Core network element dynamic management method and system

Abstract

The application discloses a kind of core network element dynamic management method and system, the method includes: the first state information of core network is collected, first state information includes the number of network element equipment in active state in each logical pool in core network and the number of network element equipment in activation pending state;Second state information of external network connected with core network communication is collected, second state information includes the type of request message from user equipment and the number of each class request message;First state information and second state information are processed based on intelligent model to obtain network element adjustment information;The state of network element equipment in each logical pool is adjusted based on network element adjustment information, so that the service capability of logical pool is adapted to network traffic demand.The above method can make network element management more intelligent, realize the dynamic control of network element equipment activation number, to adapt to the change of network traffic, and can effectively optimize resource consumption, and reduce operating cost.

Description

Technical Field

[0001] This invention relates to the field of mobile communication technology, and in particular to a method and system for dynamic management of core network elements. Background Technology

[0002] In modern communication networks, the core network serves as a crucial bridge connecting user equipment and internet services, and its performance and efficiency directly impact the overall quality of service. With the rapid expansion of mobile internet and IoT applications, one of the main challenges facing the core network is how to effectively manage the ever-increasing network traffic, particularly how to reduce operating costs while ensuring service quality. While traditional core network load balancing methods have addressed some early problems, they are gradually revealing a series of significant limitations when dealing with current and future network demands.

[0003] A major problem with traditional load balancing methods is significant resource waste. To cope with the surge in requests during peak network traffic periods, operators typically deploy a large number of similar network elements in each pool. These elements remain operational even during periods of low traffic, leading to unnecessary energy consumption and wasted hardware resources. Specifically, continuously running network elements not only consume substantial amounts of electricity but also generate additional cooling requirements, further increasing energy consumption. Furthermore, the fixed number of network elements implies a large initial hardware investment, especially when dealing with potential high traffic surges, necessitating sufficient redundancy. This fixed resource configuration results in significant resource idleness during periods of low daily traffic, thereby increasing operating costs.

[0004] Secondly, traditional load-sharing methods perform poorly in terms of resource management and dynamic adaptability. In traditional methods, the number and configuration of network elements are usually fixed, making dynamic adjustments impossible based on actual business needs. When network traffic suddenly surges, the existing number of network elements may be insufficient to cope, and temporarily adding new network elements requires a long time to procure, install, and configure equipment, hindering rapid response to emergencies. Conversely, when network traffic is low, many network elements remain idle, resulting in low resource utilization. Furthermore, the fixed number of network elements limits system flexibility, making it difficult to effectively allocate tasks based on real-time network conditions, impacting overall service quality and user experience. For example, traffic in a specific area may be significantly higher than in other areas during certain time periods, and traditional methods cannot dynamically adjust resource allocation, leading to some network elements being overloaded while others remain idle, further exacerbating resource waste and performance bottlenecks. Summary of the Invention

[0005] The purpose of this invention is to provide a core network element dynamic management method and system that can dynamically adjust the number of active network elements based on changes in network traffic.

[0006] To achieve the above objectives, the present invention provides a dynamic management method for core network elements. The core network is configured with several logical pools corresponding to different types of network elements, and each logical pool contains multiple network element devices with the same function. In each logical pool, the state of each network element device includes an active state during normal operation and a silent, pending activation state. The dynamic management method includes:

[0007] Collect first status information of the core network, which includes the number of network element devices in an active state and the number of network element devices in a pending activation state in each of the logical pools of the core network.

[0008] Collect second status information of external networks that are communicatively connected to the core network. The second status information includes the type of request messages from user equipment and the number of each type of request message.

[0009] The first state information and the second state information are processed based on an intelligent model to obtain network element adjustment information; the intelligent model is constructed and pre-trained based on a self-learning neural network model.

[0010] The state of the network element devices in each of the logical pools is adjusted based on the network element adjustment information so that the service capacity of the logical pools is adapted to the network traffic demand.

[0011] Preferably, the first status information further includes one or more of the following:

[0012] The virtual memory size used by the process corresponding to the network element device;

[0013] The size of the process corresponding to the network element device currently residing in physical memory;

[0014] The percentage of CPU time occupied by the process corresponding to the network element device;

[0015] The percentage of physical memory occupied by the process corresponding to the network element device;

[0016] Network error rate;

[0017] Packet loss rate;

[0018] Retransmission rate;

[0019] Network element delay time;

[0020] The length of the internal task queue of the network element device.

[0021] Preferably, the type of the request message in the second status information includes one or more of the following: voice message, SMS message, and video message.

[0022] Preferably, the first state information and the second state information are collected periodically according to the time interval set by the timer.

[0023] Preferably, the network element adjustment information and the second status information are also stored, and the network element adjustment information generated in the current time period is coupled with the second status information collected in the next time period into a data pair;

[0024] During a preset idle period, the intelligent model reads the data pairs for training and updates the neural network parameters of the intelligent model based on the training results.

[0025] Preferably, the intelligent model is a reinforcement learning model.

[0026] Preferably, the intelligent model is set in the network data analysis function of the core network.

[0027] The present invention also provides a core network element dynamic management system, which includes a system controller, the system controller operating based on the core network element dynamic management method described above.

[0028] The present invention also provides a core network element dynamic management system, which includes:

[0029] One or more processors;

[0030] Memory;

[0031] And one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the programs including instructions for performing the core network element dynamic management method as described above.

[0032] The present invention also provides a computer-readable storage medium comprising a computer program that can be executed by a processor to perform the core network element dynamic management method as described above.

[0033] Compared with existing technologies, the core network element dynamic management method provided by this invention processes the first state information reflecting the status of network element devices in each logical pool of the core network and the second state information reflecting the network traffic of the external network through an intelligent model to output network element adjustment information. Based on this network element adjustment information, the status of various types of network element devices in the current core network is adjusted, so that the service capacity of active network element devices is commensurate with the current network demand. Therefore, the above-mentioned network element dynamic management method can make network element management more intelligent, realize dynamic control of the number of activated network element devices to adapt to changes in network traffic, and effectively optimize resource consumption and reduce operating costs. Attached Figure Description

[0034] Figure 1 This is a flowchart of the core network element dynamic management method in an embodiment of the present invention. Detailed Implementation

[0035] To illustrate the technical content, structural features, objectives, and effects of the present invention in detail, the following description is provided in conjunction with the embodiments and accompanying drawings.

[0036] This embodiment discloses a method for dynamic management of core network elements, so as to realize the dynamic adjustment of core network elements according to the dynamic changes of network traffic.

[0037] First, it should be noted that the core network of this embodiment is configured with several logical pools, each corresponding to different types of network elements. Each logical pool contains multiple network element devices with the same function. Within each logical pool, the state of each network element device includes an active state of normal operation and a silent, pending activation state. Specifically, for any given logical pool of multiple network element devices, a corresponding number of network element devices can be activated as needed, while inactive network element devices remain in a pending activation state.

[0038] Based on this, the dynamic management method includes the following process:

[0039] S10: Collect the first status information of the core network. The first status information includes the number of network element devices in an active state and the number of network element devices in a pending activation state in each of the logical pools in the core network. This first status information reflects the current service capacity and scalability of the logical pool.

[0040] S11: Collect second status information of the external network that is communicatively connected to the core network. The second status information includes the type of request messages from the user equipment and the number of each type of request message. This second status information reflects the network traffic of the external network.

[0041] S12: The first state information and the second state information are processed based on the intelligent model to obtain network element adjustment information. The intelligent model is built and pre-trained based on a self-learning neural network model.

[0042] S13: Adjust the state of the network element devices in each of the logical pools based on the network element adjustment information, so that the service capacity of the logical pools can be adapted to the network traffic demand.

[0043] Based on this management method, the first state information reflecting the status of network element devices in each logical pool of the core network and the second state information reflecting the network traffic of the external network are processed by an intelligent model to output network element adjustment information. Based on this network element adjustment information, the status of various types of network element devices in the current core network is adjusted so that the service capacity of active network element devices is comparable to the current network demand.

[0044] Therefore, the above-mentioned dynamic network element management method can make network element management more intelligent and realize dynamic control of the number of activated network element devices to adapt to changes in network traffic.

[0045] Moreover, the above management methods can reduce the number of active network elements during off-peak traffic periods, significantly reducing energy consumption and hardware resource waste. At the same time, during peak traffic periods, the number of active network elements can be increased according to actual needs to ensure the stability and reliability of the communication system, thereby effectively optimizing resource consumption and reducing operating costs.

[0046] Specifically, the first status information also includes one or more of the following:

[0047] The virtual memory size used by the process corresponding to the network element device;

[0048] The size of the process corresponding to the network element device currently residing in physical memory;

[0049] The percentage of CPU time occupied by the process corresponding to the network element device;

[0050] The percentage of physical memory occupied by the process corresponding to the network element device;

[0051] Network error rate;

[0052] Packet loss rate;

[0053] Retransmission rate;

[0054] Network element delay time;

[0055] The length of the internal task queue of the network element device.

[0056] Furthermore, the request message type mentioned in the second status information includes one or more of the following: voice message, SMS message, and video message. Therefore, the number of activated network elements is adjusted according to different types of network traffic.

[0057] On the other hand, since changes in network traffic require time to accumulate, in order to reduce the energy demand required for the operation of this management method, the first status information and the second status information are collected periodically according to the time interval set by the timer, and then the status of the network element devices in the logic pool is updated according to the time interval.

[0058] On the other hand, to continuously improve the accuracy of the intelligent model's output strategy, the network element adjustment information and the second state information are also stored, and the network element adjustment information generated in the current time period is coupled with the second state information collected in the next time period into a data pair.

[0059] During a preset idle period, the intelligent model reads the data pairs for training and updates the neural network parameters of the intelligent model based on the training results, thereby improving the predictive ability of the intelligent model in real time.

[0060] Specifically, the intelligent model is a reinforcement learning model.

[0061] On the other hand, the intelligent model is set in the network data analysis function NWAD of the core network.

[0062] In another preferred embodiment of the present invention, a core network element dynamic management system is also disclosed, which includes a system controller, the system controller operating based on the core network element dynamic management method in the above embodiment.

[0063] This invention also discloses another core network element dynamic management system, which includes one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors. The programs include instructions for executing the core network element dynamic management method as described above. The processor may be a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, used to execute relevant programs to implement the functions required by the modules in the core network element dynamic management system of this application embodiment, or to execute the core network element dynamic management method of this application method embodiment.

[0064] This invention also discloses a computer-readable storage medium comprising a computer program that can be executed by a processor to perform the core network element dynamic management method described above. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium can be read-only memory (ROM), random access memory (RAM), or magnetic media, such as floppy disks, hard disks, magnetic tapes, magnetic disks, or optical media, such as digital versatile discs (DVDs), or semiconductor media, such as solid-state disks (SSDs).

[0065] This application also discloses a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. The processor of an electronic device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the electronic device to perform the aforementioned core network element dynamic management method.

[0066] The above-disclosed embodiments are merely preferred embodiments of the present invention and should not be construed as limiting the scope of the present invention. Therefore, any equivalent variations made in accordance with the claims of the present invention are still within the scope of the present invention.

Claims

1. A core network element dynamic management method, characterized in that, The core network is provided with a plurality of logical pools corresponding to different types of network elements, and each of the logical pools is provided with a plurality of network element devices with the same function; In each of the logical pools, the state of each of the network element devices includes an active state in normal operation and a silent state to be activated; The dynamic management method comprises: Collecting first state information of the core network, the first state information including the number of network element devices in each of the logical pools in the core network in an active state and the number of network element devices in a state to be activated; Collecting second state information of an external network in communication connection with the core network, the second state information including the type of request messages from user equipment and the number of each type of request messages; Processing the first state information and the second state information based on an intelligent model to obtain network element adjustment information; the intelligent model is constructed based on a self-learning neural network model and is pre-trained; Based on the network element adjustment information, the state of the network element device in each of the logical pools is adjusted to adapt the service capability of the logical pool to the network traffic demand.

2. The method of claim 1, wherein the core network element dynamic management method is characterized by, The first state information further includes any one or more of the following information: The size of the virtual memory used by the process corresponding to the network element device; The size of the process corresponding to the network element device currently residing in the physical memory; The percentage of CPU time occupied by the process corresponding to the network element device; The percentage of physical memory occupied by the process corresponding to the network element device; Network error rate; Packet loss rate; Re-transmission rate; Network element device delay time; Network element device internal task queue length.

3. The method of claim 1, wherein the core network element dynamic management method is characterized by, The types of request messages in the second state information include one or more of voice messages, short message messages, and video messages.

4. The method of claim 1, wherein the core network element dynamic management method is characterized by, The first state information and the second state information are collected at a time interval set by a timer.

5. The method of claim 1, wherein the core network element dynamic management method is characterized by, The network element adjustment information and the second state information are also stored, and the network element adjustment information generated in the current time period is coupled with the second state information collected in the next time period to form a data pair; In a pre-set idle time period, the intelligent model reads the data pair for training, and updates the neural network parameters of the intelligent model according to the training result.

6. The method of claim 1, wherein the core network element dynamic management method is characterized by, The intelligent model is a reinforcement learning model.

7. The method of claim 1, wherein the core network element dynamic management method is characterized by, The intelligent model is provided in a network data analysis function of the core network.

8. A core network element dynamic management system, characterized in that, It comprises a system controller that works based on the core network network element dynamic management method of any one of claims 1 to 7.

9. A core network element dynamic management system, characterized in that, It comprises: One or more processors; Memory; And one or more programs, wherein one or more programs are stored in the memory and configured to be executed by the one or more processors, the programs including instructions for executing the core network network element dynamic management method of any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, It comprises a computer program that can be executed by a processor to complete the core network network element dynamic management method of any one of claims 1 to 7.

Images