Optical network flow prediction method and related equipment

Abstract

The invention provides an optical network traffic prediction method and related equipment, and relates to the technical field of artificial intelligence. The method comprises the following steps: acquiring network performance data of a target optical network; based on network knowledge information of a first preset time period pre-stored in a knowledge base, time sequence analysis is carried out on the network performance data to obtain a time sequence association result, and the network knowledge information is structured information related to historical flow information of the target optical network; the time sequence association result is used for representing an association relationship between the network performance data and the network knowledge information; and inputting the network performance data, the time sequence association result and supplementary traffic information pre-stored in a knowledge base into a pre-trained traffic prediction model, and outputting predicted network traffic of the target optical network in a second preset time period, the supplementary traffic information being manually input unstructured information. The accuracy of the optical network flow prediction result can be improved, adjustment is quickly performed based on the existing network resources, and the waste of the network resources is reduced.

Description

Background Art

[0002] Today, 5G and other network services have been widely used, making the existing network operation and maintenance scenarios more complex and diverse. Operation and maintenance personnel often have to face a large amount of real-time and historical data. In related technologies, the autoregressive moving average ARMA model and the seasonal autoregressive integrated moving average SARIMA model are usually used.

[0003] Among them, the ARMA model is suitable for stationary time series data without trend or seasonality. It is based on the autocorrelation and moving average properties of the time series and is easy to understand and implement. The SARIMA model is suitable for time series data with obvious seasonal patterns. It can not only process stationary time series, but also process data with obvious seasonal and trend components. It has wide applicability.

[0004] However, when faced with large-scale and highly dynamic network traffic data, related technologies are often unable to effectively capture complex dependencies and system uncertainties. At the same time, related technologies lack application processes for traffic prediction and analysis, and are unable to quickly respond to bandwidth adjustments, capacity expansion and other actions based on existing network resources. Therefore, this may lead to waste of network resources and poor customer experience.

[0005] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0006] The present disclosure provides an optical network traffic prediction method, apparatus, device, medium and program product, which at least to a certain extent overcome the problem in the related art that the traffic cannot be accurately predicted and corresponding adjustments can be provided.

[0007] Other features and advantages of the present disclosure will become apparent from the following detailed description, or may be learned in part by the practice of the present disclosure.

[0008] According to one aspect of the present disclosure, there is provided an optical network traffic prediction method, comprising: acquiring network performance data of a target optical network; performing a time series analysis on the network performance data based on network knowledge information of a first preset time period pre-stored in a knowledge base to obtain a time series correlation result, wherein the network knowledge information is structured information related to historical traffic information of the target optical network, and the time series correlation result is used to represent the correlation relationship between the network performance data and the network knowledge information; inputting the network performance data, the time series correlation result and supplementary traffic information pre-stored in the knowledge base into a pre-trained traffic prediction model, and outputting the predicted network traffic of the target optical network within a second preset time period, wherein the supplementary traffic information is manually input unstructured information related to the historical traffic information of the target optical network, and the second preset time period is later than the first preset time period.

[0009] In some embodiments, before performing a timing analysis on the network performance data based on network knowledge information of a first preset time period pre-stored in a knowledge base to obtain a timing correlation result, the method further includes: obtaining historical traffic information and supplementary traffic information of the target optical network within the first preset time period, wherein the historical traffic information includes historical traffic conditions on a preset date and historical traffic conditions at a preset time point; structuring the historical traffic information according to a preset network field format to obtain network knowledge information; and constructing a knowledge base based on the network knowledge information and the supplementary traffic information.

[0010] In some embodiments, the preset network field includes time information, corresponding network bandwidth information, and an event identifier or a time identifier.

[0011] In some embodiments, after inputting the network performance data, the timing correlation results and the supplementary traffic information pre-stored in the knowledge base into a pre-trained traffic prediction model and outputting the predicted network traffic of the target optical network within a second preset time period, the method further includes: calculating the maximum bandwidth of the target optical network based on the acquired network performance data of the target optical network; and selecting a corresponding network resource adjustment strategy based on whether the maximum bandwidth meets the target bandwidth corresponding to the predicted network traffic.

[0012] In some embodiments, according to whether the maximum bandwidth meets the target bandwidth corresponding to the predicted network traffic, a corresponding network resource adjustment strategy is selected, including: if the maximum bandwidth of the target optical network meets the target bandwidth corresponding to the predicted network traffic, the bandwidth of the target optical network is adjusted to the target bandwidth; if the maximum bandwidth of the target optical network does not meet the target bandwidth corresponding to the predicted network traffic, a resource call application is sent to the outside of the target optical network.

[0013] In some embodiments, adjusting the bandwidth of the target optical network to the target bandwidth includes: obtaining the transmission protocol type of the target optical network, and selecting a corresponding bandwidth adjustment scheme according to the transmission protocol type; based on the bandwidth adjustment scheme, adjusting the bandwidth of the target optical network so that the bandwidth of the target optical network reaches the target bandwidth.

[0014] In some embodiments, after selecting a corresponding network resource adjustment strategy based on whether the maximum bandwidth meets the target bandwidth corresponding to the predicted network traffic, the method further includes: constructing a model training set based on network performance data of the target optical network, network knowledge information of a first preset time period pre-stored in a knowledge base, and the adopted network resource adjustment strategy; and training a traffic prediction model based on the model training set to optimize the results output by the traffic prediction model.

[0015] According to another aspect of the present disclosure, an optical network traffic prediction device is also provided, including: a network performance data acquisition module, used to acquire network performance data of a target optical network; a timing correlation result analysis module, used to perform timing analysis on the network performance data based on network knowledge information of a first preset time period pre-stored in a knowledge base, to obtain a timing correlation result, wherein the network knowledge information is structured information related to historical traffic information of the target optical network, and the timing correlation result is used to represent the correlation relationship between the network performance data and the network knowledge information; a target network traffic prediction module, used to input the network performance data, the timing correlation result and the supplementary traffic information pre-stored in the knowledge base into a pre-trained traffic prediction model, and output the predicted network traffic of the target optical network within a second preset time period, wherein the supplementary traffic information is manually input unstructured information related to the historical traffic information of the target optical network, and the second preset time period is later than the first preset time period.

[0016] According to another aspect of the present disclosure, an electronic device is also provided, which includes: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute any one of the optical network traffic prediction methods described above by executing the executable instructions.

[0017] According to another aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the optical network traffic prediction method described in any one of the above is implemented.

[0018] According to another aspect of the present disclosure, a computer program product is also provided, including a computer program, and when the computer program is executed by a processor, any one of the above optical network traffic prediction methods is implemented.

[0019] The optical network traffic prediction method, device, equipment, medium and program product provided in the embodiments of the present disclosure, after obtaining the network performance data of the target optical network, performs time series analysis on the network performance data based on the network knowledge information of the first preset time period pre-stored in the knowledge base, obtains the time series correlation result, and then inputs the network performance data, the time series correlation result and the supplementary traffic information pre-stored in the knowledge base into the pre-trained traffic prediction model, and outputs the predicted network traffic of the target optical network in the second preset time period. The embodiments of the present disclosure can improve the accuracy of the optical network traffic prediction results, and quickly adjust based on the existing network resources to reduce the waste of network resources.

[0020] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification are used to explain the principles of the present disclosure. Obviously, the accompanying drawings described below are only some embodiments of the present disclosure, and for ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without creative work.

[0022] Figure 1 A flow chart of an optical network traffic prediction method according to an embodiment of the present disclosure is shown;

[0023] Figure 2 A schematic diagram of a system structure for implementing an optical network traffic prediction method in an embodiment of the present disclosure is shown;

[0024] Figure 3 A schematic diagram showing a large model training data set format in an embodiment of the present disclosure is shown;

[0025] Figure 4 A schematic diagram of an optical network traffic prediction device according to an embodiment of the present disclosure is shown;

[0026] Figure 5 A structural block diagram of an electronic device in an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0027] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that the disclosure will be more comprehensive and complete and to fully convey the concepts 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.

[0028] In addition, the accompanying drawings are only schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0029] The specific implementation of the embodiment of the present disclosure is described in detail below with reference to the accompanying drawings.

[0030] Figure 1 A flow chart of an optical network traffic prediction method according to an embodiment of the present disclosure is shown as follows: Figure 1 As shown, the method comprises the following steps:

[0031] S102: Acquire network performance data of a target optical network.

[0032] In one embodiment of the present disclosure, the network performance data of the target network may include but is not limited to timing data, topology data, network element data, service bandwidth and flow data, and other network performance data.

[0033] S104, based on the network knowledge information of the first preset time period pre-stored in the knowledge base, perform a timing analysis on the network performance data to obtain a timing correlation result, wherein the network knowledge information is structured information related to the historical traffic information of the target optical network, and the timing correlation result is used to represent the correlation relationship between the network performance data and the network knowledge information.

[0034] In one embodiment of the present disclosure, the acquired network performance data is subjected to time series analysis based on the network knowledge information of the first preset time period in the pre-built knowledge base. The first preset time period may be a certain historical time period, and the network knowledge information may include but is not limited to trend law information and information such as cutover, maintenance, and update and upgrade during system operation and maintenance. Through time series analysis, the network performance data may be converted into structured information as a time series association result.

[0035] S106, input the network performance data, timing correlation results and supplementary traffic information pre-stored in the knowledge base into a pre-trained traffic prediction model, and output the predicted network traffic of the target optical network within a second preset time period, wherein the supplementary traffic information is manually input unstructured information related to the historical traffic information of the target optical network, and the second preset time period is later than the first preset time period.

[0036] In one embodiment of the present disclosure, the supplementary flow information may be unstructured supplementary information manually input into a pre-built knowledge base. Since some temporarily reported information or remark information in historical work orders cannot be identified in a structured form, it is necessary to manually input them as supplementary information. The supplementary flow information may also include a tolerance preset by humans. The second preset time period may be a certain time period in the future. The flow prediction model predicts the flow of the target optical network within the second preset time period based on the network performance data, the timing correlation result and the supplementary flow information.

[0037] It should be noted that whether the above-mentioned supplementary flow information needs to be added to the prediction process of the flow prediction model can be determined according to actual conditions, and the embodiments of the present disclosure do not make specific limitations on this.

[0038] As can be seen from the above, after acquiring the network performance data of the target optical network, the disclosed embodiment performs a time series analysis on the network performance data based on the network knowledge information of the first preset time period pre-stored in the knowledge base, obtains a time series correlation result, and then inputs the network performance data, the time series correlation result and the supplementary flow information pre-stored in the knowledge base into a pre-trained flow prediction model, and outputs the predicted network flow of the target optical network in the second preset time period. The disclosed embodiment can improve the accuracy of the optical network flow prediction results, and quickly adjust based on the existing network resources to reduce the waste of network resources.

[0039] In one embodiment of the present disclosure, before the above S104, the method also includes: obtaining historical traffic information and supplementary traffic information of the target optical network within a first preset time period, wherein the historical traffic information includes historical traffic conditions on a preset date and historical traffic conditions at a preset time point; structuring the historical traffic information according to a preset network field format to obtain network knowledge information; and constructing a knowledge base based on the network knowledge information and the supplementary traffic information.

[0040] In one embodiment of the present disclosure, the preset network field includes time information, corresponding network bandwidth information, and an event identifier or a time identifier.

[0041] In one embodiment of the present disclosure, the historical traffic conditions on a preset date may include conditions on special date nodes in previous years. For example, the current traffic bandwidth demand is large on certain holidays or special hot spots. It can be structured into a preset field format for knowledge entry, for example, timestamp + event number + bandwidth value.

[0042] In one embodiment of the present disclosure, the historical traffic conditions at preset time points may include conditions at regular time nodes such as cutover, maintenance, update and upgrade during system operation and maintenance, which can be structured into a preset field format for knowledge entry, for example, timestamp + operation number + bandwidth value.

[0043] In one embodiment of the present disclosure, the supplementary flow information may include the situation information temporarily reported within a preset historical period or the remark description information in the historical data work order, which is an unstructured description content related to the historical flow information. It is impossible to structure this part of the data in batches, so it needs to be input manually. Since the pre-trained flow prediction model has good semantic understanding ability and certain task processing capabilities, the flow prediction model can process the supplementary flow information together with other input information data. In some actual situations, if the unstructured description content is not received, it can be omitted.

[0044] In one embodiment of the present disclosure, the supplementary flow information may further include a tolerance, which may be a manually preset value. In some practical situations, if the preset tolerance is not received, the default value may be input.

[0045] In one embodiment of the present disclosure, the timestamp field in the network knowledge information can be associated with the acquired network performance data to obtain a time series association result as a supplement to the input data of the traffic prediction model.

[0046] In one embodiment of the present disclosure, a label may be set, such as a normal traffic label, an abnormal traffic label, etc., and the network knowledge information and the acquired network performance data may be associated with the preset label to obtain a time series association result as a supplement to the input data of the traffic prediction model. For example, by presetting an abnormal traffic label, a time series association result between the network knowledge information and the acquired network performance data may be obtained, and corresponding prediction information and warning information may be output.

[0047] In one embodiment of the present disclosure, after the above S106, the method further includes: calculating the maximum bandwidth of the target optical network based on the acquired network performance data of the target optical network; and selecting a corresponding network resource adjustment strategy based on whether the maximum bandwidth meets the target bandwidth corresponding to the predicted network traffic.

[0048] In one embodiment of the present disclosure, a corresponding network resource adjustment strategy is selected according to whether the maximum bandwidth meets the target bandwidth corresponding to the predicted network traffic, including: if the maximum bandwidth of the target optical network meets the target bandwidth corresponding to the predicted network traffic, the bandwidth of the target optical network is adjusted to the target bandwidth; if the maximum bandwidth of the target optical network does not meet the target bandwidth corresponding to the predicted network traffic, a resource call application is sent to the outside of the target optical network.

[0049] In one embodiment of the present disclosure, target bandwidth=predicted throughput*(1+tolerance).

[0050] In one embodiment of the present disclosure, after calculating the maximum bandwidth of the target optical network, it is determined whether the maximum bandwidth meets the target bandwidth corresponding to the predicted network traffic. The period and bandwidth of the target optical network may be adjusted by default to achieve the predicted network traffic. If the predicted network traffic cannot be achieved, an additional resource application may be output. Specifically, the resource application may involve adjusting the device, board, or port.

[0051] In one embodiment of the present disclosure, adjusting the bandwidth of a target optical network to a target bandwidth includes: obtaining a transmission protocol type of the target optical network, and selecting a corresponding bandwidth adjustment scheme according to the transmission protocol type; and adjusting the bandwidth of the target optical network based on the bandwidth adjustment scheme so that the bandwidth of the target optical network reaches the target bandwidth.

[0052] In one embodiment of the present disclosure, a corresponding bandwidth adjustment scheme is adopted according to the protocol type of the optical network. Specifically, if the optical network is a synchronous digital hierarchy SDH network, a link capacity adjustment scheme LCAS can be used to dynamically adjust the link capacity. LCAS allows the number of member virtual containers VC to be increased or decreased without affecting existing services, thereby flexibly adjusting the bandwidth of the transmission path, and can adjust the bandwidth as needed while maintaining the connection, thereby improving the utilization rate of network resources; if the optical network is an optical transport network OTN, since the flexible optical channel data unit ODUflex in the OTN is a container with a variable bandwidth, it is used to carry data signals of any rate, and its size can be adjusted according to actual business needs, providing a more refined bandwidth allocation capability; if the optical network is an Ethernet service, by setting the port rate limit on the switch or other network equipment, it can be ensured that a specific port or service will not occupy bandwidth exceeding the specified limit, which is very useful for preventing network congestion, ensuring key business performance, and implementing traffic engineering. It can also be combined with QoS strategies, such as priority queues, weighted fair queues, etc., to further refine the management of network traffic.

[0053] It should be noted that the bandwidth adjustment schemes corresponding to the above network types are only exemplary, and any other schemes that can play a role in bandwidth adjustment can be adopted according to actual conditions, and the embodiments of the present disclosure do not make specific limitations on this.

[0054] In one embodiment of the present disclosure, after selecting a corresponding network resource adjustment strategy based on whether the maximum bandwidth meets the target bandwidth corresponding to the predicted network traffic, the method also includes: constructing a model training set based on network performance data of the target optical network, network knowledge information of a first preset time period pre-stored in a knowledge base, and the adopted network resource adjustment strategy; and training a traffic prediction model based on the model training set to optimize the results output by the traffic prediction model.

[0055] In one embodiment of the present disclosure, the network predicted traffic output by the traffic prediction model, the network knowledge information within the first preset time period, and the bandwidth adjustment scheme adopted based on the current optical network type can be fused and spliced, and the training data set of the traffic prediction model can be continuously accumulated to optimize the output result of the traffic prediction model. The continuous optimization of the traffic prediction model is achieved through data accumulation to improve the accuracy of the model in practical applications and reduce the need for external intervention.

[0056] In one embodiment of the present disclosure, the pre-trained traffic prediction model belongs to a large model, which refers to a machine learning model with a large number of parameters and complex structure, which can process massive data and complete various complex tasks, such as natural language processing, computer vision, speech recognition, etc. Deep learning technology has been widely used and recognized in various fields, especially the development of large model technology, which has been implemented in many fields with its powerful context understanding ability, nonlinear modeling ability, automatic feature extraction ability and efficient scalability, and can significantly improve the AI+ application ability of the operation and maintenance system and meet the needs of the new generation of networks for accurate prediction of traffic bandwidth.

[0057] Figure 2 A schematic diagram of a system structure for implementing an optical network traffic prediction method according to an embodiment of the present disclosure is shown. Figure 2 As shown, the system includes: an analysis and decision-making unit and an execution unit.

[0058] In one embodiment of the present disclosure, the analysis and decision unit and the execution unit can be connected to the interface of the network management system in the related technology. Specifically, the analysis and decision unit includes a network data collection module, a multi-source knowledge base, a correlation analysis module, a historical data collection module and a decision module; the execution unit performs operations such as bandwidth adjustment and capacity expansion resource application based on the output results of the analysis and prediction unit and the existing resource conditions of the target optical network.

[0059] Step 1: Control system (i.e. Figure 2 The transmission network management system or controller shown in the figure) obtains network performance data from the target optical network device through a data collection method. The data collection method may include but is not limited to the simple network management protocol SNMP, the command line interface CLI / secure shell protocol SSH, etc. It should be noted that in actual situations, a suitable data collection method should be selected according to the actual network architecture and system compatibility, and the embodiments of the present disclosure do not specifically limit this.

[0060] Step 2: The network traffic collection module obtains network performance data from the management and control system, which may include but is not limited to timing data, topology data, network element data, service bandwidth, traffic data and other network performance data.

[0061] Step 3, the preset network expertise within the first preset time period in the knowledge base (i.e., the above-mentioned network knowledge information, i.e., structured information related to the historical traffic information of the target optical network) is transmitted as input to the correlation analysis module and the traffic prediction module respectively. Specifically, the network expertise may include but is not limited to trend law information and information such as cutover, maintenance, update and upgrade during system operation and maintenance.

[0062] Step 4: The correlation analysis module receives the network performance data integrated by the network data collection module and the preset network expertise in the knowledge base, performs a preliminary time series correlation analysis, and obtains a time series correlation result.

[0063] Step 5: The time series correlation result of the correlation analysis module is transmitted as input to the traffic prediction module.

[0064] Step 6, transmit the manually input information within the first preset time period in the knowledge base as input to the traffic prediction module, and clean and standardize the data in the module. Among them, the manually input information is unstructured information related to the historical traffic information of the target optical network, which may include manually set tolerance parameters, temporarily reported situation information, and notes information of historical data work orders. It should be noted that if the tolerance parameters are not manually preset in actual situations, the tolerance parameters are provided according to the default values. If no supplementary instructions are provided, the default supplementary traffic information is empty, and the embodiments of the present disclosure do not make specific limitations on this.

[0065] Step 7: The traffic prediction module receives the output data of the network data collection module, the manual input information in the knowledge base and the output data of the association analysis module, integrates the prompt words and finally obtains the predicted network traffic within the second preset time period.

[0066] Step 8: The decision module outputs the target capacity of the target optical network based on the network predicted traffic, and generates a conclusion on resource application or bandwidth adjustment. Target bandwidth = predicted throughput * (1 + tolerance). If the target optical network fails to meet the adjustment requirements, execute step 8.1; if the target optical network can meet the adjustment requirements, execute step 8.2.

[0067] Specifically, in step 8.1, the decision module outputs additional resource applications, which may involve adjustments to devices, boards, or ports, etc., to achieve the expansion of the target optical network capacity. In step 8.2, the decision module outputs the adjustment cycle and target bandwidth of the management and control system, and the management and control system implements a series of adjustment operations to optimize the transmission network.

[0068] Step 9: The management and control system takes bandwidth adjustment measures to optimize the optical network according to the protocol type of the optical transmission network. For example, the LCAS adjustment method can be used for SDH; the ODUflex adjustment method can be used for OTN; and the port speed limit method can be directly used for Ethernet services.

[0069] It should be noted that the bandwidth adjustment schemes corresponding to the above network types are only exemplary, and any other schemes that can play a role in bandwidth adjustment can be adopted according to actual conditions, and the embodiments of the present disclosure do not make specific limitations on this.

[0070] Step 10, the historical data collection module is responsible for collecting the output data of the network data collection module, the preset knowledge matched in the knowledge base, and the action data of the execution unit, and fusing and splicing these three types of data to continuously accumulate the training data set of the large model for optimizing the large model of the traffic prediction module.

[0071] As can be seen from the above, after acquiring the network performance data of the target optical network, the disclosed embodiment performs a time series analysis on the network performance data based on the network knowledge information of the first preset time period pre-stored in the knowledge base, obtains a time series correlation result, and then inputs the network performance data, the time series correlation result and the supplementary flow information pre-stored in the knowledge base into a pre-trained flow prediction model, and outputs the predicted network flow of the target optical network in the second preset time period. The disclosed embodiment can improve the accuracy of the optical network flow prediction results, and quickly adjust based on the existing network resources to reduce the waste of network resources.

[0072] In one embodiment of the present disclosure, the system can be verified in the intelligent scenario of the access-type OTN management and control system, which focuses on the operation and maintenance of optical networks, especially resource management and optimization, generates prediction results through data processing, supports scientific adjustment decisions, optimizes resource application and adjustment cycles, thereby improving management efficiency, and is applicable to traffic prediction and adjustment of various optical network bearer technologies. At the same time, a multi-level knowledge fusion strategy is implemented to organically combine structured information (such as network performance data, traffic bandwidth statistics) with unstructured information (such as manual knowledge input, user feedback, etc.), broaden the breadth of data sources, and improve the model's integration of different information types and data quality; the ability mechanism to capture and analyze traffic fluctuations caused by specific events or behavioral changes, effectively improve the inaccuracies in time-series correlation predictions, and adjust the prediction strategy in a timely manner, thereby ensuring efficiency and accuracy in a complex and changing network environment.

[0073] In one embodiment of the present disclosure, the names and contents of the input fields of the traffic prediction module may be as shown in Table 1:

[0074] Table 1

[0075] Data field name describe Topology ID / Port ID / Line Card ID / Network Element ID / Location ID / Time Index yyyymmddhhmmss eg20240618110100 RX_BYTES(average) per port / time cycle TX_BYTES(average) per port / time cycle Service Bandwidth / Error-tolerant Rate 0～1 Notes supplementary notes for necessary explanation

[0076] In one embodiment of the present disclosure, the names and contents of the output fields of the traffic prediction module may be as shown in Table 2:

[0077] Table 2

[0078] Data field name describe Predicted Time Index yyyymmddhhmmss eg20240720120500 Predicted Throughput bits / s

[0079] It should be noted that the above-mentioned traffic prediction module input field and output field are only for illustrative purposes, and the input and output field types and contents may be added or reduced according to actual conditions, and the embodiments of the present disclosure do not make specific limitations on this.

[0080] In one embodiment of the present disclosure, the traffic prediction module has powerful semantic understanding and adaptive task processing capabilities, and can achieve the target function by fine-tuning the training data and task prompt words according to the differences in specific tasks.

[0081] In one embodiment of the present disclosure, Figure 3 A schematic diagram showing a large model training data set format in an embodiment of the present disclosure is shown. Figure 3 As shown in the figure, regarding the problem part, the real-time network information output by the current management and control system is as follows:

[0082] Topology ID: XXXX;

[0083] Port ID: XXXX;

[0084] Interface board ID (Line Card ID): XXXX;

[0085] Network Element ID: XXXX;

[0086] Location ID:XXXX;

[0087] Time Index: XXXXXXXXXXXX;

[0088] Received bytes (average) RX_BYTES (average): XXXXXXXX;

[0089] TX_BYTES(average):XXXXXXXX;

[0090] Service Bandwidth: XXXXXXXX;

[0091] The other parameters currently added are as follows:

[0092] Error-tolerant Rate: 0.0X;

[0093] Notes: XXXXXXXXXXXXX.

[0094] Requirements: Based on the above information, please predict the traffic bandwidth (Predicted Throughput) at the specified time (Predicted Time Index). The output format requirements are as follows:

[0095] Time Index: XXXXXXXXXXXX;

[0096] Predicted Throughput: XXXXXXXX

[0097] Regarding the reply part:

[0098] Time Index: XXXXXXXXXXXX;

[0099] Predicted Throughput: XXXXXXXX

[0100] In one embodiment of the present disclosure, the name and content of the output data of the decision module may be as shown in Table 3:

[0101] Table 3

[0102]

[0103] It should be noted that the output data of the above-mentioned decision module is only for illustrative purposes, and the output data type and content may be added or reduced according to actual conditions, and the embodiments of the present disclosure do not make specific limitations on this.

[0104] In one embodiment of the present disclosure, by analyzing the interface connection between the decision-making unit and the execution unit and the network management system in the relevant technology, integrating internal and external knowledge information, building a multi-dimensional and dynamic knowledge base, introducing a large model as the core link of predictive analysis, combining data training and scenario task prompts, the traffic bandwidth prediction capability can be achieved through the real-time parameter indicators of the management and control system.

[0105] In one embodiment of the present disclosure, a dual knowledge input mechanism is used to effectively integrate static and dynamic knowledge resources, greatly expanding the model knowledge system so that it can timely capture traffic fluctuations caused by specific emergencies or activities; at the same time, the mechanism also significantly enhances the model's contextual understanding and reasoning capabilities, thereby effectively improving the problem of emergencies that are difficult to predict by relying on existing data and patterns.

[0106] In one embodiment of the present disclosure, the system can be applied to the traffic prediction and related decision-making process of any optical transport network, and is easy to implement in combination with the existing network management / controller system, with greater breadth and availability. In addition, in the process of implementing the optical network traffic prediction method, the system refines the technical solution for specific network adjustment, which is divided into two scenarios: bandwidth adjustment and capacity expansion, so that the prediction results can be closely combined with the actual operation, and better meet the specific needs of network operation.

[0107] Based on the same inventive concept, the present disclosure also provides an optical network traffic prediction device, as described in the following embodiments. Since the principle of solving the problem in the device embodiment is similar to that in the above method embodiment, the implementation of the device embodiment can refer to the implementation of the above method embodiment, and the repeated parts will not be repeated.

[0108] Figure 4 A schematic diagram of an optical network traffic prediction device according to an embodiment of the present disclosure is shown. Figure 4 As shown, the device includes: a network performance data acquisition module 401, a timing correlation result analysis module 402 and a target network traffic prediction module 403.

[0109] Among them, the network performance data acquisition module 401 is used to obtain the network performance data of the target optical network; the timing correlation result analysis module 402 is used to perform timing analysis on the network performance data based on the network knowledge information of the first preset time period pre-stored in the knowledge base, and obtain the timing correlation result, wherein the network knowledge information is structured information related to the historical traffic information of the target optical network, and the timing correlation result is used to represent the correlation relationship between the network performance data and the network knowledge information; the target network traffic prediction module 403 is used to input the network performance data, the timing correlation result and the supplementary traffic information pre-stored in the knowledge base into a pre-trained traffic prediction model, and output the predicted network traffic of the target optical network in the second preset time period, wherein the supplementary traffic information is manually input unstructured information related to the historical traffic information of the target optical network, and the second preset time period is later than the first preset time period.

[0110] As can be seen from the above, after acquiring the network performance data of the target optical network, the disclosed embodiment performs a time series analysis on the network performance data based on the network knowledge information of the first preset time period pre-stored in the knowledge base, obtains a time series correlation result, and then inputs the network performance data, the time series correlation result and the supplementary flow information pre-stored in the knowledge base into a pre-trained flow prediction model, and outputs the predicted network flow of the target optical network in the second preset time period. The disclosed embodiment can improve the accuracy of the optical network flow prediction results, and quickly adjust based on the existing network resources to reduce the waste of network resources.

[0111] In one embodiment of the present disclosure, the device also includes: a knowledge base construction module 404, which is used to obtain historical traffic information and supplementary traffic information of the target optical network within a first preset time period, wherein the historical traffic information includes historical traffic conditions on a preset date and historical traffic conditions at a preset time point; structure the historical traffic information according to a preset network field format to obtain network knowledge information; and construct a knowledge base based on the network knowledge information and supplementary traffic information.

[0112] In one embodiment of the present disclosure, the preset network field includes time information, corresponding network bandwidth information, and an event identifier or a time identifier.

[0113] In one embodiment of the present disclosure, the device also includes: a network resource adjustment module 405, which is used to calculate the maximum bandwidth of the target optical network based on the acquired network performance data of the target optical network; and select a corresponding network resource adjustment strategy based on whether the maximum bandwidth meets the target bandwidth corresponding to the predicted network traffic.

[0114] In one embodiment of the present disclosure, the network resource adjustment module 405 is further used to adjust the bandwidth of the target optical network to the target bandwidth if the maximum bandwidth of the target optical network meets the target bandwidth corresponding to the predicted network traffic; if the maximum bandwidth of the target optical network does not meet the target bandwidth corresponding to the predicted network traffic, send a resource call application to the outside of the target optical network.

[0115] In one embodiment of the present disclosure, the network resource adjustment module 405 is further used to obtain the transmission protocol type of the target optical network, and select a corresponding bandwidth adjustment scheme according to the transmission protocol type; based on the bandwidth adjustment scheme, the bandwidth of the target optical network is adjusted so that the bandwidth of the target optical network reaches the target bandwidth.

[0116] In one embodiment of the present disclosure, the device also includes: a traffic prediction model optimization module 406, which is used to form a model training set based on the network performance data of the target optical network, the network knowledge information of the first preset time period pre-stored in the knowledge base, and the adopted network resource adjustment strategy; and train the traffic prediction model based on the model training set to optimize the results output by the traffic prediction model.

[0117] Those skilled in the art will appreciate that various aspects of the present disclosure may be implemented as systems, methods or program products. Therefore, various aspects of the present disclosure may be specifically implemented in the following forms, namely: complete hardware implementation, complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to herein as "circuits", "modules" or "systems".

[0118] Refer to the following Figure 5The electronic device 500 according to this embodiment of the present disclosure is described. Figure 5 The electronic device 500 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0119] like Figure 5 As shown, the electronic device 500 is in the form of a general computing device. The components of the electronic device 500 may include but are not limited to: at least one processing unit 510, at least one storage unit 520, and a bus 530 connecting different system components (including the storage unit 520 and the processing unit 510).

[0120] The storage unit stores a program code, and the program code can be executed by the processing unit 510, so that the processing unit 510 executes the steps described in the above "Exemplary Method" section of this specification according to various exemplary embodiments of the present disclosure. For example, the processing unit 510 can execute the following steps of the above method embodiment: obtaining network performance data of the target optical network; based on the network knowledge information of the first preset time period pre-stored in the knowledge base, performing time series analysis on the network performance data to obtain a time series correlation result, wherein the network knowledge information is structured information related to the historical traffic information of the target optical network, and the time series correlation result is used to represent the correlation relationship between the network performance data and the network knowledge information; inputting the network performance data, the time series correlation result and the supplementary traffic information pre-stored in the knowledge base into the pre-trained traffic prediction model, and outputting the predicted network traffic of the target optical network in the second preset time period, wherein the supplementary traffic information is unstructured information related to the historical traffic information of the target optical network that is manually input, and the second preset time period is later than the first preset time period.

[0121] The storage unit 520 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 5201 and / or a cache storage unit 5202 , and may further include a read-only storage unit (ROM) 5203 .

[0122] The storage unit 520 may also include a program / utility 5204 having a set (at least one) of program modules 5205, such program modules 5205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0123] Bus 530 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0124] The electronic device 500 may also communicate with one or more external devices 540 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 500, and / or communicate with any device that enables the electronic device 500 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 550. Furthermore, the electronic device 500 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 560. As shown, the network adapter 560 communicates with other modules of the electronic device 500 via a bus 530. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 500, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0125] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0126] Based on the same inventive concept, a computer-readable storage medium is also provided in the embodiment of the present disclosure, on which a computer program is stored, and when the computer program is executed by a processor, any of the above optical network traffic prediction methods is implemented. Since the principle of solving the problem in the computer-readable storage medium embodiment is similar to that in the above method embodiment, the implementation of the computer-readable storage medium embodiment can refer to the implementation of the above method embodiment, and the repeated parts will not be repeated.

[0127] More specific examples of computer-readable storage media in the present disclosure may include, but are not limited to, an electrical connection having one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0128] In the present disclosure, a computer readable storage medium may include a data signal propagated in baseband or as part of a carrier wave, wherein a readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A readable signal medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0129] Alternatively, the program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0130] In a specific implementation, the program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., using an Internet service provider to connect through the Internet).

[0131] Based on the same inventive concept, a computer program product is also provided in an embodiment of the present disclosure, including a computer program product, including: a computer program or an instruction, wherein when the computer program or the instruction is executed by a processor, the optical network traffic prediction method of any one of the above method embodiments is implemented. Since the principle of solving the problem in the computer program product embodiment is similar to that in the above method embodiment, the implementation of the computer program product embodiment can refer to the implementation of the above method embodiment, and the repeated parts will not be repeated.

[0132] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0133] In addition, although the steps of the method in the present disclosure are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0134] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0135] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variations, uses or adaptations of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the appended claims.

Claims

1. A method for predicting optical network traffic, characterized in that: include: Obtain network performance data of the target optical network; Based on the network knowledge information of the first preset time period pre-stored in the knowledge base, the network performance data is subjected to time series analysis to obtain a time series correlation result, wherein the network knowledge information is structured information related to the historical traffic information of the target optical network, and the time series correlation result is used to represent the correlation relationship between the network performance data and the network knowledge information; The network performance data, the timing correlation result and the supplementary traffic information pre-stored in the knowledge base are input into a pre-trained traffic prediction model, and the predicted network traffic of the target optical network within a second preset time period is output, wherein the supplementary traffic information is manually input unstructured information related to the historical traffic information of the target optical network, and the second preset time period is later than the first preset time period.

2. The optical network traffic prediction method according to claim 1, characterized in that: Before performing time series analysis on the network performance data based on the network knowledge information of the first preset time period pre-stored in the knowledge base to obtain the time series correlation result, the method further includes: Acquire historical traffic information and supplementary traffic information of the target optical network within a first preset time period, wherein the historical traffic information includes historical traffic conditions on a preset date and historical traffic conditions at a preset time point; According to a preset network field format, the historical traffic information is structured to obtain network knowledge information; A knowledge base is constructed based on the network knowledge information and the supplementary flow information.

3. The optical network traffic prediction method according to claim 2, characterized in that: The preset network field includes time information, corresponding network bandwidth information, and an event identifier or a time identifier.

4. The optical network traffic prediction method according to claim 1, characterized in that: After inputting the network performance data, the timing correlation result and the supplementary traffic information pre-stored in the knowledge base into a pre-trained traffic prediction model and outputting the predicted network traffic of the target optical network within a second preset time period, the method further includes: Calculating the maximum bandwidth of the target optical network according to the acquired network performance data of the target optical network; A corresponding network resource adjustment strategy is selected according to whether the maximum bandwidth meets the target bandwidth corresponding to the predicted network traffic.

5. The optical network traffic prediction method according to claim 4, characterized in that: According to whether the maximum bandwidth meets the target bandwidth corresponding to the predicted network traffic, a corresponding network resource adjustment strategy is selected, including: If the maximum bandwidth of the target optical network meets the target bandwidth corresponding to the predicted network traffic, adjusting the bandwidth of the target optical network to the target bandwidth; If the maximum bandwidth of the target optical network does not meet the target bandwidth corresponding to the predicted network traffic, a resource call request is sent to the outside of the target optical network.

6. The optical network traffic prediction method according to claim 5, characterized in that: The step of adjusting the bandwidth of the target optical network to the target bandwidth includes: Acquire a transmission protocol type of the target optical network, and select a corresponding bandwidth adjustment scheme according to the transmission protocol type; Based on the bandwidth adjustment scheme, the bandwidth of the target optical network is adjusted so that the bandwidth of the target optical network reaches the target bandwidth.

7. The optical network traffic prediction method according to claim 4, characterized in that: After selecting a corresponding network resource adjustment strategy according to whether the maximum bandwidth satisfies a target bandwidth corresponding to the predicted network traffic, the method further includes: A model training set is formed according to the network performance data of the target optical network, the network knowledge information of the first preset time period pre-stored in the knowledge base, and the adopted network resource adjustment strategy; The traffic prediction model is trained based on the model training set to optimize the results output by the traffic prediction model.

8. An optical network traffic prediction device, characterized in that: include: A network performance data acquisition module, used to acquire network performance data of a target optical network; A timing correlation result analysis module, used to perform timing analysis on the network performance data based on network knowledge information of a first preset time period pre-stored in a knowledge base to obtain a timing correlation result, wherein the network knowledge information is structured information related to historical traffic information of the target optical network, and the timing correlation result is used to represent the correlation relationship between the network performance data and the network knowledge information; A target network traffic prediction module is used to input the network performance data, the timing correlation result and the supplementary traffic information pre-stored in the knowledge base into a pre-trained traffic prediction model, and output the predicted network traffic of the target optical network within a second preset time period, wherein the supplementary traffic information is manually input unstructured information related to the historical traffic information of the target optical network, and the second preset time period is later than the first preset time period.

9. An electronic device, characterized in that: include: processor; as well as A memory, configured to store executable instructions of the processor; The processor is configured to execute the optical network traffic prediction method according to any one of claims 1 to 7 by executing the executable instructions.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the optical network traffic prediction method according to any one of claims 1 to 7 is implemented.

11. A computer program product comprising: A computer program or instruction, characterized in that when the computer program or instruction is executed by a processor, the optical network traffic prediction method according to any one of claims 1 to 7 is implemented.

Images