Multi-satellite network IP service processing method and system
Through the coordinated processing of CPU and FPGA, the problem of high-performance CPUs being susceptible to single-particle interference in harsh environments is solved, and high-reliability and high-performance IP service processing in multi-star networks is realized, which is suitable for satellite communications.
Patent Information
- Application Number
- CN202510666326.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-22
- Publication Date
- 2025-09-02
AI Technical Summary
In the prior art, high-performance CPUs are susceptible to single-particle interference in harsh environments, resulting in poor IP service processing reliability in satellite communications.
The CPU and FPGA are used to process in conjunction with each other. The IP processing module and RIP diffusion processing module are set up in the FPGA. Data forwarding is realized through the RIP diffusion table and IP tag forwarding table, and configuration frames are generated in combination with the CPU's protocol analysis and sent to the FPGA for processing.
It improves the reliability and stability of IP service processing in satellite networks, reduces the requirements for device performance, and enhances the stability of on-orbit operation.
Smart Images

Figure CN120583070A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to a multi-satellite network IP service processing method and system, belonging to the field of IP service communication. Background Art
[0002] The traditional method of implementing IP service processing is mainly through high-performance CPUs, which handle IP service-related protocol parsing, service data forwarding, and RIP diffusion.
[0003] The above existing technologies are not applicable due to the harsh environment in which satellites are located. High-performance CPUs use more advanced manufacturing processes and have high processing performance but are susceptible to single-particle interference, resulting in service interruptions and poor reliability. Summary of the Invention
[0004] The technical problem solved by the present invention is to overcome the deficiencies of the prior art and propose a multi-satellite network IP service processing method and system, which are implemented through collaborative processing by FPGA and CPU.
[0005] The technical solution of the present invention is: a multi-satellite network IP service processing system, which is implemented by the collaboration of a CPU and an FPGA, wherein the FPGA is provided with an IP processing module, a RIP diffusion processing module, and a forwarding processing module; the forwarding processing module is used to receive service data transmitted from the ground and forward the service data to the IP processing module or the RIP diffusion processing module according to the frame type;
[0006] The CPU parses and processes the received protocol data packets according to the various protocols currently used in the multi-satellite network, generates a RIP diffusion table, an IP label forwarding table, and corresponding configuration frames containing the destination station address and forwarding label information, and sends the configuration frames to the corresponding IP processing module and RIP diffusion processing module of the FPGA in real time;
[0007] Two areas, a protocol processing unit and a data processing unit, are set in the IP processing module and the RIP diffusion processing module. At the same time, one of the two areas serves as a configuration area and the other as a query area; the protocol processing unit parses the configuration frame and configures the parsed content in the form of a table in the configuration area. After the configuration of the configuration area is completed, it is immediately switched to the query area. The configuration is a full configuration; the data processing unit receives the business data input by the forwarding processing module, and forwards the business data to the corresponding destination address through the forwarding processing module in combination with the table content in the query area.
[0008] Preferably, in addition to sending the configuration frames of each protocol to the protocol processing module corresponding to the FPGA in real time, the CPU also sends the configuration frames to the FPGA according to a preset period.
[0009] Preferably, the preset period is 1-3 minutes.
[0010] Preferably, the protocols include ISIS protocol and RIP protocol.
[0011] Preferably, the CPU parses the received RIP protocol data packets and ISIS protocol data packets according to the RIP protocol and the ISIS protocol, extracts the destination station address and the forwarding label in the data packets to form a RIP diffusion table and a corresponding RIP diffusion table configuration frame, and sends the RIP diffusion table configuration frame to the RIP diffusion processing module in the FPGA;
[0012] The protocol processing unit parses the RIP diffusion table configuration frame and stores the destination station address and forwarding label related to the diffusion distribution in the RIP diffusion table in the configuration area in sequence; the data processing unit stores the received business data, namely the RIP business data packet, in RAM, traverses the RIP diffusion table in the query area, extracts the destination station address in the table entry, and distributes the RIP business data packet in RAM to the corresponding destination station address through the forwarding processing module according to the table entry.
[0013] Preferably, the CPU parses the received RIP protocol data packets and ISIS protocol data packets according to the RIP protocol and the ISIS protocol, extracts the destination station address and forwarding label in the data packets to generate an IP label forwarding table and a corresponding configuration frame, and sends the IP label forwarding table configuration frame to the IP processing module of the FPGA;
[0014] The protocol processing unit parses the IP label forwarding table configuration frame and stores the forwarding-related destination station address and forwarding label in the IP label forwarding table in the configuration area in sequence;
[0015] The data processing unit stores the received IP service data in RAM and extracts its label information. The label information is matched with the entry in the IP label table in the query area to obtain the destination station address corresponding to the label, and the IP service data is forwarded to the station address, thus completing the IP service forwarding processing.
[0016] A multi-satellite network IP service processing method, comprising:
[0017] The CPU parses and processes the received protocol data packets according to the various protocols currently used in the multi-satellite network, generates a RIP diffusion table, an IP label forwarding table, and the corresponding configuration frame containing the target station address and forwarding label information, and sends the configuration frame to the FPGA in real time;
[0018] The RAM in the FPGA is configured with two areas, one as a configuration area and the other as a query area at the same time. The FPGA parses the received configuration frame and stores the table entry content in the configuration area. After the configuration of the configuration area is completed, the configuration area is immediately switched to the query area. The configuration is a full configuration.
[0019] The FPGA receives and caches the service data transmitted from the ground, and forwards the service data to the corresponding destination station address based on the table content in the query area.
[0020] Preferably, the CPU sends a configuration frame to the FPGA according to a preset period, and the preset periodicity is 1-3 minutes.
[0021] Preferably, the protocols are RIP protocol and ISIS protocol, the CPU parses the received RIP protocol data packets and ISIS protocol data packets according to the RIP protocol and ISIS protocol, extracts the destination station address and forwarding label in the data packets to form a RIP spread table and a corresponding RIP spread table configuration frame, and sends the RIP spread table configuration frame to the FPGA;
[0022] The FPGA parses the configuration frame and stores the destination address and forwarding label related to the diffusion distribution in the RIP diffusion table in the configuration area of RAM in sequence;
[0023] The FPGA receives the business data transmitted from the ground, namely the RIP business data packet, which is stored in the RAM. It traverses the RIP diffusion table in the query area, extracts the destination station address, and distributes the RIP business data packet in the RAM to the corresponding destination station address according to the table entries.
[0024] Preferably, the protocol is ISIS protocol and RIP protocol;
[0025] The CPU generates an IP label forwarding table and a corresponding configuration frame based on the ISIS protocol data packet and the RIP protocol data packet, and sends the IP label forwarding table configuration frame to the FPGA;
[0026] The FPGA parses the IP label forwarding table configuration frame and stores the forwarding-related destination station address and forwarding label in the IP label table in the configuration area of RAM in sequence;
[0027] The FPGA stores the received IP service data in RAM and extracts its label information. The label information is matched with the entry in the IP label table in the query area to obtain the destination station address corresponding to the label, and the IP service data is forwarded to the station address, thus completing the IP service forwarding processing.
[0028] The advantages of the present invention compared with the prior art are:
[0029] (1) The present invention is implemented through collaborative processing by CPU and FPGA, with relatively low requirements on device performance and high on-orbit reliability.
[0030] (2) The forwarding table of the present invention is implemented in the form of an A / B table, ensuring that the service is not affected during the table entry update process.
[0031] (3) In addition to real-time configuration, the present invention also adds periodic configuration, so that the entry memory can automatically return to normal within a short period of time after being affected by a single particle in space, ensuring the long-term stable operation of the equipment in orbit. BRIEF DESCRIPTION OF THE DRAWINGS
[0032] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiment below. The accompanying drawings are for illustration purposes only and are not to be considered as limiting the present invention. The same reference symbols are used throughout the drawings to represent the same components. In the drawings:
[0033] Figure 1 Schematic diagram of the IP service processing system designed for the present invention;
[0034] Figure 2 Schematic diagram of the RIP diffusion process designed for the present invention;
[0035] Figure 3 Schematic diagram of IP forwarding processing designed for the present invention. DETAILED DESCRIPTION
[0036] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.
[0037] The present invention proposes a multi-satellite network IP service processing system, which is applied to data processing equipment with IP processing requirements.
[0038] The IP service processing system is as follows Figure 1 As shown in the figure, the processing system is implemented by the collaboration of CPU and FPGA, making full use of the strong computing power of CPU and the low processing delay of FPGA. The CPU is used for ISIS protocol processing and RIP protocol processing, and the FPGA is used to implement RIP data frame diffusion and IP service data table lookup and forwarding. It has the characteristics of good performance and high reliability, achieving the goal of completing highly reliable and high-performance IP service processing using devices with relatively low processing performance.
[0039] The CPU parses the ISIS and RIP protocol packets, combining the station address and forwarding label information obtained into a RIP diffusion table configuration frame. The CPU then sends this frame to the FPGA for RIP diffusion table configuration. The FPGA parses the RIP diffusion table configuration frame and stores the entry contents at the address specified by the entry address field in RAM.
[0040] Table 1 RIP diffusion table configuration frame format table
[0041]
[0042] The CPU parses the ISIS and RIP protocol packets to obtain the station address and forwarding label information, forming an IP label table configuration frame. This frame is then sent to the FPGA for IP label table configuration. The FPGA parses the IP label table configuration frame and stores the table entries in RAM. The FPGA is equipped with a RIP diffusion processing module and a forwarding processing module.
[0043] The RIP diffusion processing module solves the RIP business data diffusion requirements and uses FPGA to achieve large-scale high-speed diffusion. Figure 2 As shown in the figure, this function consists of two parts. The first part is RIP diffusion table configuration, which parses the configuration frame from the CPU and sequentially stores key information related to diffusion distribution, such as the destination station address and forwarding label, in the RIP diffusion table. The second part is table lookup forwarding processing, which stores the received RIP service data packet in RAM, traverses the RIP diffusion table, extracts the destination station address information, and distributes the data to the corresponding destination station address according to the table entries.
[0044] In the present invention, the RIP diffusion table stored in the RAM is divided into two areas, one of which is used as a configuration area and the other as a query area at the same time; the configuration area is immediately switched to the query area after configuration is completed, and the configuration is full configuration.
[0045] Table 2 IP label table configuration frame format table
[0046]
[0047] The IP service data forwarding process in the FPGA consists of a receiving section, a table lookup section, and a sending section. The receiving section (implemented by the forwarding processing module) is responsible for receiving IP service data, storing it in the cache, and extracting the forwarding label information. The table lookup section matches the forwarding label with the forwarding label in the IP label table to obtain the forwarding station address. The sending section (implemented by the forwarding processing module) is responsible for reading data from the cache and sending it to the forwarding station address.
[0048] The IP processing module is set up in the FPGA; the IP processing module mainly solves the business communication needs and uses FPGA to achieve high-speed and low-latency forwarding processing. Figure 3As shown in Figure 1, this function consists of two parts. The first part is IP label table configuration, which parses the configuration frame from the CPU and stores key information related to forwarding, such as the destination station address and forwarding label, in the IP label table in order. The second part is table lookup forwarding processing, which extracts the label of the received IP packet, traverses the IP label table, extracts the destination station address that matches the label, and then forwards the IP service data to the corresponding station address.
[0049] The IP label table stored in the RAM in the present invention is divided into two areas, one of which is used as a configuration area and the other as a query area at the same time; the configuration area is immediately switched to the query area after the configuration is completed, and the configuration is a full configuration.
[0050] A multi-satellite network IP service processing method, the steps are as follows:
[0051] (1) Configuration: The CPU obtains the contents of the RIP diffusion table and the IP label table by parsing the RIP protocol data packets and the ISIS protocol data packets.
[0052] (2) After obtaining the RIP diffusion table entry content and the IP label table entry content through step (1), the entry content is sent to the FPGA in a frame format (configuration frame).
[0053] (3) FPGA parses the received configuration frame and stores the table entry content into the corresponding configuration area of the RIP diffusion table and the configuration area of the IP label table.
[0054] (4) After completing the configuration in step (3), switch the configuration area and the query area.
[0055] (5) Based on step (4), the FPGA receives the service data (RIP diffusion packet or IP service data packet) and stores it in the cache.
[0056] (6) Query the RIP diffusion table or IP label table in the query area (different frame types are used to represent RIP data or IP data, respectively, based on the frame type).
[0057] (7) Based on step (6), the RIP data is diffused or the IP data is forwarded.
[0058] For the relevant contents of the method of the present invention, reference can be made to the corresponding description in the system and will not be repeated here.
[0059] Compared with existing technologies, this invention can achieve high-speed IP service processing using a combination of lower-performance components. Compared with high-performance components, lower-performance components require a larger manufacturing process and are less susceptible to single-particle impacts in space. This provides an effective solution for the long-term stable operation of satellite payload processors.
[0060] The above-described embodiments are only preferred specific implementations of the present invention. Common changes and substitutions made by those skilled in the art within the scope of the technical solution of the present invention should be included in the protection scope of the present invention.
Claims
1. A multi-satellite network IP service processing system, characterized in that The system is implemented by the collaboration of the CPU and FPGA, wherein the FPGA is provided with an IP processing module, a RIP diffusion processing module, and a forwarding processing module; the forwarding processing module is used to receive service data transmitted from the ground and forward the service data to the IP processing module or the RIP diffusion processing module according to the frame type; The CPU parses and processes the received protocol data packets according to the various protocols currently used in the multi-satellite network, generates a RIP diffusion table, an IP label forwarding table, and corresponding configuration frames containing the destination station address and forwarding label information, and sends the configuration frames to the corresponding IP processing module and RIP diffusion processing module of the FPGA in real time; Two areas, a protocol processing unit and a data processing unit, are set in the IP processing module and the RIP diffusion processing module. At the same time, one of the two areas serves as a configuration area and the other as a query area; the protocol processing unit parses the configuration frame and configures the parsed content in the form of a table in the configuration area. After the configuration of the configuration area is completed, it is immediately switched to the query area. The configuration is a full configuration; the data processing unit receives the business data input by the forwarding processing module, and forwards the business data to the corresponding destination address through the forwarding processing module in combination with the table content in the query area.
2. The system according to claim 1, wherein: In addition to sending the configuration frames of each protocol to the protocol processing module corresponding to the FPGA in real time, the CPU also sends the configuration frames to the FPGA according to a preset period.
3. The system according to claim 2, characterized in that: The preset period is 1-3 minutes.
4. The system according to claim 1, wherein: The protocols include ISIS protocol and RIP protocol.
5. The system according to claim 4, characterized in that: The CPU parses the received RIP and ISIS packets according to the RIP and ISIS protocols, extracts the destination address and forwarding label from the packets, forms a RIP diffusion table and a corresponding RIP diffusion table configuration frame, and sends the RIP diffusion table configuration frame to the RIP diffusion processing module in the FPGA. The protocol processing unit parses the RIP diffusion table configuration frame and stores the destination address and forwarding label related to diffusion distribution in the RIP diffusion table in the configuration area in order. The data processing unit stores the received business data, namely the RIP business data packet, in RAM, traverses the RIP diffusion table in the query area, extracts the destination station address in the table entry, and distributes the RIP business data packet in RAM to the corresponding destination station address through the forwarding processing module according to the table entry.
6. The system according to claim 4, characterized in that: The CPU parses the received RIP and ISIS protocol packets according to the RIP and ISIS protocols, extracts the destination address and forwarding label from the packets, generates an IP label forwarding table and a corresponding configuration frame, and sends the IP label forwarding table configuration frame to the IP processing module of the FPGA. The protocol processing unit parses the IP label forwarding table configuration frame and stores the forwarding-related destination station address and forwarding label in the IP label forwarding table in the configuration area in sequence; The data processing unit stores the received IP service data in RAM and extracts its label information. The label information is matched with the entry in the IP label table in the query area to obtain the destination station address corresponding to the label, and the IP service data is forwarded to the station address, thus completing the IP service forwarding processing.
7. A multi-satellite network IP service processing method, characterized in that include: The CPU parses and processes the received protocol data packets according to the various protocols currently used in the multi-satellite network, generates a RIP diffusion table, an IP label forwarding table, and the corresponding configuration frame containing the target station address and forwarding label information, and sends the configuration frame to the FPGA in real time; The RAM in the FPGA is configured with two areas, one as a configuration area and the other as a query area at the same time. The FPGA parses the received configuration frame and stores the table entry content in the configuration area. After the configuration of the configuration area is completed, the configuration area is immediately switched to the query area. The configuration is a full configuration. The FPGA receives and caches the service data transmitted from the ground, and forwards the service data to the corresponding destination station address based on the table content in the query area.
8. The method according to claim 7, wherein: The CPU sends a configuration frame to the FPGA according to a preset period, and the preset period is 1-3 minutes.
9. The method according to claim 7, wherein: The protocols are RIP and ISIS. The CPU parses the received RIP and ISIS packets according to the RIP and ISIS protocols, extracts the destination address and forwarding label in the packets to form a RIP diffusion table and a corresponding RIP diffusion table configuration frame, and sends the RIP diffusion table configuration frame to the FPGA. The FPGA parses the configuration frame and stores the destination address and forwarding label related to the diffusion distribution in the RIP diffusion table in the configuration area of RAM in sequence; The FPGA receives the business data transmitted from the ground, namely the RIP business data packet, which is stored in the RAM. It traverses the RIP diffusion table in the query area, extracts the destination station address, and distributes the RIP business data packet in the RAM to the corresponding destination station address according to the table entries.
10. The method according to claim 7, wherein: The protocols are ISIS and RIP. The CPU generates an IP label forwarding table and a corresponding configuration frame based on the ISIS protocol data packet and the RIP protocol data packet, and sends the IP label forwarding table configuration frame to the FPGA; The FPGA parses the IP label forwarding table configuration frame and stores the forwarding-related destination station address and forwarding label in the IP label table in the configuration area of RAM in sequence; The FPGA stores the received IP service data in RAM and extracts its label information. The label information is matched with the entry in the IP label table in the query area to obtain the destination station address corresponding to the label, and the IP service data is forwarded to the station address, thus completing the IP service forwarding processing.