CN115843050A - Network slice configuration method and system, computer storage medium - Google Patents
Network slice configuration method and system, computer storage medium Download PDFInfo
- Publication number
- CN115843050A CN115843050A CN202211445997.2A CN202211445997A CN115843050A CN 115843050 A CN115843050 A CN 115843050A CN 202211445997 A CN202211445997 A CN 202211445997A CN 115843050 A CN115843050 A CN 115843050A
- Authority
- CN
- China
- Prior art keywords
- network slice
- time slot
- current time
- slice configuration
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Mobile Radio Communication Systems (AREA)
Abstract
The disclosure relates to a network slice configuration method and system, and a computer-readable storage medium, and relates to the technical field of wireless communication. The network slice configuration system comprises: a RAN layer device configured to: generating service level information of the current time slot according to the user level information of the user layer equipment in the current time slot; predicting service demand information of a user in the current time slot by utilizing a first machine learning model according to the service level information of the current time slot; sending service level information and service requirement information of the current time slot; an SDN controller configured to: determining a network slice configuration strategy of the current time slot by utilizing a second machine learning model according to the service level information and the service requirement information of the current time slot from the RAN layer equipment; carrying out slice configuration verification on a network slice configuration strategy of the current time slot by using a digital twin body based on user layer equipment and RAN layer equipment; and in case of passing the verification, sending the network slice configuration strategy of the current time slot to the RAN layer equipment.
Description
Technical Field
The present disclosure relates to the field of wireless communications technologies, and in particular, to a network slice configuration method and system, and a computer-readable storage medium.
Background
The 6G network needs to satisfy diversified services, and network slicing is a potential method to support this vision implementation. A network slice is a virtual network that builds multiple logical isolations for different services on top of a common physical network. The QoS (Quality of Service) requirements of different services can be guaranteed by an economical and efficient slice management strategy in the preparation, planning and operation phases of the network slice lifecycle. While 6G networks need to support a variety of new services while meeting their different and stringent QoS requirements, this further increases the complexity of slice management.
Disclosure of Invention
The utility model provides a solution, can realize intelligent dynamic slice management, promote the success rate of resource utilization ratio and network slice configuration, reduce the harmful effects to the physical network.
According to a first aspect of the present disclosure, there is provided a network slice configuration system, comprising: a Radio Access Network (RAN) layer device configured to: generating service level information of the current time slot according to the user level information of the user layer equipment in the current time slot; predicting service demand information of a user in the current time slot by utilizing a first machine learning model according to the service level information of the current time slot; sending the service level information and the service requirement information of the current time slot; a Software Defined Network (SDN) controller configured to: determining a network slice configuration strategy of the current time slot by utilizing a second machine learning model according to the service level information and the service requirement information of the current time slot from the RAN layer equipment; carrying out slice configuration verification on the network slice configuration strategy of the current time slot by utilizing a digital twin body based on the user layer equipment and the RAN layer equipment; and in the case of passing the verification, sending the network slice configuration strategy of the current time slot to the RAN layer equipment.
In some embodiments, the SDN controller is further configured to: sending a network slice configuration policy for the current time slot to the digital twin; deploying and operating a network slice configuration strategy of the current time slot at the digital twin; acquiring the performance of the estimated network slice after the network slice configuration strategy of the current time slot is operated; and carrying out slice configuration verification on the network slice configuration strategy of the current time slot according to the estimated gain of the network slice performance, wherein the verification is passed under the condition that the estimated gain of the network slice performance exceeds a gain threshold value.
In some embodiments, the RAN-layer device is further configured to: receiving a network slice configuration policy for a current time slot from the SDN controller; running a network slice configuration strategy of the current time slot; measuring feedback information of a user on the network slice configuration strategy of the current time slot, wherein the feedback information reflects the actual network slice performance under the network slice configuration strategy of the current time slot; sending the feedback information to the SDN controller for the SDN controller to determine a network slice configuration policy for a time slot next to the current time slot.
In some embodiments, the network slice configuration system further comprises: a digital twin layer device deploying the digital twin, configured to receive real-time network information from the user layer device and the RAN layer device, and update the digital twin according to the real-time network information.
In some embodiments, an uplink between the RAN layer device and the digital twin layer device is comprised of a high bandwidth, high rate data link and a downlink between the RAN layer device and the digital twin layer device is a control channel.
In some embodiments, the user level information includes at least one of a service demand pattern of the user, a movement pattern of the user, location information of the user, and a random channel condition of the user.
In some embodiments, the RAN-layer device is further configured to perform at least one of: analyzing the service requirement mode of the user to obtain the requirements of the user on time delay, bandwidth and service content information as service level information; analyzing the movement mode of the user to obtain the movement rule of the user as service level information; obtaining the signal-to-noise ratio of the current channel as service level information according to the random channel condition of the user; and determining the density information of the user as service level information according to the position information of the user.
In some embodiments, the first machine learning model comprises a long short term memory network (LSTM) model; and/or the second machine learning model comprises a deep reinforcement learning model.
In some embodiments, the network slice configuration system further comprises: the user layer device is configured to send user level information of the current time slot to the RAN layer device.
In some embodiments, the RAN layer device comprises an access point device of the RAN layer.
According to a second aspect of the present disclosure, there is provided a network slice configuration method, including: the RAN layer equipment of the radio access network generates service level information according to the user level information of the user layer equipment in the current time slot; the RAN layer equipment predicts the service demand information of the user in the current time slot by using a first machine learning model according to the service level information of the current time slot; RAN layer equipment sends service level information and service requirement information of the current time slot; a Software Defined Network (SDN) controller determines a network slice configuration strategy of the current time slot by utilizing a second machine learning model according to the service level information and the service requirement information of the current time slot from the RAN layer equipment; the SDN controller carries out slice configuration verification on the network slice configuration strategy of the current time slot by using a digital twin body based on the user layer equipment and the RAN layer equipment; and the SDN controller sends the network slice configuration strategy of the current time slot to the RAN layer equipment under the condition of passing verification.
According to a third aspect of the present disclosure, there is provided a network slice configuration system, including: a memory; and a processor coupled to the memory, the processor configured to perform the network slice configuration method of any of the above embodiments based on instructions stored in the memory.
According to a fourth aspect of the present disclosure, there is provided a computer-storable medium having stored thereon computer program instructions which, when executed by a processor, implement the network slice configuration method of any of the above embodiments.
In the embodiment, intelligent dynamic slice management can be realized, the resource utilization rate and the success rate of network slice configuration are improved, and the adverse effect on a physical network is reduced. .
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description, serve to explain the principles of the disclosure.
The present disclosure may be more clearly understood from the following detailed description, taken with reference to the accompanying drawings, in which:
fig. 1 is a block diagram illustrating a network slice configuration system according to some embodiments of the present disclosure;
FIG. 2 is a block diagram illustrating a network slice configuration system according to further embodiments of the present disclosure;
fig. 3 is an architectural diagram illustrating a network slice configuration system according to some embodiments of the present disclosure;
fig. 4 is a flow diagram illustrating a network slice configuration method according to some embodiments of the present disclosure;
FIG. 5 is a flow diagram illustrating a network slice configuration method according to further embodiments of the present disclosure;
FIG. 6 is a block diagram illustrating a network slice configuration system in accordance with still further embodiments of the present disclosure;
figure 7 is a block diagram illustrating a computer system for implementing some embodiments of the present disclosure.
Detailed Description
Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that: the relative arrangement of the components and steps, the numerical expressions, and numerical values set forth in these embodiments do not limit the scope of the present disclosure unless specifically stated otherwise.
Meanwhile, it should be understood that the sizes of the respective portions shown in the drawings are not drawn in an actual proportional relationship for the convenience of description.
The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the disclosure, its application, or uses.
Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail but are intended to be part of the specification where appropriate.
In all examples shown and discussed herein, any particular value should be construed as merely illustrative, and not limiting. Thus, other examples of the exemplary embodiments may have different values.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, further discussion thereof is not required in subsequent figures.
Fig. 1 is a block diagram illustrating a network slice configuration system according to some embodiments of the present disclosure.
As shown in fig. 1, the Network slice configuration system 1 includes a RAN (Radio Access Network) layer device 11 and an SDN (Software Defined Network) controller 13.
The RAN layer device 11 is configured to generate service level information of the current time slot according to the user level information of the user layer device in the current time slot; predicting service demand information of a user in the current time slot by utilizing a first machine learning model according to the service level information of the current time slot; and sends the service level information and the service requirement information of the current time slot to the SDN controller 13.
In some embodiments, the user level information includes at least one of a service demand pattern of the user, a movement pattern of the user, location information of the user, and a random channel condition of the user.
In some embodiments, the RAN-layer device is further configured to perform at least one of: analyzing a service requirement mode of a user to obtain the requirements of the user on time delay, bandwidth and service content information as service level information; analyzing the movement mode of the user to obtain the movement rule of the user as service level information; obtaining the signal-to-noise ratio of the current channel as service level information according to the random channel condition of the user; and determining density information of the user as service level information according to the position information of the user.
In some embodiments, the first machine learning model comprises a LSTM (Long short-term memory network) model.
In some embodiments, the RAN layer device comprises an Access Point (AP) device of the RAN layer.
The SDN controller 13 is configured to determine, using the second machine learning model, a network slice configuration policy for a current time slot according to the service level information and the service requirement information of the current time slot from the RAN layer device; carrying out slice configuration verification on a network slice configuration strategy of the current time slot by using a digital twin body based on user layer equipment and RAN layer equipment; and sending the network slice configuration strategy of the current time slot to the RAN layer equipment under the condition that the verification is passed.
In some embodiments, the second machine Learning model comprises a Deep Reinforcement Learning (DRL) model.
In some embodiments, the SDN controller 13 is further configured to send a network slice configuration policy for the current time slot to the digital twin; deploying and operating a network slice configuration strategy of the current time slot in the digital twin; acquiring the performance of the estimated network slice after the network slice configuration strategy of the current time slot is operated; and carrying out slice configuration verification on the network slice configuration strategy of the current time slot according to the gain of the estimated network slice performance. And in the case that the gain of the predicted network slice performance exceeds the gain threshold, the verification is passed.
In some embodiments, the RAN layer device 11 is further configured to receive a network slice configuration policy for a current time slot from the SDN controller; operating a network slice configuration strategy of the current time slot; measuring feedback information of a network slice configuration strategy of a user on a current time slot, wherein the feedback information reflects the actual network slice performance under the network slice configuration strategy of the current time slot; sending feedback information to the SDN controller 13. The feedback information is used for the SDN controller to determine a network slice configuration policy for a time slot next to the current time slot.
Fig. 2 is a block diagram illustrating a network slice configuration system according to further embodiments of the present disclosure. Fig. 2 differs from fig. 1 in that fig. 2 shows other configurations of network slice configuration systems of further embodiments. Only the differences between fig. 2 and fig. 1 will be described below, and the same parts will not be described again.
In some embodiments, as shown in fig. 2, the network slice configuration system 1 further comprises a digital twinning layer device 12 that deploys a digital twinner. The digital twin layer device 12 is configured to receive real-time network information from the user layer device and the RAN layer device and update the digital twin according to the real-time network information. For example, a digital twin is a digital twin network of a physical network consisting of user layer devices and RAN layer devices.
In some embodiments, the uplink between the RAN layer device and the digital twin layer device is comprised of a high-bandwidth, high-rate data link, and the downlink between the RAN layer device and the digital twin layer device is a control channel.
In some embodiments, as shown in fig. 2, the network slice configuration system 1 further comprises a user layer device 10. The user layer device 10 is configured to send user level information for the current time slot to the RAN layer device 11.
The deep reinforcement learning agent in the SDN controller learns an optimal network slicing strategy based on observation of a real network environment, forwards the slicing strategy to the DT, and performs pre-verification in the DT before the strategy is issued to the real network, so that the situation that the strategy performance is unknown and is directly deployed in the network to cause harm is avoided, the cost of network slicing configuration is reduced, and the success rate of network slicing configuration is improved.
The method introduces a digital twin into a network architecture, achieves the effect of predicting the requirements of users through the design and construction of related network intelligent modules, and monitors the performance of a slicing strategy under the condition of not influencing a physical network. In addition, the present disclosure proposes a wireless communication network architecture (SDN controller, RAN layer device, digital twin layer device, etc.) supporting digital twins that build wireless networks to simulate their complex environment and predict the dynamic characteristics of the network.
Fig. 3 is an architectural schematic diagram illustrating a network slice configuration system according to some embodiments of the present disclosure.
As shown in fig. 3, the architecture of the network slice configuration system, also referred to as a 6G wireless network architecture with intelligence generation or a digital twin architecture for network slice configuration, has a four-layer structure including, from bottom to top, a user layer, a RAN layer, a digital twin layer, and an SDN controller layer. The user layer and the RAN layer form a physical network. The RAN layer uploads real-time information of a physical network to the digital twin layer, and the digital twin layer issues network slicing decisions or strategies to the RAN layer. The RAN layer also uploads the predicted user requirements and the performance of the network slice to the SDN controller layer separately at different time slots. The information passed by the SDN controller layer to the digital twin layer includes the optimized slicing strategy.
The uplink between the RAN layer and the digital twin layer is composed of a high-bandwidth and high-speed data link, network real-time information can be rapidly uploaded to the digital twin layer, a downlink between the RAN layer and the digital twin layer is a control channel, and the requirement that a slicing strategy is timely and accurately issued is met.
An LSTM-based intelligent algorithm model located on the RAN side is trained by data collected from a wireless network environment to learn user demand characteristics. The trained model can predict the user requirements in the future time slot, and updates the model in the process of continuously interacting with the wireless network environment (including the uplink and downlink rates, the successful access number of uplink and downlink connections, the congestion condition of the current wireless network link and other wireless network states), so that the performance of the model is improved. And a DRL intelligent agent (DRL model) positioned in an SDN controller layer carries out network slicing decision according to the prediction data of the user requirement provided by the RAN side, receives feedback information of the network slicing performance in each time slot and completes self optimization.
To enable intelligent and efficient management of network slices, the present disclosure proposes a digital twin-based network slice architecture in the 6G network shown in fig. 3. At the bottom layer is a User Equipment (UE) in the 6G network, and according to the vision of the 6G network to provide interconnection of everything, the UE has various access modes and personalized QoS requirements. The upper layer of the UE is an access network RAN layer, and the RAN layer and the UE layer form a real physical network. The digital twin layer (DT layer) is the mapping of the real physical network, creates the digital twin of the physical network entity and the network topology, simulates the complex environment of the physical network and dynamically updates along with the change of the physical network. The top layer of the framework provided by the disclosure is an SDN controller, an agent based on a DRL intelligent algorithm is deployed in the SDN controller, information of a processed service level from a RAN layer and information of user demand prediction by an LSTM algorithm deployed in the RAN layer are received by the SDN controller and stored in a database, and are used for the DRL agent to extract data from the data for training to generate an optimal network slicing strategy.
Fig. 4 is a flow diagram illustrating a network slice configuration method according to some embodiments of the present disclosure.
As shown in fig. 4, the network slice configuration method includes steps S410 to S460.
In step S410, the RAN layer device generates service level information according to the user level information of the user layer device in the current time slot.
In step S420, the RAN layer device predicts the service requirement information of the user in the current time slot by using the first machine learning model according to the service level information of the current time slot.
In step S430, the RAN layer device transmits service level information and service requirement information of the current time slot.
In step S440, the SDN controller determines a network slice configuration policy of the current time slot according to the service level information and the service requirement information of the current time slot from the RAN layer device, by using the second machine learning model.
In step S450, the SDN controller performs slice configuration verification on the network slice configuration policy of the current timeslot by using a digital twin based on the user layer device and the RAN layer device.
In step S460, the SDN controller sends the network slice configuration policy of the current time slot to the RAN layer device if the authentication passes.
The content of the foregoing network slice configuration system can be referred to in the related embodiments of each step in the network slice configuration method, and details are not described here.
Fig. 5 is a flow chart illustrating a network slice configuration method according to further embodiments of the present disclosure.
As shown in fig. 5, the network slice configuration method includes steps S501 to S514.
In step S501, an access point device (AP) in the RAN layer collects and transmits random information of a User level from a UE (User Equipment) in the User layer to the RAN layer device. For example, the user-level random information includes, but is not limited to, the end user's service demand pattern, mobility pattern, location information, and random channel conditions.
In step S502, an intelligent algorithm (i.e., a machine learning model) deployed on the RAN side converts the user level information into required service level information. For example, by analyzing the service requirement pattern of the user, the requirement of the user on the delay, the bandwidth and the service content information can be obtained. By analyzing the movement pattern, the movement rule of the user can be obtained, and the subsequent prediction of the movement of the user is facilitated. The signal-to-noise ratio of the current channel can be obtained through the random channel condition, the switching of the user access channel is conveniently realized by combining the moving rule of the user, and the service quality of the user is ensured. By processing the user location information, user density information can be obtained. After data of the service level information is abstracted, fused and analyzed, the service requirement of the user is predicted by using an intelligent algorithm.
In step S503, the DT layer initializes a digital twin that generates a physical network composed of a user layer and a RAN layer.
In step S504, the RAN layer transmits the processed service level information including the prediction of the user service demand to the SDN controller.
In step S505, the SDN controller runs a decision algorithm based on the DRL model according to the predicted service demand to make an optimal decision for the network slice according to the collected service level information (including the predicted user service demand information).
In step S506, the SDN controller decides to issue to the DT layer for pre-verification.
In step S507, a planning decision determined by a DRL agent in the SDN controller is performed in the DT for pre-verification, so as to avoid a hazard caused by poor AI model effect but direct deployment into the network.
In some embodiments, for cases where AI models are poorly interpretable and training effects are unknown, network slicing decisions are run in the DT prior to deployment into the real network. If the gain of the strategy on the network slice performance exceeds a certain threshold value, the strategy is issued to the RAN side, and if the strategy cannot generate gain or bring adverse effect on the network slice performance, the strategy is not issued.
In step S508, the validated planning decision is sent back to all Access Points (APs) in the RAN layer.
In step S509, the Access Point (AP) in the RAN layer performs the received planning decision. E.g., reserving network resources or allocating bandwidth for the respective slice.
In step S510, the users in service report their real-time information to the DT layer. For example, the real-time information includes channel conditions and corresponding service relationships between users and Access Points (APs), and the like.
In step S511, the DT layer is updated according to the real-time information in the wireless network environment.
In step S512, the RAN side evaluates and detects the performance of the network slice by measuring feedback information of the user for all slice decisions in the last time slot. For example, the feedback information includes a satisfaction rate.
In step S513, an Access Point (AP) in the RAN layer sends the slice capability to the SDN controller.
In step S514, the SDN controller makes a network slice planning decision for the next time slot and adjusts a planning strategy according to the feedback information.
The method provides an intelligent endogenous 6G wireless network architecture, aiming at the conditions that the interpretability of an AI model is poor and the training effect is unknown, the efficient management of a digital twin layer enabled network slice is introduced, the key step of pre-verification is added in the full life cycle management of the network slice, and the harm caused by poor effect of the AI model but direct deployment of the AI model into the network is avoided.
The disclosure also provides a detailed flow of slice information exchange in a digital twin architecture oriented to network slices in a 6G network. An intelligent algorithm is introduced at the RAN side and the SDN controller side, network slices are intelligently managed, and slice management is assisted in a dynamic mode through interaction with a physical network.
Fig. 6 is a block diagram illustrating a network slice configuration system according to still further embodiments of the present disclosure.
As shown in fig. 6, the network slice configuration system 6 includes a memory 61; and a processor 62 coupled to the memory 61. The memory 61 is used for storing instructions for executing the corresponding embodiments of the network slice configuration method. The processor 62 is configured to perform the network slice configuration method in any of the embodiments of the present disclosure based on instructions stored in the memory 61.
FIG. 7 is a block diagram illustrating a computer system for implementing some embodiments of the present disclosure.
As shown in FIG. 7, the computer system 70 may be embodied in the form of a general purpose computing device. Computer system 70 includes a memory 710, a processor 720, and a bus 700 that couples various system components.
The memory 710 may include, for example, system memory, non-volatile storage media, and the like. The system memory stores, for example, an operating system, an application program, a Boot Loader (Boot Loader), and other programs. The system memory may include volatile storage media such as Random Access Memory (RAM) and/or cache memory. The non-volatile storage medium, for instance, stores instructions to perform corresponding embodiments of at least one of the network slice configuration methods. Non-volatile storage media include, but are not limited to, magnetic disk storage, optical storage, flash memory, and the like.
The computer system 70 may also include an input-output interface 730, a network interface 740, a storage interface 750, and the like. These interfaces 730, 740, 750, as well as the memory 710 and the processor 720, may be connected by a bus 700. The input/output interface 730 may provide a connection interface for input/output devices such as a display, a mouse, and a keyboard. The network interface 740 provides a connection interface for various networking devices. The storage interface 750 provides a connection interface for external storage devices such as a floppy disk, a usb disk, and an SD card.
Various aspects of the present disclosure are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus and computer program products according to embodiments of the disclosure. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.
These computer-readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable apparatus to produce a machine, such that the execution of the instructions by the processor results in an apparatus that implements the functions specified in the flowchart and/or block diagram block or blocks.
These computer-readable program instructions may also be stored in a computer-readable memory that can direct a computer to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart and/or block diagram block or blocks.
The present disclosure may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects.
By the network slice configuration method and system and the computer storage medium in the embodiment, intelligent dynamic slice management can be realized, the resource utilization rate and the success rate of network slice configuration are improved, and adverse effects on a physical network are reduced.
Thus far, a network slice configuration method and system, computer-storable medium, in accordance with the present disclosure have been described in detail. Some details that are well known in the art have not been described in order to avoid obscuring the concepts of the present disclosure. It will be fully apparent to those skilled in the art from the foregoing description how to practice the presently disclosed embodiments.
Claims (13)
1. A network slice configuration system, comprising:
a Radio Access Network (RAN) layer device configured to:
generating service level information of the current time slot according to the user level information of the user layer equipment in the current time slot;
predicting service demand information of a user in the current time slot by utilizing a first machine learning model according to the service level information of the current time slot;
sending the service level information and the service requirement information of the current time slot;
a Software Defined Network (SDN) controller configured to:
determining a network slice configuration strategy of the current time slot by utilizing a second machine learning model according to the service level information and the service requirement information of the current time slot from the RAN layer equipment;
carrying out slice configuration verification on the network slice configuration strategy of the current time slot by utilizing a digital twin based on the user layer equipment and the RAN layer equipment;
and in the case of passing the verification, sending the network slice configuration strategy of the current time slot to the RAN layer equipment.
2. The network slice configuration system of claim 1, wherein the SDN controller is further configured to:
sending a network slice configuration policy for the current time slot to the digital twin;
deploying and operating a network slice configuration strategy of the current time slot at the digital twin;
acquiring the performance of the estimated network slice after the network slice configuration strategy of the current time slot is operated;
and carrying out slice configuration verification on the network slice configuration strategy of the current time slot according to the estimated gain of the network slice performance, wherein the verification is passed under the condition that the estimated gain of the network slice performance exceeds a gain threshold value.
3. The network slice configuration system of claim 1 or 2, wherein the RAN layer device is further configured to:
receiving a network slice configuration policy for a current time slot from the SDN controller;
running a network slice configuration strategy of the current time slot;
measuring feedback information of a user on the network slice configuration strategy of the current time slot, wherein the feedback information reflects the actual network slice performance under the network slice configuration strategy of the current time slot;
sending the feedback information to the SDN controller for the SDN controller to determine a network slice configuration policy for a time slot next to the current time slot.
4. The network slice configuration system of claim 1, further comprising:
a digital twin layer device deploying the digital twin, configured to receive real-time network information from the user layer device and the RAN layer device, and update the digital twin according to the real-time network information.
5. The network slice configuration system of claim 4, wherein an uplink between the RAN layer device and the digital twin layer device is comprised of a high-bandwidth, high-rate data link, and a downlink between the RAN layer device and the digital twin layer device is a control channel.
6. The network slice configuration system of claim 1, wherein the user level information comprises at least one of a service demand pattern of the user, a movement pattern of the user, location information of the user, and random channel conditions of the user.
7. The network slice configuration system of claim 6, wherein the RAN layer device is further configured to perform at least one of:
analyzing the service requirement mode of the user to obtain the requirements of the user on time delay, bandwidth and service content information as service level information;
analyzing the movement mode of the user to obtain the movement rule of the user as service level information;
obtaining the signal-to-noise ratio of the current channel as service level information according to the random channel condition of the user; and
and determining the density information of the user as service level information according to the position information of the user.
8. The network slice configuration system of claim 1,
the first machine learning model comprises a long short term memory network (LSTM) model; and/or
The second machine learning model comprises a deep reinforcement learning model.
9. The network slice configuration system of claim 1, further comprising:
the user layer device is configured to send user level information of the current time slot to the RAN layer device.
10. The network slice configuration system of claim 1 wherein the RAN layer device comprises an access point device of a RAN layer.
11. A network slice configuration method, comprising:
the RAN layer equipment of the radio access network generates service level information according to the user level information of the user layer equipment in the current time slot;
the RAN layer equipment predicts the service demand information of the user in the current time slot by using a first machine learning model according to the service level information of the current time slot;
RAN layer equipment sends service level information and service requirement information of the current time slot;
a Software Defined Network (SDN) controller determines a network slice configuration strategy of the current time slot by utilizing a second machine learning model according to the service level information and the service requirement information of the current time slot from the RAN layer equipment;
the SDN controller carries out slice configuration verification on the network slice configuration strategy of the current time slot by using a digital twin body based on the user layer equipment and the RAN layer equipment;
and the SDN controller sends the network slice configuration strategy of the current time slot to the RAN layer equipment under the condition of passing verification.
12. A network slice configuration system, comprising:
a memory; and
a processor coupled to the memory, the processor configured to perform the network slice configuration method of claim 11 based on instructions stored in the memory.
13. A computer-storable medium having stored thereon computer program instructions which, when executed by a processor, implement the network slice configuration method of claim 11.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211445997.2A CN115843050A (en) | 2022-11-18 | 2022-11-18 | Network slice configuration method and system, computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211445997.2A CN115843050A (en) | 2022-11-18 | 2022-11-18 | Network slice configuration method and system, computer storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115843050A true CN115843050A (en) | 2023-03-24 |
Family
ID=85575686
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211445997.2A Pending CN115843050A (en) | 2022-11-18 | 2022-11-18 | Network slice configuration method and system, computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115843050A (en) |
-
2022
- 2022-11-18 CN CN202211445997.2A patent/CN115843050A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chih-Lin et al. | The big-data-driven intelligent wireless network: architecture, use cases, solutions, and future trends | |
| CN110121180B (en) | Data analysis device, system and method | |
| EP3972339A1 (en) | Handover success rate prediction and management using machine learning for 5g networks | |
| US20210042578A1 (en) | Feature engineering orchestration method and apparatus | |
| Zeljković et al. | ABRAHAM: machine learning backed proactive handover algorithm using SDN | |
| CN110839184A (en) | Method and device for adjusting bandwidth of mobile fronthaul optical network based on flow prediction | |
| CN113498508A (en) | Dynamic network configuration | |
| WO2022226713A1 (en) | Method and apparatus for determining policy | |
| CN113869521A (en) | Method, device, computing equipment and storage medium for constructing prediction model | |
| WO2023143267A1 (en) | Model configuration method and apparatus | |
| EP4156631A1 (en) | Reinforcement learning (rl) and graph neural network (gnn)-based resource management for wireless access networks | |
| Moysen et al. | On the potential of ensemble regression techniques for future mobile network planning | |
| Kim et al. | Network-Aided Intelligent Traffic Steering in 5G Mobile Networks. | |
| CN115066006A (en) | Base station dormancy method, equipment and medium based on reinforcement learning | |
| CN115843050A (en) | Network slice configuration method and system, computer storage medium | |
| US11622322B1 (en) | Systems and methods for providing satellite backhaul management over terrestrial fiber | |
| Maksymyuk et al. | Artificial intelligence based 5G coverage design and optimization using deep generative adversarial neural networks | |
| Murudkar et al. | Network Architecture for Machine Learning: A Network Operator's Perspective | |
| Chu et al. | Reinforcement learning based multi-access control with energy harvesting | |
| CN109151895B (en) | Data transmission method, device, server and network center node | |
| Ren et al. | End-to-End Network SLA Quality Assurance for C-RAN: A Closed-Loop Management Method Based on Digital Twin Network | |
| Falahatraftar et al. | A multiple linear regression model for predicting congestion in heterogeneous vehicular networks | |
| Panchenko et al. | The method of adaptive selection of a wireless access network in a heterogeneous environment based on the theory of fuzzy sets | |
| CN112637904A (en) | Load balancing method and device and computing equipment | |
| CN112996067B (en) | Method, device and storage medium for determining serving cell |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |