acceleration based on the safe distance, and the lower controller uses the LQR algorithm to ensure that the actual acceleration of the vehicle stably follows the desired acceleration command under the influence of delay.

[0123] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal, and its internal structure diagram may be as follows. Figure 5 As shown, the computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores data for a stability control method based on a time-sensitive network (TSN) adaptive cruise control system. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a stability control method for a time-sensitive network-based adaptive cruise control system.

[0124] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0125] In one exemplary embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0126] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0127] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0128] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0129] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0130] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0131] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0132] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A stability control method for an adaptive cruise control system based on time-sensitive networks, characterized in that, The stability control method of the time-sensitive network-based adaptive cruise control system includes: Define the optimization objective; Determine the gate list; the gate list includes: gate list periodic constraints, window opening length constraints for each priority level, and window opening offset constraints; Obtain the solution vector; the solution vector includes a set of real numbers; Each real number in the solution vector is decoded into the window length and window offset; The decoded solution vector is fine-tuned so that the window length and window offset of each real number in the decoded solution vector satisfy the window length constraint and window offset constraint of each priority. The optimization objective is solved based on the decoded and fine-tuned solution vector to obtain the worst end-to-end delay of the flow; The optimization objective is solved based on the worst-case end-to-end delay of the flow and a genetic algorithm to obtain the scheduling scheme with the lowest delay. Based on the scheduling scheme with the lowest latency, a closed-loop system matrix considering latency is constructed; the eigenvalues ​​of the closed-loop system matrix considering latency are located inside the unit circle. The adaptive cruise control system is controlled based on the closed-loop system matrix that takes time delay into account.

2. The stability control method for an adaptive cruise control system based on a time-sensitive network according to claim 1, characterized in that, The expression for the optimization objective is as follows: Where J is the optimization objective, f i Let i be a stream, F be the set of streams, and D be the stream i. fi The worst-case end-to-end delay for the flow.

3. The stability control method for an adaptive cruise control system based on a time-sensitive network according to claim 1, characterized in that, The expressions for the gated list periodic constraint, the window length constraint for each priority level, and the window offset constraint are as follows: T GCL ≤min({f i .D|f i ∈F}) HPmodT GCL =0 Among them, T GCL Indicates the period of the gated list, f i .D is the deadline for solving the flow, f i Let i be a stream, F be the set of streams, and P be a stream. m Let m be the priority, and P be the set of all priorities. It is port P. m Priority window length, O is the set of all ports, HP is the timeout; in, It is the window opening length, f i .size is the size of the stream, f i T is the period of the flow. This indicates that the transmission priority through port o is P. m The set of flows, where B is the network bandwidth. For the length of the protective belt; Among them, P o It is the sum of priorities on o. It is the window length of the BE stream at port o. It is a collection of BE streams transmitted through port o; in, P is the windowing time offset of the window with priority m on port o. n It is priority n. It is the windowing time offset of the window with priority n on port o. It is the window length of the window with priority n on port o.

4. The stability control method for an adaptive cruise control system based on a time-sensitive network according to claim 1, characterized in that, The length of the solution vector is: Where O represents the set of all ports, o represents the current port, and P o This represents the sum of priorities on o.

5. The stability control method for an adaptive cruise control system based on a time-sensitive network according to claim 2, characterized in that, The following formula is used to decode each real number in the solution vector into the window length and window offset: in, and These are the corresponding o-ports P in the solution vector. m The window's length and offset are real numbers.

6. The stability control method for an adaptive cruise control system based on a time-sensitive network according to claim 1, characterized in that, The optimization objective is solved based on the decoded and fine-tuned solution vector, and the worst end-to-end delay of the flow is obtained using the following formula: in, This represents the worst-case end-to-end delay, where O represents the set of all ports, and o represents the current port. t represents the queuing and transmission delay of a flow with priority m at port o. prop Indicates the propagation delay, t proc This indicates a processing delay.

7. The stability control method for an adaptive cruise control system based on a time-sensitive network according to claim 1, characterized in that, The expression for the closed-loop system matrix considering time delay is as follows: in, All represent the discrete coefficient matrix of the ACC state-space equations, Δ i,k Let represent the uncertainty coefficient matrix introduced by the random time-varying delay, i = 1, ..., γ, and K represent the optimal control matrix calculated by the linear quadratic regulator based on the state-space equation without considering the delay.

8. A computer device, comprising: The memory and processor contain a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the steps of the stability control method for an adaptive cruise control system based on a time-sensitive network as described in any one of claims 1-7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the stability control method of the adaptive cruise control system based on time-sensitive networks as described in any one of claims 1-7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the stability control method of the adaptive cruise control system based on time-sensitive networks as described in any one of claims 1-7.

Images