Time synchronization method, system and equipment of intelligent transportation system

Abstract

The invention discloses a time synchronization method, system and device of an intelligent traffic system. The method comprises the following steps: receiving a time synchronization request of a time synchronization device in the intelligent traffic system; establishing a time synchronization connection between the time synchronization device and the master clock according to the request; based on the time synchronization connection, a network domain corresponding to the time synchronization equipment and a data timing requirement of the intelligent traffic system, performing time message exchange between the time synchronization equipment and a main clock by using a time redundancy strategy; calculating a time offset between the time synchronization device and the master clock according to the time message; and based on the time offset, performing time error compensation and control on the time synchronization equipment by using a compensation control algorithm. According to the invention, a network delay measurement mechanism and a time error compensation control mechanism based on a time redundancy principle are adopted to carry out time synchronization, the data timing requirements of the intelligent traffic system in different scenes are considered, the change of end-to-end network delay is reduced, and the time synchronization precision and stability are improved.

Description

Technical Field

[0001] The present application relates to the field of time synchronization technology, and in particular to a time synchronization method, system, and device for an intelligent transportation system. Background Art

[0002] Time synchronization is fundamental to a smart digital society, as the infrastructure of the future is filled with distributed systems interconnected by ubiquitous networks. At the same time, networks are expected to become increasingly deterministic, providing not only bandwidth and reliability guarantees but also time guarantees. With the increasing availability of time-engineered communication services, networks must support time accuracy in data transmission as a core communication service. Time-Sensitive Networking (TSN), which prioritizes time synchronization as a key feature, is rapidly becoming the standard for deterministic networking in local area networks. Within the wireless communications community, the Third Generation Partnership Project (3GPP) has made significant progress in enabling fifth-generation (5G) systems to support latency-sensitive use cases through Ultra-Reliable Low-Latency Communication (URLLC). Cellular systems offer inherent access flexibility, which other systems lack. Driven by the need to provide deterministic communication over wireless networks, URLLC was defined in 5G standard releases 15 to 17. 5G interoperability with time-sensitive networking (TSN), known as 5G time-sensitive communication (TSC), has been addressed in Releases 16 and 17, and support for deterministic networking (DetNet) is being prepared for Release 18. However, current support for 5G and TSN combined is insufficient for future end-to-end time-sensitive applications, particularly in areas such as cross-domain collaborative management and end-to-end real-time traffic scheduling. This capability must be significantly enhanced in sixth-generation (6G) networks to achieve fully deterministic end-to-end communication.

[0003] Therefore, achieving time synchronization over a wider area and at a lower cost to serve time-sensitive applications is becoming increasingly important. Intelligent transportation systems (ITS) are a prime example of these applications. By leveraging information and communication technologies, they provide an efficient approach to improving the performance of transportation systems, enhancing safety, and promoting environmental sustainability. Intelligent transportation systems (ITS) encompass numerous components, including sensors, communication networks, data processing and analysis systems, traffic control equipment, and intelligent traffic management centers. These elements work together to collect, process, transmit, and apply traffic-related information. The frequent interactions and collaborative integration between vehicles (via on-board units (OBUs), road infrastructure (via roadside units (RSUs), and the cloud are driving the demand for time synchronization towards higher precision and a wider scope. For example, the coordination of activities between ITS components requires timely and accurate data delivery. In this context, the temporal accuracy of this data becomes crucial. The success of networked and autonomous driving depends on a foundation of seamless collaboration between roadside and onboard equipment. In this context, the fusion of perception of the vehicle environment (including vision, radar, and network-based inputs) becomes a cornerstone. Furthermore, a key prerequisite for maintaining consistent event observation during the perception process is precise time synchronization between different sensing source devices. Furthermore, vehicle automation involves the dynamic interaction between programmable logic controllers, sensors, and actuators. To effectively coordinate this complex process, synchronization accuracy, from milliseconds to sub-milliseconds, is essential.

[0004] In order to ensure accurate time coordination between the various components of the Intelligent Transportation System (ITS), researchers have developed a variety of synchronization strategies. The IEEE802.11p protocol was first standardized in 2012 and subsequently incorporated into the updated IEEE802.11-2020 specification, establishing a vehicle communication framework through its WAVE extension. To address the challenges of urban navigation, Neil et al. designed a cluster-based synchronization architecture in which collaborative vehicles share time measurement data to compensate for the attenuation of GPS signals in dense urban areas, which is a key requirement for the operation of autonomous vehicles. At the same time, Hasan et al. verified the feasibility of GPS-assisted synchronization through field experiments, confirming that it can meet the strict ITS synchronization requirements. Ben-El-Kezadri et al. developed a synchronization technology that uses GPS accuracy to coordinate the differences between the network interface and host system clocks, effectively alleviating the clock drift problem in mobile networks.

[0005] In the context of network time synchronization, Gohar et al. explored the use of the IEEE 1588 standard to develop a microsecond-level synchronization protocol to improve the efficiency of inter-vehicle communication. To overcome the limitations of rigid and resource-intensive dedicated synchronization infrastructure, Han et al. introduced a software-defined centralized framework that can dynamically optimize synchronization resource allocation and path planning. Similarly, Ruffini et al. designed an SDN-based synchronization-as-a-service model that deploys virtual coordinators through standardized interfaces to aggregate cross-domain timing data. H. Li et al. introduced a time synchronization framework for converged networks that leverages SDN principles. This innovative approach separates time transmission from accuracy compensation, ensuring that intelligent transportation infrastructure (such as OBU and RSU) can achieve high-precision timing in both wired and wireless communication networks.

[0006] Although there are many methods for achieving precise time synchronization, such as using the Global Navigation Satellite System (GNSS), the Precision Time Protocol (PTP), 3GPP's TSC, and more. However, when considering the continuous interaction between vehicles and urban environments, achieving guaranteed synchronization accuracy while meeting a wide range of requirements is undoubtedly a huge challenge. For example, GNSS fails in scenarios such as underground tunnels and exhibits significant performance degradation in urban canyon environments. PTP requires the establishment of a dedicated time synchronization network to ensure high accuracy. TSC requires additional TSN converters to achieve the desired effect. Therefore, there is an urgent need for a precise time synchronization solution to meet the complex requirements in wide-area networks for vehicle-city interaction. Summary of the Invention

[0007] The embodiments of the present application provide a time synchronization method, system, and device for an intelligent transportation system to improve the time synchronization accuracy and stability of a converged network scenario.

[0008] The embodiments of this application adopt the following technical solutions:

[0009] In a first aspect, an embodiment of the present application provides a time synchronization method for an intelligent transportation system, wherein the time synchronization method for the intelligent transportation system is performed by a time synchronization system, and the time synchronization method for the intelligent transportation system includes:

[0010] Receiving a time synchronization request from a time synchronization device in an intelligent transportation system;

[0011] establishing a time synchronization connection between the time synchronization device and a master clock according to the time synchronization request;

[0012] Based on the time synchronization connection between the time synchronization device and the master clock, the network domain corresponding to the time synchronization device, and the data timing requirements of the intelligent transportation system, the time redundancy strategy is used to exchange time messages between the time synchronization device and the master clock;

[0013] Calculating the time offset between the time synchronization device and the master clock based on the exchanged time messages;

[0014] Based on the time offset between the time synchronization device and the master clock, a preset compensation control algorithm is used to compensate and control the time error of the time synchronization device.

[0015] Optionally, the time synchronization system includes a synchronization controller, a coordination controller, and a domain controller, and receiving a time synchronization request from a time synchronization device in the intelligent transportation system includes:

[0016] receiving, by the synchronization controller, a time synchronization request from a time synchronization device in an intelligent transportation system;

[0017] The establishing of a time synchronization connection between the time synchronization device and the master clock according to the time synchronization request comprises:

[0018] According to the time synchronization request, the synchronization controller generates a time synchronization task and sends it to the coordination controller, and receives an optimal time synchronization path between the time synchronization device and the master clock returned by the coordination controller;

[0019] According to the optimal time synchronization path between the time synchronization device and the master clock, a time synchronization connection between the time synchronization device and the master clock is established through the domain controller using a precise time synchronization protocol.

[0020] Optionally, the time synchronization device includes a roadside unit, and the exchanging of time messages between the time synchronization device and the master clock using a time redundancy strategy based on the time synchronization connection between the time synchronization device and the master clock, the network domain corresponding to the time synchronization device, and the data timing requirements of the intelligent transportation system includes:

[0021] Based on the time synchronization connection between the roadside unit and the master clock, the TSN network domain corresponding to the roadside unit, and the data timing requirements of the roadside unit, a time redundancy strategy is used to exchange time messages between the roadside unit and the master clock.

[0022] Optionally, the time synchronization device includes an on-board unit, and the exchanging of time messages between the time synchronization device and the master clock using a time redundancy strategy based on the time synchronization connection between the time synchronization device and the master clock, the network domain corresponding to the time synchronization device, and the data timing requirements of the intelligent transportation system includes:

[0023] Based on the time synchronization connection between the on-board unit and the master clock, the TSN network domain and cellular network domain corresponding to the on-board unit, and the data timing requirements of the on-board unit, a time redundancy strategy is used to exchange time messages between the on-board unit and the master clock.

[0024] Optionally, the exchanging time messages between the time synchronization device and the master clock using a time redundancy strategy based on the time synchronization connection between the time synchronization device and the master clock, the network domain corresponding to the time synchronization device, and the data timing requirements of the intelligent transportation system includes:

[0025] Determine the time synchronization accuracy corresponding to the current business scenario based on the data timing requirements of the intelligent transportation system;

[0026] Determining a frame replication interval and a redundancy coefficient in the time redundancy strategy according to the time synchronization accuracy corresponding to the current service scenario, wherein the redundancy coefficient is used to determine the number of frame replications;

[0027] In a TSN network domain of the master clock, based on the frame replication interval and the redundancy coefficient, a time critical message to be sent by the master clock to the time synchronization device is replicated to obtain a replicated frame of the time critical information, where the time critical message is one of a synchronization message and a delay request message;

[0028] transmitting the copy frame of the time-critical information to the time synchronization device via the cellular network domain;

[0029] In the TSN network domain of the time synchronization device, redundant processing is performed on the received duplicate frames of the time-critical information.

[0030] Optionally, in the TSN network domain of the time synchronization device, performing redundancy processing on the received duplicate frames of the time-critical information includes:

[0031] In the TSN network domain of the time synchronization device, the first received copy frame of the time critical information is retained, and all other copy frames of the time critical information are discarded.

[0032] Optionally, calculating the time offset between the time synchronization device and the master clock according to the exchanged time messages includes:

[0033] Determine, based on the redundant processing result of the exchanged time messages, a reception timestamp and a corresponding transmission timestamp of the synchronization message first received by the time synchronization device, and a reception timestamp and a corresponding transmission timestamp of the delay request message first received by the master clock;

[0034] The time synchronization device calculates the time offset between the time synchronization device and the master clock based on the reception timestamp and the corresponding sending timestamp of the synchronization message first received by the time synchronization device, and the reception timestamp and the corresponding sending timestamp of the delay request message first received by the master clock.

[0035] Optionally, the preset compensation control algorithm is a neural network-based PID controller, the input of the PID controller includes the redundancy coefficient in the time redundancy strategy, and the neural network-based PID controller can learn and adjust the coefficient of the PID controller online through the neural network to compensate and control the time error of the time synchronization device through the coefficient of the PID controller.

[0036] In a second aspect, an embodiment of the present application further provides a time synchronization system, the time synchronization system comprising: a synchronization controller, a coordination controller, a domain controller, a time synchronization device, and a network domain corresponding to the time synchronization device;

[0037] The synchronization controller is used to receive a time synchronization request from a time synchronization device in an intelligent transportation system;

[0038] The coordination controller and the domain controller are configured to establish a time synchronization connection between the time synchronization device and the master clock according to the time synchronization request;

[0039] The network domain corresponding to the time synchronization device is used to exchange time messages between the time synchronization device and the master clock using a time redundancy strategy based on the time synchronization connection between the time synchronization device and the master clock, the network domain corresponding to the time synchronization device, and the data timing requirements of the intelligent transportation system;

[0040] The time synchronization device is used to send the time synchronization request to the synchronization controller, and calculate the time offset between the time synchronization device and the master clock based on the exchanged time message, and based on the time offset between the time synchronization device and the master clock, use a preset compensation control algorithm to compensate and control the time error of the time synchronization device.

[0041] In a third aspect, an embodiment of the present application further provides a device, including:

[0042] A processor; and a memory arranged to store computer-executable instructions, which, when executed, cause the processor to perform any of the aforementioned time synchronization methods for the intelligent transportation system.

[0043] At least one of the above-mentioned technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects: the time synchronization method of the intelligent transportation system in the embodiments of the present application is executed by the time synchronization system, which first receives a time synchronization request from a time synchronization device in the intelligent transportation system; then, according to the time synchronization request, a time synchronization connection is established between the time synchronization device and the master clock; then, based on the time synchronization connection between the time synchronization device and the master clock, the network domain corresponding to the time synchronization device, and the data timing requirements of the intelligent transportation system, a time redundancy strategy is used to exchange time messages between the time synchronization device and the master clock; then, based on the exchanged time messages, the time offset between the time synchronization device and the master clock is calculated; finally, based on the time offset between the time synchronization device and the master clock, a preset compensation control algorithm is used to compensate and control the time error of the time synchronization device. The time synchronization method for the intelligent transportation system of the embodiment of the present application proposes a network delay measurement mechanism based on the principle of time redundancy, which reduces the variation of end-to-end network delay and can limit the end-to-end relative time error of the wired and wireless converged network to the microsecond level without modifying the existing network infrastructure. In addition, the preset compensation control algorithm is used to optimize the time error compensation control, which can reduce the time jitter of the slave clock device during the local clock correction process, improve the response speed of the compensation process, and ensure the time synchronization accuracy of the slave clock device. In addition, the present application takes into account the impact of the data timing requirements of the intelligent transportation system in different scenarios on the time synchronization accuracy, and meets the time synchronization needs of different scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0045] Figure 1 This is a schematic diagram of a layered architecture of a time synchronization system across multiple network domains in an intelligent transportation system in an embodiment of the present application;

[0046] Figure 2 A schematic flow chart of a time synchronization method for an intelligent transportation system according to an embodiment of the present application;

[0047] Figure 3 This is a schematic diagram of the main working process of a time synchronization system in an embodiment of the present application;

[0048] Figure 4This is a process diagram of a delay measurement mechanism based on the time redundancy principle in a TSN network in an embodiment of the present application;

[0049] Figure 5 This is a schematic diagram of the principle of a neural network-based PID controller in an embodiment of the present application;

[0050] Figure 6 This is a structural diagram of a time synchronization system in an embodiment of the present application;

[0051] Figure 7 This is a structural diagram of a device in an embodiment of the present application. DETAILED DESCRIPTION

[0052] To make the purpose, technical solutions, and advantages of this application more clear, the technical solutions of this application will be clearly and completely described below in conjunction with the specific embodiments of this application and the corresponding drawings. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0053] The following describes in detail the technical solutions provided by various embodiments of the present application in conjunction with the accompanying drawings.

[0054] In order to facilitate the understanding of the various embodiments of this application, Figure 1 As shown, a schematic diagram of the layered architecture of a time synchronization system across multiple network domains in an intelligent transportation system in an embodiment of the present application is provided. The entire architecture consists of two layers: the data layer and the control layer. The data layer includes network devices, intelligent transportation system (ITS) components and clock devices, while the control layer is divided into two levels: domain controllers and coordination controllers. The control layer abstracts the hardware resources of the data layer, thereby realizing the logical centralized control, management and orchestration of virtual resources. The relationship and basic functions of each component are as follows:

[0055] Data layer: Components of an intelligent transportation system (ITS) typically include communication networks, sensors and detectors, data processing and analysis systems, traffic management centers, and various types of intelligent transportation equipment, such as electronic toll collection systems, variable message signs, and intelligent traffic lights. In addition to the equipment directly involved in the ITS, clock devices that constitute the source of time synchronization are also taken into consideration.

[0056] Control layer: It mainly covers the controllers of the TSN domain and the cellular domain. The domain controller is a central entity that understands the network topology. It collects network element (NE) information and link information through a global view of the network. It configures network element functions (for example, flow tables, timestamp reporting functions added based on SDN principles). In addition, a synchronization controller is introduced in the architecture to respond to time synchronization requests, manage and configure the corresponding synchronization functions. Its design purpose is to determine the synchronization paths that need to be accurately compensated, generate compensation tasks to calculate the time error introduced by the packet network, obtain the compensation value, and finally send it to certain ITS devices.

[0057] Coordinator Controller: This controller communicates with domain controllers, coordinating network control and management instructions between them. With a global network perspective, the coordinator controller centrally controls time synchronization, enabling interconnection and interoperability between heterogeneous wired and wireless systems. In a multi-domain time synchronization architecture, the coordinator controller is the core management component of the entire network system, responsible for efficient cross-domain communication coordination and resource optimization. Its primary functions include managing and coordinating the interconnection between TSN and cellular networks, and implementing latency measurement mechanisms.

[0058] The embodiment of the present application provides a time synchronization method for an intelligent transportation system, such as Figure 2 As shown, a flow chart of a time synchronization method for an intelligent transportation system in an embodiment of the present application is provided. The time synchronization method for the intelligent transportation system is executed by a time synchronization system, and includes the following steps S210 to S250:

[0059] Step S210: receiving a time synchronization request from a time synchronization device in an intelligent transportation system.

[0060] The time synchronization method of the intelligent transportation system in the embodiment of the present application is as follows: Figure 1 The time synchronization system shown in the figure is executed, and the time synchronization interaction occurs between the time synchronization devices (such as RSU / OBU), network domains (such as TSN network components, cellular network components), master clocks, and controllers in the intelligent transportation system. Figure 3 , provides a schematic diagram of the main workflow of a time synchronization system in an embodiment of the present application. The whole process is divided into two stages: the synchronization path establishment stage and the timing message exchange stage.

[0061] When performing time synchronization interaction, it is necessary to first receive the time synchronization request sent by the time synchronization device such as OBU / RSU device to the synchronization controller. The request can carry information such as device identification and request type. By parsing the time synchronization request, the device identification, request type and other information can be obtained.

[0062] Step S220: Establish a time synchronization connection between the time synchronization device and a master clock according to the time synchronization request.

[0063] After receiving a time synchronization request, the device must establish a time synchronization connection with a designated master clock based on the parsed request information. This connection serves as the transmission channel for subsequent time synchronization messages. The master clock can be, for example, a high-precision clock source (such as a GPS clock, atomic clock, etc.) or a local clock that has been synchronized with another high-precision clock.

[0064] Step S230, based on the time synchronization connection between the time synchronization device and the master clock, the network domain corresponding to the time synchronization device, and the data timing requirements of the intelligent transportation system, the time redundancy strategy is used to exchange time messages between the time synchronization device and the master clock.

[0065] Significant variations in air interface delays in cellular networks are a primary cause of low time synchronization accuracy. In the IEEE 1588 protocol, the master and slave clocks interact multiple times to calculate network delays. During a synchronization process, the interval between synchronization messages and delay request messages can vary from 1 / 128 second to several seconds, depending on the configuration. Because the IEEE 1588 protocol assumes symmetric uplink and downlink delays, the dynamic variations in the propagation delays of these two asynchronously generated messages can lead to significant errors in the offset values ​​calculated by the slave clocks.

[0066] To mitigate the impact of this dynamic delay variation, embodiments of the present application design a delay measurement mechanism based on the principle of time redundancy in TSN networks. This mechanism replicates associated frames on the sender side and performs redundant processing on the received replicated frames on the receiver side. This time-redundant delay measurement mechanism is used to exchange time messages between the time synchronization device and the master clock.

[0067] In addition, considering that different specific parameter settings in the time redundancy mechanism will affect the actual time synchronization accuracy, and that the intelligent transportation system may have different time synchronization accuracy requirements in different scenarios, and time synchronization accuracy is related to the data timing requirements of the intelligent transportation system, the embodiments of the present application further consider the impact of the data timing requirements of the intelligent transportation system on the time synchronization mechanism. Time synchronization processing is performed based on the data timing requirements of the intelligent transportation system and the time redundancy mechanism, thereby ensuring the time synchronization accuracy requirements of different scenarios.

[0068] Step S240: Calculate the time offset between the time synchronization device and the master clock according to the exchanged time messages.

[0069] Based on the time messages exchanged between the time synchronization device and the master clock, key time information (such as the key message sending and receiving timestamps) is extracted. Based on this extracted time information, the time offset between the time synchronization device and the master clock is calculated. This calculation process may involve calculating the difference in timestamps and compensating for network delays. The calculated time offset is applied to the time synchronization device's clock, adjusting its local time to achieve synchronization with the master clock.

[0070] Step S250 : Based on the time offset between the time synchronization device and the master clock, a preset compensation control algorithm is used to compensate and control the time error of the time synchronization device.

[0071] Taking into account that the time offset calculated in the above steps cannot be directly used to modify the local time of the slave clock, because direct application will cause problems such as overshoot, oscillation or steady-state error of the slave clock, the embodiment of the present application further proposes to use a preset compensation control algorithm to compensate and control the time error of the time synchronization device. The preset compensation control algorithm can be implemented using a PID controller based on a neural network to solve the stability control problem of time error compensation.

[0072] The time synchronization method for the intelligent transportation system of the embodiment of the present application proposes a network delay measurement mechanism based on the principle of time redundancy, which reduces the variation of end-to-end network delay and can limit the end-to-end relative time error of the wired and wireless converged network to the microsecond level without modifying the existing network infrastructure. In addition, the preset compensation control algorithm is used to optimize the time error compensation control, which can reduce the time jitter of the slave clock device during the local clock correction process, improve the response speed of the compensation process, and ensure the time synchronization accuracy of the slave clock device. In addition, the present application takes into account the impact of the data timing requirements of the intelligent transportation system in different scenarios on the time synchronization accuracy, and meets the time synchronization needs of different scenarios.

[0073] In some embodiments of the present application, the time synchronization system includes a synchronization controller, a coordination controller and a domain controller, and the receiving of a time synchronization request from a time synchronization device in an intelligent transportation system includes: receiving a time synchronization request from a time synchronization device in the intelligent transportation system through the synchronization controller; establishing a time synchronization connection between the time synchronization device and the master clock according to the time synchronization request includes: generating a time synchronization task through the synchronization controller according to the time synchronization request and sending it to the coordination controller, and receiving an optimal time synchronization path between the time synchronization device and the master clock returned by the coordination controller; and establishing a time synchronization connection between the time synchronization device and the master clock through the domain controller using a precise time synchronization protocol according to the optimal time synchronization path between the time synchronization device and the master clock.

[0074] Continue to refer Figure 3 As a core component of the time synchronization system, the synchronization controller is responsible for receiving time synchronization requests from various time synchronization devices in the intelligent transportation system. The synchronization controller sets up a listening port at the network or application layer to continuously listen for and receive request messages from time synchronization devices. Request messages contain key information such as the device identifier and request type. Upon receiving a request, the synchronization controller first parses and verifies the message to ensure its legitimacy and validity.

[0075] Based on the received time synchronization request, the synchronization controller generates a time synchronization task. This task contains information such as the time synchronization device identifier and the requested time synchronization accuracy. The synchronization controller sends the generated time synchronization task to the coordination controller for further processing and coordination.

[0076] After receiving the time synchronization task, the coordination controller calculates the optimal time synchronization path between the time synchronization device and the master clock based on information such as network topology, device status, and link quality.

[0077] Based on the optimal time synchronization path, the domain controller selects an appropriate precision time synchronization protocol (such as IEEE 1588v2 PTP or NTP) to establish a time synchronization connection between the time synchronization device and the master clock. The domain controller is responsible for configuring network elements (such as switches and routers) to support the selected time synchronization protocol. Then, through protocol interaction, the time synchronization connection between the time synchronization device and the master clock is established.

[0078] Through the collaborative work of the synchronization controller, coordination controller, and domain controller, the system can more accurately calculate the time offset between the time synchronization device and the master clock and establish a more reliable time synchronization connection.

[0079] The application of the Precision Time Synchronization Protocol further improves the accuracy and reliability of time synchronization and reduces the impact of network latency and jitter on time synchronization. By calculating the optimal time synchronization path, the coordination controller can more efficiently utilize network resources and avoid unnecessary network congestion and latency. The domain controller configures network element functions based on the optimal path, further improving network resource utilization.

[0080] This application supports time synchronization across multiple network domains, enabling the system to adapt to intelligent transportation systems of varying scale and complexity. Through the modular design of synchronization controllers, coordination controllers, and domain controllers, the system can easily expand and upgrade its functionality to meet changing business needs. By dividing the time synchronization function among multiple controllers for collaborative operation, the complexity and load of a single controller are reduced. The modular design also makes system maintenance and upgrades more convenient and efficient, reducing maintenance costs.

[0081] In some embodiments of the present application, the time synchronization device includes a roadside unit, and the exchange of time messages between the time synchronization device and the master clock using a time redundancy strategy based on the time synchronization connection between the time synchronization device and the master clock, the network domain corresponding to the time synchronization device, and the data timing requirements of the intelligent transportation system includes: based on the time synchronization connection between the roadside unit and the master clock, the TSN network domain corresponding to the roadside unit, and the data timing requirements of the roadside unit, the exchange of time messages between the roadside unit and the master clock using a time redundancy strategy.

[0082] As a time synchronization device, the Roadside Unit (RSU) must first establish a time synchronization connection with the master clock. This process involves network configuration and protocol negotiation to ensure stable and reliable data communication between the RSU and the master clock. Once the connection is established, a time synchronization channel is established between the RSU and the master clock for subsequent time message exchange.

[0083] Time message exchange between the RSU and the master clock occurs over the TSN (Time-Sensitive Networking) network domain. TSN networks provide deterministic data transmission services, ensuring that the latency and jitter of time messages during transmission remain within acceptable limits. In TSN networks, time messages may be transmitted over specific time-sensitive streams (such as PTP protocol streams) to ensure their priority and determinism.

[0084] Due to the uncertainty of packet queuing delay in the TSN bridge, in order to accurately correct the time offset, it is necessary to record the inbound and outbound timestamps of the time synchronization message at both the RSU and the master clock.

[0085] On the RSU side, when receiving a time synchronization message from the master clock, the message's inbound timestamp is recorded. When the RSU sends a time synchronization message to the master clock, the message's outbound timestamp is recorded. Similarly, the master clock side also needs to perform corresponding timestamp recording operations.

[0086] Based on the timestamp information (including inbound and outbound timestamps), combined with the network topology and known network delay parameters, the actual time offset between the RSU and the master clock is calculated. Finally, the calculated offset is sent to the RSU, which adjusts its local clock based on the offset to achieve time synchronization with the master clock.

[0087] By recording the inbound and outbound timestamps of time synchronization messages and using this timestamp information for offset correction, the accuracy of time synchronization between the RSU and the master clock can be significantly improved. This approach accounts for the uncertainty of packet queuing delays in TSN networks, making time synchronization more accurate and reliable. Even in the presence of packet queuing delays in TSN networks, the system can still maintain high time synchronization accuracy through timestamp recording and offset correction mechanisms, enhancing the system's robustness to network changes and enabling stable operation of intelligent transportation systems in various network environments.

[0088] In some embodiments of the present application, the time synchronization device includes an on-board unit, and the exchange of time messages between the time synchronization device and the master clock using a time redundancy strategy based on the time synchronization connection between the time synchronization device and the master clock, the network domain corresponding to the time synchronization device, and the data timing requirements of the intelligent transportation system includes: based on the time synchronization connection between the on-board unit and the master clock, the TSN network domain and cellular network domain corresponding to the on-board unit, and the data timing requirements of the on-board unit, the exchange of time messages between the on-board unit and the master clock using a time redundancy strategy.

[0089] As a time synchronization device, the on-board unit (OBU) must establish a stable time synchronization connection with the master clock. This process also involves network access, protocol negotiation, and identity authentication to ensure that the OBU can communicate securely and reliably with the master clock. Once the connection is established, a bidirectional time synchronization channel is established between the OBU and the master clock for subsequent time message exchange.

[0090] Time message exchange between the OMU and the master clock is accomplished through both the TSN and cellular network domains. The TSN network domain provides deterministic data transmission services, ensuring low-latency and low-jitter transmission of time messages within the local area network. The cellular network domain provides wide-area coverage, ensuring that the OMU maintains time synchronization with the master clock while on the move. When exchanging time messages, the system dynamically selects either the TSN or cellular network domain for transmission, or utilizes both for redundant transmission, based on factors such as network conditions and time synchronization accuracy requirements.

[0091] The OBU is in a mobile state and needs to exchange time information with the master clock through a multi-domain network composed of TSN and cellular networks. In this process, not only will the TSN bridge introduce time errors, but the wireless channel will also produce more significant errors. Therefore, in order to improve the reliability and accuracy of time synchronization, the embodiment of the present application is based on the data timing requirements and time redundancy mechanism of the on-board unit. In the TSN network domain and the cellular network domain, a copy of the time-critical message is sent at the sending end, and the copy of the time-critical message is redundantly processed at the receiving end. Finally, the time offset is calculated based on the timestamp of the exchanged time message. According to the calculated offset, the on-board unit adjusts its local clock to achieve time synchronization with the master clock.

[0092] By exchanging time messages across the TSN and cellular network domains, and applying time redundancy strategies, the system can significantly improve the reliability and accuracy of time synchronization. This embodiment of the application supports time synchronization of onboard units across different network domains while on the move, enhancing the flexibility and adaptability of the system.

[0093] Complex intelligent transportation scenarios, such as autonomous driving and vehicle-road collaboration, place extremely high demands on the accuracy and reliability of time synchronization. The embodiments of this application, through time synchronization and time redundancy strategies across multiple network domains, can meet the time synchronization requirements of these complex scenarios, providing strong support for the development of intelligent transportation systems.

[0094] In some embodiments of the present application, the exchange of time messages between the time synchronization device and the master clock using a time redundancy strategy based on the time synchronization connection between the time synchronization device and the master clock, the network domain corresponding to the time synchronization device, and the data timing requirements of the intelligent transportation system includes: determining the time synchronization accuracy corresponding to the current business scenario based on the data timing requirements of the intelligent transportation system; determining the frame replication interval and redundancy coefficient in the time redundancy strategy according to the time synchronization accuracy corresponding to the current business scenario, the redundancy coefficient being used to determine the number of frame replications; in the TSN network domain of the master clock, replicating the time critical message to be sent by the master clock to the time synchronization device based on the frame replication interval and the redundancy coefficient to obtain a replica frame of time critical information, the time critical message being one of a synchronization message and a delay request message; transmitting the replica frame of the time critical information to the time synchronization device through the cellular network domain; and performing redundancy processing on the received replica frame of the time critical information in the TSN network domain of the time synchronization device.

[0095] Vehicle-road collaboration integrates heterogeneous data, including vehicles, road infrastructure, traffic participants (pedestrians, non-motorized vehicles), environmental information, and cloud services. The vehicle-road collaboration system achieves safer, more efficient, and more intelligent transportation and urban management through real-time monitoring, analysis, prediction, and scheduling of this massive amount of data. Data fusion analysis integrates, correlates, and analyzes data from different sensors, systems, and entities (vehicles, roads, and people) to gain global situational awareness, deep insights, and precise decision-making that cannot be achieved with a single data source.

[0096] Data timing is the cornerstone and prerequisite for effective data fusion and analysis. Without accurate timestamps, data fusion becomes extremely difficult and can even produce misleading results. Specific pain points include data misalignment, distorted situational awareness, difficulty in event tracing, and inefficient data management. Data timing is the process of assigning specific time identifiers to vehicle-road collaborative data. By adding timestamps to data, the time points of data generation, processing, or transmission can be clearly identified, providing important time dimension information for data management, analysis, and application.

[0097] Based on this, the data timing requirements (timestamp granularity) of typical intelligent transportation systems are listed in Table 1 below.

[0098] Table 1

[0099] grade Timestamp granularity Typical scenarios S1 1s Event logging and traffic light control S2 100ms Lane change warning and forward collision warning S3 10ms Pre-collision perception warning and high-precision collaborative perception S4 1ms Frequency hopping and scheduling during communication sleep phase S5 100us Analysis of channel activity between concurrent transmissions

[0100] Network time synchronization ensures that all nodes in an intelligent transportation system (ITS) share a unified reference clock time across the network, which is crucial for various collaborative and automated applications. Therefore, the time synchronization requirements in ITS include not only synchronization accuracy but also performance, compatibility, and feasibility.

[0101] Compared to many other industrial networks, ITS components are characterized by their high dynamism and mobility. In an ITS, the relative speed between two nodes can reach over 200 km / h. Consequently, high-speed moving nodes only remain within the transmission range of other nodes for a few seconds, making synchronization accuracy even more critical. Existing research on ITS application scenarios typically analyzes end-to-end latency. This embodiment of the present application classifies the time synchronization accuracy of intelligent transportation systems based on latency and the data timing requirements of the applications shown in Table 2 above.

[0102] First, it should be made clear that to distinguish delays of several hundred milliseconds, the time synchronization accuracy must reach 100 milliseconds or higher. Therefore, based on the requirements of the terminal application, the embodiment of the present application divides the time synchronization accuracy of ITS applications into five levels: E1 to E5. As shown in Table 2 below, the time synchronization requirements and categories in typical intelligent transportation system use cases are listed, and their meanings are as follows:

[0103] E1: Time synchronization accuracy is 100 milliseconds to 1 second. Typical applications include event logging and traffic light control.

[0104] Level E2: Time synchronization accuracy is 10 milliseconds to 100 milliseconds. Typical applications include lane change warning and forward collision warning.

[0105] Level E3: Time synchronization accuracy is 1 millisecond to 10 milliseconds. Typical applications include pre-collision perception warning and high-precision collaborative perception.

[0106] E4: Time synchronization accuracy is 100 microseconds to 1 millisecond. Typical applications include frequency hopping and scheduling during communication sleep. E5: Time synchronization accuracy is 100 microseconds or higher. It is typically used for analyzing channel activity between concurrent transmissions.

[0107] Table 2

[0108] grade Time synchronization accuracy Typical applications and scenarios E1 100ms–1s Event logging and traffic light control E2 10ms–100ms Lane change warning and forward collision warning E3 1ms–10ms Pre-collision perception warning and high-precision collaborative perception E4 100us–1ms Frequency hopping and scheduling during communication sleep phase E5 <100us Analysis of channel activity between concurrent transmissions

[0109] Based on Tables 1 and 2 above, you can determine the time synchronization accuracy requirements for the current business application scenario. For example, if it is a traffic light control scenario, the time synchronization accuracy requirement is 100ms–1s. If it is a lane change warning scenario, the time synchronization accuracy requirement is 10ms–100ms.

[0110] In the TSN network domain of the master clock, a frame replication interval and redundancy factor must first be set. This interval determines the frequency with which time-critical messages (such as synchronization messages and delay request messages) are replicated, while the redundancy factor determines the number of times a frame is replicated. The setting of the frame replication interval and redundancy factor requires comprehensive consideration of factors such as time synchronization accuracy requirements, network bandwidth, and device processing capabilities to ensure that they meet time synchronization accuracy requirements without placing an excessive burden on the network. Therefore, after determining the time synchronization accuracy requirements for the actual application scenario based on Tables 1 and 2 above, the parameters of the time redundancy strategy, such as the interval and number of frame replications, can be set in combination with factors such as time synchronization accuracy requirements and network bandwidth.

[0111] Time-critical messages to be sent to time synchronization devices are replicated based on the frame replication interval and redundancy factor. These time-critical messages, including synchronization messages (used to synchronize clock times) and delay request messages (used to measure network latency), are key data for ensuring time synchronization accuracy. The replication process is completed within the TSN network domain of the master clock, generating replicated frames of the time-critical information. Each replicated frame contains all the information from the original time-critical message, ensuring that even if some frames are lost during transmission, the original data can be restored through other replicated frames.

[0112] After the replica frame is generated, it is transmitted to the time synchronization device via the cellular network domain, which provides wide-area coverage and stable communication connections, ensuring that the replica frame can be reliably transmitted to the target device.

[0113] After receiving the duplicate frames of time-critical information from the cellular network domain, the time synchronization device performs redundant processing within its own TSN network domain. Based on the results of the redundant processing, the time synchronization device can calculate a more accurate time offset and make corresponding clock adjustments.

[0114] Through frame duplication and redundant transmission, time synchronization devices can receive sufficient time-critical information even when the network is unstable or there is interference, thereby improving the reliability of time synchronization. The redundant processing mechanism can identify and correct errors during the transmission process, ensuring that the accuracy of time synchronization is not affected by network problems.

[0115] The frame replication interval and redundancy factor settings enable more reliable transmission of time-critical messages, thereby reducing time synchronization delays and jitter. By receiving and processing duplicate frames, time synchronization devices can calculate more accurate time offsets, improving time synchronization accuracy.

[0116] The embodiments of this application are applicable to complex network environments, including mixed use of TSN network domains and cellular network domains. By replicating and transmitting time-critical information between different network domains, reliable time synchronization can be achieved under various network conditions. This is of great significance for application scenarios such as intelligent transportation systems that require high-precision time synchronization.

[0117] In some embodiments of the present application, the redundant processing of the received duplicate frames of time-critical information in the TSN network domain of the time synchronization device includes: retaining the duplicate frame of the time-critical information received first in the TSN network domain of the time synchronization device, and discarding all other duplicate frames of time-critical information.

[0118] The time synchronization device receives duplicate frames of time-critical information from the cellular network domain or other network domains in its TSN network domain. These duplicate frames are copied and transmitted based on the frame replication interval and redundancy coefficient.

[0119] After receiving multiple duplicate frames, the time synchronization device records the reception time of each duplicate frame. Based on the reception time, the time synchronization device retains the first received duplicate frame containing time-critical information and discards all other duplicate frames containing time-critical information. This is because the first received frame may have experienced less delay and jitter during network transmission and is therefore closer to the original transmission time. By using the first received duplicate frame, the time synchronization device can more accurately estimate the time difference with the master clock and make appropriate adjustments.

[0120] By retaining the first received duplicate frame, the time synchronization device can avoid using duplicate frames that have experienced large delays or jitter during network transmission, thereby improving the accuracy of time synchronization and enhancing the system's robustness to network changes, enabling the intelligent transportation system to operate stably in various network environments.

[0121] In some embodiments of the present application, the calculation of the time offset between the time synchronization device and the master clock based on the exchanged time messages includes: determining the reception timestamp and the corresponding transmission timestamp of the synchronization message first received by the time synchronization device, and the reception timestamp and the corresponding transmission timestamp of the delay request message first received by the master clock based on the redundant processing results of the exchanged time messages; calculating the time offset between the time synchronization device and the master clock through the time synchronization device based on the reception timestamp and the corresponding transmission timestamp of the synchronization message first received by the time synchronization device, and the reception timestamp and the corresponding transmission timestamp of the delay request message first received by the master clock.

[0122] In order to facilitate the understanding of the above embodiments, Figure 4 As shown, a process diagram of a delay measurement mechanism based on the time redundancy principle in the TSN network in an embodiment of the present application is provided. Synchronization and delay request messages are defined as time-critical messages. When these messages need to be forwarded, the TSN Bridge copies the key frames and continuously transmits the generated copies at the interface between the cellular domain and the TSN domain. When these copies cross the logical bridge (Logical Bridge) between the cellular domain and the TSN domain, at the interface on the other side, the TSN bridge retains the first frame that arrives and discards all subsequent copies, thereby reducing the impact of dynamic delay changes.

[0123] The fusion network can be modeled as: G = {(V, E) | V∈D};

[0124] Where V, E, and D represent the network node set, network link set, and network domain set, respectively. Based on the characteristics of the network nodes in set V, they are divided into different network domains, including wired domains and wireless domains.

[0125] The transmission time of the rth copy frame of the sender can be expressed as:

[0126]

[0127] Where t0 represents the time of the first frame transmission, Δt is the frame transmission interval, and r is the redundancy coefficient, which determines the number of times the frame is replicated.

[0128] The end-to-end delay can be expressed as:

[0129]

[0130] Among them, D n Represents the network domain, and N represents the number of end-to-end network connections.

[0131] The time it takes for the receiving end to receive a data frame is calculated as follows:

[0132]

[0133] The slave clock calculates the offset between itself and the master clock using the following formula:

[0134]

[0135] Among them, t2 is the reception timestamp of the synchronization message first received by the time synchronization device, t′1 is the sending timestamp corresponding to the synchronization message first received by the time synchronization device, t4 is the reception timestamp of the delay request message first received by the master clock, and t′3 is the sending timestamp corresponding to the delay request message first received by the master clock.

[0136] Due to the impact of wireless links on end-to-end delay, May be earlier than In a converged network, the communication link between terminals typically consists of only one path. In this case, the spatial redundancy of the communication channel supported by the TSN domain becomes ineffective. Unlike the spatial redundancy of TSN, the temporal redundancy mechanism proposed in the embodiments of the present application involves duplicating time-critical frames and transmitting them continuously, while on the other side, redundant frames are eliminated.

[0137] In some embodiments of the present application, the preset compensation control algorithm is a neural network-based PID controller, the input of the PID controller includes the redundancy coefficient in the time redundancy strategy, and the neural network-based PID controller can learn and adjust the coefficient of the PID controller online through the neural network to compensate and control the time error of the time synchronization device through the coefficient of the PID controller.

[0138] The offset calculated by formula (4) in the aforementioned embodiment cannot be used directly to modify the local time of the slave clock. Direct application may cause problems such as overshoot, oscillation, or steady-state error in the slave clock. Based on this, the present embodiment further proposes using a neural network-based PID algorithm to solve the stability control problem of time error compensation.

[0139] like Figure 5 As shown, a schematic diagram of the principle of a neural network-based PID controller in an embodiment of the present application is provided. The time error compensation control is adjusted online by the neural network to achieve dynamic performance and anti-interference performance requirements. The neural network uses gradient search technology to continuously correct the weights in the network according to the deviation e(k) between the system expected value and the actual value until the deviation e(k) reaches the minimum value. Through self-learning and weighting coefficients, the neural network adjusts the parameters of the PID controller online in real time to achieve the optimal combination of PID parameters.

[0140] The incremental PID controller can be expressed as follows:

[0141] u(k)=u(k-1)+Δu(k), (5)

[0142]

[0143] Among them, r is the redundancy coefficient in the time redundancy strategy, K p (k), K i (k), K d (k) represents the proportional, integral and differential control coefficients respectively; u(k) is the total input of the system; Δu(k) is the control increment. K is adjusted online through the neural network learning algorithm p (k), K i (k), K d (k).

[0144] The three control coefficients of the PID controller are learned online through a multilayer perceptron. For example, a three-layer neural network can be used: the input layer can contain three neurons, which are the desired time error compensation value C1(k), the actual time error output value C2(k) and the deviation value C3(k); the number of neurons in the hidden layer is 5; the number of neurons in the output layer is 3, which are the three control coefficients K of the PID controller to be learned p (k), K i (k), K d (k).

[0145] The relationship between the three neurons in the input layer of the multilayer perceptron and the expected value and actual value is:

[0146]

[0147] Among them, c in (k) represents the expected compensation value, y out (k) represents the actual compensation value. Select the appropriate initial value of the control parameter K p (0), K i (0), K d (0), and then iterate, the specific expression is as follows:

[0148]

[0149] The input layer is:

[0150]

[0151] The input and output of the hidden layer are:

[0152]

[0153] in, is the weight coefficient of the hidden layer; the superscripts (1), (2), and (3) represent the input layer, hidden layer, and output layer respectively. The activation function of the hidden layer is the hyperbolic tangent Sigmoid function:

[0154]

[0155] And because the output of the output layer is K P , K I , K D , must be a positive number, so the non-negative Sigmoid function is selected as the activation function:

[0156]

[0157] There are derivatives:

[0158] g′(x)=2g(x)[1-g(x)], (16)

[0159] The input and output of the output layer are:

[0160]

[0161] in,

[0162]

[0163] The performance index function is E(k):

[0164]

[0165] Use the gradient descent method to correct the connection weights in the direction of the negative gradient and find the global minimum inertia term, where η is the learning rate and α is the inertia coefficient:

[0166]

[0167] have:

[0168]

[0169] because Unknown, so use function instead. After simplification and approximation, the change in weights after learning the output layer can be obtained as:

[0170]

[0171] Similarly, the weights of the hidden layer after learning are:

[0172]

[0173] By continuously sampling, c in (k) and y out (k), calculate the deviation e(k) between the expected value and the actual value of the system and the input and output of each layer of the neural network, and feed the output u(k) of the PID controller back to the neural network. Through comprehensive calculation, the multi-layer perceptron of the neural network continuously learns and adjusts the coefficient K of the PID controller online. P , K I , and K D Learning stops when the performance indicator function E(k) is less than the set value or the number of sampling times reaches the set value. At this time, the output of the output layer is the optimal parameter of the PID controller. Since all slave clocks have a certain degree of punctuality, in network time synchronization, even if the time synchronization is once per second, the synchronization accuracy of the sub-microsecond level can be achieved. Considering the time complexity of the neural network calculation and the compensation control optimization effect, the update frequency of the PID controller coefficient can be set to once per time synchronization cycle or once per multiple time synchronization cycles according to the time synchronization cycle and the actual operation of the network.

[0174] After the proposed time error compensation mechanism obtains the time error introduced by the packet network, the PID controller is used to optimize the time error compensation control. The coefficients of the PID controller are updated online using a neural network-based adjustment algorithm. This can reduce the time jitter of the slave clock during the process of correcting the local clock, while improving the response speed of the compensation process and ensuring the time synchronization accuracy of the slave clock.

[0175] To verify the performance of the time synchronization solution proposed in this application, a test platform was built in a real-world environment, consisting of two TSN domains and one cellular domain. TSN Domain A and TSN Domain C each consist of two TSN switches, while the cellular domain based on the 5G version 17 release includes customer premises equipment (CPE), base stations, and a core network. The controller unit consists of several x86 servers, forming an SDN environment in which the coordination controller, synchronization controller, core network, and domain controllers operate. The master clock equipped with a rubidium oscillator is synchronized with the Global Navigation Satellite System (GNSS), and the time synchronization period is set to 1 second. Both the master and slave clocks in the test platform support hardware timestamps. The TSN switches can replicate key frames and transmit them sequentially according to the configuration settings. On the other hand, the first arriving frame is captured from each set of replicated frames.

[0176] By changing the frame interval of key frame replication (10 μs, 20 μs, 50 μs, 100 μs, 200 μs), experimental data were obtained in different frame replication scenarios under the same time dimension communication path in the context of 5GTSN fusion network.

[0177] Experimental results show that, calculated with a 50-microsecond frame interval, the round-trip time (RTT) ranges from 6 milliseconds to 180 milliseconds, with 90% of delays below 20 milliseconds. Delay variations range from a few hundred nanoseconds to 160 milliseconds, with 90% of jitter falling within 12 milliseconds. This indicates that due to delay uncertainty in the wireless channel, delay variations in wireless networks can reach as much as 160 milliseconds, severely impacting the performance of time synchronization methods based on delay measurement in wireless network environments. The probability density function (PDF) curve for delay variation shows that the most likely delay variation is 8.069 milliseconds. This suggests that directly applying the PTP protocol in cellular networks without any additional processing will result in synchronization accuracy of approximately 8 milliseconds.

[0178] To further analyze the impact of temporal redundancy on network delay measurement, key frames were replicated four times, with Δt varying from 10 μs to 200 μs. The minimum delay and its probability of occurrence were recorded. Experimental results show that when Δt is 10 μs, 20 μs, 50 μs, 100 μs, and 200 μs, the minimum delays are 6.708 ms, 6.666 ms, 6.649 ms, 6.186 ms, and 6.506 ms, respectively. To measure the repeatability of the minimum delay, the minimum delay is defined as a distance δ, and the time it takes for the recurrence to not exceed the clock oscillator drift is defined as the maximum interval delay. In this case, any delay that differs from the minimum delay by δ is considered the minimum delay. When the minimum delay is used as the valid synchronization decision criterion, the maximum interval delay represents the decision error. In these cases, the maximum interval delays are 1.124 ms, 0.719 ms, 0.339 ms, 0.845 ms, and 0.489 ms, respectively. It can be seen from the maximum interval delay that the decision error of the minimum delay is the smallest when the frame interval is 50 μs.

[0179] Furthermore, experimental results show that, under the same minimum delay decision error, the probability of minimum delay occurring is highest when the frame interval is 50 microseconds. The probability of minimum delay occurring decreases as the frame interval increases or decreases. This indicates that a 50 microsecond frame interval is optimal for the time synchronization scheme based on temporal redundancy proposed in this application.

[0180] Based on the above analysis results, the frame interval of the time redundancy algorithm was set to 50 microseconds, and the relative time errors of time synchronization methods based on time redundancy and those without time redundancy were measured. The experimental results show that, without time redundancy, the PTP protocol exhibits limited time synchronization accuracy when transmitted over a 5G TSN converged network. Specifically, the relative time error fluctuates within a range of approximately -4 milliseconds to 4 milliseconds. This performance level is a direct result of the inherent challenges posed by the convergence of TSN and 5G networks, as well as the dynamic and asymmetric delays introduced by the wireless communication channel. In this case, the measured MTIE value is approximately 8 milliseconds, indicating significant fluctuation in synchronization accuracy. These findings are consistent with the theoretical analysis presented above and further confirm the limitations of the traditional PTP protocol under such network conditions. When the time redundancy-based time synchronization method is enabled, the accuracy of the slave clocks is significantly improved. The relative time error is controlled within the range of -150 microseconds to 150 microseconds, a significant improvement compared to the traditional method. Furthermore, the maximum time error (MTIE) is reduced to approximately 300 microseconds, demonstrating the stability and reliability of the synchronization process in a 5G TSN converged network environment. This level of accuracy meets the stringent requirements of Intelligent Transportation System (ITS) applications, providing robust performance for scenarios requiring precise timing. This accuracy is particularly important for cooperative vehicle systems, real-time traffic management, and autonomous driving tasks. In addition, this approach is also well suited for mobile devices such as on-board units (OBUs), which operate in dynamic and heterogeneous network environments. By addressing the inherent time synchronization challenges of these systems, the time redundancy-based approach ensures reliable synchronization, providing a foundation for improvements in security, efficiency, and scalability in ITS deployments.

[0181] The embodiment of the present application also provides a time synchronization system 600, such as Figure 6 As shown, a schematic diagram of the structure of a time synchronization system in an embodiment of the present application is provided, wherein the time synchronization system 600 includes: a synchronization controller 610, a coordination controller 620, a domain controller 630, a time synchronization device 640, and a network domain 650 corresponding to the time synchronization device;

[0182] The synchronization controller 610 is used to receive a time synchronization request from a time synchronization device in an intelligent transportation system;

[0183] The coordination controller 620 and the domain controller 630 are configured to establish a time synchronization connection between the time synchronization device and the master clock according to the time synchronization request;

[0184] The network domain 650 corresponding to the time synchronization device is used to exchange time messages between the time synchronization device and the master clock using a time redundancy strategy based on the time synchronization connection between the time synchronization device and the master clock, the network domain corresponding to the time synchronization device, and the data timing requirements of the intelligent transportation system;

[0185] The time synchronization device 640 is used to send the time synchronization request to the synchronization controller, and calculate the time offset between the time synchronization device and the master clock based on the exchanged time message, and based on the time offset between the time synchronization device and the master clock, use a preset compensation control algorithm to compensate and control the time error of the time synchronization device.

[0186] In some embodiments of the present application, the synchronization controller 610 is used to receive a time synchronization request from a time synchronization device in an intelligent transportation system, and generate a time synchronization task based on the time synchronization request and send it to the coordination controller; the coordination controller 620 is used to calculate the optimal time synchronization path between the time synchronization device and the master clock based on the time synchronization task; the domain controller 630 is used to establish a time synchronization connection between the time synchronization device and the master clock through a precise time synchronization protocol based on the optimal time synchronization path between the time synchronization device and the master clock.

[0187] In some embodiments of the present application, the time synchronization device 640 includes a roadside unit, and the network domain 650 corresponding to the time synchronization device is also used to: based on the time synchronization connection between the roadside unit and the master clock and the TSN network domain corresponding to the roadside unit and the data timing requirements of the roadside unit, use the time redundancy strategy to exchange time messages between the roadside unit and the master clock.

[0188] In some embodiments of the present application, the time synchronization device includes an on-board unit, and the network domain 650 corresponding to the time synchronization device is also used to: based on the time synchronization connection between the on-board unit and the master clock and the TSN network domain and cellular network domain corresponding to the on-board unit and the data timing requirements of the on-board unit, use the time redundancy strategy to exchange time messages between the on-board unit and the master clock.

[0189] In some embodiments of the present application, the network domain 650 corresponding to the time synchronization device is also used to: determine the time synchronization accuracy corresponding to the current business scenario based on the data timing requirements of the intelligent transportation system; determine the frame replication interval and redundancy coefficient in the time redundancy strategy according to the time synchronization accuracy corresponding to the current business scenario, and the redundancy coefficient is used to determine the number of frame replications; in the TSN network domain of the master clock, based on the frame replication interval and the redundancy coefficient, replicate the time critical message to be sent by the master clock to the time synchronization device to obtain a replicated frame of time critical information, and the time critical message is one of a synchronization message and a delay request message; transmit the replicated frame of the time critical information to the time synchronization device through the cellular network domain; in the TSN network domain of the time synchronization device, perform redundant processing on the received replicated frame of the time critical information.

[0190] In some embodiments of the present application, the network domain 650 corresponding to the time synchronization device is further used to: retain the first received copy frame of time-critical information in the TSN network domain of the time synchronization device, and discard all other copy frames of time-critical information.

[0191] In some embodiments of the present application, the time synchronization device 640 is also used to: determine the reception timestamp and corresponding sending timestamp of the synchronization message first received by the time synchronization device, and the reception timestamp and corresponding sending timestamp of the delay request message first received by the master clock based on the redundant processing results of the exchanged time messages; calculate the time offset between the time synchronization device and the master clock through the time synchronization device based on the reception timestamp and corresponding sending timestamp of the synchronization message first received by the time synchronization device, and the reception timestamp and corresponding sending timestamp of the delay request message first received by the master clock.

[0192] In some embodiments of the present application, the preset compensation control algorithm is a neural network-based PID controller, the input of the PID controller includes the redundancy coefficient in the time redundancy strategy, and the neural network-based PID controller can learn and adjust the coefficient of the PID controller online through the neural network to compensate and control the time error of the time synchronization device through the coefficient of the PID controller.

[0193] It can be understood that the above-mentioned time synchronization system can implement each step of the time synchronization method of the intelligent transportation system provided in the above-mentioned embodiment. The relevant explanations on the time synchronization method of the intelligent transportation system are applicable to the time synchronization system and will not be repeated here.

[0194] Figure 7 This is a schematic diagram of the structure of a device in the embodiment of the present application. Figure 7As shown, the device includes one or more processors (or processing units), may further include one or more memories coupled to the processors, and may further include a communication module coupled to the processors.

[0195] The communication module can be used to communicate with other devices or apparatuses, such as sending or receiving data and / or signals. The communication module can include at least one communication module for communication. The communication module can include any interface necessary for communicating with other devices. Exemplarily, the communication module can be a transceiver, circuit, bus, module, or other type of communication module.

[0196] The processor may include, but is not limited to, at least one of the following: a general-purpose computer, a special-purpose computer, a microcontroller, a digital signal processor (DSP), or one or more of a controller-based multi-core controller architecture. A device may have multiple processors, such as application-specific integrated circuit chips, which are time-slave to a clock synchronized with a main processor.

[0197] The memory may include one or more non-volatile memories and one or more volatile memories. Examples of non-volatile memories include, but are not limited to, at least one of the following: read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, hard disk, compact disc (CD), digital video disc (DVD), or other magnetic storage and / or optical storage. Examples of volatile memories include, but are not limited to, at least one of the following: random access memory (RAM), or other volatile memories that do not persist during a power outage.

[0198] A computer program includes computer-executable instructions that are executed by an associated processor. The program may be stored in ROM. The processor may perform any suitable actions and processes by loading the program into RAM.

[0199] The possible implementation of the present application can be realized by means of a program, so that the communication device can perform any process discussed in the above embodiments. The possible implementation of the present application can also be realized by hardware or by a combination of software and hardware.

[0200] In some embodiments, the program may be tangibly contained in a computer-readable storage medium that may be included in the device (such as in a memory) or other storage device accessible by the device. The program may be loaded from the computer-readable storage medium into RAM for execution. The computer-readable storage medium may include any type of tangible non-volatile memory, such as ROM, EPROM, flash memory, hard disk, CD, DVD, etc.

[0201] The present application also provides a computer-readable storage medium having computer instructions or program codes stored thereon, which, when executed by a processor, causes the processor to perform the methods and functions described in any of the above embodiments. A computer-readable medium may be any tangible medium containing or storing a program for or related to an instruction execution system, apparatus, or device. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. Computer-readable media may include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any suitable combination thereof. The computer-readable storage medium may be any available medium that a computer can access, or a data storage device such as a server or data center that includes one or more available media integrated therein. More detailed examples of computer-readable storage media include electrical connections with one or more wires, magnetic media (e.g., magnetic disks, floppy disks, hard disks, tapes, magnetic storage devices), optical media (e.g., optical storage devices, DVDs), semiconductor media (e.g., solid-state drives), random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), or any suitable combination thereof.

[0202] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The embodiments of the present application also provide at least one computer program product tangibly stored on a non-transitory computer-readable storage medium. The computer program product includes one or more computer-executable instructions, such as instructions included in a program module, which are executed in a device on a real or virtual processor of the target to perform the processes, methods and functions involved in any of the above embodiments. When the computer program instructions are loaded and executed on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) method.

[0203] In general, various embodiments of the present application can be implemented in hardware or dedicated circuits, software, logic, or any combination thereof. Some aspects can be implemented in hardware, while other aspects can be implemented in firmware or software, which can be executed by a controller, microprocessor, or other computing device. Although various aspects of the embodiments of the present disclosure are shown and described as block diagrams, flow charts, or using some other graphical representation, it should be understood that the blocks, devices, systems, techniques, or methods described herein can be implemented as, by way of non-limiting example, hardware, software, firmware, dedicated circuits or logic, general-purpose hardware or a controller or other computing device, or some combination thereof.

[0204] It should be noted that although the embodiments of the present application are described above in conjunction with the accompanying drawings, the above embodiments are not independent of each other, and they can also be combined to obtain other embodiments. The methods, situations, categories, and divisions of the embodiments in the embodiments of the present application are only for the convenience of description and should not constitute special limitations. The features of the various methods, categories, situations, and embodiments can be combined with each other when they are logical. The various embodiments of the present application can be combined arbitrarily to achieve different technical effects. The embodiments of the present application no longer list various combinations.

[0205] In addition, although the operations of the method of the present disclosure are described in a particular order in the accompanying drawings, this does not require or imply that these operations must be performed in this particular order, or that all the operations shown must be performed to achieve the desired result. On the contrary, the steps depicted in the flowchart can change the order of execution. Additionally or alternatively, certain steps can be omitted, multiple steps can be combined into one step, and / or one step can be decomposed into multiple steps. It should also be noted that the features and functions of two or more devices according to the present disclosure can be embodied in one device. Conversely, the features and functions of a device described above can be further divided into being embodied by multiple devices.

[0206] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0207] The foregoing is merely an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application should be included within the scope of the claims of the present application.

Claims

1. A time synchronization method for an intelligent transportation system, characterized in that: The time synchronization method of the intelligent transportation system is executed by a time synchronization system, and the time synchronization method of the intelligent transportation system includes: Receiving a time synchronization request from a time synchronization device in an intelligent transportation system; establishing a time synchronization connection between the time synchronization device and a master clock according to the time synchronization request; Based on the time synchronization connection between the time synchronization device and the master clock, the network domain corresponding to the time synchronization device, and the data timing requirements of the intelligent transportation system, the time redundancy strategy is used to exchange time messages between the time synchronization device and the master clock; Calculating the time offset between the time synchronization device and the master clock based on the exchanged time messages; Based on the time offset between the time synchronization device and the master clock, a preset compensation control algorithm is used to compensate and control the time error of the time synchronization device.

2. The time synchronization method of the intelligent transportation system according to claim 1, characterized in that: The time synchronization system includes a synchronization controller, a coordination controller, and a domain controller, and receiving a time synchronization request from a time synchronization device in the intelligent transportation system includes: receiving, by the synchronization controller, a time synchronization request from a time synchronization device in an intelligent transportation system; The establishing of a time synchronization connection between the time synchronization device and the master clock according to the time synchronization request comprises: According to the time synchronization request, the synchronization controller generates a time synchronization task and sends it to the coordination controller, and receives an optimal time synchronization path between the time synchronization device and the master clock returned by the coordination controller; According to the optimal time synchronization path between the time synchronization device and the master clock, a time synchronization connection between the time synchronization device and the master clock is established through the domain controller using a precise time synchronization protocol.

3. The time synchronization method of the intelligent transportation system according to claim 1, characterized in that: The time synchronization device includes a roadside unit, and the exchanging of time messages between the time synchronization device and the master clock using a time redundancy strategy based on a time synchronization connection between the time synchronization device and the master clock, a network domain corresponding to the time synchronization device, and data timing requirements of the intelligent transportation system includes: Based on the time synchronization connection between the roadside unit and the master clock, the TSN network domain corresponding to the roadside unit, and the data timing requirements of the roadside unit, a time redundancy strategy is used to exchange time messages between the roadside unit and the master clock.

4. The time synchronization method of the intelligent transportation system according to claim 1, characterized in that: The time synchronization device includes an on-board unit, and the exchanging of time messages between the time synchronization device and the master clock using a time redundancy strategy based on a time synchronization connection between the time synchronization device and the master clock, a network domain corresponding to the time synchronization device, and data timing requirements of the intelligent transportation system includes: Based on the time synchronization connection between the on-board unit and the master clock, the TSN network domain and cellular network domain corresponding to the on-board unit, and the data timing requirements of the on-board unit, a time redundancy strategy is used to exchange time messages between the on-board unit and the master clock.

5. The time synchronization method of the intelligent transportation system according to claim 4, characterized in that: The exchanging of time messages between the time synchronization device and the master clock by using a time redundancy strategy based on the time synchronization connection between the time synchronization device and the master clock, the network domain corresponding to the time synchronization device, and the data timing requirement of the intelligent transportation system includes: Determine the time synchronization accuracy corresponding to the current business scenario based on the data timing requirements of the intelligent transportation system; Determining a frame replication interval and a redundancy coefficient in the time redundancy strategy according to the time synchronization accuracy corresponding to the current service scenario, wherein the redundancy coefficient is used to determine the number of frame replications; In a TSN network domain of the master clock, based on the frame replication interval and the redundancy coefficient, a time critical message to be sent by the master clock to the time synchronization device is replicated to obtain a replicated frame of the time critical information, where the time critical message is one of a synchronization message and a delay request message; transmitting the copy frame of the time-critical information to the time synchronization device via the cellular network domain; In the TSN network domain of the time synchronization device, redundant processing is performed on the received duplicate frames of the time-critical information.

6. The time synchronization method of the intelligent transportation system according to claim 5, characterized in that: The performing redundancy processing on the received duplicate frames of the time-critical information in the TSN network domain of the time synchronization device includes: In the TSN network domain of the time synchronization device, the first received copy frame of the time critical information is retained, and all other copy frames of the time critical information are discarded.

7. The time synchronization method of the intelligent transportation system according to claim 6, characterized in that: Calculating the time offset between the time synchronization device and the master clock according to the exchanged time messages includes: Determine, based on the redundant processing result of the exchanged time messages, a reception timestamp and a corresponding transmission timestamp of the synchronization message first received by the time synchronization device, and a reception timestamp and a corresponding transmission timestamp of the delay request message first received by the master clock; The time synchronization device calculates the time offset between the time synchronization device and the master clock based on the reception timestamp and the corresponding sending timestamp of the synchronization message first received by the time synchronization device, and the reception timestamp and the corresponding sending timestamp of the delay request message first received by the master clock.

8. The time synchronization method of an intelligent transportation system according to any one of claims 1 to 7, characterized in that: The preset compensation control algorithm is a neural network-based PID controller, the input of the PID controller includes the redundancy coefficient in the time redundancy strategy, and the neural network-based PID controller can learn and adjust the coefficient of the PID controller online through the neural network to compensate and control the time error of the time synchronization device through the coefficient of the PID controller.

9. A time synchronization system, characterized in that: The time synchronization system includes: a synchronization controller, a coordination controller, a domain controller, a time synchronization device, and a network domain corresponding to the time synchronization device; The synchronization controller is used to receive a time synchronization request from a time synchronization device in an intelligent transportation system; The coordination controller and the domain controller are configured to establish a time synchronization connection between the time synchronization device and the master clock according to the time synchronization request; The network domain corresponding to the time synchronization device is used to exchange time messages between the time synchronization device and the master clock using a time redundancy strategy based on the time synchronization connection between the time synchronization device and the master clock, the network domain corresponding to the time synchronization device, and the data timing requirements of the intelligent transportation system; The time synchronization device is used to send the time synchronization request to the synchronization controller, and calculate the time offset between the time synchronization device and the master clock based on the exchanged time message, and based on the time offset between the time synchronization device and the master clock, use a preset compensation control algorithm to compensate and control the time error of the time synchronization device.

10. A device comprising: processor; and a memory arranged to store computer-executable instructions, wherein when the instructions are executed, the processor executes the time synchronization method for the intelligent transportation system according to any one of claims 1 to 8.

Images