End-to-end network bridge equipment supporting aviation non-compressed video network
By designing a bridge device, the latency and jitter problems caused by transmission contention in airborne communication networks were solved, achieving deterministic transmission and flexible architecture, suitable for differentiated business scenarios of avionics systems, and providing dynamic upgrade capabilities.
Patent Information
- Application Number
- CN202511830644.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-06
- Publication Date
- 2026-03-20
AI Technical Summary
In existing airborne communication networks, traditional communication mechanisms lead to uncontrollable delays and jitter due to data transmission competition, which cannot meet the safety-critical requirements at different times. At the same time, the TTE communication mode imposes strong constraints on application service integration, resulting in an overly closed system that lacks flexibility and dynamic upgrade capabilities.
Design a bridge device comprising a global configuration loading module, a communication configuration register module, a frame receiving port, a frame filtering management module, a traffic monitoring module, a route query module, a frame buffer module, a switching matrix management module, a priority reset module, a traffic queuing metering module, a timer module based on a global time base, a gated scheduling list storage module, and a multi-service scheduler to achieve deterministic transmission based on time window checksum and forwarding.
It enables secure and deterministic data flow transmission within a dynamic and flexible network architecture, applicable to different safety-critical and distributed cross-network communications in avionics systems, and provides flexible architectural capacity and dynamic upgrade and iteration capabilities.
Smart Images
Figure CN121711206A_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of airborne bus communication technology in avionics systems, and specifically relates to a bridge device that supports end-to-end uncompressed video network in aviation. Background Technology
[0002] With the rapid development of sensor technology in the avionics field, the types and numbers of sensors integrated into airborne aircraft systems are increasing. The different transmission requirements of system users for data from different sensors necessitate avionics communications capable of distributed communication with varying safety and real-time demands. Traditional airborne communication networks such as fiber optic Ethernet, AFDX, and FC employ event-triggered communication mechanisms. Due to their random access transmission methods, transmission contention inevitably leads to uncontrollable latency and jitter, failing to meet the needs of applications with varying time-critical safety requirements. Time-triggered communication mechanisms based on clock synchronization offer an opportunity to improve the determinism and real-time performance of airborne buses. Switched time-triggered networks, belonging to the time-triggered architecture of airborne buses, establish a global synchronization clock for the network through a distributed time synchronization algorithm. Based on this global synchronization clock, TDMA is used to allocate communication bandwidth, enabling flow management of data frames based on globally clock-allocated receive time slots and time-triggered forwarding scheduling based on transmit time slots. The time slots allocated by TDMA are bound to data frames according to the communication flow ID, ensuring contention-free time-triggered communication and meeting the integration needs of application tasks with different time-critical levels.
[0003] Time-triggered network communication employs a time-triggered communication mechanism, enabling data transmission and reception to be completed within a specified time sequence, exhibiting high determinism and reliability. The time-triggered architecture is compatible with both event-triggered and time-triggered guidance methods. Time-triggered communication resolves message sharing conflicts on the link, and message transmission is strictly deterministic. Current mainstream time-triggered switching networks (TTEs) for aerospace applications, with their message-level time-triggered scheduling and allocation constraints, are too closed off for carrying business communication in the diverse airborne environments with varying operating modes, hindering system integration and iterative maintenance. Summary of the Invention
[0004] Purpose of the invention: To provide a design method for a bridge device for deterministic transmission communication in differentiated business scenarios, which solves the problem that the existing communication mechanism, which uses random access transmission, causes uncontrollable delays and jitter in the transmission of data at the forwarding port and output port, thus failing to meet the security-critical requirements at different times. At the same time, it avoids the strong constraints of TTE communication mode on application service integration, which makes the system too closed. Thus, it provides a certain degree of flexibility and dynamic upgrade and iteration capabilities, provides deterministic communication services for airborne mission communication service integration, and provides a more flexible architecture carrying capacity. Technical solution: A bridge device supporting end-to-end aviation uncompressed video network, the bridge device comprising: a global configuration loading module, n communication configuration register modules, n frame receiving ports, n frame input memories, n frame filtering management modules, n traffic monitoring modules, a global route query module, a global route storage module, a global frame buffer module, a global switching matrix management module, n priority reset modules, n traffic queuing metering modules, n timer modules based on global time base, n gated scheduling list storage modules, n gated list scheduling modules, n output port memories, and a multi-service scheduler for each output port based on multi-service time-aware TAS, flow-controlled CBS, and interstitial BE services.
[0005] Furthermore, the global configuration loading module obtains the system's local bridge configuration information file, and the methods of obtaining this information include: Method 1: Input from any receiving port of the bridge device; Method 2: Design a controller for the bridge device, and write the configuration information file into the controller; Method 3: A soft core is created on the core chip inside the bridge device to obtain the configuration information file and write it to the global configuration loading module; The global configuration loading module parses and reassembles the configuration information file content and stores it in each communication configuration register module for communication retrieval.
[0006] Furthermore, after the bridge device powers on and loads the configuration information file, it connects to the network system to obtain system synchronization information, maintains a global synchronization timer, and outputs the timer pulse to the timer module based on the global time base of each output port to realize periodic timing based on the scheduling cycle size configured by the system.
[0007] Furthermore, each frame receiving port acquires data frames and enters the frame input memory of each receiving port according to a first-in-first-out mechanism. The frame filtering management module of each port performs a check on the integrity of the corresponding link layer protocol for the input frame. The frames that do not meet the integrity check criteria are discarded, and the number of discarded data is accumulated into the error category counter in the communication information database of the bridge device according to the corresponding filtering category.
[0008] Furthermore, the traffic police module identifies the frame type of the input frame data; If the frame is identified as a TAS / BE category frame, it will be allowed to pass directly. The frame is identified as a Credit Management (CBS) type frame. The input traffic of this frame is controlled according to the algorithm model composed of the upper and lower limits of credit capacity, the credit increment slope and the consumption rate planned by the system, thereby controlling the input rate and capacity of CBS traffic.
[0009] Furthermore, the scheduler for time-aware TAS, flow-controlled CBS, and BE services based on multiple services is in the form of queues, with a maximum of 8 queues, corresponding to the 8 service priority levels of the system. Each forwarding queue is used to store forwarding frame information for the corresponding service priority. First, determine if the number of scheduling queues to be configured exceeds 8. If it exceeds 8, record this as a configuration input anomaly in the bridge's status log and arrange them according to the maximum capacity of 8 scheduling queues. If it is 8 or less, design according to the configuration information. Identify the storage depth and service type of each queue according to the configuration requirements. The depth depends on the cumulative forwarding data capacity of the corresponding queue in a period. The storage service type identification is as follows: for TAS services, each queue corresponds to a unique type of service; for CBS and BE services, each queue performs mixed storage of different levels and types of services.
[0010] Furthermore, by querying the global routing query module within the bridge, the information used for routing query in the data frame is extracted and input into the global routing storage module to query the forwarding path information of the data frame. Based on the queried routing forwarding path information, the frame input memory and output port memory are connected through the global switching matrix management module to realize the dequeueing of data frame information to the corresponding output port memory. The data frame content corresponding to the data frame information that is validly entered into the output port is read from the frame input memory of each receiving port in a time-division round-robin manner and written to the global frame buffer module. The bridge device identifies that the current data frame requires redundant transmission, and acts as the redundancy initiation point. It will copy the corresponding number of frame copies according to the number of redundant paths configured in the data frame and distribute them to the output port memory of the corresponding redundant path.
[0011] Furthermore, the data frames entering the output port memory are processed according to the system configuration, and priority reset processing is selected for the data frames. The priority and VID parameters in the data frames are extracted, and the priority is reset through the priority mapping table in the priority reset module of each port, thus completing the mapping of the data frames to the corresponding scheduling queues.
[0012] Furthermore, the data frames that enter the corresponding scheduling queue buffer of the output port will be periodically scheduled and output strictly according to the synchronous timing of this port; Based on the configuration file information, the gating schedule lists of each output port are extracted and stored in the gating schedule list storage module. The elements are stored sequentially according to the system-defined list element order, along with the scheduling queue information mapped to each gating element and the corresponding time slot size. Each output port will drive the elements in the gating schedule list storage module based on its own synchronization timing, switching execution according to the order of storage. Before the output port's synchronization timing cycle begins, the first element in the storage module is indexed and retrieved. Data transmission of the corresponding scheduling queue is scheduled within the time slot specified by the element. Before the current time slot ends, the next element in the storage module is indexed and retrieved, and the above processing is performed. The execution time of the last element in the storage module depends on the remaining time of the entire scheduling cycle, not the element's own time slice size. When the entire scheduling cycle timing is complete, the element's scheduling execution is finished, and the first element in the storage module is indexed and retrieved.
[0013] Furthermore, when the scheduling cycle timer completes the timing of the previous gated list element and switches to scheduling the current element, the corresponding scheduling output is performed according to the scheduling queue pointed to by the current element: 1) When the current scheduling queue is of type TAS, the gating of the current unique scheduling queue is opened, and the data frames of the scheduling queue are sent back to back in the order of enqueueing; input to the gating list scheduling module, and implement periodic gating list scheduling based on the status control of the timing point within the period; 2) When the current scheduling queue is a flow control type CBS or a gap-filling type BE service, CBS service is scheduled first. According to the current credit margin control and priority scheduling combination, the corresponding data frame is scheduled for transmission. This includes enabling the frame information output of the scheduling queue, sending the data frame content to the bridge's global frame buffer according to the information index to the physical link, and completing the reclamation of the frame buffer space of the global frame buffer module.
[0014] Beneficial effects: Compared with existing technologies, this invention designs a bridge device for deterministic transmission communication for differentiated business scenarios. It realizes the integrated transmission of three services, TAS, AVB and BE, based on the static or dynamic planning mode of the system. It ensures the improved security and deterministic transmission capability of ordinary Ethernet data streams in a relatively dynamic and flexible access network architecture. It is well-suited for distributed cross-network communication applications with different safety criticalities and safety-related aspects in avionics systems.
[0015] This invention proposes a design method for deterministic transmission communication bridge devices for differentiated business scenarios. As one of the core technologies of airborne mission system networks, it effectively promotes the development of time-triggered networks by providing a general design implementation based on time window verification and time window forwarding. This provides better protection for network transmission security and determinism of data services, and greatly enriches the methods for network selection in applications with high security requirements such as airborne mission systems, high-speed rail control systems, and industrial field control. At the same time, the application of this invention is independent of hardware platforms, has a wide range of applications, and has significant market prospects and economic benefits.
[0016] It is understood that those skilled in the art can make equivalent substitutions or modifications to the technical solution and inventive concept of the present invention, and all such substitutions or modifications should fall within the protection scope of the appended claims. Attached Figure Description
[0017] Figure 1 This is a schematic diagram of a bridge device that supports end-to-end uncompressed video networking in aviation. Detailed Implementation
[0018] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.
[0019] In this application, the terms "upper," "lower," "left," "right," "front," "rear," "top," "bottom," "inner," "outer," "middle," "vertical," "horizontal," "lateral," and "longitudinal" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. These terms are primarily for the purpose of better describing this application and its embodiments, and are not intended to limit the indicated device, element, or component to having a specific orientation, or to be constructed and operated in a specific orientation.
[0020] Furthermore, the terms "installation," "setup," "equipped with," "connection," "linking," and "socketing" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral structure; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium, or an internal connection between two devices, components, or parts. Those skilled in the art can understand the specific meaning of these terms in this application based on the specific circumstances.
[0021] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.
[0022] A bridge device for deterministic transmission communication for differentiated service scenarios includes a global configuration loading module, n communication configuration register modules, n frame receiving ports, n frame input memories, n frame filtering management modules (category, frame integrity), n traffic monitoring modules, a global route query module, a global route storage module, a global frame buffer module, a global switching matrix management module, n priority reset modules, n traffic queuing metering modules, n timer modules based on global time base, n gated scheduling list storage modules, n gated list scheduling modules, n output port memories, and schedulers for each output port based on multi-service time-aware TAS, flow-controlled CBS, and interstitial transmission BE services.
[0023] The global configuration loading module obtains the configuration information file of the bridge in the system through the following channels and methods: 1. Communication input from any port of the bridge device; 2. The controller of the management plane designed for the bridge device writes the configuration file; 3. A soft core is opened on the core chip inside the bridge device to obtain the information file and write it to the global configuration loading module. This module completes the parsing and reorganization of the configuration information file content and stores it in the communication configuration register of each port for communication query.
[0024] Each frame receiving port collects data frames and enters the frame input memory of each receiving port according to the first-in-first-out mechanism. The frame filtering management module of each port performs a corresponding link layer protocol integrity check on the input frame, such as VLAN category, frame length, and frame protocol type. Data that does not meet the integrity check criteria is discarded, and the number of discarded data is accumulated into the error category counter in the communication information database of the bridge device according to the corresponding category.
[0025] Each receiving port's traffic police module identifies Credit Management (CBS) type frames. It then uses an algorithm model comprised of the system-planned upper and lower limits of credit capacity, the credit increment slope, and the consumption rate to control the input bandwidth capacity of CBS traffic data frames. CBS data frames exceeding the capacity controlled by the credit model are discarded. The number of discarded data frames is accumulated according to their corresponding categories in the bridge device's communication information database error category counter (system planning is conducted through offline user data collection or online planning and distribution of rules by the online system manager; the planning benchmark is determined based on the load and transmission time characteristics of the corresponding logical link for this type of service; this rule information is ultimately managed in the global configuration loading module).
[0026] The incoming data frame is processed by the global routing query module inside the bridge. The address to be queued for the data frame is extracted and input into the global routing storage module to retrieve the routing information of the data frame. Based on the retrieved routing information, the frame input memory and output port memory are connected through the global switching matrix management module to realize the dequeueing of the data frame information into the corresponding output port memory.
[0027] The data frame content corresponding to the data frame information that is validly entered into the output port memory is read from the frame input memory of each receiving port in a time-division polling manner and written to the global frame buffer module. The time-division polling is based on the number of ports of the bridge device and the time slots are evenly distributed for polling. The data frame information input to the output end is prioritized through the priority reset module of each port to complete the mapping of the data frame to the corresponding scheduling queue and find the corresponding scheduling queue.
[0028] Before data frames enter the scheduling queue for transmission, the load of different types of data frames entering the corresponding queue is measured and controlled by the traffic enqueue metering module. Data frames that do not meet the metering requirements will be discarded outside the scheduling queue, ensuring that the data entering the queue buffer can be sent completely within the planned time slots, and that the traffic usage will not exceed the scheduling bandwidth capacity of the buffer and time slots.
[0029] Each output port uses a timer module based on a global time base to time its output port scheduling cycle. The clock is input to the gating list scheduling module, which controls the state of the timing point within the cycle to achieve scheduling based on a pre-set periodic gating list. By periodically scanning the gating list storage module, the module outputs the time slot element corresponding to the current gating list, and dynamically provides an on / off control scheduling mechanism for different scheduling queues in a predefined order.
[0030] Based on the synchronous timing-driven gating list sequence switching, the multi-service scheduler is activated according to the scheduling category of the output port pointed to by the current gating list element. Transmission scheduling is selected according to the service categories of time-aware TAS, flow-controlled CBS, and BE (Before and After) services. For time-aware TAS services, when a queue gating is opened, all data buffered in that TAS queue is scheduled for back-to-back transmission. This includes enabling the output of frame information for the scheduling queue, sending the data frame content from the bridge's global frame buffer to the physical link based on the information index, and reclaiming the frame buffer space of the global frame buffer module. For CBS and BE services, when queues are opened, a combination of CBS control and priority scheduling is used to schedule the corresponding data frames for transmission.
[0031] This invention discloses a design method for a bridge device for deterministic transmission communication in differentiated service scenarios. The device operates under a unified planning mode of the network system. This unified planning mode generates a pre-defined planning configuration using either an offline pre-planning configuration mode or an online operational planning configuration mode. The system planning is based on user communication characteristics collected by the system, including parameters such as the source and destination of the service, service refresh cycle, load capacity, and service characteristic requirement categories (determined by indicators such as tolerable latency). The network system generates network configurations that constrain the operating mode of each bridge through a global configuration method. The configuration generation includes parameters such as the CBS receive control threshold and control slope for each bridge's receive port, frame forwarding path, enqueue metering capacity threshold for each output port, scheduling gate list, scheduling queue type, service type with corresponding priority stored in each scheduling queue, CBS output control threshold, and control slope. Each bridge can then communicate according to the planned mode by loading the unique configuration generated globally by the system.
[0032] The design of a bridge device for deterministic transmission communication in differentiated service scenarios is disclosed. This device acts as a relay device for service transmission in a network system. Following the system planning model, it synchronizes with the system, initializes and establishes a communication scheduling queue, constructs a management mechanism for the scheduling queue, and builds a gated list management mechanism to map the element sequence of the gated queue to the scheduling queue, implements scheduling queue on / off control and on / off time slot timing control, performs CBS service reception and transmission shaping control and bandwidth constraints according to agreed CBS service flow control rules, completes received service filtering, verification, bandwidth metering, and finally remapping to the scheduling queue. The bridge device includes the following steps: Step 1: The centralized user configuration entity generates configurations for various network devices, including bridge devices, based on collected services. The bridge receives the configuration information file distributed by this entity, loads the corresponding system configuration through a global configuration loading module, and stores the loaded configuration information in the communication configuration register of each port. The bridge device then completes the configuration loading function and performs the receiving, exchanging, and forwarding of data frames according to the corresponding configuration. The communication between the bridge device and the configuration information generation and loading can be achieved through the following three channels and methods: 1. Remotely loading the configuration information file through communication on any port of the bridge device; 2. The system designs a management plane controller for the bridge device, and the configuration file is written through the interconnection interface between the controller and the bridge core chip; 3. A soft core is created on the core chip inside the bridge device to obtain the information file and write it to the global configuration loading module. Step Two: After the bridge powers on and completes configuration loading, it connects to the network system and obtains system synchronization functionality (system synchronization can be achieved using distributed IEEE 1588 network functionality, or standard synchronization technologies such as IEEE 802.1AS or AS6802). Under local clock excitation, it performs basic synchronization functions such as system synchronization timing, periodic timing, and periodic maintenance and correction. After obtaining system synchronization, the bridge maintains a global synchronization timer and outputs the timer pulses to the global time base-based timer module of each output port. This enables periodic timing based on the system-configured scheduling cycle size. Based on the periodic synchronization timing of this port, it achieves the switching and scheduling of the gating list for that output port. After the output port completes a scheduling cycle, it scans and outputs the list elements in the entire gating scheduling list storage module, achieving data frame scheduling output for all scheduling queues on the entire port. Step 3: Based on the configuration information defined in Step 1, design forwarding queues for each output port for time-aware scheduling (TAS), flow-based shaping (CBS), and best-effort transmission (BE) services. The system supports a maximum of 8 forwarding queues, corresponding to 8 service priority levels. Each forwarding queue stores forwarding frame information for its corresponding service priority. For each output port, a scheduling queue is designed. First, it is determined whether the number of scheduling queues to be configured exceeds 8. If it exceeds 8, this is recorded as a configuration input anomaly in the bridge's status log, and the queues are arranged according to the maximum capacity of 8 scheduling queues. If the number is less than or equal to 8, the queues are designed according to the configuration information. The storage depth and service type of each queue are identified according to the configuration requirements. The depth depends on the cumulative forwarding data capacity of the corresponding queue within a period. For TAS services, each queue corresponds to a unique type of service (single-level priority service). For CBS and BE services, each queue performs mixed storage of different levels and types of services. Step 4: Based on the configuration information defined in Step 1, extract the gating schedule list of each output port and store it in the gating schedule list storage module. Store the elements in the storage module sequentially according to the order defined by the system, and store the scheduling queue information mapped to each gating element and the corresponding time slot size. Each output port will drive the elements in the gating schedule list storage module based on its own synchronization time. The execution switching will be performed according to the order of storage. Before the output port's synchronization timer cycle begins, the first element in the storage module will be indexed and extracted. Data transmission of the corresponding scheduling queue will be scheduled within the time slot specified by the element's configuration. Before the end of the current time slot, the next element in the storage module will be indexed and extracted, and the above processing will be performed. The execution time of the last element in the storage module depends on the remaining time of the entire scheduling cycle rather than the element's own time slice size (it is generally not recommended to place TAS type scheduling elements at the end of the scheduling list). When the entire scheduling cycle timer is completed, the element's scheduling execution is completed, and the first element in the storage module will be indexed and extracted.
[0033] Step 5: The receiving port of the bridge collects data frames and puts them into the frame input memory of each receiving port according to the first-in-first-out mechanism. The frame filtering management module of each port performs corresponding link layer protocol integrity checks on the input frames, such as VLAN category, frame length, and frame protocol type. Data that does not meet the integrity check standards is discarded. The number of discarded data is accumulated into the error category counter in the communication information database of the bridge device according to the corresponding filtering category. Step Six: After the data frame completes the integrity verification, it enters the traffic management module for classification processing. If it is identified as a TAS type frame, it is directly released; if it is identified as a Credit Management (CBS) type frame, the input traffic of the frame is controlled according to the algorithm model composed of the upper and lower limits of the credit capacity, the credit increment slope and the consumption rate planned by the system, thereby controlling the input rate and capacity of CBS traffic. Step 7: Complete all queuing checks by inputting flow-controlled data frames. Query the global routing query module within the bridge to extract routing query information from the data frames and input it into the global routing storage module to retrieve the forwarding path information for the data frame. Based on the retrieved routing forwarding path information, connect the frame input memory and output port memory through the global switching matrix management module to dequeue the data frame information to the corresponding output port memory. Read the data frame content corresponding to the data frame information that has effectively entered the output scheduling port from the frame input memory of each receiving port in a time-division round-robin manner and write it to the global frame buffer module. This bridge device identifies the current data frame's need for redundant transmission and, acting as the redundancy initiator, replicates the corresponding number of frame copies according to the number of redundant paths configured for the data frame, distributing them to the output port memory of the corresponding redundant paths. Step 8: For data frames entering the output port memory, select the priority reset processing for the data frame according to the system configuration (the system usually sets the priority reset in the first-level bridge adjacent to the data frame sending device. If the data frame is processed through the previous level bridge to the next level bridge, ensure that the data priority between bridges is consistent, and disable the priority reset function option for the data frame). Extract the priority and VID parameters in the data frame, and reset the priority through the priority mapping relationship table in the priority reset module of each port to complete the relationship mapping of the data frame to the corresponding scheduling queue. Step 9: Before data frames are transmitted through priority mapping to the scheduling queue, they need to undergo dequeue scheduling capacity control processing by the traffic inbound metering module. This process measures the load of different types of data frames entering the corresponding queues. Data frames that do not meet the metering requirements will be discarded outside the scheduling queue. Data entering the queue buffer can be sent completely within the planned time slots, ensuring that the deterministically scheduled traffic does not exceed the scheduling bandwidth capacity of the buffer and time slots. This guarantees deterministic transmission of the corresponding type of service under a guaranteed bandwidth resource. The traffic inbound metering mentioned above does not apply to time-sensitive TAS service flows, which do not involve any form of inbound metering or control. The gateway performs redundant frame elimination processing, identifying data frames before dequeue scheduling as inputs from different redundant paths and mutually redundant. The mutually redundant data copies will undergo redundancy elimination processing, and the remaining first-arriving valid frame will enter the dequeue scheduling. Step 10: The data frames that enter the corresponding scheduling queue buffer of the output port will be periodically scheduled and output in strict accordance with the synchronization time of this port; the scheduling period based on the output port and the scheduling will be executed according to step 4. When the scheduling cycle timer completes the timing of the previous gated list element and switches to the current element's scheduling, the corresponding scheduling output is performed according to the scheduling queue pointed to by the current element: 1. When the current scheduling queue is of type TAS, the gate of the current unique scheduling queue is opened, and the data frames of the scheduling queue are sent back-to-back in the order of entry into the queue. Under reasonable constraints and planning, the time slot allocated to this element will complete the transmission of the cumulative TAS service frames entering the queue within this cycle, ensuring that the data buffer scheduling is empty before the time slot switch; input to the gated list scheduling module, and implement the periodic gated list scheduling based on the status control of the timing point within the cycle; 2. When the current scheduling queue is of type CBS (Flow Controlled Broadband) and type BE (Blank Space Transmission) service, CBS services are scheduled first. According to the combination of current credit margin control and priority scheduling, the corresponding data frames are scheduled for transmission: including enabling the frame information output of the scheduling queue, sending the data frame content in the global frame buffer of the bridge according to the information index to the physical link, and completing the reclamation of the frame buffer space of the global frame buffer module.
[0034] The above description is merely a specific embodiment of the present invention, providing a detailed description of the invention. Parts not covered herein are conventional techniques. However, the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention. The scope of protection of the present invention should be determined by the scope of the claims.
Claims
1. A bridge device supporting end-to-end aviation uncompressed video network, characterized in that: The bridge device includes: a global configuration loading module, n communication configuration register modules, n frame receiving ports, n frame input memories, n frame filtering management modules, n traffic monitoring modules, a global route query module, a global route storage module, a global frame buffer module, a global switching matrix management module, n priority reset modules, n traffic queuing metering modules, n timer modules based on global time base, n gated scheduling list storage modules, n gated list scheduling modules, n output port memories, and a multi-service scheduler for each output port based on multi-service time-aware TAS, flow-controlled CBS, and BE services.
2. The bridge device according to claim 1, characterized in that: The global configuration loading module obtains the system's local bridge configuration information file, and the methods of obtaining this information include: Method 1: Input from any receiving port of the bridge device; Method 2: Design a controller for the bridge device, and write the configuration information file into the controller; Method 3: A soft core is created on the core chip inside the bridge device to obtain the configuration information file and write it to the global configuration loading module; The global configuration loading module parses and reassembles the configuration information file content and stores it in each communication configuration register module for communication retrieval.
3. The bridge device according to claim 2, characterized in that: After the bridge device is powered on and the configuration information file is loaded, it connects to the network system to obtain system synchronization information, maintains a global synchronization timer, and outputs the timer pulse to the timer module based on the global time base of each output port to realize periodic timing based on the scheduling cycle size configured by the system.
4. The bridge device according to claim 3, characterized in that: Each receiving port collects data frames and puts the data frames into the frame input memory of each receiving port according to the first-in-first-out mechanism; The frame filtering management module of each port performs a check on the integrity of the corresponding link layer protocol for the input frame. The frames that do not meet the integrity check criteria are discarded, and the number of discarded data is accumulated into the error category counter in the communication information database of the bridge device according to the corresponding filtering category.
5. The bridge device according to claim 4, characterized in that: The traffic police module identifies the frame type of the input frame data; If the frame is identified as a TAS / BE category frame, it will be allowed to pass directly. The frame is identified as a Credit Management (CBS) type frame. The input traffic of this frame is controlled according to the algorithm model composed of the upper and lower limits of credit capacity, the credit increment slope and the consumption rate planned by the system, thereby controlling the input rate and capacity of CBS traffic.
6. The bridge device according to claim 5, characterized in that: The scheduler for multi-service time-aware TAS, flow-controlled CBS, and BE-based interleaving services is in the form of queues, with a maximum of 8 queues, corresponding to the 8 service priority levels of the system. Each forwarding queue is used to store forwarding frame information for the corresponding service priority. First, determine if the number of scheduling queues to be configured exceeds 8. If it exceeds 8, record this as a configuration input anomaly in the bridge's status log and arrange them according to the maximum capacity of 8 scheduling queues. If it is 8 or less, design according to the configuration information. Identify the storage depth and service type of each queue according to the configuration requirements. The depth depends on the cumulative forwarding data capacity of the corresponding queue in a period. The storage service type identification is as follows: for TAS services, each queue corresponds to a unique type of service; for CBS and BE services, each queue performs mixed storage of different levels and types of services.
7. The bridge device according to claim 6, characterized in that: By querying the global routing query module inside the bridge, the information used for routing query in the data frame is extracted and input into the global routing storage module to query the forwarding path information of the data frame. Based on the queried routing forwarding path information, the frame input memory and output port memory are connected through the global switching matrix management module to realize the dequeueing of data frame information to the corresponding output port memory. The data frame content corresponding to the data frame information that is validly entered into the output port is read from the frame input memory of each receiving port in a time-division polling manner and written to the global frame buffer module. This bridge device recognizes that the current data frame requires redundant transmission, and acts as the redundancy initiator. It will copy the corresponding number of frame copies according to the number of redundant paths configured in the data frame, and distribute them to the output port memory of the corresponding redundant paths.
8. The bridge device according to claim 7, characterized in that: The data frame entering the output port memory selects the priority reset processing according to the system configuration, extracts the priority and VID parameters in the data frame, and resets the priority through the priority mapping relationship table in the priority reset module of each port, thus completing the relationship mapping of the data frame to the corresponding scheduling queue.
9. The bridge device according to claim 8, characterized in that: Data frames that enter the corresponding scheduling queue buffer of the output port will be periodically scheduled and output strictly according to the synchronous timing of this port; Based on the configuration file information, the gating schedule lists of each output port are extracted and stored in the gating schedule list storage module. The elements are stored sequentially according to the system-defined list element order, along with the scheduling queue information mapped to each gating element and the corresponding time slot size. Each output port will drive the elements in the gating schedule list storage module based on its own synchronization timing, switching execution according to the order of storage. Before the output port's synchronization timing cycle begins, the first element in the storage module is indexed and retrieved. Data transmission of the corresponding scheduling queue is scheduled within the time slot specified by the element. Before the current time slot ends, the next element in the storage module is indexed and retrieved, and the above processing is performed. The execution time of the last element in the storage module depends on the remaining time of the entire scheduling cycle, not the element's own time slice size. When the entire scheduling cycle timing is complete, the element's scheduling execution is finished, and the first element in the storage module is indexed and retrieved.
10. The bridge device according to claim 9, characterized in that: When the scheduling cycle timer finishes timing the previous gated list element and switches to scheduling the current element, the corresponding scheduling output is performed according to the scheduling queue pointed to by the current element: 1) When the current scheduling queue is of type TAS, the gating of the current unique scheduling queue is opened, and the data frames of the scheduling queue are sent back to back in the order of enqueueing; input to the gating list scheduling module, and implement periodic gating list scheduling based on the status control of the timing point within the period; 2) When the current scheduling queue is a flow control type CBS or a gap-filling type BE service, CBS service is scheduled first. According to the current credit margin control and priority scheduling combination, the corresponding data frame is scheduled for transmission. This includes enabling the frame information output of the scheduling queue, sending the data frame content to the bridge's global frame buffer according to the information index to the physical link, and completing the reclamation of the frame buffer space of the global frame buffer module.