Network slicing migration method, device, electronic device and storage medium

Abstract

The present disclosure provides a network slice migration method, device, electronic device and storage medium, which relate to the field of optical network technology. The method includes: when the target service is assigned to the target slice, the predicted network resources of the target slice are determined according to the strong prediction model, and the network resources include at least one of the predicted computing resources and the predicted spectrum resources; determining whether the predicted network resources of the target slice meet the first preset condition; if the predicted network resources do not meet the first preset condition, the nodes and paths of the target slice are migrated; if the migrated nodes and paths meet the second preset condition, the corresponding network resources are occupied. The present disclosure can realize the migration of the target slice in advance based on the prediction of future traffic, avoid network migration lag, effectively improve the flexibility and reliability of network slice migration, and improve service quality.

Description

Background Art

[0002] With the development of optical network technology, network slicing technology has greatly improved network performance and service quality. Network slicing allows operators to create multiple logically independent slices on the same physical network infrastructure, and each slice can be optimized for a specific type of service or industry. As an advanced optical transport network architecture, EON (Elastic Optical Network) can provide flexible spectrum resource allocation and transmission configuration adjustment capabilities. This means that EON can dynamically adjust the bandwidth and other parameters of the optical channel according to actual needs, thereby providing tailored network slices for different users to meet their differentiated needs and achieve efficient use of spectrum resources.

[0003] However, the network slice migration technology in related technologies often lacks sufficient flexibility and reliability to cope with rapidly changing business needs. For example, when network traffic suddenly increases, the network slice migration method provided by related technologies may not be able to respond and adjust related network resources in time, resulting in a decline in service quality.

[0004] 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

[0005] The present disclosure provides a network slice migration method, device, electronic device and storage medium, which at least to a certain extent overcome the problem that related technologies lack flexibility and reliability to cope with rapidly changing business needs, thereby causing a decline in service quality.

[0006] 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.

[0007] According to one aspect of the present disclosure, a network slice migration method is provided, including:

[0008] When the target service is allocated to the target slice, determining a predicted network resource of the target slice according to the strong prediction model, the network resource comprising at least one of a predicted computing resource and a predicted spectrum resource;

[0009] Determining whether the predicted network resources of the target slice meet a first preset condition;

[0010] If the predicted network resources do not meet the first preset condition, migrating the nodes and paths of the target slice;

[0011] If the migrated nodes and paths meet the second preset condition, the corresponding network resources are occupied.

[0012] In some embodiments, the network slice migration method provided by the embodiments of the present disclosure further includes:

[0013] Determine a plurality of basic models, wherein the basic models include at least one of a BP (Backpropagation, back propagation neural network) model, an RNN (Recurrent Neural Network, recurrent neural network) model, and an LSTM (Long Short-Term Memory, long short-term memory network) model;

[0014] Training the multiple basic models respectively to obtain multiple trained basic models;

[0015] The strong prediction model is obtained according to the multiple trained basic models.

[0016] In some embodiments, determining the predicted network resource of the target slice according to the strong prediction model includes:

[0017] Predicting the network resources of the target slices according to the trained basic models;

[0018] The network resource values ​​predicted by each trained basic model are processed according to an integrated learning algorithm to obtain the predicted network resources of the target slice.

[0019] In some embodiments, the first preset condition includes at least one of a first sub-condition and a second sub-condition;

[0020] Among them, the first sub-condition is used to describe that the predicted computing resources occupied by the target service on each node do not exceed the remaining computing resources of the corresponding node, and the second sub-condition is used to describe that the predicted frequency slot resources occupied by the target service on each optical fiber link do not exceed the capacity of the corresponding optical fiber link.

[0021] In some embodiments, if the predicted network resources do not meet the first preset condition, migrating the nodes and paths of the target slice includes:

[0022] If the predicted computing resources do not satisfy the first sub-condition and / or the predicted frequency slot resources do not satisfy the second sub-condition, the nodes and paths of the target slice are migrated.

[0023] In some embodiments, the second preset condition includes at least one of the first sub-condition, the second sub-condition, the third sub-condition, the fourth sub-condition and the fifth sub-condition;

[0024] Among them, the third sub-condition is used to describe that the spectrum resources allocated to the target service on each optical fiber link along the path are the same, the fourth sub-condition is used to describe that the frequency slot resources on the optical fiber link through which the optical path passes are the same, and the fifth sub-condition is used to describe that the frequency slot resources occupied by the target service and other services are different.

[0025] According to another aspect of the present disclosure, a network slice migration device is also provided, including:

[0026] A predicted network resource determination module, configured to determine, when a target service is allocated to a target slice, a predicted network resource of the target slice according to a strong prediction model, wherein the network resource includes at least one of a predicted computing resource and a predicted spectrum resource;

[0027] A first preset condition judgment module, used to determine whether the predicted network resources of the target slice meet the first preset condition;

[0028] A migration module, configured to migrate the nodes and paths of the target slice if the predicted network resources do not meet the first preset condition;

[0029] The network resource occupying module is used to occupy corresponding network resources if the migrated nodes and paths meet the second preset condition.

[0030] In some embodiments, the network slice migration device provided by the embodiment of the present disclosure further includes:

[0031] A strong prediction model determination module is used to determine multiple basic models, wherein the basic models include at least one of a BP model, an RNN model, and an LSTM model; the multiple basic models are trained separately to obtain multiple trained basic models; and the strong prediction model is obtained based on the multiple trained basic models.

[0032] In some embodiments, the predicted network resource determination module is used to predict the network resources of the target slice according to each trained basic model; the network resource values ​​predicted by each trained basic model are processed according to the integrated learning algorithm to obtain the predicted network resources of the target slice.

[0033] In some embodiments, the first preset condition includes at least one of a first sub-condition and a second sub-condition; wherein, the first sub-condition is used to describe that the predicted computing resources occupied by the target service on each node do not exceed the remaining computing resources of the corresponding node, and the second sub-condition is used to describe that the predicted frequency slot resources occupied by the target service on each optical fiber link do not exceed the capacity of the corresponding optical fiber link.

[0034] In some embodiments, the migration module is used to migrate the nodes and paths of the target slice if the predicted computing resources do not meet the first sub-condition and / or the predicted frequency slot resources do not meet the second sub-condition.

[0035] In some embodiments, the second preset condition includes at least one of the first sub-condition, the second sub-condition, the third sub-condition, the fourth sub-condition and the fifth sub-condition; wherein the third sub-condition is used to describe that the spectrum resources allocated on each optical fiber link along the path of the target service are the same, the fourth sub-condition is used to describe that the frequency slot resources on the optical fiber link through which the optical path passes are the same, and the fifth sub-condition is used to describe that the frequency slot resources occupied by the target service and other services are different.

[0036] 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 above-mentioned network slice migration methods by executing the executable instructions.

[0037] According to another aspect of the present disclosure, a computer-readable storage medium is also provided, on which a computer program is stored. When the computer program is executed by a processor, any one of the above-mentioned network slice migration methods is implemented.

[0038] According to another aspect of the present disclosure, a computer program product or a computer program is provided, the computer program product or the computer program including computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the electronic device executes the network slice migration method provided in various optional ways in any embodiment of the present disclosure.

[0039] The technical solution provided in the embodiments of the present disclosure can determine the predicted network resources of the target slice according to the strong prediction model, thereby realizing the migration of the target slice in advance based on the prediction of future traffic, avoiding network migration delays, effectively improving the flexibility and reliability of network slice migration, and improving service quality.

[0040] 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

[0041] 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.

[0042] Figure 1 A schematic diagram showing a system architecture in an embodiment of the present disclosure;

[0043] Figure 2 A flow chart of a network slice migration method according to an embodiment of the present disclosure is shown;

[0044] Figure 3 A schematic diagram of a process of an integrated flow prediction algorithm in an embodiment of the present disclosure is shown;

[0045] Figure 4 A flowchart of another network slice migration method in an embodiment of the present disclosure is shown;

[0046] Figure 5 A schematic diagram of a network slice migration device in an embodiment of the present disclosure is shown;

[0047] Figure 6 A structural block diagram of an electronic device according to an embodiment of the present disclosure is shown;

[0048] Figure 7 A schematic diagram of a computer-readable storage medium in an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0049] 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.

[0050] 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.

[0051] The specific implementation of the embodiment of the present disclosure is described in detail below with reference to the accompanying drawings.

[0052] Figure 1 FIG. 1 is a schematic diagram of an exemplary application system architecture to which the network slice migration method in the embodiment of the present disclosure can be applied. Figure 1 As shown, the system architecture may include a terminal device 101 , a network 102 and a server 103 .

[0053] Among them, the terminal device 101 can send the target service to the server 103. The server 103 is used to determine the predicted network resources of the target slice according to the strong prediction model when the target service is assigned to the target slice, and the network resources include at least one of the predicted computing resources and the predicted spectrum resources. Then, the server 103 can determine whether the predicted network resources of the target slice meet the first preset condition. If the predicted network resources do not meet the first preset condition, the nodes and paths of the target slice are migrated. Finally, the server 103 can also be used to occupy the corresponding network resources if the migrated nodes and paths meet the second preset condition.

[0054] The network 102 is a medium for providing a communication link between the terminal device 101 and the server 103, and can be a wired network or a wireless network.

[0055] Optionally, the wireless network or wired network described above uses standard communication technology and / or protocols. The network is typically the Internet, but may also be any network, including but not limited to a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), a mobile, wired or wireless network, a private network or any combination of a virtual private network). In some embodiments, technologies and / or formats including Hyper Text Mark-up Language (HTML), Extensible Markup Language (XML), etc. are used to represent data exchanged over the network. In addition, conventional encryption technologies such as Secure Socket Layer (SSL), Transport Layer Security (TLS), Virtual Private Network (VPN), Internet Protocol Security (IPSec), etc. may be used to encrypt all or some links. In other embodiments, customized and / or dedicated data communication technologies may also be used to replace or supplement the above data communication technologies.

[0056] The terminal device 101 can be various electronic devices, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, smart speakers, smart watches, wearable devices, augmented reality devices, virtual reality devices, etc.

[0057] Optionally, the client of the application installed in different terminal devices 101 is the same, or the client of the same type of application based on different operating systems. Based on the different terminal platforms, the specific form of the client of the application can also be different, for example, the application client can be a mobile client, a PC client, etc.

[0058] The server 103 may be a server that provides various services, such as a background management server that provides support for the device operated by the user using the terminal device 101. The background management server may analyze and process the received request and other data, and feed back the processing results to the terminal device.

[0059] Optionally, the server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), as well as big data and artificial intelligence platforms.

[0060] Those skilled in the art will know that Figure 1 The number of terminal devices 101, networks 102 and servers 103 is only illustrative, and any number of terminal devices 101, networks 102 and servers 103 may be provided according to actual needs. The embodiments of the present disclosure are not limited to this.

[0061] Under the above system architecture, a network slice migration method is provided in an embodiment of the present disclosure, which can be executed by any electronic device with computing and processing capabilities.

[0062] In some embodiments, the network slice migration method provided in the embodiments of the present disclosure can be executed by the server in the above-mentioned system architecture; in other embodiments, the network slice migration method provided in the embodiments of the present disclosure can be implemented by the terminal device and the server in the above-mentioned system architecture through interaction.

[0063] Figure 2 A flow chart of a network slice migration method in an embodiment of the present disclosure is shown as follows: Figure 2As shown, the network slice migration method provided in the embodiment of the present disclosure includes the following steps S202 to S208.

[0064] S202: When a target service is allocated to a target slice, a predicted network resource of the target slice is determined according to a strong prediction model, where the network resource includes at least one of a predicted computing resource and a predicted spectrum resource.

[0065] The disclosed embodiments do not limit the type of target business. For example, the target business may be video data transmission, distributed computing, blockchain data, social network data transmission, etc.

[0066] Exemplarily, the server may receive a service request corresponding to a target service, and after reading the service request, the server may allocate the target service to a target slice for processing.

[0067] Exemplarily, the target slice may be a dynamic slice of an elastic optical network. The embodiments of the present disclosure do not limit the target slice. The spectrum width and modulation format supported by the target slice may be adjusted based on corresponding business scenarios or experience.

[0068] In some exemplary embodiments, the network slice migration method provided by the embodiments of the present disclosure may also include: determining multiple basic models, wherein the basic model includes at least one of a BP model, an RNN model, and an LSTM model; training the multiple basic models separately to obtain multiple trained basic models; and obtaining the strong prediction model based on the multiple trained basic models.

[0069] In a possible implementation, historical traffic data may be obtained to obtain a training data set, which may include input features and corresponding traffic data. Exemplarily, the input feature may be a time feature, such as date, time, whether it is a holiday, etc. In addition, the input feature may also include external factor features, such as weather, special events, etc. The traffic data may correspond to the input features one by one, and the traffic data is used to characterize at least one of the instantaneous traffic, cumulative traffic, and average traffic corresponding to any input feature.

[0070] In an exemplary embodiment, multiple subsets may be randomly extracted with replacement from a training data set based on Bootstrap sampling, and each subset is used to train a basic model, thereby obtaining each trained basic model.

[0071] It should be noted that the embodiments of the present disclosure perform independent training on each basic model based on different subsets. Since the basic models are learned on different data subsets, each basic model may generate a different prediction mode.

[0072] In a possible implementation, three basic models may be included, namely, BP model, RNN model and LSTM model. It should be noted that the structure of the BP model is relatively simple, and it can capture multi-service traffic patterns for traffic prediction scenarios, and can handle nonlinear data well, and quickly form a business traffic specialized model. The RNN model can be used to solve short-term time series problems, but there is a long-term dependency, which is prone to gradient vanishing and gradient explosion problems. The LSTM model can be used to process long time series problems, but the LSTM model is relatively complex.

[0073] The disclosed embodiment integrates multiple basic models, thereby being able to capture more information about historical traffic, thereby improving the accuracy of predicting network resources.

[0074] In an exemplary embodiment, the basic model may also include a GRU (Gated Recurrent Unit) model, a Transformer model, etc. The selection of the basic model may be determined based on application scenarios and experience, and the embodiments of the present disclosure are not limited thereto.

[0075] Therefore, the embodiment of the present disclosure obtains a strong prediction model based on the combination of the above three basic models, which can process nonlinear data based on the BP model, process short-term time series data based on the RNN model, and process long-term time series data based on the LSTM model. Therefore, the strong prediction model provided by the embodiment of the present disclosure can effectively improve the accuracy of traffic prediction, thereby improving the accuracy of predicting network resources for determining the target slice, and showing robustness in a complex traffic environment.

[0076] In some exemplary embodiments, the predicted network resources of the target slice are determined according to the strong prediction model, including: predicting the network resources of the target slice according to each trained basic model; processing the network resource values ​​predicted by each trained basic model according to an integrated learning algorithm to obtain the predicted network resources of the target slice.

[0077] The embodiments of the present disclosure do not limit the ensemble learning algorithm, for example, it can be a Bagging (Bootstrap aggregating) algorithm. By processing the network resource values ​​predicted by each trained basic model through the Bagging algorithm, the model variance can be further reduced, thereby further improving the accuracy of traffic prediction, thereby improving the accuracy of the predicted network resources for determining the target slice.

[0078] In some embodiments, each trained basic model can be used to predict network resources, and the prediction results of each trained basic model can be aggregated based on the following formula (1) to obtain a strong prediction model.

[0079] (1)

[0080] Exemplarily, the formula (1) includes three basic models as an example, where P can represent the final predicted network resource value. P1, P2, P3 can represent the predicted network resource values ​​corresponding to each basic model. ω1, ω2, ω3 can represent the weight coefficients corresponding to each basic model.

[0081] In an exemplary embodiment, the weight coefficients corresponding to the basic models can be calculated based on formula (2).

[0082] (2)

[0083] For example, the formula (2) still includes three basic models as an example, where ω j It can represent the weight coefficient corresponding to the basic model j, j is an integer, and the value of j is used to characterize different basic models. j It can represent the average accuracy of prediction by basic model j.

[0084] In an exemplary embodiment, the average accuracy rate r of the predictions made by each basic model is j It can be calculated based on formula (3).

[0085] (3)

[0086] For example, y i ' can represent the actual value corresponding to the i-th flow prediction for any basic model, y i It can represent the predicted value of the i-th flow prediction by any basic model.

[0087] In an exemplary embodiment, the performance of a strong prediction model may be evaluated after it is obtained. For example, the RMSE (Root Mean Squared Error) formula may be used as an indicator to evaluate the accuracy of the model.

[0088] In some exemplary embodiments, the network resources required for the service at the next moment may be predicted based on the strong prediction model, thereby determining the predicted network resources required for the target service to occupy the target slice. The predicted network resources may include at least one of predicted computing resources and predicted spectrum resources.

[0089] It should be noted that the embodiments of the present disclosure predict the network resources of the target slice through a strong prediction model, so as to perceive the traffic of the future network slice and make decisions in advance. If there is a lot of traffic in the future, the network slice can be migrated in time to effectively avoid network congestion. Therefore, the embodiments of the present disclosure can have sufficient flexibility and reliability when dealing with rapidly changing business needs.

[0090] S204: Determine whether the predicted network resources of the target slice meet a first preset condition.

[0091] Exemplarily, the initialized underlying physical network information and network slice mapping information can be obtained in advance. The underlying physical network information is used to represent the initialized underlying computing resources, spectrum resources, and network topology. The network slice mapping information is used to describe the nodes, optical fiber links, and network resources occupied by each existing network slice.

[0092] Then, when the target service is allocated to the target slice, the predicted network resources of the target slice can be determined through the strong prediction model, so as to make a judgment on the first preset condition.

[0093] In some exemplary embodiments, the first preset condition includes at least one of a first sub-condition and a second sub-condition, wherein the first sub-condition is used to describe that the predicted computing resources occupied by the target service on each node do not exceed the remaining computing resources of the corresponding node, and the second sub-condition is used to describe that the predicted frequency slot resources occupied by the target service on each optical fiber link do not exceed the capacity of the corresponding optical fiber link.

[0094] In some possible implementations, the first sub-condition is used to make a corresponding judgment on the predicted computing resources, and the second sub-condition is used to make a corresponding judgment on the predicted spectrum resources.

[0095] Exemplarily, the first sub-condition can be expressed by the following formula (4).

[0096] (4)

[0097] In formula (4), T is used to represent the business task set, and V is used to represent the node set. It can represent the computing resources that node v is expected to provide for business t. It can represent the computing resources currently occupied by node v. v It is used to indicate the maximum computing capacity that the node v can provide. Exemplarily, the above service t may be a target service.

[0098] Exemplarily, the second sub-condition can be expressed by the following formula (5).

[0099] (5)

[0100] In formula (5), T is used to represent the service task set, and E is used to represent the fiber link set. Nodes vs and vd both belong to E. F is used to represent the capacity of the fiber link. f is used to represent the fiber frequency gap. It should be noted that the fiber frequency gap is a granularity unit obtained by finely segmenting spectrum resources in the elastic optical network.

[0101] in addition, Used to represent the slave node v s To node v d The number of fiber frequency slots occupied on the passed fiber link.

[0102] In an exemplary embodiment, if the network resources include predicted computing resources and predicted spectrum resources, when the predicted computing resources satisfy the first sub-condition and the predicted spectrum resources satisfy the second sub-condition, it is determined that the predicted network resources of the target slice satisfy the first preset condition; otherwise, it is determined that the predicted network resources of the target slice do not satisfy the first preset condition.

[0103] In some other exemplary embodiments, if the network resources include predicted computing resources, when the predicted computing resources meet the first sub-condition, it is determined that the predicted network resources of the target slice meet the first preset condition; otherwise, it is determined that the predicted network resources of the target slice do not meet the first preset condition. Alternatively, if the network resources include predicted spectrum resources, when the predicted spectrum resources meet the second sub-condition, it is determined that the predicted network resources of the target slice meet the first preset condition; otherwise, it is determined that the predicted network resources of the target slice do not meet the first preset condition.

[0104] S206: If the predicted network resources do not meet the first preset condition, the nodes and paths of the target slice are migrated.

[0105] In some exemplary embodiments, if the predicted network resources do not meet the first preset condition, the nodes and paths of the target slice are migrated, including: if the predicted computing resources do not meet the first sub-condition and / or the predicted frequency slot resources do not meet the second sub-condition, the nodes and paths of the target slice are migrated.

[0106] In an exemplary embodiment, when the predicted network resources of the target slice do not meet the first preset condition, k candidate paths can be re-planned for the computing nodes that do not meet the first sub-condition and the optical fiber links that do not meet the second sub-condition according to the KSP (K-Shortest Paths) algorithm, where k is a positive integer.

[0107] Then, the candidate paths can be sorted from large to small according to the size of the remaining resources, and the first candidate path can be selected to migrate the nodes and paths of the target slice.

[0108] S208: If the migrated node and path meet the second preset condition, the corresponding network resources are occupied.

[0109] In some exemplary embodiments, the second preset condition includes at least one of the first sub-condition, the second sub-condition, the third sub-condition, the fourth sub-condition and the fifth sub-condition. The third sub-condition is used to describe that the spectrum resources allocated on each optical fiber link along the path of the target service are the same, the fourth sub-condition is used to describe that the frequency slot resources on the optical fiber link through which the optical path passes are the same, and the fifth sub-condition is used to describe that the frequency slot resources occupied by the target service and other services are different.

[0110] It should be noted that when the second preset condition includes multiple sub-conditions, the multiple sub-conditions need to be met before the migrated nodes and paths meet the second preset condition.

[0111] Exemplarily, the third sub-condition can be expressed by the following formula (6).

[0112] (6)

[0113] in, MAX can represent a constant with a relatively large value, and the embodiment of the present disclosure does not limit the value of MAX. In addition, the meanings of other parameters in formula (6) can be found in the above formulas (1) to (5), which will not be repeated here.

[0114] It should be noted that formula (6) can be used to express spectrum continuity constraints.

[0115] Exemplarily, the fourth sub-condition can be expressed by the following formula (7).

[0116] (7)

[0117] Among them, (v s ,v d ) is used to represent the slave node v s To node v d The optical fiber link between d ,v s ) is used to represent the slave node v d To node v s The optical fiber link between t Indicates the starting node of service t, d t Indicates the destination node of service t.

[0118] therefore, Used to represent the slave node v s To node vd The number of fiber frequency slots occupied on the passed fiber link. Used to represent the slave node v d To node v s The number of fiber frequency slots occupied on the passed fiber link.

[0119] In addition, the meanings of other parameters in formula (7) can be found in the above formulas (1) to (5), which will not be repeated here.

[0120] It should be noted that formula (7) can be used to express spectrum consistency constraints.

[0121] Exemplarily, the fifth sub-condition can be expressed by the following formula (8).

[0122] (8)

[0123] Among them, f t It can represent the starting index of the spectrum FS occupied by service t, f t is an integer variable. t ' can represent the starting index of the spectrum FS occupied by service t', f t ' is an integer variable. t，t’ Can be a binary variable, if f t <f t ', that is, the starting index of the spectrum FS occupied by service t is less than the starting index of the spectrum FS occupied by service t', then δ t，t’ The value is 1, otherwise δ t，t’ The value is 0.

[0124] In addition, the meanings of other parameters in formula (8) can be found in the above formulas (1) to (5), which will not be repeated here.

[0125] In an exemplary embodiment, if the predicted network resources meet the first preset condition, it is not necessary to migrate the nodes and paths of the target slice, and it is possible to directly determine whether the target slice of the node and path that have not been migrated meets the second preset condition. If not, it is determined that the target service is blocked.

[0126] In addition, the embodiment of the present disclosure can also determine whether there are other services currently after occupying the corresponding network resources. If there are other services, each step from S202 to S208 can be cyclically executed for the other services.

[0127] The method provided by the embodiment of the present disclosure can determine the predicted network resources of the target slice according to the strong prediction model, thereby realizing the migration of the target slice in advance based on the prediction of future traffic, avoiding network migration delays, effectively improving the flexibility and reliability of network slice migration, and improving service quality.

[0128] In a possible exemplary embodiment, if the line load in zone C of a metropolitan area network is high, important services of the enterprise dedicated line can be detected based on the method provided in the embodiment of the present disclosure and actively sliced ​​and migrated to unpopular areas.

[0129] First, environmental detection can be performed to obtain the underlying physical network information and network slice mapping information. Then, business perception can be performed to import the basic models in the strong prediction model for training based on past historical data. Then, business model identification can be performed, for example, features can be identified and captured based on the high weight of the BP model plus the RNN model and the low weight of the LSTM model.

[0130] Exemplarily, the predicted network resources can then be determined based on the strong prediction model and the path selection can be performed. For example, a candidate path for area C can be generated based on the KSP algorithm, and line L1 with more remaining resources can be selected for node and path migration of the slice. Finally, the migration can be performed. After selecting line L1 for migration, it is determined that the migrated nodes and paths meet the second preset condition. If so, the network resources and network slice mapping information are updated accordingly.

[0131] Figure 3 A schematic diagram of a process of integrating a flow prediction algorithm in an embodiment of the present disclosure is shown. Figure 3 As shown, the integrated traffic prediction algorithm provided in the embodiment of the present disclosure can first obtain the initial historical traffic information, then split the sub-training set, and then perform basic model training, and finally obtain a strong training model.

[0132] Figure 4 A flow chart of a network slice migration method in an embodiment of the present disclosure is shown as follows: Figure 4 As shown, the network slice migration method provided in the embodiment of the present disclosure may include the following steps S402 to S428.

[0133] S402, start.

[0134] S404, obtain the initialized underlying physical network information and network slice mapping information.

[0135] S406, the target service is allocated to the target slice.

[0136] S408: Determine predicted network resources of the target slice using a strong prediction model.

[0137] S410, determining whether the predicted network resources of the target slice meet a first preset condition.

[0138] If the first preset condition is met, then S412 is continued to be executed; if the first preset condition is not met, then S418 is continued to be executed.

[0139] S412: re-plan k candidate paths according to the KSP algorithm.

[0140] S414, sorting the candidate paths from large to small according to the size of the remaining resources.

[0141] S416, select the first candidate path to migrate nodes and paths for the target slice.

[0142] S418: Determine whether the migrated node and path meet a second preset condition.

[0143] If the second preset condition is met, then S420 is continued to be executed; if the second preset condition is not met, then S422 is continued to be executed.

[0144] S420, occupy corresponding network resources.

[0145] S422, record the blocked service request +1.

[0146] S424, update network resources and network slice mapping information.

[0147] S426: Determine whether the service request set is empty.

[0148] If it is empty, continue to execute S428; if it is not empty, continue to execute S406.

[0149] S428, end.

[0150] It should be noted that the present disclosure implements a dynamic network slice migration strategy for elastic optical networks based on integrated traffic prediction. By selecting a machine learning model as the basic model for targeted services and using bagging technology for enhanced integration, the present disclosure implements the ability to focus on regular services and can quickly identify service models, while providing temporal prediction capabilities for the perception of sudden hot events in the long and short term.

[0151] Secondly, the present disclosure can perform targeted optical network resource perception and network slice migration for strong prediction models. The present disclosure can realize real-time text generation on terminal devices, while making full use of cloud computing resources to provide efficient solutions for resource-constrained scenarios.

[0152] It should be noted that the acquisition, storage, use, and processing of data in the technical solution disclosed in this disclosure are in compliance with the relevant provisions of national laws and regulations, and various types of data such as personal identity data, operation data, behavioral data, etc. related to individuals, customers, and groups obtained in the embodiments of this disclosure have all been authorized.

[0153] Based on the same inventive concept, a network slice migration device is also provided in the embodiments of the present disclosure, as described in the following embodiments. Since the principle of solving the problem in the embodiment of the device is similar to that in the above method embodiment, the implementation of the embodiment of the device can refer to the implementation of the above method embodiment, and the repeated parts will not be repeated.

[0154] Figure 5 A schematic diagram of a network slice migration device in an embodiment of the present disclosure is shown. Figure 5 As shown, the device comprises:

[0155] A predicted network resource determination module 501 is used to determine predicted network resources of the target slice according to the strong prediction model when the target service is allocated to the target slice, where the network resources include at least one of predicted computing resources and predicted spectrum resources;

[0156] A first preset condition judgment module 502, used to determine whether the predicted network resources of the target slice meet the first preset condition;

[0157] A migration module 503, configured to migrate nodes and paths of a target slice if the predicted network resources do not meet a first preset condition;

[0158] The network resource occupying module 504 is configured to occupy corresponding network resources if the migrated nodes and paths meet a second preset condition.

[0159] In some embodiments, the network slice migration device provided by the embodiment of the present disclosure further includes:

[0160] The strong prediction model determination module is used to determine multiple basic models, wherein the basic model includes at least one of a BP model, an RNN model, and an LSTM model; train the multiple basic models separately to obtain multiple trained basic models; and obtain a strong prediction model based on the multiple trained basic models.

[0161] In some embodiments, the predicted network resource determination module 501 is used to predict the network resources of the target slice according to each trained basic model; the network resource values ​​predicted by each trained basic model are processed according to the integrated learning algorithm to obtain the predicted network resources of the target slice.

[0162] In some embodiments, the first preset condition includes at least one of a first sub-condition and a second sub-condition; wherein the first sub-condition is used to describe that the predicted computing resources occupied by the target service on each node do not exceed the remaining computing resources of the corresponding node, and the second sub-condition is used to describe that the predicted frequency slot resources occupied by the target service on each optical fiber link do not exceed the capacity of the corresponding optical fiber link.

[0163] In some embodiments, the migration module 503 is used to migrate the nodes and paths of the target slice if the predicted computing resources do not meet the first sub-condition and / or the predicted frequency slot resources do not meet the second sub-condition.

[0164] In some embodiments, the second preset condition includes at least one of the first sub-condition, the second sub-condition, the third sub-condition, the fourth sub-condition and the fifth sub-condition; wherein the third sub-condition is used to describe that the spectrum resources allocated to the target service along each optical fiber link in the path are the same, the fourth sub-condition is used to describe that the frequency slot resources on the optical fiber link through which the optical path passes are the same, and the fifth sub-condition is used to describe that the frequency slot resources occupied by the target service and other services are different.

[0165] The device provided by the embodiment of the present disclosure can determine the predicted network resources of the target slice according to the strong prediction model, thereby realizing the migration of the target slice in advance based on the prediction of future traffic, avoiding network migration delays, effectively improving the flexibility and reliability of network slice migration, and improving service quality.

[0166] It should be noted that the above-mentioned predicted network resource determination module 501, the first preset condition judgment module 502, the migration module 503, and the network resource occupation module 504 correspond to S202 to S208 in the method embodiment, and the examples and application scenarios implemented by the above-mentioned modules and corresponding steps are the same, but are not limited to the contents disclosed in the above-mentioned method embodiment. It should be noted that the above-mentioned modules as part of the device can be executed in a computer system such as a set of computer executable instructions.

[0167] 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".

[0168] The present disclosure embodiment provides an electronic device, exemplarily comprising: a processor and a memory. The memory can be used to store executable instructions of the processor. The processor is configured to perform the network slice migration method provided by the present disclosure embodiment by executing the above executable instructions.

[0169] Refer to the following Figure 6 The electronic device 600 according to this embodiment of the present disclosure is described. Figure 6 The electronic device 600 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.

[0170] like Figure 6 As shown, the electronic device 600 is in the form of a general computing device. The components of the electronic device 600 may include but are not limited to: at least one processing unit 610, at least one storage unit 620, and a bus 630 connecting different system components (including the storage unit 620 and the processing unit 610).

[0171] The storage unit stores a program code, which can be executed by the processing unit 610, so that the processing unit 610 performs the steps of various exemplary embodiments of the present disclosure described in the above “Exemplary Method” section of this specification. For example, the processing unit 610 can perform the following steps of the above method embodiment:

[0172] When the target service is assigned to the target slice, the predicted network resources of the target slice are determined according to the strong prediction model, and the network resources include at least one of predicted computing resources and predicted spectrum resources; it is determined whether the predicted network resources of the target slice meet the first preset condition; if the predicted network resources do not meet the first preset condition, the nodes and paths of the target slice are migrated; if the migrated nodes and paths meet the second preset condition, the corresponding network resources are occupied.

[0173] The storage unit 620 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 6201 and / or a cache memory unit 6202 , and may further include a read-only memory unit (ROM) 6203 .

[0174] The storage unit 620 may also include a program / utility 6204 having a set (at least one) of program modules 6205, such program modules 6205 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.

[0175] Bus 630 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.

[0176] The electronic device 600 may also communicate with one or more external devices 640 (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 600, and / or communicate with any device that enables the electronic device 600 to communicate with one or more other computing devices (e.g., routers, modems, etc.). This communication may be performed through an input / output (I / O) interface 650. In addition, the electronic device 600 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) through a network adapter 660. As shown, the network adapter 660 communicates with other modules of the electronic device 600 through a bus 630. 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 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0177] 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, and includes a number of 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.

[0178] In particular, according to an embodiment of the present disclosure, the process described in the above reference flowchart can be implemented as a computer program product, which includes: a computer program, which implements the above-mentioned network slice migration method when executed by a processor.

[0179] In an exemplary embodiment of the present disclosure, a computer-readable storage medium is also provided, on which a computer program is stored, and when the computer program is executed by a processor, the network slice migration method provided in the embodiment of the present disclosure can be implemented. The computer-readable storage medium can be a readable signal medium or a readable storage medium.

[0180] Figure 7 A schematic diagram of a computer-readable storage medium in an embodiment of the present disclosure is shown. Figure 7As shown, a program product capable of implementing the above method of the present disclosure is stored on the computer-readable storage medium 700. In some possible implementations, various aspects of the present disclosure may also be implemented in the form of a program product, which includes a program code. When the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps according to various exemplary implementations of the present disclosure described in the above “Exemplary Method” section of this specification.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] In specific implementation, the program code for performing the operation 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" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as an independent 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).

[0185] 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.

[0186] 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.

[0187] Through the description of the above implementation modes, it is easy for those skilled in the art to understand that the example implementation modes described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation mode 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, and includes 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 mode of the present disclosure.

[0188] 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 technical means in the art that are not disclosed in the present disclosure. The description and examples are to be regarded as exemplary only, and the true scope of the present disclosure is indicated by the appended claims.

Claims

1. A network slice migration method, characterized in that: include: When a target service is allocated to a target slice, the predicted network resources required for the target service to occupy the target slice are determined according to the strong prediction model, wherein the network resources include at least one of predicted computing resources and predicted spectrum resources, and the basic models included in the strong prediction model include a back propagation neural network BP model, a recurrent neural network RNN ​​model, and a long short-term memory network LSTM model, each of which is independently trained based on different subsets, wherein the BP model is used to capture multi-service traffic patterns and process nonlinear data to form a service traffic specialized model; Determining whether the predicted network resources of the target slice meet a first preset condition, wherein the first preset condition includes a first sub-condition for making a corresponding judgment on the predicted computing resources occupied by the target service on each node, and a second sub-condition for making a corresponding judgment on the predicted spectrum resources occupied by the target service on each optical fiber link; If the predicted network resources do not meet the first preset condition, the nodes and paths of the target slice are migrated, including replanning candidate paths for computing nodes that do not meet the first sub-condition and optical fiber links that do not meet the second sub-condition; If the migrated nodes and paths meet the second preset condition, the corresponding network resources are occupied, and the second preset condition includes at least one of the first sub-condition, the second sub-condition, the third sub-condition, the fourth sub-condition and the fifth sub-condition; wherein the third sub-condition is used to describe that the spectrum resources allocated to the target service along each optical fiber link in the path are the same, the fourth sub-condition is used to describe that the frequency slot resources on the optical fiber link through which the optical path passes are the same, and the fifth sub-condition is used to describe that the frequency slot resources occupied by the target service and other services are different.

2. The network slice migration method according to claim 1, characterized in that: The method further comprises: Identify multiple basic models; Training the multiple basic models respectively to obtain multiple trained basic models; The strong prediction model is obtained according to the multiple trained basic models.

3. The network slice migration method according to claim 2, characterized in that: The determining the predicted network resource of the target slice according to the strong prediction model includes: Predicting the network resources of the target slices according to the trained basic models; The network resource values ​​predicted by each trained basic model are processed according to an integrated learning algorithm to obtain the predicted network resources of the target slice.

4. The network slice migration method according to any one of claims 1 to 3, characterized in that: in, The first sub-condition is used to describe that the predicted computing resources occupied by the target service on each node do not exceed the remaining computing resources of the corresponding node, and the second sub-condition is used to describe that the predicted frequency slot resources occupied by the target service on each optical fiber link do not exceed the capacity of the corresponding optical fiber link.

5. The network slice migration method according to claim 4, characterized in that: If the predicted network resources do not meet the first preset condition, migrating the nodes and paths of the target slice includes: If the predicted computing resources do not satisfy the first sub-condition and / or the predicted frequency slot resources do not satisfy the second sub-condition, the nodes and paths of the target slice are migrated.

6. A network slice migration device, characterized in that: include: A predicted network resource determination module, used for determining the predicted network resources required for the target slice to be occupied by the target service according to the strong prediction model when the target service is allocated to the target slice, wherein the network resources include at least one of predicted computing resources and predicted spectrum resources, and the basic models included in the strong prediction model include a back propagation neural network BP model, a recurrent neural network RNN ​​model, and a long short-term memory network LSTM model, each of which is independently trained based on different subsets, wherein the BP model is used to capture multi-service traffic patterns and process nonlinear data to form a service traffic specialized model; A first preset condition judgment module, used to determine whether the predicted network resources of the target slice meet the first preset condition, wherein the first preset condition includes a first sub-condition for making a corresponding judgment on the predicted computing resources occupied by the target service on each node, and a second sub-condition for making a corresponding judgment on the predicted spectrum resources occupied by the target service on each optical fiber link; A migration module, configured to migrate the nodes and paths of the target slice if the predicted network resources do not meet the first preset condition, including replanning candidate paths for computing nodes that do not meet the first sub-condition and optical fiber links that do not meet the second sub-condition; A network resource occupation module is used to occupy corresponding network resources if the migrated nodes and paths meet a second preset condition, wherein the second preset condition includes at least one of the first sub-condition, the second sub-condition, the third sub-condition, the fourth sub-condition and the fifth sub-condition; wherein the third sub-condition is used to describe that the spectrum resources allocated to the target service along each optical fiber link in the path are the same, the fourth sub-condition is used to describe that the frequency slot resources on the optical fiber link through which the optical path passes are the same, and the fifth sub-condition is used to describe that the frequency slot resources occupied by the target service and other services are different.

7. 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 network slice migration method described in any one of claims 1 to 5 by executing the executable instructions.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the network slice migration method described in any one of claims 1 to 5 is implemented.

9. A computer program product, characterized in that The computer program product includes computer instructions, which are stored in a computer-readable storage medium. The processor of the electronic device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the electronic device performs the network slice migration method as described in any one of claims 1 to 5.

Images