CN117377102A

CN117377102A - Scheduling policy adjustment method, device, electronic equipment and storage medium

Info

Publication number: CN117377102A
Application number: CN202311320797.9A
Authority: CN
Inventors: 张志荣
Original assignee: China Telecom Technology Innovation Center; China Telecom Corp Ltd
Current assignee: China Telecom Technology Innovation Center; China Telecom Corp Ltd
Priority date: 2023-10-12
Filing date: 2023-10-12
Publication date: 2024-01-09

Abstract

The embodiment of the disclosure provides a scheduling policy adjustment method, a scheduling policy adjustment device, electronic equipment and a storage medium, and relates to the field of mobile communication. The method comprises the following steps: acquiring a TSN data packet to be processed corresponding to a TSN service, and acquiring characteristic information of the TSN data packet to be processed; inputting the TSN data packet to be processed and the characteristic information of the TSN data packet to be processed into a flow prediction model, outputting flow change dynamic information corresponding to the TSN data packet to be processed, and generating prediction information of TSN service according to the flow change dynamic information; and adjusting the scheduling strategy of the TSN service according to the prediction information of the TSN service. The method can combine the prediction information of the TSN business with the adjustment of the scheduling strategy, and the scheduling strategy can be adaptively adjusted according to different requirements on time delay, jitter, reliability and the like in different TSN business scenes.

Description

Scheduling policy adjustment method, device, electronic equipment and storage medium

Technical Field

The present disclosure relates to the field of mobile communications, and in particular, to a scheduling policy adjustment method, a scheduling policy adjustment apparatus, an electronic device, and a computer-readable storage medium.

Background

TSN (Time-Sensitive Network, time sensitive network) is a generic term for a series of data link layer protocol specifications developed by the IEEE 802.1TSN working group, defining a Time sensitive mechanism for ethernet data transmission, adding certainty and reliability to standard ethernet to ensure real-Time, deterministic and reliable data transmission. 5G/5G+TSN refers to a 5G/5G+network based time sensitive network, which is a technique for real-time communication and control that provides high precision and reliable clock synchronization over 5G/5G+networks.

In the related art, a 5G/5G+ base station scheduler cannot make special scheduling according to the data characteristics of TSN service, the time delay certainty of the TSN service cannot be guaranteed, and equipment downtime is caused by the time delay and jitter change of a data packet, so that how to adaptively adjust a scheduling strategy according to the data characteristics of the TSN service is a problem which needs to be solved in a TSN service application scene.

It should be noted that the information disclosed in the above background section is only for enhancing understanding of the background of the present disclosure and thus may include information that does not constitute prior art known to those of ordinary skill in the art.

Disclosure of Invention

The embodiment of the disclosure provides a scheduling policy adjustment method, a scheduling policy adjustment device, electronic equipment and a computer readable storage medium.

Other features and advantages of the present disclosure will be apparent from the following detailed description, or may be learned in part by the practice of the disclosure.

According to one aspect of the present disclosure, there is provided a scheduling policy adjustment method, the method including: acquiring a TSN data packet to be processed corresponding to a TSN service of a time sensitive network, and acquiring characteristic information of the TSN data packet to be processed; inputting the TSN data packet to be processed and the characteristic information of the TSN data packet to be processed into a flow prediction model, outputting flow change dynamic information corresponding to the TSN data packet to be processed, and generating prediction information of the TSN service according to the flow change dynamic information; and adjusting the scheduling strategy of the TSN service according to the prediction information of the TSN service.

In some embodiments of the present disclosure, the prediction information of the TSN service includes one or more of a predicted length of the target TSN packet, a predicted arrival time interval of the target TSN packet, a predicted transmission duty cycle of the target TSN packet, a predicted transmission delay of the target TSN packet, a predicted jitter of the target TSN packet, and a predicted priority of the target TSN packet.

In some embodiments of the present disclosure, the adjusting the scheduling policy of the TSN service according to the prediction information of the TSN service includes: according to the prediction information of the TSN service, the length of the radio link control RLC payload in the scheduling strategy is adjusted; and adjusting a modulation coding scheme and a control retransmission scheme in the scheduling strategy according to the prediction information of the TSN service.

In some embodiments of the present disclosure, the adjusting the radio link control RLC payload length in the scheduling policy according to the prediction information of the TSN service includes: if the TSN service is determined to be the real-time requirement service according to the prediction information of the TSN service, reducing and adjusting the length of the RLC payload in the scheduling strategy; and if the TSN service is determined to be the non-real-time requirement service according to the prediction information of the TSN service, increasing and adjusting the length of the RLC payload in the scheduling strategy.

In some embodiments of the present disclosure, the method comprises: and if one or more of the predicted length being smaller than a first length threshold, the predicted arrival time interval being larger than a first arrival time interval threshold and the predicted transmission duty cycle being smaller than a first duty cycle threshold are met, determining that the TSN service is the real-time required service, otherwise, determining that the TSN service is the non-real-time required service.

In some embodiments of the present disclosure, the adjusting the modulation coding scheme and the control retransmission scheme in the scheduling policy according to the prediction information of the TSN service includes: if the target TSN data packet is determined to be a key data packet according to the prediction information of the TSN service, copying the target TSN data packet according to a first number of copies, degrading the modulation coding scheme, transmitting the copied target TSN data packet by using the degraded modulation coding scheme, and starting a negative feedback statistical function; if the target TSN data packet is determined to be a general data packet according to the prediction information of the TSN service, determining to transmit the target TSN data packet by using the modulation and coding scheme, and starting the negative feedback statistical function; and if the target TSN data packet is determined to be a non-key data packet according to the prediction information of the TSN service, determining to transmit the target TSN data packet by using the modulation and coding scheme, and determining to close the negative feedback statistical function.

In some embodiments of the present disclosure, the target TSN packet is the critical packet, and the method further includes: counting the transmission failure times through the negative feedback statistical function, and judging whether the transmission failure times are smaller than or equal to a retransmission times threshold value; if yes, determining to copy the target TSN data packet according to the second number of copies, and degrading the degraded modulation coding scheme to obtain a new modulation coding scheme so as to transmit the copied target TSN data packet by using the new modulation coding scheme; wherein the second number of copies and the level of the new modulation coding scheme are determined according to the number of transmission failures; if not, determining that the transmission of the target TSN data packet fails.

In some embodiments of the present disclosure, the target TSN packet is the generic packet, and the method further includes: counting the transmission failure times through the negative feedback counting function; and if the transmission failure times reach a retransmission times threshold, copying the target TSN data packet according to the first number of copies, and degrading the modulation coding scheme so as to transmit the copied target TSN data packet by using the degraded modulation coding scheme.

In some embodiments of the present disclosure, the method further comprises: determining the target TSN packet as the critical packet if one or more of the following options are satisfied: the predicted length is less than a second length threshold, the predicted arrival time interval is less than a second arrival time interval threshold, the predicted transmission duty cycle is greater than a second duty cycle threshold, the predicted transmission delay is less than a first transmission delay threshold, the predicted jitter is less than a first jitter threshold, and the predicted priority is a high priority; determining the target TSN packet as the generic packet if one or more of the following options are satisfied: the predicted length is greater than or equal to the second length threshold and less than a third length threshold, the predicted arrival time interval is greater than or equal to the second arrival time interval threshold and less than a third arrival time interval threshold, the predicted transmission duty cycle is less than or equal to the second duty cycle threshold and greater than a third duty cycle threshold, the predicted transmission delay is greater than or equal to the first transmission delay threshold and less than a second transmission delay threshold, the predicted jitter is greater than or equal to the first jitter threshold and less than a second jitter threshold, and the predicted priority is a medium priority; determining the target TSN packet as the non-critical packet if one or more of the following options are satisfied: the predicted length is greater than or equal to the third length threshold, the predicted arrival time interval is greater than or equal to the third arrival time interval threshold, the predicted transmission duty cycle is less than or equal to the third duty cycle threshold, the predicted transmission delay is greater than or equal to the second transmission delay threshold, the predicted jitter is greater than or equal to the second jitter threshold, and the predicted priority is a low priority.

In some embodiments of the present disclosure, the generating, according to the traffic variation dynamic information, prediction information of the TSN service includes: analyzing the time sequence characteristics of the TSN data packet to be processed to obtain a time sequence analysis result of the TSN data packet to be processed; and generating the prediction information of the TSN service according to the flow change dynamic information and the time sequence analysis result of the TSN data packet to be processed.

In some embodiments of the present disclosure, the traffic prediction model is obtained based on training of a machine learning algorithm, and the traffic prediction model is configured to output traffic variation dynamic information corresponding to an input TSN data packet according to the input TSN data packet and feature information of the input TSN data packet.

According to still another aspect of the present disclosure, there is provided a scheduling policy adjustment apparatus, the apparatus including: the data acquisition module is used for acquiring a TSN data packet to be processed corresponding to a time sensitive network TSN service and acquiring characteristic information of the TSN data packet to be processed; the business prediction module is used for inputting the TSN data packet to be processed and the characteristic information of the TSN data packet to be processed into a flow prediction model, outputting flow change dynamic information corresponding to the TSN data packet to be processed, and generating prediction information of the TSN business according to the flow change dynamic information; and the scheduling processing module is used for adjusting the scheduling strategy of the TSN service according to the prediction information of the TSN service.

According to still another aspect of the present disclosure, there is provided an electronic apparatus including: one or more processors; and a storage configured to store one or more programs that, when executed by the one or more processors, cause the one or more processors to implement the scheduling policy adjustment method as described in the above embodiments.

According to yet another aspect of the present disclosure, there is provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements a scheduling policy adjustment method as described in the above embodiments.

According to the scheduling policy adjustment method provided by the embodiment of the disclosure, the TSN flow trend can be obtained according to the TSN data packet to be processed corresponding to the TSN service and the corresponding characteristic information thereof, so that the prediction information of the TSN service is determined, then the scheduling policy is adjusted according to the prediction information, the prediction information of the TSN service can be combined with the adjustment of the scheduling policy, and the scheduling policy is adaptively adjusted according to different requirements of time delay, jitter, reliability and the like in different TSN service scenes, so that the TSN network performance is effectively ensured, the requirements of the TSN service on low-delay, high-reliability and real-time transmission are better met, the user experience in the TSN service scenes is improved, and equipment downtime caused by incapacity of ensuring the time delay of the TSN service is avoided.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure and do not constitute an undue limitation on the disclosure.

Fig. 1 illustrates a network architecture schematic diagram of a TSN system based on 5G/5g+ to which embodiments of the present disclosure are applicable;

fig. 2 shows a schematic diagram of the composition and structure of a scheduling processing module of a 5G/5g+ base station;

FIG. 3 illustrates a flow chart of a scheduling policy adjustment method according to an embodiment of the present disclosure;

fig. 4 illustrates a flow chart of adjusting RLC payload length in a scheduling policy according to an embodiment of the present disclosure;

fig. 5 shows a flow chart of adjusting a modulation coding scheme and a control retransmission scheme in a modulation scheme according to an embodiment of the present disclosure;

FIG. 6 illustrates a flow chart of a scheduling policy adjustment method according to yet another embodiment of the present disclosure;

FIG. 7 is a schematic diagram of a scheduling policy adjustment device according to an embodiment of the disclosure;

fig. 8 shows a block diagram of an electronic device in an embodiment of the disclosure.

Detailed Description

Example embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments may be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

Furthermore, the drawings are merely schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus a repetitive description thereof will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software or in one or more hardware modules or integrated circuits or in different networks and/or processor devices and/or microcontroller devices.

It should be noted that, the embodiments of the present disclosure refer to ordinal terms such as "first," "second," etc. for distinguishing a plurality of objects, and are not used to define an order, a timing, a priority, or an importance of the plurality of objects, and the descriptions of "first," "second," and the like do not necessarily define that the objects are different.

Fig. 1 shows a network architecture schematic of a TSN system based on 5G/5g+ to which embodiments of the present disclosure are applicable. Referring to fig. 1, the TSN system based on 5G/5g+ includes 5G/5g+time Domain (5G/5g+time Domain) and TSN Time Domain (TSN Time Domain).

The TSN Time Domain includes a TSN Bridge (TSN Bridge), a TSN GM (TSN master clock, GM is generally called grandmaster clock), in the TSN protocol, the GM is a master clock in a master-slave synchronization model, and is responsible for synchronizing Time information to a slave clock), and a TSN End Station (TSN End Station, including a transceiver End), where each node is kept synchronous with the TSN GM. The 5G/5G+Time Domain includes 5G/5G+GM (5G/5G+Master clock), DS-TT (Device-side TSN translator, terminal side TSN adapter), NW-TT (Network-side TSN translator, network side TSN adapter), UE (User Equipment), 5G/5G+base station and 5G/5G+core Network, each node keeps synchronous with 5G/5G+GM.

In the TSN, DS-TT and NW-TT are two different types of adapters for connection and communication between the UE and the network device, respectively. The DS-TT refers to an adapter for connecting a UE (e.g., sensor, actuator, etc.) to a TSN network. The UEs may use different protocols and data formats, and the function of the DS-TT is to adapt and integrate the devices with the TSN network, enabling the transmission and processing of time sensitive data. NW-TT refers to an adapter for connecting a TSN network with an external network (e.g., internet, ethernet, etc.). These external networks may use different protocols and data formats, while the NW-TT functions to adapt and interconnect the TSN network with the external network, enabling the transmission and processing of time-sensitive data between the two networks. The DS-TT and the NW-TT need to sense the time of two different time domains at the same time, and the 5G/5G+ base station does not need to sense the TSN time.

In the related art, a 5G/5G+ base station scheduler cannot make special scheduling according to the data characteristics of TSN service, the time delay certainty of the TSN service cannot be guaranteed, and equipment downtime is caused by the time delay and jitter change of a data packet, so that how to adaptively adjust a scheduling strategy according to the data characteristics of the TSN service is a problem which needs to be solved in a TSN service application scene. In order to solve the above problem, a data acquisition module and a service prediction module may be newly added in the 5G/5g+ base station, and the functions of the scheduling processing module may be modified, and the functions of adjusting the scheduling policy according to the service prediction information may be newly added.

Specifically, the data acquisition module supports the 5G/5g+ base station to acquire the TSN data packet, and extracts characteristics of the TSN data packet, such as the TSN data packet size, the transmission timestamp, the priority, and the like. The service prediction module can train a service prediction model by adopting a machine learning algorithm, and the input of the model is a TSN data packet and corresponding characteristics, and the output of the model is a TSN flow trend. In the training process, different optimization algorithms and loss functions can be selected for optimization, so that a service prediction model obtained through training can better predict results. The service prediction module can use the trained service prediction model to predict unknown TSN data packet characteristics to obtain corresponding TSN flow trend, and obtain TSN service prediction information such as TSN data packet size, TSN data packet arrival time interval, duty cycle, time delay, jitter, TSN data packet priority and the like.

Fig. 2 shows a schematic diagram of the composition structure of a scheduling processing module of a 5G/5g+ base station. As shown in fig. 2, the scheduling processing module may be composed of a QoS (Quality of Service ) management sub-module, a physical layer measurement value processing sub-module, a user selection sub-module, a NACK (Negative Acknowledgement, negative feedback), a receiver notifying the sender only when no data is received, a MCS (Modulation and Coding Scheme ) selection sub-module, a resource allocation sub-module, and the like. The Input signals of the scheduling processing module include QoS (e.g., set and optimized by parameters 5QI, GBR, and AMBR), channel status indication, HARQ (Hybrid Automatic Repeat Request ) feedback, RLC (Radio Link Control) data buffer, downlink transmit power, downlink MIMO (Multiple-Input Multiple-Output) scheme, traffic prediction information, and the Output signals include selecting user, RLC payload size, selecting MCS, controlling retransmission, antenna, and resource mapping.

The scheduling processing module can adjust the scheduling policy according to the newly added input signal, namely the service prediction information, besides generating the scheduling policy according to the existing input signal, and particularly can adjust the RLC payload size, select MCS and control retransmission in the scheduling policy.

Next, a scheduling policy adjustment method according to an embodiment of the present disclosure is described in detail with reference to the accompanying drawings. Fig. 3 shows a flowchart of a scheduling policy adjustment method according to an embodiment of the present disclosure. The scheduling policy adjustment method provided in the embodiment of fig. 3 may be performed by a base station, for example, the 5G/5g+ base station in fig. 1. As shown in fig. 3, the scheduling policy adjustment method specifically includes the following steps S310 to S330.

Step S310, a TSN data packet to be processed corresponding to the TSN service is acquired, and feature information of the TSN data packet to be processed is acquired.

The TSN business can be business such as industrial automation, intelligent transportation, aerospace, intelligent mine, intelligent power grid, automobile electronics, automatic driving, telemedicine and the like, and different TSN businesses have different requirements on time delay, jitter, reliability and the like. For example, TSN service application scenes such as internet of vehicles, industrial automation, telemedicine and the like have very high requirements on real-time performance, and delay and jitter of data transmission need to be strictly controlled to ensure timeliness and accuracy of data.

The to-be-processed TSN packet may be understood as a known TSN packet, and the characteristic information of the to-be-processed TSN packet may include information such as a size of the TSN packet, a transmission timestamp of the TSN packet, and a priority of the TSN packet. The size of the data packet refers to the length of the data packet, the occurrence time stamp of the data packet refers to the sending time of the data packet, and the priority of the data packet refers to the priority level when the data packet is transmitted in the network.

In this step, a specific TSN service data packet may be collected, and features of the data packet may be extracted, and then, a traffic trend of the TSN service may be predicted according to the collected data packet and the data packet features to obtain TSN service prediction information, and then, a scheduling policy may be adjusted by combining the TSN service prediction information, so that the adjusted scheduling policy is matched with the TSN service.

Step S320, inputting the TSN data packet to be processed and the characteristic information of the TSN data packet to be processed into a flow prediction model, outputting flow change dynamic information corresponding to the TSN data packet to be processed, and generating prediction information of TSN service according to the flow change dynamic information.

In some embodiments of the present disclosure, the flow prediction model is obtained based on machine learning algorithm training, e.g., using random forest algorithm training to obtain the flow prediction model. The flow prediction model is a trained flow prediction model, and is used for outputting flow change dynamic information corresponding to the input TSN data packet according to the input TSN data packet and the characteristic information of the input TSN data packet.

The traffic change dynamic information corresponding to the TSN packet may be understood as a TSN traffic trend, for example, information such as a transmission frequency of the TSN packet, a traffic size of the TSN packet, a priority of the TSN packet, and a transmission delay of the TSN packet. By analyzing the characteristics of the arrival time interval, the duty ratio and the like of the data packets, the transmission frequency trend of the TSN data packets can be predicted, for example, whether the data packets are transmitted densely or sparsely; by analyzing the characteristics of the size and the like of the data packet, the flow size trend of the TSN data packet, such as whether the data packet flow is larger or smaller, can be predicted; by analyzing the characteristics of the priority of the data packets, the priority trend of the TSN data packets can be predicted, for example, whether the data packets with high priority are more or whether the data packets with low priority are more; by analyzing the characteristics of delay, jitter and the like of the data packet, the transmission delay trend of the TSN data packet can be predicted, for example, whether the transmission delay of the data packet is larger or smaller. Of course, the flow trend may also include other information, which is not limited by the disclosed embodiments.

In the embodiment of the disclosure, the trained traffic prediction model can be obtained according to the following method: acquiring a historical TSN data packet, wherein the historical TSN data packet is a training sample, acquiring an actual flow trend corresponding to the historical TSN data packet, and extracting characteristic information of the historical TSN data packet; inputting the historical TSN data packet and the corresponding characteristic information thereof into an untrained flow prediction model, and outputting a predicted flow trend corresponding to the historical TSN data packet; and selecting different optimization algorithms, such as random gradient descent, genetic algorithm and the like, and loss functions, such as root mean square error, cross entropy and the like, calculating model loss values according to the predicted flow trend and the actual flow trend, and continuously adjusting model parameters until the model loss values meet preset conditions, such as being smaller than a preset loss threshold value, so as to obtain the flow prediction model after training.

In some embodiments of the present disclosure, generating the prediction information of the TSN service according to the traffic variation dynamic information may include: analyzing the time sequence characteristics of the TSN data packet to be processed to obtain a time sequence analysis result of the TSN data packet to be processed; and generating the prediction information of the TSN service according to the flow change dynamic information and the time sequence analysis result of the TSN data packet to be processed.

And analyzing the time sequence characteristics of the TSN data packets to be processed to obtain time sequence analysis results of the TSN data packets to be processed, such as TSN data packet arrival time interval, duty cycle, time delay, jitter and the like. Where arrival time interval refers to the time required for a data packet to be transmitted from one device to another; duty cycle generally refers to the proportion of time that the network is occupied by data transmissions during a particular period of time, i.e., the proportion of time that the network is active; time delay refers to the time required for a data packet to be sent from a sender to a receiver; jitter is the irregularity of the arrival time intervals between packets of data.

In the embodiment of the disclosure, a traffic prediction model is adopted to process a TSN data packet to be processed and corresponding features to obtain a corresponding TSN traffic trend, time sequence analysis is carried out on the TSN data packet to be processed to obtain a time sequence analysis result, and the TSN traffic trend and the time sequence analysis result are combined to obtain prediction information of TSN service.

The prediction information of the TSN service may be understood as information of a predicted target TSN packet, which may be understood as an unknown packet transmitted after the TSN packet is to be processed, and the prediction information may include one or more of a predicted length of the target TSN packet, a predicted arrival time interval of the target TSN packet, a predicted transmission duty cycle of the target TSN packet, a predicted transmission delay of the target TSN packet, a predicted jitter of the target TSN packet, and a predicted priority of the target TSN packet.

In the embodiment of the disclosure, the TSN flow trend is obtained based on the pre-trained flow prediction model, so that the prediction information of TSN service is obtained, the prediction information is used as an important basis for base station scheduling in a 5G/5G+TSN system, a dynamic adjustment scheduling strategy is realized, the performance and user experience of the 5G/5G+TSN network are improved, and the method has stronger pertinence for the evolution of a wireless network towards the 6G direction.

Step S330, the scheduling strategy of the TSN business is adjusted according to the prediction information of the TSN business.

The scheduling policy may include selecting a user scheme, an antenna and resource mapping scheme, RLC payload length setting, a modulation coding scheme, and a control retransmission scheme. The selection user scheme mainly decides which users can obtain more resources according to factors such as user priority, channel quality, data caching and the like; the antenna and resource mapping scheme mainly decides how to allocate wireless resources according to factors such as channel state, data transmission rate, antenna state and the like; the RLC payload length setting mainly reflects the size of data transmitted by an RLC layer, and the proper RLC payload length can be determined by the factors of data buffer size, HARQ feedback, scheduling decision and the like so as to ensure the reliable transmission and high performance of the data; the modulation coding scheme mainly selects the optimal modulation and coding scheme according to the current channel state, the data buffer size, the QoS requirement and other factors so as to ensure the reliability and the efficiency of data transmission; the retransmission control scheme mainly decides when data needs to be retransmitted according to NACK feedback statistical results and how to reasonably utilize resources for retransmission.

In some embodiments of the present disclosure, adjusting a scheduling policy of a TSN service according to prediction information of the TSN service includes: according to the prediction information of the TSN service, the length of the RLC payload in the scheduling strategy is adjusted; and adjusting a modulation coding scheme and a control retransmission scheme in the modulation strategy according to the prediction information of the TSN service.

In the embodiment of the disclosure, the RLC payload size, MCS selection and retransmission control are dynamically adjusted according to the prediction information of the TSN service, so that the dynamic real-time adjustment of scheduling strategies in different TSN service scenes is realized, and the completeness, adaptability and flexibility of the base station in the 5G/5G+TSN system are improved.

Fig. 4 shows a flowchart of adjusting RLC payload length in a scheduling policy according to an embodiment of the present disclosure. As shown in fig. 4, adjusting the RLC payload length may include the following steps.

In step S410, if it is determined that the TSN service is the real-time request service according to the prediction information of the TSN service, the RLC payload length in the scheduling policy is reduced and adjusted.

Step S420, if it is determined that the TSN service is the non-real-time request service according to the prediction information of the TSN service, the RLC payload length in the scheduling policy is increased and adjusted.

Real-time requirements services can be understood as services requiring strict delay and jitter requirements, requiring accurate time synchronization and low-delay data transmission, so as to ensure real-time, synchronicity, time accuracy and other requirements. The non-real-time requirement service can be understood as a service with relaxed requirements on time delay and jitter, and has low requirements on real-time performance, and the reliability and stability of data transmission are emphasized.

RLC payload refers to the amount of effective data that can be carried by one data transmission in the RLC protocol. When the length of the RLC payload is adjusted according to the prediction information of the TSN service, whether the TSN service is a real-time requirement service or not can be judged according to the prediction information of the TSN service. If the TSN service is judged to be the real-time requirement service, the length of the RLC payload is reduced; if the TSN service is judged to be the non-real-time requirement service, the length of the RLC payload is increased.

Further, whether the TSN service is a real-time requirement service can be determined according to the following method: and if one or more of the predicted length being smaller than the first length threshold, the predicted arrival time interval being larger than the first arrival time interval threshold and the predicted transmission duty cycle being smaller than the first duty cycle threshold are met, determining that the TSN service is a real-time required service, otherwise, determining that the TSN service is a non-real-time required service.

If the predicted length of the target TSN data packet is smaller than the first length threshold value, obtaining that the target TSN data packet is small according to the service predicted information; if the predicted arrival time interval of the target TSN data packet is larger than the first arrival time interval, obtaining that the arrival time interval of the target TSN data packet is long according to the service prediction information; if the predicted transmission duty ratio of the target TSN data packet is smaller than the first duty ratio threshold, the target TSN data packet is obtained to have a small duty ratio according to the service prediction information. If the target TSN data packet is small or the arrival time interval of the target TSN data packet is long or the duty ratio is small, the TSN service is considered to be real-time requirement service, and the RLC payload is reduced; otherwise, the TSN service is considered as a non-real-time requirement service, and the RLC payload is increased.

In the embodiment of the disclosure, if the TSN service is judged to be the real-time requirement service according to the TSN service prediction information, the length of the RLC payload is reduced, so that the transmission frequency of the data packet can be increased, the transmission delay is reduced, and the real-time performance of the data can be improved to meet the strict requirements of time delay and jitter; if the TSN service is judged to be the non-real-time requirement service according to the TSN service prediction information, the length of the RLC payload is increased, so that the reliability of the data packet can be increased, and the reliability of the data is improved.

Fig. 5 shows a flow chart of adjusting a modulation coding scheme and a control retransmission scheme in a modulation scheme according to an embodiment of the present disclosure. As shown in fig. 5, the adjustment of the modulation coding scheme and the control retransmission scheme may include the following steps.

In step S510, if it is determined that the target TSN data packet is the key data packet according to the prediction information of the TSN service, it is determined that the target TSN data packet is copied according to the first number of copies, the modulation coding scheme is degraded, so that the copied target TSN data packet is transmitted by using the degraded modulation coding scheme, and the negative feedback statistical function is started.

Modulation coding scheme, i.e. selecting MCS, is a key parameter for adjusting data transmission rate and reliability in a wireless network, and when selecting MCS, signal quality, interference level, transmission distance, system load and resource utilization need to be considered in general; the control retransmission scheme refers to that data may not be successfully transmitted at one time due to various reasons (e.g., interference, signal attenuation, etc.) in a wireless network, and the control retransmission scheme is used to decide when and how to retransmit the data. The embodiment of the disclosure can adjust the modulation coding scheme and the control retransmission scheme according to the prediction information of the TSN service.

When the modulation coding scheme and the control retransmission scheme are adjusted according to the prediction information of the TSN service, the target TSN data packet can be judged to be a key data packet, a general data packet or a non-key data packet according to the prediction information of the TSN service, and then the modulation coding scheme and the control retransmission scheme are adjusted under the condition that the type of the target TSN data packet is determined.

The key data packet may be understood as a data packet carrying key information, such as a data packet carrying key instruction or control information, which is critical to normal operation of the system or the application; the general data packet can be understood as a conventional data packet or a standard data packet, and the carried information amount is moderate, so that the general data packet possibly belongs to a general service data packet; non-critical packets are understood to be packets that are not particularly critical or urgent, carrying a large amount of information or data.

In some embodiments of the present disclosure, the target TSN packet is determined to be a critical packet if one or more of the following options are met: the predicted length is less than the second length threshold, the predicted arrival time interval is less than the second arrival time interval threshold, the predicted transmission duty cycle is greater than the second duty cycle threshold, the predicted transmission delay is less than the first transmission delay threshold, the predicted jitter is less than the first jitter threshold, and the predicted priority is a high priority.

If the predicted length of the target TSN data packet is smaller than the second length threshold value, determining that the target TSN data packet is small; if the predicted arrival time interval of the target TSN data packet is smaller than the second arrival time interval, determining that the arrival time interval of the target TSN data packet is short; if the predicted transmission duty cycle of the target TSN data packet is larger than the second duty cycle threshold, determining that the duty cycle of the target TSN data packet is large; if the predicted transmission delay of the target TSN data packet is smaller than the first transmission delay threshold value, determining that the delay is small; if the predicted jitter of the target TSN data packet is smaller than a first jitter threshold value, determining that the jitter is small; if the predicted priority of the target TSN packet is high, the priority is determined to be high.

In the embodiment of the disclosure, if one or more of the options of small target TSN packet, short target TSN packet arrival time interval, large space ratio, small delay, small jitter, and high priority are satisfied, the target TSN packet is determined to be a critical packet. In this case, the target TSN packet may belong to a control class or instruction class packet with high priority, low latency, and high real-time, and needs to be transmitted frequently and at high speed, and the network needs to have high stability and low latency.

And under the condition that the target TSN data packet is determined to be the key data packet, copying the target TSN data packet, degrading the modulation coding scheme, transmitting the copied target TSN data packet by using the degraded modulation coding scheme, and starting a negative feedback statistical function. For example, the target TSN data packet is copied into 2 parts, the primary MCS transmission is reduced, and the NACK real-time statistics sub-module is started.

In the embodiment of the disclosure, under the condition that the target TSN data packet is determined to be a key data packet, the coverage area of the data packet can be increased by copying the data packet, so that the success rate of data transmission is improved; the complexity and interference of data transmission can be reduced by reducing the modulation and coding scheme, and the reliability of the data transmission can be improved; after the NACK real-time statistics sub-module is started, when the data packet which is damaged or lost is received by the receiving party when the data packet is received by the receiving party, NACK response is sent, and the quality of data transmission can be known by counting the number of NACK responses.

In some embodiments of the present disclosure, in a case where the target TSN packet is determined to be a critical packet, the scheduling policy adjustment method may further include: counting the transmission failure times through a negative feedback counting function, and judging whether the transmission failure times are smaller than or equal to a retransmission times threshold value; if yes, determining to copy the target TSN data packet according to the second number of copies, degrading the degraded modulation coding scheme to obtain a new modulation coding scheme, and transmitting the copied target TSN data packet by using the new modulation coding scheme; wherein the second number of copies and the level of the new modulation coding scheme are determined according to the number of transmission failures; if not, determining that the transmission of the target TSN data packet fails.

After the negative feedback statistical function is started, the number of data transmission failures can be counted through the negative feedback statistical function, and when the number of the transmission failures does not exceed the threshold value of the retransmission number, the target TSN data packet can be copied, and the modulation coding scheme is continuously degraded. For example, the retransmission time threshold is set to 3 times, when the NACK real-time statistics submodule continuously counts the number of times of transmission failure to exceed 1 time, the target TSN data packet is copied to 4 parts, then the primary MCS transmission is reduced, when the NACK real-time statistics submodule continuously counts the number of times of transmission failure to exceed 2 times, the target TSN data packet is copied to 8 parts, and the primary MCS transmission is continuously reduced.

In the embodiment of the disclosure, when the target TSN data packet is determined to be the key data packet, the negative feedback statistical function is started to count the transmission failure times, and when the transmission failure times do not exceed the retransmission times threshold, the target TSN data packet is copied for more times, the level of the modulation and coding scheme is continuously reduced, the system capacity is reduced, the reliability of the transmission of the target TSN data packet is ensured, and the time delay and jitter are reduced.

In step S520, if it is determined that the target TSN packet is a general packet according to the prediction information of the TSN service, it is determined that the target TSN packet is transmitted by using the modulation and coding scheme, and the negative feedback statistical function is turned on.

In some embodiments of the present disclosure, the target TSN packet is determined to be a generic packet if one or more of the following options are met: the predicted length is greater than or equal to the second length threshold and less than the third length threshold, the predicted arrival time interval is greater than or equal to the second arrival time interval threshold and less than the third arrival time interval threshold, the predicted transmission duty cycle is less than or equal to the second duty cycle threshold and greater than the third duty cycle threshold, the predicted transmission delay is greater than or equal to the first transmission delay threshold and less than the second transmission delay threshold, the predicted jitter is greater than or equal to the first jitter threshold and less than the second jitter threshold, and the predicted priority is a medium priority. The second length threshold is smaller than the third length threshold, the second arrival time interval threshold is smaller than the third arrival time interval threshold, the second duty cycle threshold is larger than the third duty cycle threshold, the first transmission delay threshold is smaller than the second transmission delay threshold, and the first jitter threshold is smaller than the second jitter threshold.

If the predicted length of the target TSN data packet is larger than or equal to the second length threshold value and smaller than the third length threshold value, determining that the target TSN data packet belongs to a medium level, namely not belongs to a large data packet or not belongs to a small data packet; if the predicted arrival time interval of the target TSN data packet is larger than or equal to the second arrival time interval threshold and smaller than the third arrival time interval threshold, determining that the arrival time interval of the target TSN data packet is not long or short; if the predicted transmission duty cycle of the target TSN data packet is smaller than or equal to the second duty cycle threshold and larger than the third duty cycle threshold, determining that the duty cycle of the target TSN data packet is not large or small; if the predicted transmission delay of the target TSN data packet is larger than or equal to the first transmission delay threshold and smaller than the second transmission delay threshold, determining that the transmission delay is middle, namely that the transmission delay is neither long nor short; if the predicted jitter of the target TSN data packet is larger than or equal to the first jitter threshold and smaller than the second jitter threshold, determining that the jitter is not large or small; if the predicted priority of the target TSN data packet is a medium priority, determining the priority.

In an embodiment of the present disclosure, the target TSN packet is determined to be a generic packet if one or more of these options in the target TSN packet, in the target TSN packet arrival time interval, in the space ratio, in the delay, in the jitter, and in the priority are met. In this case, the target TSN packet may contain medium-sized traffic data or information, and the requirements on real-time and reliability are moderate, so that excessive pressure is not caused on network transmission.

Under the condition that the target TSN data packet is determined to be the universal data packet, the target TSN data packet can be determined not to be copied, the modulation and coding scheme in the modulation strategy is not adjusted, the transmission is normally carried out, and meanwhile, a negative feedback statistical function, namely a NACK real-time statistical sub-module, is started.

In some embodiments of the present disclosure, in a case where the target TSN packet is determined to be a generic packet, the scheduling policy adjustment method may further include: counting the number of transmission failures through a negative feedback statistics function; and if the transmission failure times reach the retransmission times threshold, copying the target TSN data packet according to the first number of copies, and degrading the modulation coding scheme to transmit the copied target TSN data packet by using the degraded modulation coding scheme.

After the negative feedback statistical function is started, the number of data transmission failures can be counted through the negative feedback statistical function, when the number of transmission failures reaches a retransmission number threshold, a target TSN data packet can be copied, and the modulation coding scheme is degraded, so that the copied target TSN data packet is transmitted by using the degraded modulation coding scheme. For example, the target TSN packet is duplicated to 2 shares, reducing the primary MCS transmission. Therefore, the effect of proper retransmission is achieved, the system capacity is improved, and meanwhile, the reliability of data transmission is guaranteed.

In step S530, if it is determined that the target TSN packet is a non-critical packet according to the prediction information of the TSN service, it is determined that the target TSN packet is transmitted by using the modulation and coding scheme, and it is determined that the negative feedback statistical function is turned off.

In some embodiments of the present disclosure, the target TSN packet is determined to be a non-critical packet if one or more of the following options are met: the predicted length is greater than or equal to a third length threshold, the predicted arrival time interval is greater than or equal to a third arrival time interval threshold, the predicted transmission duty cycle is less than or equal to a third duty cycle threshold, the predicted transmission delay is greater than or equal to a second transmission delay threshold, the predicted jitter is greater than or equal to a second jitter threshold, and the predicted priority is a low priority.

If the predicted length of the target TSN data packet is greater than or equal to a third length threshold value, determining that the target TSN data packet is large; if the predicted arrival time interval of the target TSN data packet is greater than or equal to the third arrival time interval threshold, determining that the arrival time interval of the target TSN data packet is long; if the predicted transmission duty cycle of the target TSN data packet is smaller than or equal to a third duty cycle threshold, determining that the duty cycle of the target TSN data packet is small; if the predicted transmission delay of the target TSN data packet is greater than or equal to the second transmission delay threshold value, determining that the delay is large; if the predicted jitter of the target TSN data packet is larger than or equal to a second jitter threshold value, determining that the jitter is large; if the predicted priority of the target TSN packet is low, it is determined that the priority is low.

In the embodiment of the disclosure, if one or more of the options of large target TSN packet, long target TSN packet arrival time interval, small space ratio, large delay, large jitter, and low priority are satisfied, the target TSN packet is determined to be a non-critical packet. In this case, the target TSN packet may contain a large amount of information or data, requiring a long time to transmit, and the requirements for real-time and stability may not be particularly high, requiring efficient and reliable transmission.

Under the condition that the target TSN data packet is determined to be a non-critical data packet, the target TSN data packet can be determined not to be duplicated, the modulation and coding scheme in the modulation strategy is not adjusted, the transmission is normally carried out, and meanwhile, the negative feedback statistical function is determined to be closed, namely, the NACK real-time statistical sub-module is determined to be closed, and normal retransmission is carried out according to the configured retransmission times, for example, retransmission is carried out according to the configured retransmission times of 4 times.

Specific embodiments are listed below to describe the scheduling policy adjustment method provided in the embodiments of the present disclosure. Fig. 6 shows a flowchart of a scheduling policy adjustment method according to still another embodiment of the present disclosure, and as shown in fig. 6, a specific implementation of the scheduling policy adjustment method may include the following steps.

Step S610, a TSN data packet to be processed corresponding to the TSN service is collected, and feature information of the TSN data packet to be processed is extracted.

Specifically, the data acquisition module newly added in the 5G/5g+ base station may acquire the TSN data packet and extract the characteristics of the data packet, for example, the size of the TSN data packet, the transmission timestamp of the TSN data packet, the priority of the TSN data packet, and so on.

Step S620, obtaining a flow prediction model based on the machine learning algorithm training.

Specifically, the model can be trained by a newly added service prediction module in the 5G/5G+ base station. The input of the traffic prediction model is a TSN data packet and corresponding characteristics, and the output is traffic variation dynamic information corresponding to the input TSN data packet, namely TSN traffic trend, such as the sending frequency of the TSN data packet, the traffic size of the TSN data packet, the priority of the TSN data packet, the transmission delay of the TSN data packet and the like.

In the process of training the flow prediction model, different optimization algorithms and loss functions can be selected for optimization, and training effects are continuously evaluated and verified so as to obtain the flow prediction model with accurate prediction results.

Step S630, inputting the TSN data packet to be processed and the extracted characteristics of the data packet into a flow prediction model to obtain a TSN flow trend corresponding to the TSN data packet to be processed, and performing time sequence analysis on the TSN data packet to be processed to obtain the prediction information of TSN service.

The prediction information may include one or more of a predicted length of the target TSN packet, a predicted arrival time interval of the target TSN packet, a predicted transmission duty cycle of the target TSN packet, a predicted transmission delay of the target TSN packet, a predicted jitter of the target TSN packet, and a predicted priority of the target TSN packet, where the target TSN packet may be understood as an unknown packet transmitted after the TSN packet to be processed.

Step S640, the prediction information of the TSN service is used as the newly added input signal of the scheduling processing module in the 5G/5G+ base station, and the scheduling strategy is adjusted through the scheduling processing module.

In step S650, the RLC payload size is adjusted by the scheduling processing module according to the prediction information of the TSN service.

The above-described steps S410 and S420 have already described the steps of adjusting the RLC payload size in detail, and will not be described again here.

Step S660, the modulation coding scheme and the retransmission control scheme are adjusted by the scheduling processing module according to the prediction information of the TSN service, and whether the NACK real-time statistics sub-module is started or not is determined.

The above steps S510 to S530 have already described in detail the adjustment of the modulation coding scheme and the control retransmission scheme, and whether to turn on the NACK real-time statistics sub-module, which is not described here.

According to the scheduling policy adjustment method provided by the embodiment of the disclosure, the TSN flow trend can be obtained according to the TSN data packet to be processed corresponding to the TSN service and the corresponding characteristic information thereof, so that the prediction information of the TSN service is determined, then the scheduling policy is adjusted according to the prediction information, the prediction information of the TSN service can be combined with the adjustment of the scheduling policy, the scheduling policy is adaptively adjusted according to different requirements of different TSN service scenes, such as time delay, jitter and reliability, so that the TSN network performance is effectively ensured, the user experience in the TSN service scenes is improved, and the requirements of the TSN service on low-delay, high-reliability and real-time transmission are better met.

And by adding the data acquisition module, the service prediction module and the optimal scheduling processing module in the base station of the 5G/5G+TSN system, the scheduling strategy adjustment method of the embodiment of the disclosure is realized, the completeness and flexibility of base station equipment are greatly improved, the performance of a 5G/5G+access network is improved, the realization complexity is low, and the implementation and popularization are easy.

Fig. 7 is a schematic structural diagram of a scheduling policy adjustment device according to an embodiment of the disclosure. As shown in fig. 7, the scheduling policy adjustment device 700 may include a data acquisition module 710, a traffic prediction module 720, and a scheduling processing module 730.

The data acquisition module 710 may be configured to acquire a to-be-processed TSN packet corresponding to the TSN service, and acquire feature information of the to-be-processed TSN packet; the service prediction module 720 may be configured to input the TSN data packet to be processed and the feature information of the TSN data packet to be processed into a traffic prediction model, output traffic variation dynamic information corresponding to the TSN data packet to be processed, and generate prediction information of the TSN service according to the traffic variation dynamic information; the scheduling processing module 730 may be configured to adjust a scheduling policy of the TSN service according to the prediction information of the TSN service.

In some embodiments of the present disclosure, the prediction information of the TSN traffic includes one or more of a predicted length of the target TSN packet, a predicted arrival time interval of the target TSN packet, a predicted transmission duty cycle of the target TSN packet, a predicted transmission delay of the target TSN packet, a predicted jitter of the target TSN packet, and a predicted priority of the target TSN packet.

In some embodiments of the present disclosure, the schedule processing module 730 may be further configured to: according to the prediction information of the TSN service, the length of the RLC payload in the scheduling strategy is adjusted; and adjusting a modulation coding scheme and a control retransmission scheme in the modulation strategy according to the prediction information of the TSN service.

In some embodiments of the present disclosure, the schedule processing module 730 may be further configured to: if the TSN service is determined to be the real-time requirement service according to the prediction information of the TSN service, reducing and adjusting the length of the RLC payload in the scheduling strategy; if the TSN service is determined to be the non-real-time requirement service according to the prediction information of the TSN service, the length of the RLC payload in the scheduling strategy is increased and adjusted.

In some embodiments of the present disclosure, the schedule processing module 730 may be further configured to: and if one or more of the predicted length being smaller than the first length threshold, the predicted arrival time interval being larger than the first arrival time interval threshold and the predicted transmission duty cycle being smaller than the first duty cycle threshold are met, determining that the TSN service is a real-time required service, otherwise, determining that the TSN service is a non-real-time required service.

In some embodiments of the present disclosure, the schedule processing module 730 may be further configured to: if the target TSN data packet is determined to be a key data packet according to the prediction information of the TSN service, determining to copy the target TSN data packet according to the first number of copies, degrading the modulation coding scheme, transmitting the copied target TSN data packet by using the degraded modulation coding scheme, and starting a negative feedback statistical function; if the target TSN data packet is determined to be a general data packet according to the prediction information of the TSN service, determining to transmit the target TSN data packet by using a modulation and coding scheme, and starting a negative feedback statistical function; if the target TSN data packet is determined to be a non-key data packet according to the prediction information of the TSN service, the target TSN data packet is determined to be transmitted by using a modulation and coding scheme, and the negative feedback statistical function is determined to be closed.

In some embodiments of the present disclosure, the target TSN packet is a critical packet, and the scheduling processing module 630 is further configured to: counting the transmission failure times through a negative feedback counting function, and judging whether the transmission failure times are smaller than or equal to a retransmission times threshold value; if yes, determining to copy the target TSN data packet according to the second number of copies, degrading the degraded modulation coding scheme to obtain a new modulation coding scheme, and transmitting the copied target TSN data packet by using the new modulation coding scheme; wherein the second number of copies and the level of the new modulation coding scheme are determined according to the number of transmission failures; if not, determining that the transmission of the target TSN data packet fails.

In some embodiments of the present disclosure, the target TSN packet is a generic packet, and the scheduling processing module 630 is further configured to: counting the number of transmission failures through a negative feedback statistics function; and if the transmission failure times reach the retransmission times threshold, copying the target TSN data packet according to the first number of copies, and degrading the modulation coding scheme to transmit the copied target TSN data packet by using the degraded modulation coding scheme.

In some embodiments of the present disclosure, the schedule processing module 730 may be further configured to: determining the target TSN packet as a critical packet if one or more of the following options are satisfied: the predicted length is less than a second length threshold, the predicted arrival time interval is less than a second arrival time interval threshold, the predicted transmission duty cycle is greater than a second duty cycle threshold, the predicted transmission delay is less than a first transmission delay threshold, the predicted jitter is less than a first jitter threshold, and the predicted priority is a high priority; determining the target TSN packet as a generic packet if one or more of the following options are satisfied: the predicted length is greater than or equal to the second length threshold and less than the third length threshold, the predicted arrival time interval is greater than or equal to the second arrival time interval threshold and less than the third arrival time interval threshold, the predicted transmission duty cycle is less than or equal to the second duty cycle threshold and greater than the third duty cycle threshold, the predicted transmission delay is greater than or equal to the first transmission delay threshold and less than the second transmission delay threshold, the predicted jitter is greater than or equal to the first jitter threshold and less than the second jitter threshold, and the predicted priority is a medium priority; determining the target TSN packet as a non-critical packet if one or more of the following options are satisfied: the predicted length is greater than or equal to a third length threshold, the predicted arrival time interval is greater than or equal to a third arrival time interval threshold, the predicted transmission duty cycle is less than or equal to a third duty cycle threshold, the predicted transmission delay is greater than or equal to a second transmission delay threshold, the predicted jitter is greater than or equal to a second jitter threshold, and the predicted priority is a low priority.

In some embodiments of the present disclosure, the traffic prediction module 720 may be further configured to: analyzing the time sequence characteristics of the TSN data packet to be processed to obtain a time sequence analysis result of the TSN data packet to be processed; and generating the prediction information of the TSN service according to the flow change dynamic information and the time sequence analysis result of the TSN data packet to be processed.

In some embodiments of the present disclosure, a traffic prediction model is obtained based on training of a machine learning algorithm, and the traffic prediction model is configured to output traffic variation dynamic information corresponding to an input TSN packet according to the input TSN packet and feature information of the input TSN packet.

Since the principle of the scheduling policy adjustment device embodiment for solving the problem is similar to that of the method embodiment, the implementation of the scheduling policy adjustment device embodiment can be referred to the implementation of the method embodiment, and the repetition is omitted.

Fig. 8 shows a block diagram of an electronic device in an embodiment of the disclosure. It should be noted that the electronic device shown in fig. 8 is only an example, and should not impose any limitation on the functions and the scope of use of the embodiments of the present disclosure.

As shown in fig. 8, the electronic device 800 includes a Central Processing Unit (CPU) 801 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 802 or a program loaded from a storage section 808 into a Random Access Memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the electronic device 800 are also stored. The CPU 801, ROM 802, and RAM 803 are connected to each other by a bus 804. An input/output (I/O) interface 805 is also connected to the bus 804.

The following components are connected to the I/O interface 805: an input portion 806 including a keyboard, mouse, etc.; an output portion 807 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and a speaker; a storage section 808 including a hard disk or the like; and a communication section 809 including a network interface card such as a LAN card, a modem, or the like. The communication section 809 performs communication processing via a network such as the internet. The drive 810 is also connected to the I/O interface 805 as needed. A removable medium 811 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 810 as needed so that a computer program read out therefrom is mounted into the storage section 808 as needed.

In particular, according to embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network via the communication section 809, and/or installed from the removable media 811. The above-described functions defined in the system of the present disclosure are performed when the computer program is executed by a Central Processing Unit (CPU) 801.

It should be noted that the computer readable medium shown in the present disclosure may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, terminal device, or apparatus, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, terminal device, or apparatus. In the present disclosure, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, terminal device, or apparatus. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The modules described in the embodiments of the present disclosure may be implemented in software or hardware. The described modules may also be provided in a processor, for example, as: a processor comprises a data acquisition module, a service prediction module and a scheduling processing module. The names of these modules do not limit the module itself in some cases, for example, the data acquisition module may also be described as "a module for acquiring a to-be-processed TSN packet corresponding to the TSN service and acquiring feature information of the to-be-processed TSN packet".

As another aspect, the present disclosure also provides a computer-readable storage medium that may be included in the electronic device described in the above embodiments; or may exist alone without being incorporated into the electronic device. The computer-readable storage medium carries one or more programs which, when executed by the electronic device, cause the electronic device to implement the methods described in the embodiments below. For example, the electronic device may implement the steps shown in fig. 2.

According to one aspect of the present disclosure, there is provided a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the methods provided in the various alternative implementations of the above-described embodiments.

It should be understood that any number of elements in the drawings of the present disclosure are for illustration and not limitation, and that any naming is used for distinction only and not for limitation.

Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This disclosure is intended to cover any adaptations, uses, or adaptations of the disclosure following the general principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

It is to be understood that the present disclosure is not limited to the precise arrangements and instrumentalities shown in the drawings, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A scheduling policy adjustment method, the method comprising:

acquiring a TSN data packet to be processed corresponding to a TSN service of a time sensitive network, and acquiring characteristic information of the TSN data packet to be processed;

inputting the TSN data packet to be processed and the characteristic information of the TSN data packet to be processed into a flow prediction model, outputting flow change dynamic information corresponding to the TSN data packet to be processed, and generating prediction information of the TSN service according to the flow change dynamic information;

And adjusting the scheduling strategy of the TSN service according to the prediction information of the TSN service.

2. The method of claim 1, wherein the prediction information of the TSN traffic comprises one or more of a predicted length of the target TSN packet, a predicted arrival time interval of the target TSN packet, a predicted transmission duty cycle of the target TSN packet, a predicted transmission delay of the target TSN packet, a predicted jitter of the target TSN packet, and a predicted priority of the target TSN packet.

3. The method according to claim 2, wherein said adjusting the scheduling policy of the TSN service according to the prediction information of the TSN service comprises:

according to the prediction information of the TSN service, the length of the radio link control RLC payload in the scheduling strategy is adjusted;

and adjusting a modulation coding scheme and a control retransmission scheme in the scheduling strategy according to the prediction information of the TSN service.

4. The method of claim 3, wherein the adjusting the radio link control RLC payload length in the scheduling policy according to the prediction information of the TSN service comprises:

If the TSN service is determined to be the real-time requirement service according to the prediction information of the TSN service, reducing and adjusting the length of the RLC payload in the scheduling strategy;

and if the TSN service is determined to be the non-real-time requirement service according to the prediction information of the TSN service, increasing and adjusting the length of the RLC payload in the scheduling strategy.

5. The method according to claim 4, characterized in that the method comprises:

and if one or more of the predicted length being smaller than a first length threshold, the predicted arrival time interval being larger than a first arrival time interval threshold and the predicted transmission duty cycle being smaller than a first duty cycle threshold are met, determining that the TSN service is the real-time required service, otherwise, determining that the TSN service is the non-real-time required service.

6. The method of claim 3, wherein said adjusting the modulation and coding scheme and the control retransmission scheme in the scheduling policy according to the prediction information of the TSN service comprises:

if the target TSN data packet is determined to be a key data packet according to the prediction information of the TSN service, copying the target TSN data packet according to a first number of copies, degrading the modulation coding scheme, transmitting the copied target TSN data packet by using the degraded modulation coding scheme, and starting a negative feedback statistical function;

If the target TSN data packet is determined to be a general data packet according to the prediction information of the TSN service, determining to transmit the target TSN data packet by using the modulation and coding scheme, and starting the negative feedback statistical function;

and if the target TSN data packet is determined to be a non-key data packet according to the prediction information of the TSN service, determining to transmit the target TSN data packet by using the modulation and coding scheme, and determining to close the negative feedback statistical function.

7. The method of claim 6, wherein the target TSN packet is the critical packet, the method further comprising:

counting the transmission failure times through the negative feedback statistical function, and judging whether the transmission failure times are smaller than or equal to a retransmission times threshold value;

if yes, determining to copy the target TSN data packet according to the second number of copies, and degrading the degraded modulation coding scheme to obtain a new modulation coding scheme so as to transmit the copied target TSN data packet by using the new modulation coding scheme; wherein the second number of copies and the level of the new modulation coding scheme are determined according to the number of transmission failures;

If not, determining that the transmission of the target TSN data packet fails.

8. The method of claim 6, wherein the target TSN packet is the generic packet, the method further comprising:

counting the transmission failure times through the negative feedback counting function;

and if the transmission failure times reach a retransmission times threshold, copying the target TSN data packet according to the first number of copies, and degrading the modulation coding scheme so as to transmit the copied target TSN data packet by using the degraded modulation coding scheme.

9. The method of claim 6, wherein the method further comprises:

determining the target TSN packet as the critical packet if one or more of the following options are satisfied: the predicted length is less than a second length threshold, the predicted arrival time interval is less than a second arrival time interval threshold, the predicted transmission duty cycle is greater than a second duty cycle threshold, the predicted transmission delay is less than a first transmission delay threshold, the predicted jitter is less than a first jitter threshold, and the predicted priority is a high priority;

determining the target TSN packet as the generic packet if one or more of the following options are satisfied: the predicted length is greater than or equal to the second length threshold and less than a third length threshold, the predicted arrival time interval is greater than or equal to the second arrival time interval threshold and less than a third arrival time interval threshold, the predicted transmission duty cycle is less than or equal to the second duty cycle threshold and greater than a third duty cycle threshold, the predicted transmission delay is greater than or equal to the first transmission delay threshold and less than a second transmission delay threshold, the predicted jitter is greater than or equal to the first jitter threshold and less than a second jitter threshold, and the predicted priority is a medium priority;

Determining the target TSN packet as the non-critical packet if one or more of the following options are satisfied: the predicted length is greater than or equal to the third length threshold, the predicted arrival time interval is greater than or equal to the third arrival time interval threshold, the predicted transmission duty cycle is less than or equal to the third duty cycle threshold, the predicted transmission delay is greater than or equal to the second transmission delay threshold, the predicted jitter is greater than or equal to the second jitter threshold, and the predicted priority is a low priority.

10. The method of claim 1, wherein generating the prediction information of the TSN service according to the traffic variation dynamic information comprises:

analyzing the time sequence characteristics of the TSN data packet to be processed to obtain a time sequence analysis result of the TSN data packet to be processed;

and generating the prediction information of the TSN service according to the flow change dynamic information and the time sequence analysis result of the TSN data packet to be processed.

11. The method of claim 1, wherein the traffic prediction model is obtained based on training of a machine learning algorithm, and the traffic prediction model is configured to output traffic variation dynamic information corresponding to an input TSN packet according to the input TSN packet and characteristic information of the input TSN packet.

12. A scheduling policy adjustment device, the device comprising:

the data acquisition module is used for acquiring a TSN data packet to be processed corresponding to a time sensitive network TSN service and acquiring characteristic information of the TSN data packet to be processed;

the business prediction module is used for inputting the TSN data packet to be processed and the characteristic information of the TSN data packet to be processed into a flow prediction model, outputting flow change dynamic information corresponding to the TSN data packet to be processed, and generating prediction information of the TSN business according to the flow change dynamic information;

and the scheduling processing module is used for adjusting the scheduling strategy of the TSN service according to the prediction information of the TSN service.

13. An electronic device, comprising:

one or more processors;

storage means configured to store one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the scheduling policy adjustment method of any one of claims 1 to 11.

14. A computer readable storage medium storing a computer program, wherein the computer program when executed by a processor implements the scheduling policy adjustment method according to any one of claims 1 to 11.