A data processing method for edge access nodes and an edge access node

Abstract

This application discloses a data processing method for an edge access node and an edge access node. The method includes: acquiring multiple data streams; determining multiple periodic data streams among the multiple data streams, and the temporal characteristics corresponding to each periodic data stream; the temporal characteristics include the data transmission period and the I-frame transmission time; determining the conflict period corresponding to the multiple periodic data streams based on the data transmission period corresponding to each periodic data stream; determining whether the multiple periodic data streams have transmission conflicts with each other based on the conflict period, the I-frame transmission time corresponding to each periodic data stream, and a preset conflict rule, thereby obtaining conflict information; determining the transmission link corresponding to each periodic data stream based on the conflict information; and sending each periodic data stream to the corresponding transmission link.

Description

Technical Field

[0001] This application relates to the field of information technology, and in particular to a data processing method for an edge access node and an edge access node. Background Technology

[0002] The advancement of network technology and the proliferation of applications have led to a rapid increase in network traffic. Meanwhile, the business demands of these applications require stable transmission quality, thus increasing the requirements for server bandwidth and latency. To meet these demands, server providers typically deploy applications at the network edge. However, at the network edge access segment, multiple concurrent data streams still exist. For example, at network edge access nodes and aggregation edge nodes, data streams from multiple devices need to enter the network through these nodes, resulting in multiple concurrent data streams at the network edge access segment's exit point. Currently, when distributing data streams across multiple links at the network edge access segment's exit point, scheduling is primarily based on parameters such as average bandwidth requirements and latency. This approach leads to multiple data streams with peak traffic at the same time being transmitted on the same link, resulting in I-frame superposition, increased packet loss rate, and increased instantaneous bandwidth requirements at the network edge access segment. Summary of the Invention

[0003] In view of this, the embodiments of this application provide a data processing method for an edge access node and an edge access node, so as to at least solve the above-mentioned technical problems existing in the prior art.

[0004] According to a first aspect of this application, embodiments of this application provide a data processing method for an edge access node, including:

[0005] Acquire multiple data streams; identify multiple periodic data streams within the multiple data streams, and the temporal characteristics of each periodic data stream; the temporal characteristics include the data transmission period and the I-frame transmission time; based on the data transmission period of each periodic data stream, determine the conflict period of the multiple periodic data streams; based on the conflict period, the I-frame transmission time of each periodic data stream, and preset conflict rules, determine whether the multiple periodic data streams have transmission conflicts with each other, and obtain conflict information; based on the conflict information, determine the transmission link corresponding to each periodic data stream; send each periodic data stream to the corresponding transmission link.

[0006] Optionally, the multiple periodic data streams in the multiple data streams are determined, as well as the time-domain characteristics corresponding to each periodic data stream, including:

[0007] Multiple data streams are periodically sampled multiple times within a preset time period to obtain sampled data; based on the sampled data, the message information corresponding to each data stream within the preset time period is statistically analyzed. The message information includes the time offset, message length, fragmentation information, and quintuple information of each message; based on the message information, multiple periodic data streams in the multiple data streams are determined, as well as the time domain characteristics corresponding to each periodic data stream.

[0008] Optionally, based on message information, multiple periodic data streams in the multiple data streams are determined, as well as the time-domain characteristics corresponding to each periodic data stream, including:

[0009] The message information is processed based on the periodic data stream identification model to determine whether each data stream in the multi-channel data stream is a periodic data stream, as well as the data transmission period and I-frame transmission time corresponding to the periodic data stream, thereby obtaining the multiple periodic data streams in the multi-channel data stream and the time-domain characteristics corresponding to each periodic data stream.

[0010] Optionally, based on the conflict period, the I-frame transmission time corresponding to each periodic data stream, and preset conflict rules, it is determined whether multiple periodic data streams have transmission conflicts with each other, and conflict information is obtained, including:

[0011] Within the conflict period, each time slot is traversed, and based on the I-frame transmission time corresponding to each periodic data stream, the periodic data streams existing simultaneously within the time slot are determined to obtain conflict information; or

[0012] Within the conflict period, based on the I-frame transmission time corresponding to each periodic data stream, each periodic data stream is traversed to determine other periodic data streams that coexist with the periodic data stream within the target time period corresponding to the I-frame transmission time of the periodic data stream, thereby obtaining conflict information.

[0013] Optionally, based on collision information, the transmission link corresponding to each periodic data stream is determined, including:

[0014] For each periodic data stream allocated, determine the remaining bandwidth of each transmission link and the periodic data streams currently being transmitted on each transmission link; based on the traffic volume of each periodic data stream, determine the target periodic data stream for this allocation; based on collision information, the remaining bandwidth of each transmission link, the periodic data streams currently being transmitted on each transmission link, and the bandwidth of the target periodic data stream, determine the transmission link corresponding to the target periodic data stream; until there are no available periodic data streams or no transmission links that meet the allocation conditions.

[0015] Optionally, the data processing method for edge access nodes also includes:

[0016] For any remaining unallocated periodic data stream, based on the remaining time slots of each transmission link, determine the adjustment range for adjusting the I-frame transmission time or data transmission period of the periodic data stream; based on the adjustment range of the I-frame transmission time or data transmission period, send a notification to the source end of the corresponding periodic data stream to adjust the I-frame transmission time or data transmission period of the periodic data stream at the source end.

[0017] Optionally, the data processing method for edge access nodes also includes:

[0018] Periodic data streams with changing time-domain characteristics are detected; conflict information is updated based on the changing time-domain characteristics; and transmission links are reallocated to periodic data streams with changing time-domain characteristics based on the updated conflict information.

[0019] Optionally, the data processing method for edge access nodes also includes:

[0020] Identify the time period of low-value packets in each periodic data stream within the data transmission cycle; mark the target packets in the low-value packet time period of each periodic data stream.

[0021] Optionally, the data processing method for edge access nodes also includes:

[0022] Determine if the transmission link is overloaded corresponding to the periodic data stream; discard the target packets in the periodic data stream.

[0023] According to a second aspect of this application, embodiments of this application provide an edge access node, including:

[0024] Transceiver and processor;

[0025] Transceivers are used to acquire multiple data streams and send each periodic data stream to the corresponding transmission link;

[0026] The processor is used to determine multiple periodic data streams in a multi-channel data stream, and the time-domain characteristics of each periodic data stream; the time-domain characteristics include the data transmission period and the I-frame transmission time; based on the data transmission period corresponding to each periodic data stream, the conflict period corresponding to the multiple periodic data streams is determined; based on the conflict period, the I-frame transmission time corresponding to each periodic data stream, and the preset conflict rules, it is determined whether the multiple periodic data streams have transmission conflicts with each other, and conflict information is obtained; based on the conflict information, the transmission link corresponding to each periodic data stream is determined.

[0027] The data processing method and edge access node provided in this application embodiment acquire multiple data streams; determine multiple periodic data streams in the multiple data streams, and the time domain characteristics corresponding to each periodic data stream; the time domain characteristics include the data transmission period and the I-frame transmission time; based on the data transmission period corresponding to each periodic data stream, determine the conflict period corresponding to the multiple periodic data streams; based on the conflict period, the I-frame transmission time corresponding to each periodic data stream, and the preset conflict rules, determine whether the multiple periodic data streams have transmission conflicts with each other, and obtain conflict information; based on the conflict information, determine the transmission link corresponding to each periodic data stream; and send each periodic data stream to the corresponding transmission link. In this way, multiple periodic data streams with peak values ​​at the same time can be distributed to different links for transmission, I-frames will not overlap, reducing the peak conflict of multiple periodic data streams, resulting in a low packet loss rate, and without increasing the instantaneous bandwidth requirements of the network edge access segment.

[0028] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0029] Figure 1 This is a flowchart illustrating a data processing method for an edge access node according to an embodiment of this application;

[0030] Figure 2 This is a schematic diagram of an edge access node scenario in an embodiment of this application;

[0031] Figure 3 This is a schematic diagram illustrating the transmission of multiple periodic data streams to their corresponding transmission links in an embodiment of this application.

[0032] Figure 4 This is a schematic diagram illustrating the formation process of the periodic data stream identification model in this application embodiment;

[0033] Figure 5 This is a flowchart illustrating another data processing method for an edge access node in this application embodiment;

[0034] Figure 6 This is a schematic diagram of the hardware structure of an edge access node in an embodiment of this application;

[0035] Figure 7 This is a schematic diagram of the hardware structure of another edge access node in this application embodiment. Detailed Implementation

[0036] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0037] This application provides a data processing method for edge access nodes, such as... Figure 1 As shown, it includes:

[0038] S101, acquire multiple data streams;

[0039] Specifically, multiple data streams from multiple sources need to access the network through edge access nodes; therefore, these multiple data streams flow into the edge access nodes. The edge nodes then acquire these multiple data streams.

[0040] In this embodiment, the data stream includes, but is not limited to, at least one of video stream, live stream, and industrial control stream.

[0041] In this embodiment, the edge access node includes, but is not limited to, at least one of the access nodes of a multi-access edge computing (MEC) and the aggregation node of a MEC. For example, such as Figure 2 As shown, the live streams from each broadcaster's end are connected to the live streaming platform and MEC nodes through the MEC access node (network access edge) and the MEC aggregation node (aggregation edge MEC). The MEC node forwards the live streams from each broadcaster's end to the viewer's end. Therefore, both the network access edge and the aggregation edge MEC are edge access nodes.

[0042] S102, determine the multiple periodic data streams in the multiple data streams, and the time domain characteristics corresponding to each periodic data stream; the time domain characteristics include the data transmission period and the I-frame transmission time.

[0043] Specifically, the inventors of this application discovered that video traffic, live streaming traffic, and industrial control traffic constitute the vast majority of all network traffic, and that these traffic largely exhibit periodic patterns. Therefore, the inventors conceived of a method to organize the multiple data streams acquired by the edge access node, identify periodic data streams, and, based on the transmission period of these periodic data streams and the I-frame transmission time, distribute periodic data streams that arrive at the edge access node simultaneously with I-frames to different transmission links. This prevents multiple data streams with peak values ​​at the same time from being transmitted on the same link, avoiding transmission conflicts, preventing I-frame overlap, reducing packet loss rate, and minimizing instantaneous bandwidth requirements on the transmission links. Therefore, after acquiring multiple data streams, it is possible to determine the multiple periodic data streams within them, as well as the temporal characteristics of each periodic data stream.

[0044] S103, based on the data transmission period corresponding to each periodic data stream, determine the conflict period corresponding to multiple periodic data streams.

[0045] In this embodiment, if a periodic data stream needs to be proportionally distributed to multiple transmission links, then the conflict period is calculated based on multiple periodic data streams.

[0046] In this embodiment, the conflict period is the period for determining whether multiple periodic data streams conflict with each other during transmission. A transmission conflict mainly refers to the moment when multiple periodic data streams transmit I-frames simultaneously.

[0047] In one implementation, the common multiple, such as the least common multiple, of the data transmission periods of multiple periodic data streams can be determined based on the data transmission period corresponding to each periodic data stream, thereby obtaining the conflict period corresponding to the multiple periodic data streams.

[0048] S104, based on the conflict period, the I-frame transmission time corresponding to each periodic data stream, and the preset conflict rules, determine whether multiple periodic data streams have transmission conflicts with each other, and obtain conflict information.

[0049] In one implementation, the conflict rule can be to divide the conflict period into multiple time periods. If two or more periodic data streams exist simultaneously in the same time period, it is determined that the two or more periodic data streams have a transmission conflict with each other.

[0050] In one implementation, since transmission time may fluctuate due to source-end buffering during traffic transmission, the scope of transmission collision detection can be appropriately increased. The collision rule can be that within a collision period, if other periodic data streams exist within a certain time frame before and after the I-frame transmission time of a periodic data stream, then that periodic data stream and the other periodic data streams are considered to have a transmission collision. The time frame before and after the I-frame transmission time forms the target time period. The duration of the target time period is longer than the duration of the time period in the above implementation.

[0051] Specifically, for example, if there are 6 periodic data streams, namely periodic data stream 1, periodic data stream 2, periodic data stream 3, periodic data stream 4, periodic data stream 5, and periodic data stream 6, then one detection result of transmission collision, i.e., collision information, can be shown in Table 1, where mutual transmission collisions are marked as C. Table 1 also lists the total number of collisions between each periodic data stream and other periodic data streams.

[0052] Table 1

[0053] Periodic data stream 1 2 3 4 5 6 Total number of conflicts 1 0 C 1 2 0 C C 2 3 0 0 4 0 0 5 0 0 6 0 0

[0054] S105, based on the collision information, determine the transmission link corresponding to each periodic data stream.

[0055] In this embodiment, since the conflict information can characterize which periodic data streams have transmission conflicts, multiple periodic data streams can be allocated to different transmission links based on the conflict information, so that there are no periodic data streams with transmission conflicts on each transmission link. As a result, the I-frames of the periodic data streams transmitted in each transmission link will not overlap, the packet loss rate is low, and the instantaneous bandwidth requirement of the transmission link will not increase.

[0056] In a specific embodiment, as shown in Table 1 above, periodic data stream 1 and periodic data stream 4 cannot be assigned to the same transmission link, and periodic data streams 2, 5, and 6 cannot be assigned to the same transmission link. If there are three transmission links, Link1, Link2, and Link3, then periodic data streams 2, 5, and 6 can be assigned to Link1, Link2, and Link3 respectively. Then, periodic data stream 1 is assigned to Link1, periodic data stream 4 to Link2, and periodic data stream 3 to Link3.

[0057] S106 sends each periodic data stream to the corresponding transmission link.

[0058] In this embodiment, once the transmission link corresponding to each periodic data stream is determined, each periodic data stream can be sent to the corresponding transmission link in the order in which multiple periodic data streams are received.

[0059] In a specific embodiment, for the six periodic data streams in Table 1 above, periodic data stream 2 (flow2), periodic data stream 5 (flow5), and periodic data stream 6 (flow6) have been assigned to Link1, Link2, and Link3, respectively. Periodic data stream 1 (flow1) is assigned to Link1, periodic data stream 4 (flow4) is assigned to Link2, and periodic data stream 3 (flow3) is assigned to Link3. Then, as follows... Figure 3 As shown, periodic data streams 1 and 2 can be sent to Link 1, periodic data streams 4 and 5 can be sent to Link 2, and periodic data streams 3 and 6 can be sent to Link 2. From Figure 3 As can be seen, the periodic data streams on each transmission link do not have transmission conflicts with each other.

[0060] The data processing method for edge access nodes provided in this application involves: acquiring multiple data streams; determining multiple periodic data streams within the multiple data streams, and the temporal characteristics corresponding to each periodic data stream; the temporal characteristics include the data transmission period and the I-frame transmission time; determining the conflict period corresponding to the multiple periodic data streams based on the data transmission period corresponding to each periodic data stream; determining whether the multiple periodic data streams have transmission conflicts based on the conflict period, the I-frame transmission time corresponding to each periodic data stream, and preset conflict rules, thereby obtaining conflict information; determining the transmission link corresponding to each periodic data stream based on the conflict information; and sending each periodic data stream to the corresponding transmission link. In this way, multiple periodic data streams with peak values ​​at the same time can be distributed to different links for transmission, preventing I-frame overlap, reducing peak conflicts of multiple periodic data streams, resulting in a low packet loss rate, and without increasing the instantaneous bandwidth requirements of the network edge access segment.

[0061] In an optional embodiment, step S102, therefore, determines the multiple periodic data streams in the multiple data streams, and the time-domain characteristics corresponding to each periodic data stream, including:

[0062] Multiple data streams are periodically sampled multiple times within a preset time period to obtain sampled data; based on the sampled data, the message information corresponding to each data stream within the preset time period is statistically analyzed. The message information includes the time offset, message length, fragmentation information, and quintuple information of each message; based on the message information, multiple periodic data streams in the multiple data streams are determined, as well as the time domain characteristics corresponding to each periodic data stream.

[0063] In practice, each data stream can be sampled continuously a preset number of times (e.g., 2000 times) within a preset duration (e.g., 2000 ms) according to a sampling period t (e.g., 1 ms) to obtain the sampled data for each data stream. Then, the sampled data for each data stream is statistically analyzed to obtain the time offset, message length, fragmentation information, and 5-tuple information for each packet within the preset duration, thus obtaining the packet information for each data stream. The 5-tuple information includes the source IP address, source port, destination IP address, destination port, and transport layer protocol.

[0064] In one implementation, based on message information, mathematical processing methods can be used to determine multiple periodic data streams in a multi-channel data stream, as well as the time-domain characteristics corresponding to each periodic data stream.

[0065] Specifically, based on the five-tuple information and message length of each message in each data stream, it can be determined whether there is a periodic pattern in the messages in the sampled data. If there is a periodic pattern in the messages, the data stream is determined to be a periodic data stream.

[0066] For each periodic data stream, the time offset, message length, and fragmentation information of each message are processed using the Discrete Fourier Equation to obtain the data transmission period and I-frame transmission time of that periodic data stream.

[0067] In another implementation, based on message information, AI can be used to determine multiple periodic data streams in a multi-stream data stream, as well as the time-domain characteristics of each periodic data stream.

[0068] Specifically, based on message information, multiple periodic data streams within a multi-stream data stream are determined, along with the time-domain characteristics corresponding to each periodic data stream, including:

[0069] The message information is processed based on the periodic data stream identification model to determine whether each data stream in the multi-channel data stream is a periodic data stream, as well as the data transmission period and I-frame transmission time corresponding to the periodic data stream, thereby obtaining the multiple periodic data streams in the multi-channel data stream and the time-domain characteristics corresponding to each periodic data stream.

[0070] In this implementation, a periodic data stream recognition model can be pre-trained. During the training of the periodic data stream recognition model, such as... Figure 4 As shown, sample acquisition can be performed first, that is, multiple sample periodic data streams are obtained from multiple sample data streams sent by multiple devices, as well as the sample message information corresponding to each sample periodic data stream. The sample message information includes the time offset, message length, fragmentation information, and quintuple information of each sample message within a preset duration corresponding to the sample periodic data stream.

[0071] Then, at the network access edge, such as the access edge MEC, the collected samples, including sample message information corresponding to each periodic data stream, are uploaded to the aggregation edge MEC or the central cloud to train the neural network. The training output includes whether it is a periodic data stream, the data transmission period of the periodic data stream, and the I-frame transmission time. The trained neural network is the periodic data stream recognition model. Then, the aggregation edge MEC or the central cloud distributes the trained periodic data stream model to the access edge MEC.

[0072] The MEC at the aggregation edge uploads the collected samples, including sample message information corresponding to each periodic data stream, to the central cloud to train the neural network. The training output includes whether it is a periodic data stream, the data transmission period of the periodic data stream, and the I-frame transmission time. The trained neural network is the periodic data stream recognition model. Then, the central cloud distributes the trained periodic data stream model back to the MEC at the aggregation edge.

[0073] In practical applications, whether it's an access edge MEC or an aggregation edge MEC, a periodic data stream identification model can be used to process the message information of each data stream, outputting whether each data stream is a periodic data stream, and outputting the data transmission period and I-frame transmission time for periodic data streams. This allows for the identification of multiple periodic data streams within a multi-stream dataset and the corresponding temporal characteristics of each periodic data stream.

[0074] In this implementation, the periodic data stream and its temporal characteristics are determined by a model, without the need for manual intervention or complex deep packet inspection, making it fast and accurate.

[0075] In this embodiment, since the message information of each data stream within a preset time period can reflect whether there is a periodic pattern in the data stream, the sampled data is obtained by periodically sampling multiple times within the preset time period. Based on the sampled data, the message information corresponding to each data stream within the preset time period is statistically analyzed. The message information includes the time offset, message length, fragmentation information, and quintuple information of each message. Based on the message information, multiple periodic data streams in the multiple data streams are determined, as well as the time domain characteristics corresponding to each periodic data stream. This allows for the accurate filtering of periodic data streams from the multiple data streams, and the acquisition of the data transmission period and I-frame transmission time of the periodic data streams.

[0076] In an optional embodiment, step S104, based on the conflict period, the I-frame transmission time corresponding to each periodic data stream, and a preset conflict rule, determines whether multiple periodic data streams have transmission conflicts with each other, and obtains conflict information, including:

[0077] Within the conflict period, each time slot is traversed, and based on the I-frame transmission time corresponding to each periodic data stream, the periodic data streams existing simultaneously within the time slot are determined to obtain conflict information; or

[0078] Within the conflict period, based on the I-frame transmission time corresponding to each periodic data stream, each periodic data stream is traversed to determine other periodic data streams that coexist with the periodic data stream within the target time period corresponding to the I-frame transmission time of the periodic data stream, thereby obtaining conflict information.

[0079] In specific implementation, if the conflict rule is to divide the conflict period into multiple time periods, and if two or more periodic data streams exist simultaneously in the same time period, then it is determined that the two or more periodic data streams have a transmission conflict with each other. Then, in the conflict period, each time period can be traversed to determine whether there is an I-frame transmission time for two or more periodic data streams in the same time period. If so, the two or more periodic data streams are periodic data streams that conflict with each other. The conflict information is obtained by counting the periodic data streams that conflict with each other in all time periods.

[0080] If the conflict rule is that within a conflict period, if other periodic data streams exist within a certain time frame before and after the I-frame transmission time of a periodic data stream, then that periodic data stream and those other periodic data streams are considered to have a transmission conflict. The time frame before and after the I-frame transmission time forms the target time period. Therefore, within the conflict period, based on the I-frame transmission time corresponding to each periodic data stream, iterate through each periodic data stream to determine if there are I-frame transmission times of other data streams within the target time period corresponding to the I-frame transmission time of that periodic data stream. If so, then that periodic data stream and the other periodic data streams are considered to have a transmission conflict. The conflicting periodic data streams for each periodic data stream are counted to obtain the conflict information.

[0081] In this embodiment, the main reason for the transmission conflict between the two periodic data streams is that the I-frames of the two periodic data streams need to be transmitted at the same time or in the same time period. Therefore, by traversing each time period or the target time period of each periodic data stream within the conflict period, based on the I-frame transmission time corresponding to each periodic data stream, it is possible to accurately determine which periodic data streams have transmission conflicts with each other.

[0082] In an optional embodiment, step S105, determining the transmission link corresponding to each periodic data stream based on collision information, includes:

[0083] For each periodic data stream allocated, determine the remaining bandwidth of each transmission link and the periodic data streams currently being transmitted on each transmission link; based on the traffic volume of each periodic data stream, determine the target periodic data stream for this allocation; based on collision information, the remaining bandwidth of each transmission link, the periodic data streams currently being transmitted on each transmission link, and the bandwidth of the target periodic data stream, determine the transmission link corresponding to the target periodic data stream; until there are no available periodic data streams or no transmission links that meet the allocation conditions.

[0084] In practice, the remaining bandwidth of each transmission link can be calculated first and sorted from highest to lowest. Then, the periodic data streams to be allocated can be sorted from highest to lowest traffic volume. Next, the transmission link with the largest remaining bandwidth can be selected, and from the periodic data streams to be allocated, a periodic data stream that does not conflict with the periodic data streams already transmitted on that transmission link, has the largest traffic volume, and has a bandwidth lower than the remaining bandwidth of that transmission link can be allocated to that transmission link. After allocation, the periodic data stream is removed from the list of periodic data streams to be allocated. The above steps are repeated until there are no more periodic data streams to be allocated, or no transmission link that meets the allocation conditions.

[0085] In some implementations, if there are unallocated periodic data streams, for any remaining unallocated periodic data stream, based on the remaining time slots of each transmission link, the adjustment range for adjusting the I-frame transmission time or data transmission period of the periodic data stream is determined; based on the adjustment range of the I-frame transmission time or data transmission period, a notification is sent to the source end of the corresponding periodic data stream to adjust the I-frame transmission time or data transmission period of the periodic data stream at the source end.

[0086] In practice, for any remaining unallocated periodic data stream f, the following steps can be taken on each transmission link: based on the remaining time slots of the periodic data streams already using this transmission link, starting from the I-frame transmission time, for n data transmission cycles, evaluate whether the periodic data stream f would conflict with other periodic data streams on that transmission link if it were to adjust its duration backward by a preset time starting from this time, and calculate the conflict number. The duration a with the smallest conflict number among the n evaluation results is then selected.

[0087] Then, on each transmission link, based on the remaining time slots of the periodic data streams that have used this transmission link, attempt to select a period from the range [nx, n+y] for the data transmission period of the periodic data stream f. Evaluate whether the periodic data stream f using this period as its data transmission period conflicts with other periodic data streams on the same transmission link, and calculate the conflict number. Select the smallest period t' among the n non-conflicting evaluation results.

[0088] Then, the source end is notified to adjust the data transmission period or the I-frame transmission time. The adjustment range for the I-frame transmission time is: an adjustment of duration 'a'. The adjustment range for the data transmission period is 't'.

[0089] In this implementation, the values ​​of n, x, and y can be configured manually or obtained through a periodic data stream identification model.

[0090] In this embodiment, since the adjustment range for adjusting the I-frame transmission time or data transmission period of the periodic data stream is determined based on the remaining time slots of each transmission link, the source end can successfully allocate the I-frame transmission time or data transmission period of the periodic data to the transmission link after adjusting the adjustment range based on the I-frame transmission time or data transmission period, without conflicting with other periodic data streams on the transmission link.

[0091] In this embodiment, when allocating each periodic data stream, not only are conflicting periodic data streams of the periodic data stream considered, but also the traffic volume of each periodic data stream, the remaining bandwidth of each transmission link, and the bandwidth of each periodic data stream. This allows for priority allocation of periodic data streams with large traffic volumes, thereby improving the transmission efficiency of each transmission link.

[0092] In an optional embodiment, the data processing method for the edge access node further includes:

[0093] Periodic data streams with changing time-domain characteristics are detected; conflict information is updated based on the changing time-domain characteristics; and transmission links are reallocated to periodic data streams with changing time-domain characteristics based on the updated conflict information.

[0094] In practice, the temporal characteristics of each periodic data stream can be monitored at a preset period to determine whether these characteristics have changed. Specifically, the temporal characteristics of each periodic data stream can be detected using a periodic data stream identification model at a preset period to determine whether these characteristics have changed. For periodic data streams whose data transmission period and I-frame transmission time change, they are excluded from the existing transmission links to reduce bandwidth consumption, and then added to the list of periodic data streams to be allocated, allowing for a reallocation of transmission links.

[0095] In this embodiment, by monitoring the time-domain characteristics of periodic data streams, the transmission links of periodic data streams whose time-domain characteristics change can be reallocated in a timely manner to prevent transmission conflicts of periodic data streams on the transmission links.

[0096] In an optional embodiment, such as Figure 5 As shown, the data processing method for edge access nodes also includes:

[0097] S1021, determine the time period of low-value messages for each periodic data stream within the data transmission cycle;

[0098] S1022, mark the target packets in the low-value packet time period of each periodic data stream.

[0099] In this embodiment, the low-value message time period can be configured manually or obtained through a periodic data stream identification model.

[0100] In this embodiment, the priority of the target message can also be marked, and the total number of target messages can also be calculated.

[0101] In some implementations, such as Figure 5 As shown, the data processing method for edge access nodes also includes:

[0102] S107, determine the overload of the transmission link corresponding to the periodic data stream.

[0103] S108, Discard the target message in the periodic data stream.

[0104] In practice, for S108, the overload ratio can be calculated, and then target packets in the periodic data stream can be discarded according to the priority of the target packets and the overload ratio.

[0105] In this embodiment, by marking target packets in low-value time periods in each periodic data stream, the load on the transmission link can be reduced by discarding target packets when the transmission link is overloaded, without losing important packets in the periodic data stream.

[0106] This application provides an edge access node, such as... Figure 6 As shown, it includes:

[0107] Transceiver 800 and processor 801;

[0108] The transceiver 800 is used to acquire multiple data streams and send each periodic data stream to the corresponding transmission link;

[0109] The processor 801 is used to determine multiple periodic data streams in a multi-channel data stream, and the time-domain characteristics corresponding to each periodic data stream; the time-domain characteristics include the data transmission period and the I-frame transmission time; based on the data transmission period corresponding to each periodic data stream, the conflict period corresponding to the multiple periodic data streams is determined; based on the conflict period, the I-frame transmission time corresponding to each periodic data stream, and the preset conflict rules, it is determined whether the multiple periodic data streams have transmission conflicts with each other, and conflict information is obtained; based on the conflict information, the transmission link corresponding to each periodic data stream is determined.

[0110] In some embodiments of this application, a schematic block diagram of the edge access node is shown as follows: Figure 7 As shown. Edge access nodes are intended to represent various forms of digital computers, such as laptops, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. Edge access nodes can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present application described and / or claimed herein.

[0111] like Figure 7 As shown, the edge access node includes a transceiver 800, which can acquire multiple data streams and send each periodic data stream to the corresponding transmission link. The edge access node also includes a processor 801, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 802 or a computer program loaded from storage unit 808 into random access memory (RAM) 803. The RAM 803 can also store various programs and data required for the operation of the edge access node. The processor 801, ROM 802, and RAM 803 are interconnected via bus 804. An input / output (I / O) interface 805 is also connected to bus 804.

[0112] Multiple components in the edge access node are connected to I / O interface 805, including: transceiver 800; input unit 806, such as keyboard, mouse, etc.; output unit 807, such as various types of displays, speakers, etc.; storage unit 808, such as disk, optical disk, etc.; and communication unit 809, such as network interface card, modem, wireless communication transceiver, etc. Communication unit 809 allows the edge access node to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0113] Processor 801 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 801 performs the various methods and processes described above, such as the data processing method for an edge access node. For example, in some embodiments, the data processing method for an edge access node can be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 808. In some embodiments, part or all of the computer program can be loaded and / or installed on the edge access node via ROM 802 and / or communication unit 809. When the computer program is loaded into RAM 803 and executed by processor 801, one or more steps of the data processing method for an edge access node described above can be performed. Alternatively, in other embodiments, processor 801 can be configured to perform the data processing method for an edge access node by any other suitable means (e.g., by means of firmware).

[0114] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0115] The program code used to implement the methods of this application may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing device, such that when executed by the processor or controller, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0116] In the context of this application, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0117] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0118] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0119] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0120] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this application can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this application can be achieved, and this is not limited herein.

[0121] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "a plurality of" means two or more, unless otherwise explicitly specified.

[0122] The above description is merely a specific embodiment of this application, but the scope of protection of this application 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 this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A data processing method for an edge access node, comprising: Acquire multiple data streams; Determining multiple periodic data streams within a multi-stream data stream, and the temporal characteristics corresponding to each periodic data stream, includes: periodically sampling the multiple data streams multiple times within a preset duration to obtain sampled data; statistically analyzing the message information corresponding to each data stream within the preset duration based on the sampled data, wherein the message information includes the time offset, message length, fragmentation information, and 5-tuple information of each message; and determining multiple periodic data streams within the multiple data streams, and the temporal characteristics corresponding to each periodic data stream based on the message information; wherein the temporal characteristics include the data transmission period and the I-frame transmission time. Based on the data transmission period corresponding to each of the periodic data streams, the conflict period corresponding to multiple of the periodic data streams is determined. Based on the conflict period, the I-frame transmission time corresponding to each periodic data stream, and the preset conflict rules, it is determined whether multiple periodic data streams have transmission conflicts with each other, and conflict information is obtained. Based on the conflict information, the transmission link corresponding to each of the periodic data streams is determined; Each of the periodic data streams is sent to the corresponding transmission link.

2. The data processing method for an edge access node according to claim 1, comprising determining multiple periodic data streams among the multiple data streams based on the message information, and the time-domain characteristics corresponding to each periodic data stream, including: The message information is processed based on a periodic data stream identification model to determine whether each of the multiple data streams is a periodic data stream, as well as the data transmission period and I-frame transmission time corresponding to the periodic data stream, thereby obtaining multiple periodic data streams in the multiple data streams and the time-domain features corresponding to each periodic data stream.

3. The data processing method for the edge access node according to claim 1, based on the conflict period, the I-frame transmission time corresponding to each of the periodic data streams, and a preset conflict rule, determines whether multiple periodic data streams have transmission conflicts with each other, and obtains conflict information, including: Within the conflict period, each time period is traversed, and based on the I-frame transmission time corresponding to each periodic data stream, the periodic data streams that exist simultaneously within the time period are determined to obtain conflict information. or Within the conflict period, based on the I-frame transmission time corresponding to each periodic data stream, each periodic data stream is traversed to determine other periodic data streams that coexist with the periodic data stream within the target time period corresponding to the I-frame transmission time of the periodic data stream, thereby obtaining conflict information.

4. The data processing method for an edge access node according to claim 1, wherein based on the conflict information, the transmission link corresponding to each of the periodic data streams is determined, comprising: For each periodic data stream allocated, the remaining bandwidth of each transmission link and the periodic data stream currently transmitted on each transmission link are determined. Based on the flow rate of each periodic data, determine the target periodic data flow for the current allocation; Based on the conflict information, the remaining bandwidth of each transmission link, the periodic data streams currently transmitted on each transmission link, and the bandwidth of the target periodic data stream, the transmission link corresponding to the target periodic data stream is determined; until there are no available periodic data streams or no transmission links that meet the allocation conditions.

5. The data processing method for the edge access node according to claim 4 further includes: For any remaining unallocated periodic data stream, based on the remaining time slots of each transmission link, determine the adjustment range for adjusting the I-frame transmission time or data transmission period of the periodic data stream. Based on the adjustment range of the I-frame transmission time or data transmission period, a notification is sent to the source end of the corresponding periodic data stream to adjust the I-frame transmission time or data transmission period of the periodic data stream at the source end.

6. The data processing method for the edge access node according to claim 1 further includes: Periodic data streams with changing time-domain characteristics were detected; The conflict information is updated based on the changing temporal characteristics; Based on updated conflict information, transmission links are reallocated for periodic data streams whose time-domain characteristics change.

7. The data processing method for the edge access node according to claim 1 further includes: Determine the time period of low-value messages for each of the periodic data streams within the data transmission cycle; The target packets in the low-value packet time period of each of the periodic data streams are marked.

8. The data processing method for the edge access node according to claim 7 further includes: Determine the overload of the transmission link corresponding to the periodic data stream; Discard the target message in the periodic data stream.

9. An edge access node, comprising: Transceiver and processor; The transceiver is used to acquire multiple data streams and send each periodic data stream to the corresponding transmission link; The processor is used to determine multiple periodic data streams in a multi-channel data stream, and the temporal characteristics corresponding to each periodic data stream, including: periodically sampling the multiple data streams multiple times within a preset duration to obtain sampled data; statistically analyzing the message information corresponding to each data stream within the preset duration based on the sampled data, the message information including the time offset, message length, fragmentation information, and 5-tuple information of each message; determining the multiple periodic data streams in the multi-channel data stream based on the message information, and the temporal characteristics corresponding to each periodic data stream; the temporal characteristics including the data transmission period and the I-frame transmission time; determining the conflict period corresponding to the multiple periodic data streams based on the data transmission period corresponding to each periodic data stream; determining whether the multiple periodic data streams have transmission conflicts with each other based on the conflict period, the I-frame transmission time corresponding to each periodic data stream, and a preset conflict rule, to obtain conflict information; and determining the transmission link corresponding to each periodic data stream based on the conflict information.

Images