Semantic-based dt network bp and ltp cross-layer bundle transmission method and device

Abstract

The application discloses a DTN network BP and LTP cross-layer bundle transmission method and device based on semantics and a storage medium, and the method comprises the following steps: in the sending end, bundle data is handed over from the BP layer to the LTP layer, the LTP packet header format is added, and the bundle data is segmented into a plurality of semantic blocks according to semantics; the semantic blocks are divided into the first type of semantic blocks without changes and the second type of semantic blocks with changes according to the semantic data of the packet header and the payload; in the receiving end, the first type of semantic blocks with errors in the transmission process are dynamically adjusted to the second type of semantic blocks when the LTP layer retransmits; the LTP layer carries out the second type of semantic block checking on the received semantic blocks, retransmits, and then hands over to the BP layer; the BP layer carries out checking on the received semantic blocks and stores the semantic blocks; in the retransmission process, the original error semantic blocks in the memory are replaced by the newly received semantic blocks until all the semantic blocks are reliably received or the maximum retransmission number reaches a specified number. The application can achieve the purpose of reliable transmission by using the least retransmission number and retransmission data amount while reducing the packet loss rate.

Description

Technical Field

[0001] This invention belongs to the field of satellite and deep space communication technology, specifically relating to a semantic-based DTN network BP and LTP cross-layer bundle transmission method, device and storage medium. Background Technology

[0002] Existing DTN-based data transmission requires data to be transmitted and recovered (encoded / decoded) at the bit level. However, due to the development of deep space communication and the increase in data volume, excessive transmission latency cannot meet the needs. Therefore, some research focuses on improving the transmission mechanisms of the BP or LTP layers separately or performing cross-layer joint optimization. From the perspective of bundle and segment size optimization, most of the above methods, including cross-layer optimization, are largely affected by the packet format in the data encapsulation of BP and LTP. Especially under poor channel conditions, with a fixed bundle format, the packet loss rate has a significant lower bound, which may constrain these optimization methods. On the other hand, some research considers using advanced source-channel coding algorithms to overcome high bit error rates under low signal-to-noise ratio conditions; however, these coding algorithms perform poorly under high bit error rates because they increase data redundancy in the bundle. To date, existing DTN seems to have a significant bottleneck in solving the bundle transmission problem in long-distance space communication. Summary of the Invention

[0003] To address the aforementioned problems, this invention provides a semantic-based method, apparatus, and storage medium for cross-layer bundle transmission between BP and LTP in DTN networks. In satellite and deep space network communication scenarios, for single-hop data transmission, the invention combines the semantic features of the transmitted files to perform semantic encoding and decoding of the original data and semantic-level transmission, thereby effectively reducing packet loss rate and improving transmission reliability under high-error channels.

[0004] According to a first aspect of the present disclosure, a semantic-based method for cross-layer bundle transmission between BP and LTP in a DTN network is provided, the method comprising the following steps:

[0005] At the sending end, the bundle data encapsulated by the original file is transferred from the BP layer to the LTP layer. In the LTP layer, the LTP header format is added and the data is semantically segmented into several semantic blocks. Based on the semantic data of the header and payload of the semantic blocks, the semantic blocks are divided into a first type of semantic blocks with no change and a second type of semantic blocks with change. Here, "no change" means that the data format is fixed and "change" means that the data format is random.

[0006] At the receiving end, during retransmission, the LTP layer dynamically adjusts the first type of semantic block that erroneous during transmission to the second type of semantic block; the LTP layer performs second type of semantic block verification on the received semantic block and retransmits it before handing it over to the BP layer, which verifies the received semantic block and stores it; the BP layer retransmits the erroneous semantic block, replacing the original erroneous semantic block in the memory with the newly received semantic block during the retransmission process, until all semantic blocks are reliably received or the maximum number of retransmissions has been reached.

[0007] In one embodiment, the method further includes grouping the bundle data encapsulated from the original data according to different types and then transferring it from the BP layer to the LTP layer.

[0008] In one embodiment, classifying the semantic blocks into a first category of semantic blocks with no changes and a second category of semantic blocks with changes based on the semantic data of the header and payload of the semantic blocks specifically includes:

[0009] Obtain the semantic data of each packet header and payload of the LTP layer and divide the semantic blocks into a first type of semantic blocks with no changes and a second type of semantic blocks with changes;

[0010] The second type of semantic blocks that have changed are assigned as red blocks in the LTP layer, and the first type of semantic blocks that have not changed are assigned as green blocks;

[0011] If data assigned as a green block is corrupted during transmission, the corrupted green block will be dynamically reassigned to a red block during retransmission.

[0012] In one embodiment, the LTP layer restores the received data into semantic blocks with LTP header format, and the BP layer restores the semantic blocks with LTP header format into bundle data and finally restores the original file.

[0013] According to a second aspect of the present disclosure, a semantic-based DTN network BP and LTP cross-layer bundle transmission apparatus is provided, the apparatus comprising:

[0014] The sending end is used to transfer the bundle data encapsulated by the original file from the BP layer to the LTP layer, add the LTP header format in the LTP layer and divide it into several semantic blocks according to semantics; according to the semantic data of the header and payload of the semantic blocks, the semantic blocks are divided into a first type of semantic blocks with no change and a second type of semantic blocks with change, wherein the no change refers to the data format being fixed and the change refers to the data format being random;

[0015] At the receiving end, the LTP layer dynamically adjusts the first type of semantic blocks that erroneous during transmission to the second type of semantic blocks during LTP layer retransmission. The LTP layer performs second type of semantic block verification on the received semantic blocks and retransmits them before handing them over to the BP layer. The BP layer verifies the received semantic blocks and stores them. The BP layer retransmits the erroneous semantic blocks, replacing the original erroneous semantic blocks in the memory with newly received semantic blocks during the retransmission process, until all semantic blocks are reliably received or the maximum number of retransmissions has been reached.

[0016] In one embodiment, the transmitting end further includes grouping the bundle data encapsulated from the original data into different types and then transferring it from the BP layer to the LTP layer.

[0017] In one embodiment, the sending end divides the semantic block into a first type of semantic block with no change and a second type of semantic block with change based on the semantic data of the header and payload of the semantic block, specifically including:

[0018] Obtain the semantic data of each packet header and payload of the LTP layer and divide the semantic blocks into a first type of semantic blocks with no changes and a second type of semantic blocks with changes;

[0019] The second type of semantic blocks that have changed are assigned as red blocks in the LTP layer, and the first type of semantic blocks that have not changed are assigned as green blocks;

[0020] If data assigned as a green block is corrupted during transmission, the corrupted green block will be dynamically reassigned to a red block during retransmission.

[0021] In one embodiment, the receiving end is further configured to use the LTP layer to restore the received data into semantic blocks with LTP header format, use the BP layer to restore the semantic blocks with LTP header format into bundle data, and finally restore the original file.

[0022] According to a third aspect of the present disclosure, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the above-described semantic-based DTN network BP and LTP cross-layer bundle transmission method.

[0023] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium is provided, the storage medium storing computer instructions that, when executed by a processor, implement the above-described semantic-based DTN network BP and LTP cross-layer bundle transmission method.

[0024] The technical solution provided in this disclosure is a semantic-based DTN network BP and LTP cross-layer bundle transmission method, apparatus, and storage medium, which overcomes the problems existing in current space information network transmission protocols in long-distance communication scenarios (such as satellite communication and deep space communication), such as excessive retransmissions leading to ultra-long latency and low throughput. As the communication distance increases, the packet loss rate increases exponentially, resulting in reduced accuracy during transmission and requiring multiple retransmissions to meet reliability requirements. Most existing methods for solving the problem of huge latency in long-distance communication are still based on some degree of protocol improvement within the existing DTN framework. However, due to the limitations of traditional bit-level communication in the relationship between bit error rate and packet loss rate, the improvement effects are not good, especially when the bit error rate is extremely high. Therefore, to significantly reduce packet loss rate under high bit error rate conditions, thereby reducing latency and increasing throughput, this invention proposes a novel semantic-level data transmission scheme and improves existing BP and LTP transmission protocols. First, the semantic features of the original data to be transmitted are extracted, and semantic segmentation and encoding are performed based on these features. Transmission and reconstruction are then carried out at the semantic level. Using deep learning-based semantic communication technology, both the sending and receiving ends share a semantic knowledge base containing all semantic features. Segmentation and combination standards are established, and semantic feature-based transmission and retransmission strategies for the BP and LTP layers are developed to replace existing BP and LTP layer transmission protocols. This achieves reliable transmission with minimal retransmissions and retransmission data volume while reducing packet loss rate.

[0025] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0026] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0027] Figure 1 This is a logical schematic diagram of the semantic-based DTN network BP and LTP cross-layer bundle transmission method in an embodiment of the present invention;

[0028] Figure 2 This is a schematic diagram of the BU ARQ algorithm logic in an embodiment of the present invention;

[0029] Figure 3 This is a schematic diagram of the RGA-SI ARQ algorithm logic in an embodiment of the present invention;

[0030] Figure 4 This is a schematic diagram of a semantic-based DTN network BP and LTP cross-layer bundle transmission method in an embodiment of the present invention;

[0031] Figure 5 This is an execution flowchart of the semantic-based DTN network BP and LTP cross-layer bundle transmission method in an embodiment of the present invention;

[0032] Figure 6 This is a schematic diagram of the semantic-based DTN network BP and LTP cross-layer bundle transmission device in an embodiment of the present invention.

[0033] Figure 7 This is a schematic diagram illustrating the performance comparison of semantic quality as a function of the channel in the simulation experiment of this invention. Figure 1 ;

[0034] Figure 8 This is a schematic diagram illustrating the performance comparison of semantic quality as a function of the channel in the simulation experiment of this invention. Figure 2 ;

[0035] Figure 9 This is a schematic diagram illustrating the change in the amount of retransmitted data with the number of retransmissions in an embodiment of the present invention;

[0036] Figure 10 This is a schematic diagram illustrating the impact of channel bit error rate on average delivery delay in an embodiment of the present invention;

[0037] Figure 11 This is a schematic diagram illustrating the impact of channel bit error rate on effective throughput in an embodiment of the present invention. Detailed Implementation

[0038] The present invention will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the invention. Furthermore, it should be noted that, for ease of description, only the parts relevant to the present invention are shown in the drawings, not the entire structure.

[0039] Before discussing the exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe the steps as sequential processes, many of these steps can be performed in parallel, concurrently, or simultaneously. Furthermore, the order of the steps can be rearranged. The process can be terminated when its operation is complete, but may also have additional steps not included in the figures. The process can correspond to a method, function, procedure, subroutine, subroutine, etc.

[0040] Furthermore, the terms "first," "second," etc., may be used herein to describe various directions, actions, steps, or elements, but these directions, actions, steps, or elements are not limited by these terms. These terms are only used to distinguish one direction, action, step, or element from another. For example, without departing from the scope of this application, a first type of semantic block may be referred to as a second type of semantic block, and similarly, a second type of semantic block may be referred to as a first type of semantic block. Both the first type of semantic block and the second type of semantic block are semantic blocks, but they are not the same semantic block. The terms "first," "second," etc., should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0041] This invention provides the following embodiments for a semantic-based method, apparatus, and storage medium for cross-layer bundle transmission between BP and LTP in a DTN network:

[0042] Example 1 illustrates a semantic-based method for cross-layer bundle transmission between BP and LTP in DTN networks. See [link to example]. Figure 1 This is a logic diagram of the semantic-based DTN network BP and LTP cross-layer bundle transmission method in the embodiment. The method logic includes:

[0043] Semantic Blocking and Coding Strategy (SBSC):

[0044] First, the original data to be transmitted is encapsulated into a bundle format.

[0045] Step 1: Group the bundles with payloads according to different types and determine the grouping as a preliminary semantic chunking scheme;

[0046] Step 2: Transfer the semantic block from the BP layer to the LTP layer and add the LTP header format;

[0047] Step 3: Separate the data with LTP format into multiple semantic blocks according to semantics;

[0048] Step 4: Use the RGA-SI algorithm to allocate red-green blocks to the semantic blocks of the LTP layer;

[0049] Step 5: At the receiving end, retransmissions are performed at the LTP layer and BP layer respectively, with the BP layer using the newly proposed BU retransmission scheme.

[0050] RGA-SI algorithm:

[0051] Step 1: Obtain the semantic data blocks of all headers and payloads of the LTP layer and divide all semantic blocks into two categories: unchanged and changed;

[0052] Step 2: Assign the changed parts as red-part blocks in the LTP layer, and assign the unchanged parts as green blocks;

[0053] Step 3: If the data assigned as a green block encounters an error during transmission, the erroneous green block is dynamically adjusted to a red block during retransmission to ensure reliable transmission.

[0054] See Figure 2 For the BU ARQ algorithm:

[0055] Step 1: Perform CRC check on the received bundle at the BP layer of the receiving end to determine if an error has occurred and store all data in the memory of the receiving end;

[0056] The second step is to retransmit the erroneous block but not the correct block. During each retransmission, the newly received semantic block is stored and the original erroneous semantic block in the memory is replaced until all blocks are reliably received or the maximum number of retransmissions has been reached.

[0057] See Figure 3 The two-layer retransmission ARQ strategy of BP and LTP layers (RGA-SI ARQ algorithm):

[0058] At the receiving end, the LTP layer first performs error detection, performs CRC check on red blocks and retransmits the erroneous blocks, and then hands them over to the BP layer to perform bundle update and retransmission of the BU algorithm until all data is reliably received or the maximum number of double-layer retransmissions is reached.

[0059] Based on the above algorithm, see Figure 4 The embodiment of the semantic-based DTN network BP and LTP cross-layer bundle transmission method includes the following steps:

[0060] At the sending end, the bundle data encapsulated from the original file is transferred from the BP layer to the LTP layer. The LTP layer adds an LTP header format and semantically segments the data into several semantic blocks. Based on the semantic data of the header and payload of each semantic block, the semantic blocks are divided into two categories: a first category of unchanging semantic blocks and a second category of changing semantic blocks. The first category of unchanging semantic blocks refers to the parts with relatively fixed data formats, i.e., the parts whose data formats remain consistent during deep learning-based training and actual testing. The second category of changing semantic blocks refers to the parts with highly random data formats, i.e., the new parts whose data formats differ from those during actual transmission and training.

[0061] At the receiving end, if an error occurs in the first type of semantic block during transmission, the erroneous first type of semantic block is dynamically adjusted to the second type of semantic block during retransmission at the LTP layer. The LTP layer performs the second type of semantic block verification on the received semantic block, retransmits it, and then hands it over to the BP layer. The BP layer verifies the received semantic block and stores it. The erroneous semantic block is retransmitted at the BP layer. During the retransmission process, the original erroneous semantic block in the memory is replaced with a newly received semantic block until all semantic blocks are reliably received or the maximum number of retransmissions has been reached.

[0062] The embodiment also includes transferring bundle data encapsulated from the original data from the BP layer to the LTP layer after grouping it according to different types.

[0063] Based on the semantic data in the header and payload of the semantic block, the semantic block is divided into a first category of semantic blocks with no changes and a second category of semantic blocks with changes, specifically including:

[0064] Obtain the semantic data of each packet header and payload of the LTP layer and divide the semantic blocks into a first type of semantic blocks with no changes and a second type of semantic blocks with changes;

[0065] The second type of semantic blocks that have changed are assigned as red blocks in the LTP layer, and the first type of semantic blocks that have not changed are assigned as green blocks;

[0066] If data assigned as a green block is corrupted during transmission, the corrupted green block will be dynamically reassigned to a red block during retransmission.

[0067] The LTP layer restores the received data into semantic blocks with LTP header format, and the BP layer restores the semantic blocks with LTP header format into bundle data and finally restores the original file.

[0068] Another embodiment illustrates a semantic-based DTN network BP and LTP cross-layer bundle transmission device, see [link to documentation]. Figure 5 The device 500 includes:

[0069] The sending end 510 is used to transfer the bundle data encapsulated by the original file from the BP layer to the LTP layer, add the LTP header format in the LTP layer and divide it into several semantic blocks according to semantics; and divide the semantic blocks into a first type of semantic blocks with no changes and a second type of semantic blocks with changes according to the semantic data of the header and payload of the semantic blocks.

[0070] The receiver 520 is used to dynamically adjust the erroneous first-type semantic block to the second-type semantic block during LTP layer retransmission if an error occurs in the first-type semantic block during transmission. The LTP layer performs second-type semantic block verification on the received semantic block, retransmits it, and then hands it over to the BP layer. The BP layer verifies the received semantic block and stores it. The erroneous semantic block is retransmitted in the BP layer. During the retransmission process, the original erroneous semantic block in the memory is replaced with a newly received semantic block until all semantic blocks are reliably received or the maximum number of retransmissions has been reached.

[0071] The transmitter 510 also includes grouping the bundle data encapsulated from the original data into different types and then transferring it from the BP layer to the LTP layer.

[0072] The sending end 510 divides the semantic block into a first type of semantic block with no changes and a second type of semantic block with changes based on the semantic data of the header and payload of the semantic block, specifically including:

[0073] Obtain the semantic data of each packet header and payload of the LTP layer and divide the semantic blocks into a first type of semantic blocks with no changes and a second type of semantic blocks with changes;

[0074] The second type of semantic blocks that have changed are assigned as red blocks in the LTP layer, and the first type of semantic blocks that have not changed are assigned as green blocks;

[0075] If data assigned as a green block is corrupted during transmission, the corrupted green block will be dynamically reassigned to a red block during retransmission.

[0076] The receiver 520 is also used to use the LTP layer to restore the received data into semantic blocks with LTP header format, and to use the BP layer to restore the semantic blocks with LTP header format into bundle data and finally restore the original file.

[0077] In addition to the above module, the device 500 may also include other components; however, since these components are not relevant to the contents of this disclosure, their illustrations and descriptions are omitted here.

[0078] Other specific working processes of the semantic-based DTN network BP and LTP cross-layer bundle transmission device 500 are described in the above-described embodiment of the semantic-based DTN network BP and LTP cross-layer bundle transmission method, and will not be repeated here.

[0079] Another embodiment illustrating that the system of the present invention can also be achieved by means of... Figure 6 The architecture of the computing device shown is used to implement this. Figure 6 The architecture of the computing device is shown. For example... Figure 6As shown, the computer system 610 includes a system bus 630, one or more CPUs 640, input / output 620, and memory 650. Memory 650 can store various data or files used by the computer for processing and / or communication, as well as program instructions executed by the CPU, including the semantic-based DTN network BP and LTP cross-layer bundle transmission method of the embodiment. Figure 6 The architecture shown is merely exemplary and should be adjusted according to actual needs when implementing different devices. Figure 6 One or more components in the system. The memory 650, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the semantic-based DTN network BP and LTP cross-layer bundle transmission method in this embodiment of the invention (e.g., the transmitting end 510 and receiving end 520 in the semantic-based DTN network BP and LTP cross-layer bundle transmission device 500). One or more CPUs 640 execute various functional applications and data processing of the system of the present invention by running the software programs, instructions, and modules stored in the memory 650, that is, implementing the above-described semantic-based DTN network BP and LTP cross-layer bundle transmission method, which includes:

[0080] At the sending end, the bundle data encapsulated by the original file is transferred from the BP layer to the LTP layer. The LTP layer adds the LTP header format and segments it into several semantic blocks according to semantics. Based on the semantic data of the header and payload of the semantic blocks, the semantic blocks are divided into a first type of semantic blocks with no changes and a second type of semantic blocks with changes.

[0081] At the receiving end, if an error occurs in the first type of semantic block during transmission, the erroneous first type of semantic block is dynamically adjusted to the second type of semantic block during retransmission at the LTP layer. The LTP layer performs the second type of semantic block verification on the received semantic block, retransmits it, and then hands it over to the BP layer. The BP layer verifies the received semantic block and stores it. The erroneous semantic block is retransmitted at the BP layer. During the retransmission process, the original erroneous semantic block in the memory is replaced with a newly received semantic block until all semantic blocks are reliably received or the maximum number of retransmissions has been reached.

[0082] Of course, the server provided in the embodiments of the present invention is not limited to executing the method operations described above, but can also execute related operations in the semantic-based DTN network BP and LTP cross-layer bundle transmission method provided in any embodiment of the present invention.

[0083] The memory 650 may primarily include a program storage area and a data storage area. The program storage area may store the operating system and at least one application program required for a given function; the data storage area may store data created based on terminal usage. Furthermore, the memory 650 may include high-speed random access memory and non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 650 may further include memory remotely configured relative to one or more CPUs 640, which can be connected to the device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0084] Input / output 620 can be used to receive input digital or character information, and to generate key signal inputs related to user settings and function control of the device. Input / output 620 may also include a display device such as a display screen.

[0085] This invention also provides a non-transitory computer-readable storage medium storing a computer program that, when executed by a processor, implements the semantic-based DTN network BP and LTP cross-layer bundle transmission method described in the above embodiments. The computer-readable storage medium of this invention can be any combination of one or more computer-readable media. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. For example, a computer-readable storage medium can be—but is not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0086] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0087] The program code contained on the storage medium can be transmitted using any suitable medium, including—but not limited to—wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0088] Furthermore, other specific operating procedures of a non-transitory computer-readable storage medium are described in the above-described embodiment of the semantic-based DTN network BP and LTP cross-layer bundle transmission method, and will not be repeated here.

[0089] To further demonstrate the effectiveness of the invention, the inventors conducted simulation experiments, including the following simulation performance indicators:

[0090] Semantic Quality (SQ): The product of the accuracy and completeness of data transmission at the semantic level, representing the quality of data transmission at the semantic level;

[0091]

[0092] In the above formula, s k This indicates the k-th data block transmitted, with a total of M data blocks transmitted. ρ(*) represents the number of correctly transmitted data blocks.

[0093] Retransmitted data volume: The amount of data that is repeatedly transmitted during the retransmission process.

[0094] Average file delivery latency: The total latency from when all data blocks are sent to when they are reliably received by the receiving end is the reliable delivery latency, and the average of the reliable delivery latencies of all data blocks is the average file delivery latency;

[0095]

[0096] In the above formula, Φ(s) k ) represents the k-th data block s k Reliable delivery delay.

[0097] Network effective throughput: The amount of effective data that is reliably received within a certain time interval, i.e., retransmitted data is not counted repeatedly;

[0098]

[0099] In the above formula This indicates the amount of valid data that has been reliably received.

[0100] In the simulation verification, the impact of the channel bit error rate (BER) on semantic quality is first investigated. If the BER is very low, transmission errors are almost nonexistent, and all data blocks can be effectively received. However, in long-distance space communication scenarios, the BER is extremely high, leading to degraded transmission performance. Figure 7 In general, as the channel bit error rate increases from 10⁻⁶ to 10⁻³, the semantic quality of all coding methods continuously decreases. However, the Semantic Block Combining Semantic Coding (SBSC) algorithm proposed in this invention consistently maintains the highest semantic quality, i.e., the best transmission performance. This is because the SBSC algorithm leverages prior data information from deep learning and transmits and recovers data at the semantic level, which is better than other bit-level data transmission algorithms. Figure 8 The maximum proportion of red data blocks in the LTP layer is used to reflect the quality of channel conditions; a higher proportion indicates better channel conditions and ensures reliable transmission of more data blocks. Therefore, as this proportion increases, the semantic quality of both the Random Red-Green Block Allocation (RA) scheme (the existing LTP layer strategy) and the newly proposed RGA-SI allocation scheme continuously improves. Furthermore, the higher the channel bit error rate, the worse the semantic quality of both methods. In all cases, the RGA-SI algorithm has higher semantic quality than the RA algorithm because it can allocate more transmission resources to data blocks with high semantic importance, thus improving the overall semantic reception quality.

[0101] Regarding the impact of the number of retransmissions on the amount of retransmitted data, the retransmission data volume metric reflects the performance of the retransmission protocol. A larger retransmission data volume indicates greater redundancy from repeated transmissions, meaning lower efficiency. For example... Figure 9 As shown, assuming a data packet is 2MB, the existing BP protocol requires a complete retransmission of the entire data packet each time, meaning that regardless of the number of retransmissions, the 2MB data size remains constant each time. The higher the channel error rate, the larger the amount of data that needs to be retransmitted. With the increase in the number of retransmissions, the newly proposed BP layer data retransmission protocol, the BU algorithm, can effectively reduce the amount of data that needs to be retransmitted. Furthermore, the BU algorithm, combined with the aforementioned SBSC algorithm, always achieves the minimum amount of retransmitted data in all situations.

[0102] The impact of channel bit error rate on average delivery delay and effective throughput. Figure 10 and Figure 11In general, a higher channel bit error rate results in a higher average delivery delay and a lower effective throughput. The newly proposed SBSC algorithm, combining BU and RGA-SI, consistently achieves the lowest average delivery delay and the highest effective throughput. Because deep learning-based semantic data transmission schemes possess the highest semantic quality, combining BU and RGA-SI algorithms further improves the transmission protocol at the BP and LTP layers, respectively, thereby enhancing system performance.

[0103] It should be noted that, when allocating red and green blocks at the LTP layer, although the data is a semantic block at the semantic level and is only divided into the two types of data blocks specified by the original LTP protocol, the allocation scheme of the LTP layer can be further designed to design new types of blocks in addition to red and green blocks to meet the requirements of semantic information.

[0104] Based on the technical solutions provided in the above embodiments, a semantic-based DTN network BP and LTP cross-layer bundle transmission method, apparatus, and storage medium are proposed to overcome the problems existing in current space information network transmission protocols in long-distance communication scenarios (such as satellite communication and deep space communication), such as excessive retransmissions leading to ultra-long latency and low throughput. As the communication distance increases, the packet loss rate increases exponentially, resulting in reduced accuracy during transmission and requiring multiple retransmissions to meet reliability requirements. Most existing methods for solving the problem of huge latency in long-distance communication mainly involve some improvement of the protocol within the existing DTN framework. However, due to the limitations of traditional bit-level communication in understanding the relationship between bit error rate and packet loss rate, the improvement effects are generally poor, especially when the bit error rate is extremely high. Therefore, to significantly reduce packet loss rate under high bit error rate conditions, thereby reducing latency and increasing throughput, this invention proposes a novel semantic-level data transmission scheme and improves existing BP and LTP transmission protocols. First, the semantic features of the original data to be transmitted are extracted, and semantic segmentation and encoding are performed based on these features. Transmission and reconstruction are then carried out at the semantic level. Using deep learning-based semantic communication technology, both the sending and receiving ends share a semantic knowledge base containing all semantic features. Segmentation and combination standards are established, and semantic feature-based transmission and retransmission strategies for the BP and LTP layers are developed to replace existing BP and LTP layer transmission protocols. This achieves reliable transmission with minimal retransmissions and retransmission data volume while reducing packet loss rate.

[0105] In this document, the terms “comprising,” “including,” or any other variations thereof are intended to cover non-exclusive inclusion, such that a step or method that comprises a list of elements includes not only those elements but also other elements not expressly listed or inherent to such a step or method.

[0106] The above description, in conjunction with specific preferred embodiments, provides a further detailed explanation of the present invention. It should not be construed that the specific implementation of the present invention is limited to these descriptions. For those skilled in the art, various simple deductions or substitutions can be made without departing from the concept of the present invention, and all such modifications and substitutions should be considered within the scope of protection of the present invention.

Claims

1. A semantic-based method for cross-layer bundle transmission of BP and LTP in DTN networks, characterized in that, The method includes the following steps: At the sending end, the bundle data encapsulated by the original file is transferred from the BP layer to the LTP layer. In the LTP layer, the LTP header format is added and the data is semantically segmented into several semantic blocks. Based on the semantic data of the header and payload of the semantic blocks, the semantic blocks are divided into a first type of semantic blocks with no change and a second type of semantic blocks with change. Here, "no change" means that the data format is fixed and "change" means that the data format is random. At the receiving end, during retransmission, the LTP layer dynamically adjusts the first type of semantic block that erroneous during transmission to the second type of semantic block; the LTP layer performs second type of semantic block verification on the received semantic block and retransmits it before handing it over to the BP layer, which verifies the received semantic block and stores it; the BP layer retransmits the erroneous semantic block, replacing the original erroneous semantic block in the memory with the newly received semantic block during the retransmission process, until all semantic blocks are reliably received or the maximum number of retransmissions has been reached.

2. The semantic-based DTN network BP and LTP cross-layer bundle transmission method according to claim 1, characterized in that, The method also includes transferring the bundle data, which is encapsulated from the original data, from the BP layer to the LTP layer after grouping it according to different types.

3. The semantic-based DTN network BP and LTP cross-layer bundle transmission method according to claim 1, characterized in that, The step of classifying the semantic blocks into a first category of semantic blocks with no changes and a second category of semantic blocks with changes based on the semantic data of the header and payload of the semantic blocks specifically includes: Obtain the semantic data of each packet header and payload of the LTP layer and divide the semantic blocks into a first type of semantic blocks with no changes and a second type of semantic blocks with changes; The second type of semantic blocks that have changed are assigned as red blocks in the LTP layer, and the first type of semantic blocks that have not changed are assigned as green blocks; If data assigned as a green block is corrupted during transmission, the corrupted green block will be dynamically reassigned to a red block during retransmission.

4. The semantic-based DTN network BP and LTP cross-layer bundle transmission method according to claim 1, characterized in that, At the receiving end, the LTP layer restores the received data into semantic blocks with LTP header format, and the BP layer restores the semantic blocks with LTP header format into bundle data and finally restores the original file.

5. A semantic-based DTN network BP and LTP cross-layer bundle transmission device, characterized in that, The device includes: The sending end is used to transfer the bundle data encapsulated by the original file from the BP layer to the LTP layer, add the LTP header format in the LTP layer and divide it into several semantic blocks according to semantics; according to the semantic data of the header and payload of the semantic blocks, the semantic blocks are divided into a first type of semantic blocks with no change and a second type of semantic blocks with change, wherein the no change refers to the data format being fixed and the change refers to the data format being random; At the receiving end, the LTP layer dynamically adjusts the first type of semantic blocks that erroneous during transmission to the second type of semantic blocks during LTP layer retransmission. The LTP layer performs second type of semantic block verification on the received semantic blocks and retransmits them before handing them over to the BP layer. The BP layer verifies the received semantic blocks and stores them. The BP layer retransmits the erroneous semantic blocks, replacing the original erroneous semantic blocks in the memory with newly received semantic blocks during the retransmission process, until all semantic blocks are reliably received or the maximum number of retransmissions has been reached.

6. The semantic-based DTN network BP and LTP cross-layer bundle transmission device according to claim 5, characterized in that, The transmitting end also includes grouping the bundle data encapsulated from the original data into different types and then transferring it from the BP layer to the LTP layer.

7. The semantic-based DTN network BP and LTP cross-layer bundle transmission device according to claim 5, characterized in that, The sending end classifies the semantic blocks into two categories based on the semantic data in the header and payload: a first category of semantic blocks with no changes and a second category of semantic blocks with changes. Specifically, this includes: Obtain the semantic data of each packet header and payload of the LTP layer and divide the semantic blocks into a first type of semantic blocks with no changes and a second type of semantic blocks with changes; The second type of semantic blocks that have changed are assigned as red blocks in the LTP layer, and the first type of semantic blocks that have not changed are assigned as green blocks; If data assigned as a green block is corrupted during transmission, the corrupted green block will be dynamically reassigned to a red block during retransmission.

8. The semantic-based DTN network BP and LTP cross-layer bundle transmission device according to claim 5, characterized in that, The receiving end is also used to use the LTP layer to restore the received data into semantic blocks with LTP header format, and to use the BP layer to restore the semantic blocks with LTP header format into bundle data and finally restore the original file.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the semantic-based DTN network BP and LTP cross-layer bundle transmission method as described in any one of claims 1 to 4.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, When the instructions are executed by the processor, they implement the semantic-based DTN network BP and LTP cross-layer bundle transmission method as described in any one of claims 1 to 4.

Images