WO2025252048A1 - 信息处理方法、装置、设备、可读存储介质及程序产品 - Google Patents

信息处理方法、装置、设备、可读存储介质及程序产品

Info

Publication number
WO2025252048A1
WO2025252048A1 PCT/CN2025/098619 CN2025098619W WO2025252048A1 WO 2025252048 A1 WO2025252048 A1 WO 2025252048A1 CN 2025098619 W CN2025098619 W CN 2025098619W WO 2025252048 A1 WO2025252048 A1 WO 2025252048A1
Authority
WO
WIPO (PCT)
Prior art keywords
mapping relationship
forwarding
time
policy
forwarding route
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
PCT/CN2025/098619
Other languages
English (en)
French (fr)
Inventor
杨锋
张晓秋
姜文颖
程伟强
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Mobile Communications Group Co Ltd
Research Institute of China Mobile Communication Co Ltd
Original Assignee
China Mobile Communications Group Co Ltd
Research Institute of China Mobile Communication Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by China Mobile Communications Group Co Ltd, Research Institute of China Mobile Communication Co Ltd filed Critical China Mobile Communications Group Co Ltd
Publication of WO2025252048A1 publication Critical patent/WO2025252048A1/zh
Pending legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L45/00—Routing or path finding of packets in data switching networks
    • H04L45/12—Shortest path evaluation
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/08—Configuration management of networks or network elements
    • H04L41/0894—Policy-based network configuration management
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/16—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using machine learning or artificial intelligence
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L45/00—Routing or path finding of packets in data switching networks
    • H04L45/645—Splitting route computation layer and forwarding layer, e.g. routing according to path computational element [PCE] or based on OpenFlow functionality

Definitions

  • This disclosure relates to the field of communication technology, and in particular to an information processing method, apparatus, device, readable storage medium, and program product.
  • the network needs to leverage technologies such as big data and artificial intelligence to achieve intelligent endogenous capabilities such as on-demand service orchestration, dynamic perception and scheduling of service and network status, and flexible adjustment and optimization of network capabilities.
  • the current data delivery traffic for large-scale video and AI model corpus uploads changes dynamically over time. For example, traffic peaks in the evening and is relatively low during the day, resulting in insufficient utilization of network resources.
  • traffic peaks in the evening and is relatively low during the day, resulting in insufficient utilization of network resources.
  • the high-speed movement of space satellites at different cycles, the dynamic addition and removal of space and ground equipment, and the dynamic changes in network load over time cause the integrated space-ground network topology and multi-dimensional network resources (such as link capacity and node storage) to be time-varying, making it difficult to improve network resource utilization.
  • This disclosure provides an information processing method, apparatus, device, readable storage medium, and program product to provide more intelligent network services.
  • embodiments of this disclosure provide an information processing method applied to a first network element, comprising:
  • the first mapping relationship is the mapping relationship between time, forwarding policy and forwarding route
  • the method further includes:
  • SLA Service-Level Agreement
  • the step of performing forwarding route switching related operations based on the first mapping relationship includes:
  • the forwarding route switching operation shall be performed in the first time according to the first mapping relationship.
  • obtaining the first mapping relationship includes:
  • the first mapping relationship is obtained by training an artificial intelligence (AI) model based on the second mapping relationship and the network status information of the first network element within a historical time period.
  • the network status information includes one or more of the following: information on candidate paths to the target node and information on current neighbor links.
  • obtaining the first mapping relationship includes:
  • obtaining the first mapping relationship includes:
  • K switching paths are determined based on the target algorithm, where K is an integer greater than or equal to 1;
  • candidate switching paths corresponding to different times are determined, and the mapping relationship between different times and corresponding candidate switching paths is used as the first mapping relationship.
  • the method further includes:
  • the method further includes:
  • the first mapping relationship is updated to obtain the target first mapping relationship.
  • the first mapping relationship includes:
  • mapping relationship between time, forwarding policies, and forwarding routes at the Segment Routing (SR) policy level is the mapping relationship between time, forwarding policies, and forwarding routes at the Segment Routing (SR) policy level; and/or
  • mapping relationship between time, forwarding policy and forwarding route at the segment list level is the mapping relationship between time, forwarding policy and forwarding route at the segment list level.
  • the first mapping relationship is indicated by one or more of the following methods:
  • An indicator field is added to the Network Layer Reachability Information (NLRI) of the Border Gateway Protocol (BGP) announcement SR Policy.
  • This indicator field is used to indicate the time indicated by the first mapping relationship, and, through a first Type-Length-Value (TLV), to indicate the time indicated by the mapping relationship between the forwarding policy and the forwarding route at the SR Policy level, or through a second TLV to indicate the time indicated by the mapping relationship between the forwarding policy and the forwarding route at the Segment List level.
  • TLV Type-Length-Value
  • the third TLV is used to indicate the time indicated by the mapping relationship between the forwarding policy and the forwarding route at the SR Policy level
  • the fourth TLV is used to indicate the time indicated by the mapping relationship between the forwarding policy and the forwarding route at the Segment List level.
  • performing forwarding route switching related operations based on the first mapping relationship includes one or more of the following:
  • the delay difference between each sub-flow of the load-sharing multiple flows is adjusted so that the delay difference between each sub-flow is less than the maximum delay difference between the multiple flows.
  • embodiments of this disclosure provide an information processing method applied to a second network element, comprising:
  • the second mapping relationship is the mapping relationship between time and network parameters
  • the first mapping relationship Based on the second mapping relationship, obtain the first mapping relationship and send the first mapping relationship to the first network element, or send the second mapping relationship to the first network element to obtain the first mapping relationship, wherein the first mapping relationship is a mapping relationship between time, forwarding policy and forwarding route.
  • obtaining the second mapping relationship includes:
  • the AI model is trained based on business type requirements and historical network parameter data to obtain the second mapping relationship.
  • the first mapping relationship includes:
  • mapping relationship between time, forwarding policy and forwarding route at the SR Policy level is a mapping relationship between time, forwarding policy and forwarding route at the SR Policy level.
  • the first mapping relationship is indicated by one or more of the following methods:
  • the indication field is used to indicate the time indicated by the first mapping relationship, and to indicate the time of the SR Policy level, the time indicated by the mapping relationship between the forwarding policy and the forwarding route through the first type length value TLV, or to indicate the time of the Segment List level, the time indicated by the mapping relationship between the forwarding policy and the forwarding route through the second TLV.
  • the third TLV is used to indicate the time indicated by the mapping relationship between the forwarding policy and the forwarding route at the SR Policy level
  • the fourth TLV is used to indicate the time indicated by the mapping relationship between the forwarding policy and the forwarding route at the Segment List level.
  • embodiments of this disclosure provide an information processing apparatus applied to a first network element, comprising:
  • the first acquisition module is used to acquire a first mapping relationship, wherein the first mapping relationship is a mapping relationship between time, forwarding policy and forwarding route;
  • the first processing module is used to perform forwarding route switching related operations according to the first mapping relationship.
  • the apparatus may further include:
  • the second acquisition module is used to acquire the SLA index of the network parameters of the current path at the first moment before the arrival of the first time indicated in the first mapping relationship;
  • the first processing module is further configured to perform forwarding route switching related operations at the first time according to the first mapping relationship when the SLA index of the network parameters of the current path does not meet the service requirements.
  • the first acquisition module includes:
  • the first acquisition submodule is used to receive the second mapping relationship sent by the second network element, wherein the second mapping relationship is a mapping relationship between time and network parameters;
  • the second acquisition submodule is used to train an AI model based on the second mapping relationship and the network status information of the first network element within a historical time period to obtain the first mapping relationship.
  • the network status information includes one or more of the following: information on candidate paths to the target node and information on current neighbor links.
  • the first acquisition module is further configured to: receive the first mapping relationship sent by the second network element.
  • the first acquisition module further includes:
  • the third acquisition submodule is used to determine K switching paths according to the target algorithm, where K is an integer greater than or equal to 1;
  • the fourth acquisition submodule is used to determine candidate switching paths corresponding to different times from the K switching paths, and to use the mapping relationship between different times and corresponding candidate switching paths as the first mapping relationship.
  • the apparatus may further include:
  • the first adjustment module is used to adjust the load sharing parameters of the candidate switching paths at different times.
  • the apparatus may further include:
  • the first update module is used to update the first mapping relationship to obtain the target first mapping relationship.
  • the first mapping relationship includes:
  • mapping relationship between time, forwarding policy, and forwarding route at the SR policy level is a mapping relationship between time, forwarding policy, and forwarding route at the SR policy level.
  • mapping relationship between time, forwarding policy and forwarding route at the segment list level is the mapping relationship between time, forwarding policy and forwarding route at the segment list level.
  • the first mapping relationship is indicated by one or more of the following methods:
  • the indication field is used to indicate the time indicated by the first mapping relationship, and the time indicated by the mapping relationship between the forwarding policy and the forwarding route at the SR Policy level through the first TLV, or the time indicated by the mapping relationship between the forwarding policy and the forwarding route at the Segment List level through the second TLV.
  • the third TLV is used to indicate the time indicated by the mapping relationship between the forwarding policy and the forwarding route at the SR Policy level
  • the fourth TLV is used to indicate the time indicated by the mapping relationship between the forwarding policy and the forwarding route at the Segment List level.
  • the first processing module is further configured to perform one or more of the following:
  • the delay difference between each sub-flow of the load-sharing multiple flows is adjusted so that the delay difference between each sub-flow is less than the maximum delay difference between the multiple flows.
  • embodiments of this disclosure provide an information processing apparatus applied to a second network element, comprising:
  • the first acquisition module is used to acquire the second mapping relationship, wherein the second mapping relationship is a mapping relationship between time and network parameters;
  • the first sending module is configured to obtain the first mapping relationship according to the second mapping relationship and send the first mapping relationship to the first network element, or send the second mapping relationship to the first network element to obtain the first mapping relationship, wherein the first mapping relationship is a mapping relationship between time, forwarding policy and forwarding route.
  • the first acquisition module includes:
  • the first acquisition submodule is used to train the AI model based on business type requirements and historical network parameter data to obtain the second mapping relationship.
  • the first mapping relationship includes:
  • mapping relationship between time, forwarding policy and forwarding route at the SR Policy level is a mapping relationship between time, forwarding policy and forwarding route at the SR Policy level.
  • the first mapping relationship is indicated by one or more of the following methods:
  • the indication field is used to indicate the time indicated by the first mapping relationship, and to indicate the time of the SR Policy level, the time indicated by the mapping relationship between the forwarding policy and the forwarding route through the first type length value TLV, or to indicate the time of the Segment List level, the time indicated by the mapping relationship between the forwarding policy and the forwarding route through the second TLV.
  • the third TLV is used to indicate the time indicated by the mapping relationship between the forwarding policy and the forwarding route at the SR Policy level
  • the fourth TLV is used to indicate the time indicated by the mapping relationship between the forwarding policy and the forwarding route at the Segment List level.
  • embodiments of this disclosure provide an information processing apparatus applied to a first network element, comprising: a processor;
  • the processor is configured to obtain a first mapping relationship, wherein the first mapping relationship is a mapping relationship between time, forwarding policy and forwarding route; and to perform forwarding route switching related operations according to the first mapping relationship.
  • the processor is further configured to:
  • the forwarding route switching operation shall be performed in the first time according to the first mapping relationship.
  • the information processing apparatus further includes a transceiver
  • the transceiver is used to receive a second mapping relationship sent by a second network element, wherein the second mapping relationship is a mapping relationship between time and network parameters;
  • the processor is also used for:
  • the first mapping relationship is obtained by training an AI model based on the second mapping relationship and the network status information of the first network element within a historical time period.
  • the network status information includes one or more of the following: information on candidate paths to the target node and information on current neighbor links.
  • the information processing apparatus further includes a transceiver
  • the transceiver is used to: receive the first mapping relationship sent by the second network element.
  • the processor is further configured to:
  • K switching paths are determined based on the target algorithm, where K is an integer greater than or equal to 1;
  • candidate switching paths corresponding to different times are determined, and the mapping relationship between different times and corresponding candidate switching paths is used as the first mapping relationship.
  • the processor is further configured to:
  • the processor is further configured to:
  • the first mapping relationship is updated to obtain the target first mapping relationship.
  • the first mapping relationship includes:
  • mapping relationship between time, forwarding policy, and forwarding route at the SR policy level is a mapping relationship between time, forwarding policy, and forwarding route at the SR policy level.
  • mapping relationship between time, forwarding policy and forwarding route at the segment list level is the mapping relationship between time, forwarding policy and forwarding route at the segment list level.
  • the first mapping relationship is indicated by one or more of the following methods:
  • the indication field is used to indicate the time indicated by the first mapping relationship, and the time indicated by the mapping relationship between the forwarding policy and the forwarding route at the SR Policy level through the first TLV, or the time indicated by the mapping relationship between the forwarding policy and the forwarding route at the Segment List level through the second TLV.
  • the third TLV is used to indicate the time indicated by the mapping relationship between the forwarding policy and the forwarding route at the SR Policy level
  • the fourth TLV is used to indicate the time indicated by the mapping relationship between the forwarding policy and the forwarding route at the Segment List level.
  • the processor is further configured to include one or more of the following:
  • the delay difference between each sub-flow of the load-sharing multiple flows is adjusted so that the delay difference between each sub-flow is less than the maximum delay difference between the multiple flows.
  • embodiments of this disclosure provide an information processing apparatus applied to a second network element, comprising: a processor and a transceiver;
  • the processor is configured to obtain a second mapping relationship, wherein the second mapping relationship is a mapping relationship between time and network parameters;
  • the transceiver is configured to obtain the first mapping relationship according to the second mapping relationship and send the first mapping relationship to the first network element, or send the second mapping relationship to the first network element to obtain the first mapping relationship, wherein the first mapping relationship is a mapping relationship between time, forwarding policy and forwarding route.
  • the processor is further configured to:
  • the AI model is trained based on business type requirements and historical network parameter data to obtain the second mapping relationship.
  • the first mapping relationship includes:
  • mapping relationship between time, forwarding policy and forwarding route at the SR Policy level is a mapping relationship between time, forwarding policy and forwarding route at the SR Policy level.
  • the first mapping relationship is indicated by one or more of the following methods:
  • the indication field is used to indicate the time indicated by the first mapping relationship, and to indicate the time of the SR Policy level, the time indicated by the mapping relationship between the forwarding policy and the forwarding route through the first type length value TLV, or to indicate the time of the Segment List level, the time indicated by the mapping relationship between the forwarding policy and the forwarding route through the second TLV.
  • the third TLV is used to indicate the time indicated by the mapping relationship between the forwarding policy and the forwarding route at the SR Policy level
  • the fourth TLV is used to indicate the time indicated by the mapping relationship between the forwarding policy and the forwarding route at the Segment List level.
  • embodiments of this disclosure also provide a communication device, including: a memory, a processor, and a program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps in the information processing method described above.
  • embodiments of this disclosure also provide a readable storage medium storing a program that, when executed by a processor, implements the steps in the information processing method described above.
  • embodiments of this disclosure also provide a computer program product, including computer instructions that, when executed by a processor, implement the steps in the information processing method described above.
  • the first network element can perform forwarding route switching related operations according to the first mapping relationship. Since the first mapping relationship is a mapping relationship between time, forwarding policy and forwarding route, the forwarding route switching related operations can change dynamically over time and can be adjusted according to the expected route path. This allows for advance planning and prevention of potential performance degradation or bottlenecks, packet loss, latency or bandwidth not meeting service requirements, etc., achieving efficient and rational utilization of network bandwidth and other resources, and providing more intelligent network services.
  • FIG. 1 is a flowchart of one of the information processing methods provided in the embodiments of this disclosure.
  • FIG. 2 is a second flowchart of the information processing method provided in the embodiments of this disclosure.
  • Figure 3 is a schematic diagram of the second mapping relationship according to an embodiment of this disclosure.
  • Figure 4 is a schematic diagram of the extended NLRI
  • FIGS. 5(a) and 5(b) are schematic diagrams of time-dependent sub-TLVs
  • Figures 6(a) and 6(b) are schematic diagrams of time-related sub-TLVs in embodiments of this disclosure.
  • Figure 7 is a structural diagram of an information processing apparatus provided in an embodiment of this disclosure.
  • Figure 8 is a second structural diagram of the information processing device provided in the embodiments of this disclosure.
  • Figure 9 is a third structural diagram of the information processing device provided in an embodiment of this disclosure.
  • Figure 10 is a fourth structural diagram of the information processing apparatus provided in the embodiments of this disclosure.
  • the term "and/or” describes the relationship between related objects, indicating that three relationships can exist.
  • a and/or B can represent three cases: A alone, A and B simultaneously, and B alone.
  • the character "/” generally indicates that the preceding and following related objects have an "or" relationship.
  • multiple refers to two or more, and other quantifiers are similar.
  • FIG. 1 is a flowchart of an information processing method provided in an embodiment of this disclosure, the method is used for a first network element.
  • This first network element can be, for example, a forwarding plane network element.
  • the method includes the following steps:
  • Step 101 Obtain the first mapping relationship, wherein the first mapping relationship is the mapping relationship between time, forwarding policy and forwarding route.
  • a Segment Routing IPv6 Traffic Engineering Policy can contain multiple candidate paths. Each candidate path carries a priority attribute. The highest-priority valid candidate path becomes the primary path of the SRv6 TE Policy.
  • a candidate path can contain multiple Segment Lists, each carrying a Weight attribute.
  • Each Segment List is an explicit SID (Segment Identifier) stack, which instructs network devices to forward packets. Multiple Segment Lists can be used for load balancing.
  • a second mapping relationship sent by a second network element can be received, wherein the second mapping relationship is a mapping relationship between time and network parameters.
  • an AI model is trained based on the second mapping relationship and network condition information from the first network element over a historical time period to obtain the first mapping relationship.
  • the network condition information includes one or more of the following: information on candidate paths to the target node and information on current neighbor links.
  • Network parameters include bandwidth, latency, packet loss rate, jitter, etc.
  • the terminal can use the second mapping relationship and the network status information of the first network element within a historical time period as input to the model, and train it through AI algorithms such as reinforcement learning (RL) to obtain the first mapping relationship.
  • AI model includes, but is not limited to, neural network models, decision tree models, etc.
  • the time in the second mapping relationship can include multiple moments or time periods, and the forwarding strategy includes multi-path SR strategy (SR strategy (Policy) level) and multi-segment list (Segment List level).
  • SR strategy Policy
  • Segment List level multi-segment list
  • forwarding network elements can retrain their local models (such as AI models) based on their own local candidate paths to the destination node and the current network status such as neighbor links, so as to obtain the optimal forwarding path at the current moment and the forwarding path table for subsequent moments.
  • local models such as AI models
  • the first network element may receive the first mapping relationship sent by the second network element, that is, the first mapping relationship is determined by the second network element.
  • the first network element may further determine K handover paths according to the target algorithm, where K is an integer greater than or equal to 1; from the K handover paths, candidate handover paths corresponding to different times are determined, and the mapping relationship between different times and corresponding candidate handover paths is used as the first mapping relationship.
  • the time may include multiple moments or time periods, etc.
  • the target algorithm may include, for example, the K Shortest Paths (KSP) routing algorithm, the flexible load-sharing algorithm, etc.
  • KSP K Shortest Paths
  • K switching paths can be obtained based on the KSP routing algorithm and flexible load balancing algorithm.
  • T1 the path switches to K1
  • T2 it switches to K2.
  • K1 and K2 are greater than or equal to 1.
  • T1 and T2 are any two different times.
  • the load sharing parameters of the candidate switching paths corresponding to different times can be adjusted so that the network service provided meets expectations.
  • the first network element can also update the first mapping relationship to obtain the target first mapping relationship.
  • the first network element can also perform local model training based on its own network conditions to obtain the target first mapping relationship.
  • the first mapping relationship includes:
  • the time in the first mapping relationship can be the same as the time in the second mapping relationship.
  • Table 1 shows an example of the first mapping relationship.
  • the forwarding policy at time T1 corresponding to the Policy level is represented by SRv6Policy1.
  • the forwarding routes are represented by Segment List1 and Segment List2. The choice of which forwarding policy to use at a given time depends on factors such as the network conditions at that time.
  • the multi-segment list scheme i.e., the mapping relationship between time, forwarding policy and forwarding route at the segment list level
  • the multi-stream optimization scenario mainly adopts the multi-segment routing (SR) policy scheme (i.e., the mapping relationship between time, forwarding policy and forwarding route at the SR policy level).
  • SR multi-segment routing
  • Step 102 Perform forwarding route switching operations according to the first mapping relationship.
  • a check can be performed in advance before that time arrives to determine whether forwarding route switching operations can be performed.
  • the SLA index of the network parameters of the current path is obtained. If the SLA index of the network parameters of the current path does not meet the service requirements, a forwarding route switching operation is performed at the first time according to the first mapping relationship.
  • the first time can be any time in the first mapping relationship. That is, in this embodiment of the disclosure, the SLA index is obtained in advance at a certain moment before the first time, and it is determined whether the SLA index of the network parameters of the current path meets the service requirements based on the SLA index. If the requirements are not met, a forwarding route switching operation is performed at the first time according to the forwarding policy and forwarding route corresponding to the first time in the first mapping relationship.
  • each time point can divide a day into four segments: for example, 9:00 AM, 3:00 PM, peak time (9:00 PM), and valley time (3:00 AM). Using these four points as the center, the day is divided into four time periods.
  • the switching time i.e., each of these four time periods, is the midpoint between these four time periods: 6:00 AM, 12:00 PM, 6:00 PM, and 12:00 AM.
  • X seconds or milliseconds X greater than or equal to 0
  • the forwarding route switching operation is executed.
  • the forwarding route switching related operations are imperceptible to the user and are elastically scalable (e.g., multiple policies are presented to the outside through a policy group, and multiple SLs are represented through Binding SID).
  • performing forwarding route switching related operations includes one or more of the following:
  • the first mapping relationship is updated according to the first cycle, which can be set as needed;
  • the delay difference between each sub-flow of the load-sharing multiple flows is adjusted so that the delay difference between each sub-flow is less than the maximum delay difference between the multiple flows.
  • the first mapping relationship is indicated in one or more of the following ways:
  • the indication field is used to indicate the time indicated by the first mapping relationship, and the time indicated by the mapping relationship between the forwarding policy and the forwarding route at the SR Policy level through the first TLV, or the time indicated by the mapping relationship between the forwarding policy and the forwarding route at the Segment List level through the second TLV.
  • NLRI Network Layer Reachability Information
  • the third TLV is used to indicate the time indicated by the mapping relationship between the forwarding policy and the forwarding route at the SR Policy level
  • the fourth TLV is used to indicate the time indicated by the mapping relationship between the forwarding policy and the forwarding route at the Segment List level.
  • the first network element can perform forwarding route switching related operations according to the first mapping relationship. Since the first mapping relationship is a mapping relationship between time, forwarding policy and forwarding route, the forwarding route switching related operations can change dynamically over time and can be adjusted according to the expected route path. This allows for advance planning and prevention of potential performance degradation or bottlenecks, packet loss, latency or bandwidth not meeting service requirements, etc., achieving efficient and rational utilization of network bandwidth and other resources, and providing more intelligent network services.
  • FIG. 2 is a flowchart of an information processing method provided in an embodiment of this disclosure, applied to a second network element.
  • This second network element may be, for example, a controller, an intelligent module within a controller, or an intelligent network element, etc. As shown in Figure 2, the method includes the following steps:
  • Step 201 Obtain the second mapping relationship, wherein the second mapping relationship is the mapping relationship between time and network parameters.
  • the AI model can be trained based on business type requirements and historical network parameter data to obtain the second mapping relationship.
  • the AI model can also be replaced as needed.
  • Historical network parameter data may include:
  • Packet-level and flow-level data including Deep Packet Inspection (DPI) information, flow granular data, and relevant flow characteristics (number of packets, packet size, timestamp, path, flow creation time, etc.);
  • DPI Deep Packet Inspection
  • Network status physical, topological, and logical configurations, etc.
  • SDN Software-Defined Network
  • Service level telemetry Service load, Quality of Service (QoS), bandwidth, latency, packet loss rate, and other SLA metrics;
  • QoS Quality of Service
  • social networks such as the number of people participating in a sports event
  • weather forecasts etc.
  • the aforementioned second mapping relationship can be considered as information about network parameters changing over time, such as peaks and troughs in time. Taking traffic as an example, this second mapping relationship can be considered as the curve relating traffic to time.
  • a global traffic model can be trained using AI algorithms such as Reinforcement Learning (RL) to establish a functional relationship between time and traffic bandwidth, latency, and other requirements.
  • RL Reinforcement Learning
  • adjustment thresholds can be set, for example, a bandwidth threshold of 20% or a latency threshold of X ms.
  • the switching time can be selected as follows: Divide the day into four time periods, such as 9:00 AM, 3:00 PM, peak time (9:00 PM), and valley time (3:00 AM). Using these four nodes as the center points, divide the day into four time periods. The switching time is the midpoint of these four time periods, i.e., 6:00 AM, 12:00 PM, 6:00 PM, and 12:00 AM. Then, calculate the maximum traffic bandwidth for each time period and increase the upper limit by 10% to 20%. That is, the maximum traffic bandwidth corresponding to that time period can be increased by 10% to 20%.
  • Step 202 Obtain the first mapping relationship according to the second mapping relationship, and send the first mapping relationship to the first network element, or send the second mapping relationship to the first network element to obtain the first mapping relationship, wherein the first mapping relationship is a mapping relationship between time, forwarding policy and forwarding route.
  • the second network element can retrain the AI model based on the second mapping relationship and historical network parameter data of other network elements to obtain the first mapping relationship.
  • the first mapping relationship includes:
  • mapping relationship between time, forwarding policy and forwarding route at the SR Policy level is a mapping relationship between time, forwarding policy and forwarding route at the SR Policy level.
  • the existing protocol can be extended to send the second mapping relationship to the first network element.
  • the first mapping relationship is indicated in one or more of the following ways:
  • the indication field is used to indicate the time indicated by the first mapping relationship, and the time indicated by the mapping relationship between the forwarding policy and the forwarding route at the SR Policy level through the first TLV, or the time indicated by the mapping relationship between the forwarding policy and the forwarding route at the Segment List level through the second TLV.
  • NLRI Network Layer Reachability Information
  • the third TLV is used to indicate the time indicated by the mapping relationship between the forwarding policy and the forwarding route at the SR Policy level
  • the fourth TLV is used to indicate the time indicated by the mapping relationship between the forwarding policy and the forwarding route at the Segment List level.
  • the BGP protocol advertisement SR PolicyNLRI Network Layer Reachability Information
  • SR PolicyNLRI Network Layer Reachability Information
  • Figure 4 the specific extension method is shown in Figure 4, where Time1, Time2, etc., are used to carry the aforementioned time. For example, 6:00, 12:00, 18:00, and 24:00 in Figure 3.
  • time-related sub-TLVs Type-Length-Value
  • time-related sub-TLVs can be added to indicate the time at the SR Policy level, the time indicated by the mapping relationship between forwarding policies and forwarding routes, or the time at the Segment List level, and the time indicated by the mapping relationship between forwarding policies and forwarding routes.
  • the BGP-LS (BGP Link State) protocol can be extended to add SR Policy Candidate Path (Time-Policy Level) and Segment List state TLV (Time-SL Level) to indicate the time at the SR Policy level, the time indicated by the mapping relationship between forwarding policies and forwarding routes, the time at the Segment List level, and the time indicated by the mapping relationship between forwarding policies and forwarding routes, respectively.
  • SR Policy Candidate Path Time-Policy Level
  • Segment List state TLV Time-SL Level
  • the first network element can perform forwarding route switching related operations according to the first mapping relationship. Since the first mapping relationship is a mapping relationship between time, forwarding policy and forwarding route, the forwarding route switching related operations can change dynamically over time and can be adjusted according to the expected route path. This allows for advance planning and prevention of potential performance degradation or bottlenecks, packet loss, latency or bandwidth not meeting service requirements, etc., achieving efficient and rational utilization of network bandwidth and other resources, and providing more intelligent network services.
  • FIG 7 is a structural diagram of an information processing apparatus provided in an embodiment of this disclosure, applied to a first network element.
  • the information processing apparatus includes:
  • the first acquisition module 701 is used to acquire a first mapping relationship, wherein the first mapping relationship is a mapping relationship between time, forwarding policy and forwarding route; the first processing module 702 is used to perform forwarding route switching related operations according to the first mapping relationship.
  • the apparatus may further include:
  • the second acquisition module is used to acquire the SLA index of the network parameters of the current path at the first moment before the arrival of the first time indicated in the first mapping relationship;
  • the first processing module is further configured to perform forwarding route switching related operations at the first time according to the first mapping relationship when the SLA index of the network parameters of the current path does not meet the service requirements.
  • the first acquisition module includes:
  • the first acquisition submodule is used to receive the second mapping relationship sent by the second network element, wherein the second mapping relationship is a mapping relationship between time and network parameters;
  • the second acquisition submodule is used to train an AI model based on the second mapping relationship and the network status information of the first network element within a historical time period to obtain the first mapping relationship.
  • the network status information includes one or more of the following: information on candidate paths to the target node and information on current neighbor links.
  • the first acquisition module is further configured to: receive the first mapping relationship sent by the second network element.
  • the first acquisition module further includes:
  • the third acquisition submodule is used to determine K switching paths according to the target algorithm, where K is an integer greater than or equal to 1;
  • the fourth acquisition submodule is used to determine candidate switching paths corresponding to different times from the K switching paths, and to use the mapping relationship between different times and corresponding candidate switching paths as the first mapping relationship.
  • the apparatus may further include:
  • the first adjustment module is used to adjust the load sharing parameters of the candidate switching paths at different times.
  • the apparatus may further include:
  • the first update module is used to update the first mapping relationship to obtain the target first mapping relationship.
  • mapping relationship between time, forwarding policy, and forwarding route at the SR policy level is a mapping relationship between time, forwarding policy, and forwarding route at the SR policy level.
  • mapping relationship between time, forwarding policy and forwarding route at the segment list level is the mapping relationship between time, forwarding policy and forwarding route at the segment list level.
  • the first mapping relationship is indicated by one or more of the following methods:
  • the indication field is used to indicate the time indicated by the first mapping relationship, and the time indicated by the mapping relationship between the forwarding policy and the forwarding route at the SR Policy level through the first TLV, or the time indicated by the mapping relationship between the forwarding policy and the forwarding route at the Segment List level through the second TLV.
  • the third TLV is used to indicate the time indicated by the mapping relationship between the forwarding policy and the forwarding route at the SR Policy level
  • the fourth TLV is used to indicate the time indicated by the mapping relationship between the forwarding policy and the forwarding route at the Segment List level.
  • the first processing module is further configured to perform one or more of the following:
  • the delay difference between each sub-flow of the load-sharing multiple flows is adjusted so that the delay difference between each sub-flow is less than the maximum delay difference between the multiple flows.
  • the apparatus provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effect are similar, so it will not be described again here.
  • FIG 8 is a structural diagram of an information processing apparatus provided in an embodiment of this disclosure, applied to a second network element.
  • the information processing apparatus includes:
  • the first acquisition module 801 is used to acquire a second mapping relationship, wherein the second mapping relationship is a mapping relationship between time and network parameters; the first sending module 802 is used to acquire a first mapping relationship according to the second mapping relationship and send the first mapping relationship to a first network element, or send the second mapping relationship to the first network element, wherein the first mapping relationship is a mapping relationship between time, forwarding policy and forwarding route.
  • the first acquisition module includes:
  • the first acquisition submodule is used to train the AI model based on business type requirements and historical network parameter data to obtain the second mapping relationship.
  • the first mapping relationship includes:
  • the first mapping relationship is indicated by one or more of the following methods:
  • the indication field is used to indicate the time indicated by the first mapping relationship, and to indicate the time of the SR Policy level, the time indicated by the mapping relationship between the forwarding policy and the forwarding route through the first type length value TLV, or to indicate the time of the Segment List level, the time indicated by the mapping relationship between the forwarding policy and the forwarding route through the second TLV.
  • the third TLV is used to indicate the time indicated by the mapping relationship between the forwarding policy and the forwarding route at the SR Policy level
  • the fourth TLV is used to indicate the time indicated by the mapping relationship between the forwarding policy and the forwarding route at the Segment List level.
  • the apparatus provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effect are similar, so it will not be described again here.
  • FIG 9 is a structural diagram of an information processing device provided in an embodiment of this disclosure, applied to a first network element.
  • the information processing device includes: a processor 901 and a transceiver 902;
  • the processor 901 is configured to obtain a first mapping relationship, wherein the first mapping relationship is a mapping relationship between time, forwarding policy and forwarding route; and to perform forwarding route switching related operations according to the first mapping relationship.
  • the processor 901 is further configured to:
  • the forwarding route switching operation shall be performed in the first time according to the first mapping relationship.
  • the processor 901 is further configured to: train an AI model based on the second mapping relationship and the network status information of the first network element within a historical time period to obtain the first mapping relationship, wherein the network status information includes one or more of the following: information on candidate paths to the target node and information on current neighbor links.
  • the transceiver 902 is further configured to: receive the first mapping relationship sent by the second network element.
  • the processor 901 is further configured to:
  • candidate switching paths corresponding to different times are determined, and the mapping relationship between different times and corresponding candidate switching paths is used as the first mapping relationship.
  • the processor 901 is further configured to:
  • the first mapping relationship is updated to obtain the target first mapping relationship.
  • the first mapping relationship includes:
  • mapping relationship between time, forwarding policy and forwarding route at the segment list level is the mapping relationship between time, forwarding policy and forwarding route at the segment list level.
  • the first mapping relationship is indicated by one or more of the following methods:
  • the third TLV is used to indicate the time indicated by the mapping relationship between the forwarding policy and the forwarding route at the SR Policy level
  • the fourth TLV is used to indicate the time indicated by the mapping relationship between the forwarding policy and the forwarding route at the Segment List level.
  • the processor 901 is further configured to perform one or more of the following:
  • the delay difference between each sub-flow of the load-sharing multiple flows is adjusted so that the delay difference between each sub-flow is less than the maximum delay difference between the multiple flows.
  • the apparatus provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effect are similar, so it will not be described again here.
  • the processor 1001 is used to obtain a second mapping relationship, wherein the second mapping relationship is a mapping relationship between time and network parameters;
  • the transceiver 1002 is configured to obtain the first mapping relationship according to the second mapping relationship and send the first mapping relationship to the first network element, or send the second mapping relationship to the first network element to obtain the first mapping relationship, wherein the first mapping relationship is a mapping relationship between time, forwarding policy and forwarding route.
  • the AI model is trained based on business type requirements and historical network parameter data to obtain the second mapping relationship.
  • the first mapping relationship includes:
  • the indication field is used to indicate the time indicated by the first mapping relationship, and to indicate the time of the SR Policy level, the time indicated by the mapping relationship between the forwarding policy and the forwarding route through the first type length value TLV, or to indicate the time of the Segment List level, the time indicated by the mapping relationship between the forwarding policy and the forwarding route through the second TLV.
  • the third TLV is used to indicate the time indicated by the mapping relationship between the forwarding policy and the forwarding route at the SR Policy level
  • the fourth TLV is used to indicate the time indicated by the mapping relationship between the forwarding policy and the forwarding route at the Segment List level.
  • the apparatus provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effect are similar, so it will not be described again here.
  • the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a processor-readable storage medium.
  • This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this disclosure.
  • the aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Computing Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

本公开公开了一种信息处理方法、装置、设备、可读存储介质及程序产品，涉及通信技术领域，以提供更智能化的网络服务。该方法包括：获取第一映射关系，其中，所述第一映射关系为时间、转发策略与转发路由之间的映射关系；根据所述第一映射关系，执行转发路由切换相关操作。本公开实施例可以提升网络资源利用率，提供更智能化的网络服务。

Description

信息处理方法、装置、设备、可读存储介质及程序产品
相关公开的交叉引用
本公开基于公开号为202410713252.2、公开日为2024年06月04日的中国专利公开提出，并要求该中国专利公开的优先权，该中国专利公开的全部内容在此引入本公开作为参考。
技术领域
本公开涉及通信技术领域，尤其涉及一种信息处理方法、装置、设备、可读存储介质及程序产品。
背景技术
随着算网融合一体化业务需求和网络自身演进，算网一体的网络运营面临着海量数据、业务多样差异化等方面的挑战，需要网络通过大数据、人工智能等技术，实现业务按需编排、业务和网络状态可动态感知与调度、网络能力可弹性调整优化的智能内生能力。
现有已有一些基于人工智能(Artificial Intelligence，AI)的智能网络运维技术研究，构建通信网络全生命周期的自动化、智能化运维能力。
目前的大视频、AI模型语料上传等数据快递类业务流量，随时间动态的变化，例如晚间时段为流量高峰期，白天时段相对空闲，网络资源的利用率没有得到充分的利用，同时面向6G的天地一体化网络，空间卫星不同周期的高速运动、空间与地面设备的动态加入退出、网络承载业务负荷随时间动态变化等，导致天地一体化网络拓扑和多维网络资源(如链路容量、节点存储等)具有时变性，造成网络资源利用率难以提升等问题。
发明内容
本公开实施例提供一种信息处理方法、装置、设备、可读存储介质及程序产品，以提供更智能化的网络服务。
第一方面，本公开实施例提供了一种信息处理方法，应用于第一网元，包括：
获取第一映射关系，其中，所述第一映射关系为时间、转发策略与转发路由之间的映射关系；
根据所述第一映射关系，执行转发路由切换相关操作。
在一些实施例中，所述方法还包括：
在所述第一映射关系中所指示的第一时间到达前的第一时刻，获取当前路径的网络参数的服务等级协议(Service-Level Agreement，SLA)指标；
所述根据所述第一映射关系，执行转发路由切换相关操作，包括：
在当前路径的网络参数的SLA指标不满足业务要求的情况下，在所述第一时间根据所述第一映射关系，执行转发路由切换相关操作。
在一些实施例中，所述获取第一映射关系，包括：
接收第二网元发送的第二映射关系，其中，所述第二映射关系为时间与网络参数之间的映射关系；
根据所述第二映射关系和所述第一网元的历史时间段内的网络状况信息进行人工智能(Artificial Intelligence，AI)模型训练，得到所述第一映射关系，其中，所述网络状况信息包括：到目标节点的候选路径的信息、当前邻居链路的信息中的一项或多项。
在一些实施例中，所述获取第一映射关系，包括：
接收第二网元发送的所述第一映射关系。
在一些实施例中，所述获取第一映射关系，包括：
根据目标算法确定K条切换路径，其中，K为大于或等于1的整数；
从所述K条切换路径中，确定不同时间对应的候选切换路径，并将不同时间和对应的候选切换路径之间的映射关系，作为所述第一映射关系。
在一些实施例中，所述方法还包括：
对不同时间对应的候选切换路径的负载分担参数进行调整。
在一些实施例中，所述方法还包括：
对所述第一映射关系进行更新，得到目标第一映射关系。
在一些实施例中，所述第一映射关系包括：
段路由(Segment Routing，SR)策略(Policy)级别的时间、转发策略与转发路由之间的映射关系；和/或
段列表(Segment List)级别的时间、转发策略与转发路由之间的映射关系。
在一些实施例中，所述第一映射关系通过以下一种或多种方式指示：
在边界网关协议(Border Gateway Protocol，BGP)协议通告SR Policy网络层可达信息(Network Layer Reachability Information，NLRI)中增加指示域，所述指示域用于指示所述第一映射关系所指示的时间，以及，通过第一类型长度取值(Type-Length-Value，TLV)指示所述SR Policy级别的时间、转发策略与转发路由之间的映射关系所指示的时间，或者，通过第二TLV指示段列表Segment List级别的时间、转发策略与转发路由之间的映射关系所指示的时间；
在BGP链路状态协议中增加第三TLV或第四TLV，所述第三TLV用于指示所述SR Policy级别的时间、转发策略与转发路由之间的映射关系所指示的时间，所述第四TLV用于指示Segment List级别的时间、转发策略与转发路由之间的映射关系所指示的时间。
在一些实施例中，所述根据所述第一映射关系，执行转发路由切换相关操作，包括以下一项或多项：
根据所述第一映射关系执行转发路由切换；
按照第一周期更新所述第一映射关系；
根据链路负载和带宽约束情况，剪除或调整发生拥塞的链路；
根据时延约束，计算最短传输路径；
对负载分担的多条流的每个小流之间的时延差进行调整，使得每个小流之间的时延差小于多条流间的最大时延差。
第二方面，本公开实施例提供了一种信息处理方法，应用于第二网元，包括：
获取第二映射关系，其中，所述第二映射关系为时间与网络参数之间的映射关系；
根据所述第二映射关系，获取第一映射关系，并向第一网元发送所述第一映射关系，或者，向所述第一网元发送所述第二映射关系，用于获取所述第一映射关系，其中，所述第一映射关系为时间、转发策略与转发路由之间的映射关系。
在一些实施例中，所述获取第二映射关系，包括：
根据业务类型需求信息、网络参数历史数据对AI模型进行训练，得到所述第二映射关系。
在一些实施例中，所述第一映射关系包括：
SR Policy级别的时间、转发策略与转发路由之间的映射关系；和/或
Segment List级别的时间、转发策略与转发路由之间的映射关系。
在一些实施例中，所述第一映射关系通过以下一种或多种方式指示：
在BGP协议通告SR PolicyNLRI中增加指示域，所述指示域用于指示所述第一映射关系所指示的时间，以及，通过第一类型长度取值TLV指示所述SR Policy级别的时间、转发策略与转发路由之间的映射关系所指示的时间，或者，通过第二TLV指示段列表Segment List级别的时间、转发策略与转发路由之间的映射关系所指示的时间；
在BGP链路状态协议中增加第三TLV或第四TLV，所述第三TLV用于指示所述SR Policy级别的时间、转发策略与转发路由之间的映射关系所指示的时间，所述第四TLV用于指示Segment List级别的时间、转发策略与转发路由之间的映射关系所指示的时间。
第三方面，本公开实施例提供了一种信息处理装置，应用于第一网元，包括：
第一获取模块，用于获取第一映射关系，其中，所述第一映射关系为时间、转发策略与转发路由之间的映射关系；
第一处理模块，用于根据所述第一映射关系，执行转发路由切换相关操作。
在一些实施例中，所述装置还可包括：
第二获取模块，用于在所述第一映射关系中所指示的第一时间到达前的第一时刻，获取当前路径的网络参数的SLA指标；
所述第一处理模块，还用于在当前路径的网络参数的SLA指标不满足业务要求的情况下，在所述第一时间根据所述第一映射关系，执行转发路由切换相关操作。
在一些实施例中，所述第一获取模块包括：
第一获取子模块，用于接收第二网元发送的第二映射关系，其中，所述第二映射关系为时间与网络参数之间的映射关系；
第二获取子模块，用于根据所述第二映射关系和所述第一网元的历史时间段内的网络状况信息进行AI模型训练，得到所述第一映射关系，其中，所述网络状况信息包括：到目标节点的候选路径的信息、当前邻居链路的信息中的一项或多项。
在一些实施例中，所述第一获取模块还用于：接收第二网元发送的所述第一映射关系。
在一些实施例中，所述第一获取模块还包括：
第三获取子模块，用于根据目标算法确定K条切换路径，其中，K为大于或等于1的整数；
第四获取子模块，用于从所述K条切换路径中，确定不同时间对应的候选切换路径，并将不同时间和对应的候选切换路径之间的映射关系，作为所述第一映射关系。
在一些实施例中，所述装置还可包括：
第一调整模块，用于对不同时间对应的候选切换路径的负载分担参数进行调整。
在一些实施例中，所述装置还可包括：
第一更新模块，用于对所述第一映射关系进行更新，得到目标第一映射关系。
在一些实施例中，所述第一映射关系包括：
SR策略(Policy)级别的时间、转发策略与转发路由之间的映射关系；和/或
段列表(Segment List)级别的时间、转发策略与转发路由之间的映射关系。
在一些实施例中，所述第一映射关系通过以下一种或多种方式指示：
在BGP协议通告SR Policy NLRI中增加指示域，所述指示域用于指示所述第一映射关系所指示的时间，以及，通过第一TLV指示所述SR Policy级别的时间、转发策略与转发路由之间的映射关系所指示的时间，或者，通过第二TLV指示段列表Segment List级别的时间、转发策略与转发路由之间的映射关系所指示的时间；
在BGP链路状态协议中增加第三TLV或第四TLV，所述第三TLV用于指示所述SR Policy级别的时间、转发策略与转发路由之间的映射关系所指示的时间，所述第四TLV用于指示Segment List级别的时间、转发策略与转发路由之间的映射关系所指示的时间。
在一些实施例中，所述第一处理模块还用于以下一项或多项：
根据所述第一映射关系执行转发路由切换；
按照第一周期更新所述第一映射关系；
根据链路负载和带宽约束情况，剪除或调整发生拥塞的链路；
根据时延约束，计算最短传输路径；
对负载分担的多条流的每个小流之间的时延差进行调整，使得每个小流之间的时延差小于多条流间的最大时延差。
第四方面，本公开实施例提供了一种信息处理装置，应用于第二网元，包括：
第一获取模块，用于获取第二映射关系，其中，所述第二映射关系为时间与网络参数之间的映射关系；
第一发送模块，用于根据所述第二映射关系，获取第一映射关系，并向第一网元发送所述第一映射关系，或者，向所述第一网元发送所述第二映射关系，用于获取所述第一映射关系，其中，所述第一映射关系为时间、转发策略与转发路由之间的映射关系。
在一些实施例中，所述第一获取模块包括：
第一获取子模块，用于根据业务类型需求信息、网络参数历史数据对AI模型进行训练，得到所述第二映射关系。
在一些实施例中，所述第一映射关系包括：
SR Policy级别的时间、转发策略与转发路由之间的映射关系；和/或
Segment List级别的时间、转发策略与转发路由之间的映射关系。
在一些实施例中，所述第一映射关系通过以下一种或多种方式指示：
在BGP协议通告SR PolicyNLRI中增加指示域，所述指示域用于指示所述第一映射关系所指示的时间，以及，通过第一类型长度取值TLV指示所述SR Policy级别的时间、转发策略与转发路由之间的映射关系所指示的时间，或者，通过第二TLV指示段列表Segment List级别的时间、转发策略与转发路由之间的映射关系所指示的时间；
在BGP链路状态协议中增加第三TLV或第四TLV，所述第三TLV用于指示所述SR Policy级别的时间、转发策略与转发路由之间的映射关系所指示的时间，所述第四TLV用于指示Segment List级别的时间、转发策略与转发路由之间的映射关系所指示的时间。
第五方面，本公开实施例提供了一种信息处理装置，应用于第一网元，包括：处理器；
所述处理器，用于获取第一映射关系，其中，所述第一映射关系为时间、转发策略与转发路由之间的映射关系；根据所述第一映射关系，执行转发路由切换相关操作。
在一些实施例中，所述处理器还用于：
在所述第一映射关系中所指示的第一时间到达前的第一时刻，获取当前路径的网络参数的SLA指标；
在当前路径的网络参数的SLA指标不满足业务要求的情况下，在所述第一时间根据所述第一映射关系，执行转发路由切换相关操作。
在一些实施例中，所述信息处理装置还包括收发器；
所述收发器，用于接收第二网元发送的第二映射关系，其中，所述第二映射关系为时间与网络参数之间的映射关系；
所述处理器还用于：
根据所述第二映射关系和所述第一网元的历史时间段内的网络状况信息进行AI模型训练，得到所述第一映射关系，其中，所述网络状况信息包括：到目标节点的候选路径的信息、当前邻居链路的信息中的一项或多项。
在一些实施例中，所述信息处理装置还包括收发器；
所述收发器用于：接收第二网元发送的所述第一映射关系。
在一些实施例中，所述处理器还用于：
根据目标算法确定K条切换路径，其中，K为大于或等于1的整数；
从所述K条切换路径中，确定不同时间对应的候选切换路径，并将不同时间和对应的候选切换路径之间的映射关系，作为所述第一映射关系。
在一些实施例中，所述处理器还用于：
对不同时间对应的候选切换路径的负载分担参数进行调整。
在一些实施例中，所述处理器还用于：
对所述第一映射关系进行更新，得到目标第一映射关系。
在一些实施例中，所述第一映射关系包括：
SR策略(Policy)级别的时间、转发策略与转发路由之间的映射关系；和/或
段列表(Segment List)级别的时间、转发策略与转发路由之间的映射关系。
在一些实施例中，所述第一映射关系通过以下一种或多种方式指示：
在BGP协议通告SR Policy NLRI中增加指示域，所述指示域用于指示所述第一映射关系所指示的时间，以及，通过第一TLV指示所述SR Policy级别的时间、转发策略与转发路由之间的映射关系所指示的时间，或者，通过第二TLV指示段列表Segment List级别的时间、转发策略与转发路由之间的映射关系所指示的时间；
在BGP链路状态协议中增加第三TLV或第四TLV，所述第三TLV用于指示所述SR Policy级别的时间、转发策略与转发路由之间的映射关系所指示的时间，所述第四TLV用于指示Segment List级别的时间、转发策略与转发路由之间的映射关系所指示的时间。
在一些实施例中，所述处理器还用于以下一项或多项：
根据所述第一映射关系执行转发路由切换；
按照第一周期更新所述第一映射关系；
根据链路负载和带宽约束情况，剪除或调整发生拥塞的链路；
根据时延约束，计算最短传输路径；
对负载分担的多条流的每个小流之间的时延差进行调整，使得每个小流之间的时延差小于多条流间的最大时延差。
第六方面，本公开实施例提供了一种信息处理装置，应用于第二网元，包括：处理器和收发器；
所述处理器，用于获取第二映射关系，其中，所述第二映射关系为时间与网络参数之间的映射关系；
所述收发器，用于根据所述第二映射关系，获取第一映射关系，并向第一网元发送所述第一映射关系，或者，向所述第一网元发送所述第二映射关系，用于获取所述第一映射关系，其中，所述第一映射关系为时间、转发策略与转发路由之间的映射关系。
在一些实施例中，所述处理器还用于：
根据业务类型需求信息、网络参数历史数据对AI模型进行训练，得到所述第二映射关系。
在一些实施例中，所述第一映射关系包括：
SR Policy级别的时间、转发策略与转发路由之间的映射关系；和/或
Segment List级别的时间、转发策略与转发路由之间的映射关系。
在一些实施例中，所述第一映射关系通过以下一种或多种方式指示：
在BGP协议通告SR PolicyNLRI中增加指示域，所述指示域用于指示所述第一映射关系所指示的时间，以及，通过第一类型长度取值TLV指示所述SR Policy级别的时间、转发策略与转发路由之间的映射关系所指示的时间，或者，通过第二TLV指示段列表Segment List级别的时间、转发策略与转发路由之间的映射关系所指示的时间；
在BGP链路状态协议中增加第三TLV或第四TLV，所述第三TLV用于指示所述SR Policy级别的时间、转发策略与转发路由之间的映射关系所指示的时间，所述第四TLV用于指示Segment List级别的时间、转发策略与转发路由之间的映射关系所指示的时间。
第七方面，本公开实施例还提供一种通信设备，包括：存储器、处理器及存储在存储器上并可在处理器上运行的程序，所述处理器执行所述程序时实现如上所述的信息处理方法中的步骤。
第八方面，本公开实施例还提供一种可读存储介质，所述可读存储介质上存储程序，所述程序被处理器执行时实现如上所述的信息处理方法中的步骤。
第九方面，本公开实施例还提供一种计算机程序产品，包括计算机指令，所述计算机指令被处理器执行时实现如上所述的信息处理方法中的步骤。
在本公开实施例中，第一网元可根据第一映射关系执行转发路由切换相关操作。由于所述第一映射关系为时间、转发策略与转发路由之间的映射关系，因此，执行的转发路由切换相关操作随时间可动态变化、并可以按预期调整的路由路径调整，从而可以提前规划预防潜在的性能下降或瓶颈、丢包、时延或带宽不满足业务要求等问题，实现网络带宽等资源的高效合理利用，提供更智能化的网络服务。
附图说明
图1是本公开实施例提供的信息处理方法的流程图之一；
图2是本公开实施例提供的信息处理方法的流程图之二；
图3是本公开实施例的第二映射关系的示意图；
图4是扩展NLRI的示意图；
图5(a)和5(b)是时间相关的子TLV的示意图；
图6(a)和6(b)是本公开实施例中的时间相关的子TLV的示意图；
图7是本公开实施例提供的信息处理装置的结构图之一；
图8是本公开实施例提供的信息处理装置的结构图之二；
图9是本公开实施例提供的信息处理装置的结构图之三；
图10是本公开实施例提供的信息处理装置的结构图之四。
具体实施方式
本公开实施例中术语“和/或”，描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况。字符“/”一般表示前后关联对象是一种“或”的关系。
本公开实施例中术语“多个”是指两个或两个以上，其它量词与之类似。
下面将结合本公开实施例中的附图，对本公开实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本公开一部分实施例，并不是全部的实施例。基于本公开中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本公开保护的范围。
参见图1，图1是本公开实施例提供的信息处理方法的流程图，用于第一网元。该第一网元例如可以为转发面网元。如图1所示，包括以下步骤：
步骤101、获取第一映射关系，其中，所述第一映射关系为时间、转发策略与转发路由之间的映射关系。
其中，一个IPv6段路由流量工程策略(Segment Routing IPv6 Traffic Engineering Policy，SRv6 TE Policy)可以包含多个候选路径(Candidate Path)。候选路径携带优先级属性(Preference)。优先级最高的有效候选路径作为SRv6 TE Policy的主路径。
一个候选路径可以包含多个Segment List，每个Segment List携带Weight属性。每个Segment List都是一个显式SID(段标识)栈，Segment List可以指示网络设备转发报文。多个Segment List之间可以形成负载分担。
在本公开实施例中，可接收第二网元发送的第二映射关系，其中，所述第二映射关系为时间与网络参数之间的映射关系。之后，根据所述第二映射关系和所述第一网元的历史时间段内的网络状况信息进行AI模型训练，得到所述第一映射关系，其中，所述网络状况信息包括：到目标节点的候选路径的信息、当前邻居链路的信息中的一项或多项，网络参数包括流量带宽、时延、丢包率、抖动等。通过这种方式，可在当前业务流量、网络资源随时间动态变化的场景下，转发的源路由隧道智能化地实时按需调整，以提升业务服务质量体验和网络资源利用率。
响应于得到所述第一映射关系，终端可将所述第二映射关系和所述第一网元的历史时间段内的网络状况信息作为模型的输入，并通过强化学习(Reinforcement Learning，RL)等AI算法进行训练，得到所述第一映射关系，该AI模型包括但不限于为神经网络模型、决策树模型等。
第二映射关系中的时间可包括多个时刻或时间段等，转发策略包括多路径SR策略(SR策略(Policy)级别)、多Segment List(Segment List级别)。
例如，转发网元(如路由器)等，可根据自身局部的到目的节点的候选路径情况、当前邻居链路等网络状态进行局部模型(如AI模型)的再训练，可得出当前时刻最优的转发路径以及后续时刻的转发路径表。
在一些实施例中，所述第一网元可接收第二网元发送的所述第一映射关系，也即该第一映射关系是由第二网元确定的。
在一些实施例中，第一网元还可根据目标算法确定K条切换路径，其中，K为大于或等于1的整数；从所述K条切换路径中，确定不同时间对应的候选切换路径，并将不同时间和对应的候选切换路径之间的映射关系，作为所述第一映射关系。该时间可包括多个时刻或时间段等。
其中，所述目标算法例如可包括K条最短路径(K Shortest Paths，KSP)路由算法、灵活负载分担算法等。
例如，对于互联网协议(Internet Protocol,IP)路由转发的场景，可基于KSP路由算法和灵活负载分担算法得到K条切换路径，在T1时刻切换为K1条路径，T2时刻切换为K2条路径。K1，K2大于或等于1。其中，T1和T2为任意的两个不同时刻。
在一些实施例中，对于K1条路径和K2条路径，特别是在K1条路径或K2条路径均为多于1条的情况下，还可对不同时间对应的候选切换路径的负载分担参数进行调整，以使得提供的网络服务达到预期。
在本公开实施例中，第一网元还可对所述第一映射关系进行更新，得到目标第一映射关系。例如，第一网元还可结合自身的网络情况进行局部模型训练，得到目标第一映射关系。
其中，所述第一映射关系包括：
SR策略(Policy)级别的时间、转发策略与转发路由之间的映射关系；和/或段列表(Segment List)级别的时间、转发策略与转发路由之间的映射关系。
该第一映射关系中的时间，可与第二映射关系中的时间相同。
如表1所示，为第一映射关系的一个示例。
表1
例如，在表1中，在时刻T1对应Policy级别的转发策略，其对应的转发路由通过SRv6Policy1来体现。或者，对于时刻T1对应Segment List级别的转发策略，其对应的转发路由通过Segment List1、Segment List2来体现。至于在某个时刻选择哪种转发策略，可根据该时刻的网络状况等因素决定。
在本公开实施例中，针对单流时变调整主要采用多Segment List方案(也即段列表(Segment List)级别的时间、转发策略与转发路由之间的映射关系)，多流调优场景主要采用多分段路由(Segment Routing，SR)Policy方案(也即SR策略(Policy)级别的时间、转发策略与转发路由之间的映射关系)。
例如，以T1时刻只有一个SL(Service Level，服务等级)100M(兆)，T2时刻需要两个SL 200M(Policy级别的)，T1时刻要求时延100ms，T2时刻时延50ms为例，需剔除不满足时延要求的路径SL或SR Policy，或者通过调整SR Policy方式实现。
步骤102、根据所述第一映射关系，执行转发路由切换相关操作。
对于第一映射关系中所指示的时间，可在该时间到达之前提前进行检查，以确定是否可执行转发路由切换相关操作。
具体的，对于第一映射关系中所指示的第一时间，在所述第一映射关系中所指示的第一时间到达前的第一时刻，获取当前路径的网络参数的SLA指标。在当前路径的网络参数的SLA指标不满足业务要求的情况下，在所述第一时间根据所述第一映射关系，执行转发路由切换相关操作。其中，该第一时间为第一映射关系中的任一时间。也就是说，在本公开实施例中，在第一时间之前的某个时刻，提前获得SLA指标，并根据该SLA指标确定当前路径的网络参数的SLA指标是否满足业务要求。在不满足要求的情况下，则在第一时间根据第一映射关系中该第一时间所对应的转发策略与转发路由执行转发路由切换相关操作。
其中，上述第一映射关系中的各个时间，可将一天的时间分为四段：比如，早上9点、下午3点、峰值-晚上9点、谷值-凌晨3点，以这四个节点为中心点将一天划分为四个时间段，则切换的时刻即各个时间，为这个四个时间段的中间点，即6点、12点、18点、24点。例如，可在第一时刻之前的Xs/ms(X秒或毫秒)(X大于或等于0)，通过内部网关协议(Interior Gateway Protocol，IGP)/边界网关协议(Border Gateway Protocol，BGP)等实际探测当前路径的带宽、时延、丢包率等SLA指标是否已经不满足业务要求，以结合当前网络状况进行模型推理，从而在确定不满足业务要求的情况下，确定在所述第一时间根据所述第一映射关系，执行转发路由切换相关操作。
在本公开实施例中，执行的转发路由切换相关操作对用户无感知、弹性伸缩(如多个Policy通过一个Policy group(策略组)对外呈现，多个SL通过Binding SID(绑定SID)体现)。
在此，执行转发路由切换相关操作包括以下一项或多项：
根据所述第一映射关系执行转发路由切换；
按照第一周期更新所述第一映射关系，该第一周期可根据需要设置；
根据链路负载和带宽约束情况，剪除或调整发生拥塞的链路；
根据时延约束，计算最短传输路径；
对负载分担的多条流的每个小流之间的时延差进行调整，使得每个小流之间的时延差小于多条流间的最大时延差。
在本公开实施例中，所述第一映射关系通过以下一种或多种方式指示：
在BGP协议通告SR Policy网络层可达信息NLRI中增加指示域，所述指示域用于指示所述第一映射关系所指示的时间，以及，通过第一TLV指示所述SR Policy级别的时间、转发策略与转发路由之间的映射关系所指示的时间，或者，通过第二TLV指示段列表Segment List级别的时间、转发策略与转发路由之间的映射关系所指示的时间；
在BGP链路状态协议中增加第三TLV或第四TLV，所述第三TLV用于指示所述SR Policy级别的时间、转发策略与转发路由之间的映射关系所指示的时间，所述第四TLV用于指示Segment List级别的时间、转发策略与转发路由之间的映射关系所指示的时间。
在本公开实施例中，第一网元可根据第一映射关系执行转发路由切换相关操作。由于所述第一映射关系为时间、转发策略与转发路由之间的映射关系，因此，执行的转发路由切换相关操作随时间可动态变化、并可以按预期调整的路由路径调整，从而可以提前规划预防潜在的性能下降或瓶颈、丢包、时延或带宽不满足业务要求等问题，实现网络带宽等资源的高效合理利用，提供更智能化的网络服务。
参见图2，图2是本公开实施例提供的信息处理方法的流程图，应用于第二网元。该第二网元例如可以是控制器，或者控制器中的智能模块，或者智能网元等。如图2所示，包括以下步骤：
步骤201、获取第二映射关系，其中，所述第二映射关系为时间与网络参数之间的映射关系。
在此步骤中，可根据业务类型需求信息、网络参数历史数据对AI模型进行训练，得到所述第二映射关系。在一些实施例中，上述AI模型也可根据需要进行替换。
其中，网络参数历史数据可包括：
包级别和流级别的数据：包括深度数据包检测(Deep Packet Inspection，DPI)信息、流粒度数据、相关流特征(报文数量、报文大小、时间戳、路径、流创建时间等)；
网络状态：物理、拓扑、逻辑配置等；
管控状态：软件定义网络(SoftwareDefinedNetwork，SDN)控制器、管理系统产生的信息，策略、虚拟拓扑、应用相关信息；
服务级别的遥测：服务负载、服务质量(Quality of Service，QoS)、带宽时延丢包率等SLA指标；
其他：社会网络(如参加一个运动会的人数)、天气预报等。
上述第二映射关系可认为是网络参数随时间变化的信息，例如，时间上的波峰、波谷等。以流量为例，该第二映射关系可认为是流量与时间之间的关系曲线。响应于得到所述第二映射关系，可通过强化学习(Reinforcement Learning，RL)等AI算法进行流量全局模型训练，建立时间和流量带宽、时延等要求的函数关系。另外，还可设定调整阈值，例如，带宽的阈值为20％、时延的阈值为Xms等。
如图3所示，以第二映射关系为时间与流量之间的映射关系为例。切换时刻的选取可以为如下方式：将一天的时间分为四个时间段，比如早上9点、下午3点、峰值-晚上9点、谷值-凌晨3点，以这四个节点为中心点将一天划分为四个时间段，则切换的时刻为这个四个时间段的中间点，即6点、12点、18点、24点。之后，分别计算每个时间段的流量带宽的最大值，并增加上限10％～20％。也就是说，该时间段对应的流量带宽的最大值可上调10％～20％。
步骤202、根据所述第二映射关系，获取第一映射关系，并向第一网元发送所述第一映射关系，或者，向所述第一网元发送所述第二映射关系，用于获取所述第一映射关系，其中，所述第一映射关系为时间、转发策略与转发路由之间的映射关系。
在此，第二网元可根据所述第二映射关系和其他网元的网络参数历史数据对AI模型进行再训练，得到所述第一映射关系。
其中，所述第一映射关系包括：
SR Policy级别的时间、转发策略与转发路由之间的映射关系；和/或
Segment List级别的时间、转发策略与转发路由之间的映射关系。
在本公开实施例中，可对已有的协议进行扩展，以向第一网元发送该第二映射关系。
具体的，所述第一映射关系通过以下一种或多种方式指示：
在BGP协议通告SR Policy网络层可达信息NLRI中增加指示域，所述指示域用于指示所述第一映射关系所指示的时间，以及，通过第一TLV指示所述SR Policy级别的时间、转发策略与转发路由之间的映射关系所指示的时间，或者，通过第二TLV指示段列表Segment List级别的时间、转发策略与转发路由之间的映射关系所指示的时间；
在BGP链路状态协议中增加第三TLV或第四TLV，所述第三TLV用于指示所述SR Policy级别的时间、转发策略与转发路由之间的映射关系所指示的时间，所述第四TLV用于指示Segment List级别的时间、转发策略与转发路由之间的映射关系所指示的时间。
例如，可对BGP协议通告SR PolicyNLRI(Network Layer Reachability Information，网络层可达信息)进行扩展，使其携带上述第一映射关系所指示的时间。具体的扩展方式如图4所示，其中的Time1，Time2等用于携带上述时间。例如，图3中的6点、12点、18点、24点。另外，如图5(a)和5(b)所示，还可增加时间相关的子TLV(Type-Length-Value，类型-长度-取值)，用于分别指示所述SR Policy级别的时间、转发策略与转发路由之间的映射关系所指示的时间，或者，Segment List级别的时间、转发策略与转发路由之间的映射关系所指示的时间。
例如，如图6(a)和6(b)所示，可扩展BGP-LS(BGP Link State，BGP链路状态)协议，新增SR Policy Candidate Path(Time-Policy Level)和Segment List的状态TLV(Time-SL Level)，以分别指示所述SR Policy级别的时间、转发策略与转发路由之间的映射关系所指示的时间、Segment List级别的时间、转发策略与转发路由之间的映射关系所指示的时间。
上述实施例的方案也可由管控面配合智能面系统完成。
在本公开实施例中，第一网元可根据第一映射关系执行转发路由切换相关操作。由于所述第一映射关系为时间、转发策略与转发路由之间的映射关系，因此，执行的转发路由切换相关操作随时间可动态变化、并可以按预期调整的路由路径调整，从而可以提前规划预防潜在的性能下降或瓶颈、丢包、时延或带宽不满足业务要求等问题，实现网络带宽等资源的高效合理利用，提供更智能化的网络服务。
参见图7，图7是本公开实施例提供的信息处理装置的结构图，应用于第一网元。如图7所示，信息处理装置包括：
第一获取模块701，用于获取第一映射关系，其中，所述第一映射关系为时间、转发策略与转发路由之间的映射关系；第一处理模块702，用于根据所述第一映射关系，执行转发路由切换相关操作。
在一些实施例中，所述装置还可包括：
第二获取模块，用于在所述第一映射关系中所指示的第一时间到达前的第一时刻，获取当前路径的网络参数的SLA指标；
所述第一处理模块，还用于在当前路径的网络参数的SLA指标不满足业务要求的情况下，在所述第一时间根据所述第一映射关系，执行转发路由切换相关操作。
在一些实施例中，所述第一获取模块包括：
第一获取子模块，用于接收第二网元发送的第二映射关系，其中，所述第二映射关系为时间与网络参数之间的映射关系；
第二获取子模块，用于根据所述第二映射关系和所述第一网元的历史时间段内的网络状况信息进行AI模型训练，得到所述第一映射关系，其中，所述网络状况信息包括：到目标节点的候选路径的信息、当前邻居链路的信息中的一项或多项。
在一些实施例中，所述第一获取模块还用于：接收第二网元发送的所述第一映射关系。
在一些实施例中，所述第一获取模块还包括：
第三获取子模块，用于根据目标算法确定K条切换路径，其中，K为大于或等于1的整数；
第四获取子模块，用于从所述K条切换路径中，确定不同时间对应的候选切换路径，并将不同时间和对应的候选切换路径之间的映射关系，作为所述第一映射关系。
在一些实施例中，所述装置还可包括：
第一调整模块，用于对不同时间对应的候选切换路径的负载分担参数进行调整。
在一些实施例中，所述装置还可包括：
第一更新模块，用于对所述第一映射关系进行更新，得到目标第一映射关系。
在一些实施例中，所述第一映射关系包括：
SR策略(Policy)级别的时间、转发策略与转发路由之间的映射关系；和/或
段列表(Segment List)级别的时间、转发策略与转发路由之间的映射关系。
在一些实施例中，所述第一映射关系通过以下一种或多种方式指示：
在BGP协议通告SR Policy NLRI中增加指示域，所述指示域用于指示所述第一映射关系所指示的时间，以及，通过第一TLV指示所述SR Policy级别的时间、转发策略与转发路由之间的映射关系所指示的时间，或者，通过第二TLV指示段列表Segment List级别的时间、转发策略与转发路由之间的映射关系所指示的时间；
在BGP链路状态协议中增加第三TLV或第四TLV，所述第三TLV用于指示所述SR Policy级别的时间、转发策略与转发路由之间的映射关系所指示的时间，所述第四TLV用于指示Segment List级别的时间、转发策略与转发路由之间的映射关系所指示的时间。
在一些实施例中，所述第一处理模块还用于以下一项或多项：
根据所述第一映射关系执行转发路由切换；
按照第一周期更新所述第一映射关系；
根据链路负载和带宽约束情况，剪除或调整发生拥塞的链路；
根据时延约束，计算最短传输路径；
对负载分担的多条流的每个小流之间的时延差进行调整，使得每个小流之间的时延差小于多条流间的最大时延差。
本公开实施例提供的装置，可以执行上述方法实施例，其实现原理和技术效果类似，本实施例此处不再赘述。
参见图8，图8是本公开实施例提供的信息处理装置的结构图，应用于第二网元。如图8所示，信息处理装置包括：
第一获取模块801，用于获取第二映射关系，其中，所述第二映射关系为时间与网络参数之间的映射关系；第一发送模块802，用于根据所述第二映射关系，获取第一映射关系，并向第一网元发送所述第一映射关系，或者，向所述第一网元发送所述第二映射关系，用于获取所述第一映射关系，其中，所述第一映射关系为时间、转发策略与转发路由之间的映射关系。
在一些实施例中，所述第一获取模块包括：
第一获取子模块，用于根据业务类型需求信息、网络参数历史数据对AI模型进行训练，得到所述第二映射关系。
在一些实施例中，所述第一映射关系包括：
SR Policy级别的时间、转发策略与转发路由之间的映射关系；和/或
Segment List级别的时间、转发策略与转发路由之间的映射关系。
在一些实施例中，所述第一映射关系通过以下一种或多种方式指示：
在BGP协议通告SR PolicyNLRI中增加指示域，所述指示域用于指示所述第一映射关系所指示的时间，以及，通过第一类型长度取值TLV指示所述SR Policy级别的时间、转发策略与转发路由之间的映射关系所指示的时间，或者，通过第二TLV指示段列表Segment List级别的时间、转发策略与转发路由之间的映射关系所指示的时间；
在BGP链路状态协议中增加第三TLV或第四TLV，所述第三TLV用于指示所述SR Policy级别的时间、转发策略与转发路由之间的映射关系所指示的时间，所述第四TLV用于指示Segment List级别的时间、转发策略与转发路由之间的映射关系所指示的时间。
本公开实施例提供的装置，可以执行上述方法实施例，其实现原理和技术效果类似，本实施例此处不再赘述。
参见图9，图9是本公开实施例提供的信息处理装置的结构图，应用于第一网元。如图9所示，信息处理装置包括：处理器901和收发器902；
所述处理器901，用于获取第一映射关系，其中，所述第一映射关系为时间、转发策略与转发路由之间的映射关系；根据所述第一映射关系，执行转发路由切换相关操作。
在一些实施例中，所述处理器901还用于：
在所述第一映射关系中所指示的第一时间到达前的第一时刻，获取当前路径的网络参数的SLA指标；
在当前路径的网络参数的SLA指标不满足业务要求的情况下，在所述第一时间根据所述第一映射关系，执行转发路由切换相关操作。
在一些实施例中，所述收发器902还用于：
接收第二网元发送的第二映射关系，其中，所述第二映射关系为时间与网络参数之间的映射关系；
所述处理器901还用于：根据所述第二映射关系和所述第一网元的历史时间段内的网络状况信息进行AI模型训练，得到所述第一映射关系，其中，所述网络状况信息包括：到目标节点的候选路径的信息、当前邻居链路的信息中的一项或多项。
在一些实施例中，所述收发器902还用于：接收第二网元发送的所述第一映射关系。
在一些实施例中，所述处理器901还用于：
根据目标算法确定K条切换路径，其中，K为大于或等于1的整数；
从所述K条切换路径中，确定不同时间对应的候选切换路径，并将不同时间和对应的候选切换路径之间的映射关系，作为所述第一映射关系。
在一些实施例中，所述处理器901还用于：
对不同时间对应的候选切换路径的负载分担参数进行调整。
在一些实施例中，所述处理器901还用于：
对所述第一映射关系进行更新，得到目标第一映射关系。
在一些实施例中，所述第一映射关系包括：
SR策略(Policy)级别的时间、转发策略与转发路由之间的映射关系；和/或
段列表(Segment List)级别的时间、转发策略与转发路由之间的映射关系。
在一些实施例中，所述第一映射关系通过以下一种或多种方式指示：
在BGP协议通告SR Policy NLRI中增加指示域，所述指示域用于指示所述第一映射关系所指示的时间，以及，通过第一TLV指示所述SR Policy级别的时间、转发策略与转发路由之间的映射关系所指示的时间，或者，通过第二TLV指示段列表Segment List级别的时间、转发策略与转发路由之间的映射关系所指示的时间；
在BGP链路状态协议中增加第三TLV或第四TLV，所述第三TLV用于指示所述SR Policy级别的时间、转发策略与转发路由之间的映射关系所指示的时间，所述第四TLV用于指示Segment List级别的时间、转发策略与转发路由之间的映射关系所指示的时间。
在一些实施例中，所述处理器901还用于以下一项或多项：
根据所述第一映射关系执行转发路由切换；
按照第一周期更新所述第一映射关系；
根据链路负载和带宽约束情况，剪除或调整发生拥塞的链路；
根据时延约束，计算最短传输路径；
对负载分担的多条流的每个小流之间的时延差进行调整，使得每个小流之间的时延差小于多条流间的最大时延差。
本公开实施例提供的装置，可以执行上述方法实施例，其实现原理和技术效果类似，本实施例此处不再赘述。
参见图10，图10是本公开实施例提供的信息处理装置的结构图，应用于第二网元。如图10所示，信息处理装置包括：处理器1001和收发器1002；
所述处理器1001，用于获取第二映射关系，其中，所述第二映射关系为时间与网络参数之间的映射关系；
所述收发器1002，用于根据所述第二映射关系，获取第一映射关系，并向第一网元发送所述第一映射关系，或者，向所述第一网元发送所述第二映射关系，用于获取所述第一映射关系，其中，所述第一映射关系为时间、转发策略与转发路由之间的映射关系。
在一些实施例中，所述处理器1001还用于：
根据业务类型需求信息、网络参数历史数据对AI模型进行训练，得到所述第二映射关系。
在一些实施例中，所述第一映射关系包括：
SR Policy级别的时间、转发策略与转发路由之间的映射关系；和/或
Segment List级别的时间、转发策略与转发路由之间的映射关系。
在一些实施例中，所述第一映射关系通过以下一种或多种方式指示：
在BGP协议通告SR PolicyNLRI中增加指示域，所述指示域用于指示所述第一映射关系所指示的时间，以及，通过第一类型长度取值TLV指示所述SR Policy级别的时间、转发策略与转发路由之间的映射关系所指示的时间，或者，通过第二TLV指示段列表Segment List级别的时间、转发策略与转发路由之间的映射关系所指示的时间；
在BGP链路状态协议中增加第三TLV或第四TLV，所述第三TLV用于指示所述SR Policy级别的时间、转发策略与转发路由之间的映射关系所指示的时间，所述第四TLV用于指示Segment List级别的时间、转发策略与转发路由之间的映射关系所指示的时间。
本公开实施例提供的装置，可以执行上述方法实施例，其实现原理和技术效果类似，本实施例此处不再赘述。
需要说明的是，本公开实施例中对单元的划分是示意性的，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式。另外，在本公开各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。
所述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个处理器可读取存储介质中。基于这样的理解，本公开的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)或处理器(processor)执行本公开各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(Read-Only Memory，ROM)、随机存取存储器(Random Access Memory，RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
本公开实施例提供了一种通信设备，包括：存储器、处理器及存储在所述存储器上并可在所述处理器上运行的程序；所述处理器，用于读取存储器中的程序实现如前所述的信息处理方法中的步骤。
本公开实施例还提供一种可读存储介质，可读存储介质上存储有程序，该程序被处理器执行时实现上述信息处理方法实施例的各个过程，且能达到相同的技术效果，为避免重复，这里不再赘述。其中，所述的可读存储介质，可以是处理器能够存取的任何可用介质或数据存储设备，包括但不限于磁性存储器(例如软盘、硬盘、磁带、磁光盘(MO)等)、光学存储器(例如CD、DVD、BD、HVD等)、以及半导体存储器(例如ROM、EPROM、EEPROM、非易失性存储器(NAND FLASH)、固态硬盘(SSD))等。
本公开实施例还提供一种计算机程序产品，包括计算机指令，该计算机指令被处理器执行时实现上述信息处理方法实施例的各个过程，且能达到相同的技术效果，为避免重复，这里不再赘述。
需要说明的是，在本文中，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者装置不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者装置所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括该要素的过程、方法、物品或者装置中还存在另外的相同要素。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。根据这样的理解，本公开的技术方案本质上或者说对现有技术做出贡献的部分可以以计算机软件产品的形式体现出来，该计算机软件产品存储在一个存储介质(如ROM/RAM、磁盘、光盘)中，包括若干指令用以使得一台终端(可以是手机，计算机，服务器，空调器，或者网络设备等)执行本公开各个实施例所述的方法。
上面结合附图对本公开的实施例进行了描述，但是本公开并不局限于上述的具体实施方式，上述的具体实施方式仅仅是示意性的，而不是限制性的，本领域的普通技术人员在本公开的启示下，在不脱离本公开宗旨和权利要求所保护的范围情况下，还可做出很多形式，均属于本公开的保护之内。
本公开所有实施例均可以单独被执行，也可以与其他实施例相结合被执行，均视为本公开要求的保护范围。

Claims (21)

  1. 一种信息处理方法，应用于第一网元，包括：
    获取第一映射关系，其中，所述第一映射关系为时间、转发策略与转发路由之间的映射关系；
    根据所述第一映射关系，执行转发路由切换相关操作。
  2. 根据权利要求1所述的方法，其中，所述方法还包括：
    在所述第一映射关系中所指示的第一时间到达前的第一时刻，获取当前路径的网络参数的服务等级协议SLA指标；
    所述根据所述第一映射关系，执行转发路由切换相关操作，包括：
    在当前路径的网络参数的SLA指标不满足业务要求的情况下，在所述第一时间根据所述第一映射关系，执行转发路由切换相关操作。
  3. 根据权利要求1或2所述的方法，其中，所述获取第一映射关系，包括：
    接收第二网元发送的第二映射关系，其中，所述第二映射关系为时间与网络参数之间的映射关系；
    根据所述第二映射关系和所述第一网元的历史时间段内的网络状况信息进行人工智能AI模型训练，得到所述第一映射关系，其中，所述网络状况信息包括：到目标节点的候选路径的信息、当前邻居链路的信息中的一项或多项。
  4. 根据权利要求1或2所述的方法，其中，所述获取第一映射关系，包括：
    接收第二网元发送的所述第一映射关系。
  5. 根据权利要求1或2所述的方法，其中，所述获取第一映射关系，包括：
    根据目标算法确定K条切换路径，其中，K为大于或等于1的整数；
    从所述K条切换路径中，确定不同时间对应的候选切换路径，并将不同时间和对应的候选切换路径之间的映射关系，作为所述第一映射关系。
  6. 根据权利要求5所述的方法，其中，所述方法还包括：
    对不同时间对应的候选切换路径的负载分担参数进行调整。
  7. 根据权利要求1-6任一项所述的方法，其中，所述方法还包括：
    对所述第一映射关系进行更新，得到目标第一映射关系。
  8. 根据权利要求1-7中任一项所述的方法，其中，所述第一映射关系包括：
    段路由策略SR Policy级别的时间、转发策略与转发路由之间的映射关系；和/或
    段列表Segment List级别的时间、转发策略与转发路由之间的映射关系。
  9. 根据权利要求8所述的方法，其中，所述第一映射关系通过以下一种或多种方式指示：
    在边界网关协议BGP协议通告SR Policy网络层可达信息NLRI中增加指示域，所述指示域用于指示所述第一映射关系所指示的时间，以及，通过第一类型长度取值TLV指示所述SR Policy级别的时间、转发策略与转发路由之间的映射关系所指示的时间，或者，通过第二TLV指示段列表Segment List级别的时间、转发策略与转发路由之间的映射关系所指示的时间；
    在BGP链路状态协议中增加第三TLV或第四TLV，所述第三TLV用于指示所述SR Policy级别的时间、转发策略与转发路由之间的映射关系所指示的时间，所述第四TLV用于指示Segment List级别的时间、转发策略与转发路由之间的映射关系所指示的时间。
  10. 根据权利要求1-9中任一项所述的方法，其中，所述根据所述第一映射关系，执行转发路由切换相关操作，包括以下一项或多项：
    根据所述第一映射关系执行转发路由切换；
    按照第一周期更新所述第一映射关系；
    根据链路负载和带宽约束情况，剪除或调整发生拥塞的链路；
    根据时延约束，计算最短传输路径；
    对负载分担的多条流的每个小流之间的时延差进行调整，使得每个小流之间的时延差小于多条流间的最大时延差。
  11. 一种信息处理方法，应用于第二网元，包括：
    获取第二映射关系，其中，所述第二映射关系为时间与网络参数之间的映射关系；
    根据所述第二映射关系，获取第一映射关系，并向第一网元发送所述第一映射关系，或者，向所述第一网元发送所述第二映射关系，用于获取所述第一映射关系；
    其中，所述第一映射关系为时间、转发策略与转发路由之间的映射关系。
  12. 根据权利要求11所述的方法，其中，所述获取第二映射关系，包括：
    根据业务类型需求信息、网络参数历史数据对AI模型进行训练，得到所述第二映射关系。
  13. 根据权利要求11或12所述的方法，其中，所述第一映射关系包括：
    段路由策略SR Policy级别的时间、转发策略与转发路由之间的映射关系；和/或
    Segment List级别的时间、转发策略与转发路由之间的映射关系。
  14. 根据权利要求13所述的方法，其中，所述第一映射关系通过以下一种或多种方式指示：
    在BGP协议通告SR PolicyNLRI中增加指示域，所述指示域用于指示所述第一映射关系所指示的时间，以及，通过第一类型长度取值TLV指示所述SR Policy级别的时间、转发策略与转发路由之间的映射关系所指示的时间，或者，通过第二TLV指示段列表Segment List级别的时间、转发策略与转发路由之间的映射关系所指示的时间；
    在BGP链路状态协议中增加第三TLV或第四TLV，所述第三TLV用于指示所述SR Policy级别的时间、转发策略与转发路由之间的映射关系所指示的时间，所述第四TLV用于指示Segment List级别的时间、转发策略与转发路由之间的映射关系所指示的时间。
  15. 一种信息处理装置，应用于第一网元，包括：
    第一获取模块，用于获取第一映射关系，其中，所述第一映射关系为时间、转发策略与转发路由之间的映射关系；
    第一处理模块，用于根据所述第一映射关系，执行转发路由切换相关操作。
  16. 一种信息处理装置，应用于第二网元，包括：
    第一获取模块，用于获取第二映射关系，其中，所述第二映射关系为时间与网络参数之间的映射关系；
    第一发送模块，用于根据所述第二映射关系，获取第一映射关系，并向第一网元发送所述第一映射关系，或者，向所述第一网元发送所述第二映射关系，用于获取所述第一映射关系；
    其中，所述第一映射关系为时间、转发策略与转发路由之间的映射关系。
  17. 一种信息处理装置，应用于第一网元，包括：处理器；
    所述处理器，用于获取第一映射关系，其中，所述第一映射关系为时间、转发策略与转发路由之间的映射关系；根据所述第一映射关系，执行转发路由切换相关操作。
  18. 一种信息处理装置，应用于第二网元，包括：处理器和收发器；
    所述处理器，用于获取第二映射关系，其中，所述第二映射关系为时间与网络参数之间的映射关系；
    所述收发器，用于根据所述第二映射关系，获取第一映射关系，并向第一网元发送所述第一映射关系，或者，向所述第一网元发送所述第二映射关系，用于获取所述第一映射关系，其中，所述第一映射关系为时间、转发策略与转发路由之间的映射关系。
  19. 一种通信设备，包括：存储器、处理器及存储在所述存储器上并可在所述处理器上运行的程序；其中，所述处理器，用于读取存储器中的程序实现如权利要求1至14中任一项所述的信息处理方法中的步骤。
  20. 一种可读存储介质，用于存储程序，其中，所述程序被处理器执行时实现如权利要求1至14中任一项所述的信息处理方法中的步骤。
  21. 一种计算机程序产品，包括计算机指令，所述计算机指令被处理器执行时实现如权利要求1至14中任一项所述的信息处理方法中的步骤。
PCT/CN2025/098619 2024-06-04 2025-05-30 信息处理方法、装置、设备、可读存储介质及程序产品 Pending WO2025252048A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202410713252.2 2024-06-04
CN202410713252.2A CN118802718A (zh) 2024-06-04 2024-06-04 信息处理方法、装置、设备、可读存储介质及程序产品

Publications (1)

Publication Number Publication Date
WO2025252048A1 true WO2025252048A1 (zh) 2025-12-11

Family

ID=93021304

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2025/098619 Pending WO2025252048A1 (zh) 2024-06-04 2025-05-30 信息处理方法、装置、设备、可读存储介质及程序产品

Country Status (2)

Country Link
CN (1) CN118802718A (zh)
WO (1) WO2025252048A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118802718A (zh) * 2024-06-04 2024-10-18 中国移动通信有限公司研究院 信息处理方法、装置、设备、可读存储介质及程序产品

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109714263A (zh) * 2019-01-18 2019-05-03 北京邮电大学 一种在卫星通信网络中的路径选择方法及装置
WO2022267969A1 (zh) * 2021-06-25 2022-12-29 华为技术有限公司 一种信息传输方法及相关设备
CN116938800A (zh) * 2022-04-08 2023-10-24 华为技术有限公司 一种传输路径确定方法及装置
CN117155840A (zh) * 2023-09-12 2023-12-01 烽火通信科技股份有限公司 一种时变路由方法和装置
WO2024001210A1 (zh) * 2022-06-29 2024-01-04 中兴通讯股份有限公司 路径计算方法、控制器和计算机可读存储介质
CN118802718A (zh) * 2024-06-04 2024-10-18 中国移动通信有限公司研究院 信息处理方法、装置、设备、可读存储介质及程序产品

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106452958B (zh) * 2016-09-30 2020-04-07 中国联合网络通信集团有限公司 一种流量控制方法、系统及集中控制器
CN113726657B (zh) * 2020-05-25 2024-12-03 中兴通讯股份有限公司 报文转发方法、装置、系统、设备和存储介质
CN114553760B (zh) * 2020-11-25 2023-05-16 华为技术有限公司 路径权重分配方法以及装置
CN112565082B (zh) * 2020-12-25 2022-06-17 鹏城实验室 基于混合网络的服务链映射方法、智能终端及存储介质
CN113114563B (zh) * 2021-04-14 2022-10-21 网络通信与安全紫金山实验室 基于分段路由策略的流量回切延时方法、设备、存储介质
CN117527666A (zh) * 2022-07-28 2024-02-06 华为技术有限公司 一种报文处理的方法及相关设备
CN117527672A (zh) * 2022-07-29 2024-02-06 华为技术有限公司 发送报文的方法、网络设备以及系统
CN117081655A (zh) * 2023-09-11 2023-11-17 上海卫星互联网研究院有限公司 一种数据包传输方法及卫星节点
CN116938807B (zh) * 2023-09-14 2023-12-22 新华三技术有限公司 数据报文传输方法、装置、设备及存储介质

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109714263A (zh) * 2019-01-18 2019-05-03 北京邮电大学 一种在卫星通信网络中的路径选择方法及装置
WO2022267969A1 (zh) * 2021-06-25 2022-12-29 华为技术有限公司 一种信息传输方法及相关设备
CN116938800A (zh) * 2022-04-08 2023-10-24 华为技术有限公司 一种传输路径确定方法及装置
WO2024001210A1 (zh) * 2022-06-29 2024-01-04 中兴通讯股份有限公司 路径计算方法、控制器和计算机可读存储介质
CN117155840A (zh) * 2023-09-12 2023-12-01 烽火通信科技股份有限公司 一种时变路由方法和装置
CN118802718A (zh) * 2024-06-04 2024-10-18 中国移动通信有限公司研究院 信息处理方法、装置、设备、可读存储介质及程序产品

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
SOFTBANK CORP., CISCO SYSTEMS.: "Pseudo-CR on UP Path Validation", 3GPP DRAFT; C4-191513-WAS-C4-191208-UP-PATH-VALIDATION, vol. CT WG4, 12 April 2019 (2019-04-12), Xi'an, P.R.China, pages 14, XP051706767 *

Also Published As

Publication number Publication date
CN118802718A (zh) 2024-10-18

Similar Documents

Publication Publication Date Title
JP5975083B2 (ja) 通信システム、制御装置、パケット転送経路の制御方法およびプログラム
EP2915307B1 (en) Communications network using a tunnel to connect two network nodes
US8493869B2 (en) Distributed constraints-based inter-domain network traffic management
CN106100990A (zh) 一种基于sdn架构的通信网络多维度资源调控方法和系统
US20130132542A1 (en) Method and System for Effective BGP AS-Path Pre-pending
CN106452958A (zh) 一种流量控制方法、系统及集中控制器
CN103685054A (zh) 基于业务感知的多路径负载均衡方法
CN106209621A (zh) 服务质量约束的链路故障恢复方法
US12506679B2 (en) Packet forwarding method and apparatus, and dragonfly network
CN114172842A (zh) 一种数据传输处理方法、装置、设备及可读存储介质
EP2476224A1 (en) Method and apparatus for path computation element and routing controller cooperation
CN106899503A (zh) 一种数据中心网络的路由选择方法及网络管理器
WO2023082815A1 (zh) 确定性路由的构建方法、装置和存储介质
WO2025252048A1 (zh) 信息处理方法、装置、设备、可读存储介质及程序产品
Tang et al. Constructing a DRL decision making scheme for multi-path routing in all-IP access network
Cianfrani et al. Multi agent reinforcement learning based local routing strategy to reduce end-to-end delays in segment routing networks
CN116032825B (zh) 确定性路由的计算方法、装置、存储介质和电子设备
CN109039951B (zh) 一种异构网络QoS策略的实现方法及系统
CN108366015B (zh) 用于软件定义网络的路由计算方法
CN102487352A (zh) 业务分配方法及装置
Jaron et al. QoS-aware multi-plane routing for future IP-based access networks
Wang et al. A heuristic online algorithm for routing in large-scale deterministic networks
Ito et al. Path planning method using deep learning model for traffic engineering in small networks
Lumbantoruan et al. Towards an efficient path selection for tactile Internet traffic via multi-plane routing
Lee et al. Autonomous network management using cooperative learning for network-wide load balancing in heterogeneous networks

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 25819163

Country of ref document: EP

Kind code of ref document: A1