CN113133024B

CN113133024B - Network resource configuration method and device

Info

Publication number: CN113133024B
Application number: CN201911418579.2A
Authority: CN
Inventors: 魏政元; 季平
Original assignee: Beijing Huawei Digital Technologies Co Ltd
Current assignee: Beijing Huawei Digital Technologies Co Ltd
Priority date: 2019-12-31
Filing date: 2019-12-31
Publication date: 2022-09-02
Anticipated expiration: 2039-12-31
Also published as: CN113133024A

Abstract

The application provides a method and a device for configuring network resources, and relates to the technical field of communication. By improving the limitations of the prior art on the tuning range and the tuning effect of network resource configuration, the problem of network resource optimal configuration of the whole local area network is solved. The method comprises the following steps: acquiring detection data of a plurality of network devices, wherein the detection data comprises air interface data of the network devices; obtaining path loss among the network devices according to the detection data of the network devices; obtaining network health scores corresponding to a plurality of network configurations through a neural network algorithm and a deep learning algorithm, wherein the plurality of network configurations are determined according to path loss among a plurality of network devices; and selecting the network configuration with the highest network health score to configure the plurality of network devices.

Description

Network resource configuration method and device

Technical Field

The present application relates to the field of communications technologies, and in particular, to a method and an apparatus for configuring network resources.

Background

Cellular networks are limited to limited non-overlapping communication channels, and therefore, generally any adjacent network area uses channels without frequency crossing, i.e. one channel is used by each cellular network device, and different channels are used by adjacent cellular network devices, otherwise, interference between networks is easily caused; the same channel may be used if the two cells are far enough apart that the interference is small enough. Therefore, it is necessary to optimally configure the channel resources of the cellular network, so as to make the network resource allocation of the whole network as reasonable as possible.

Because the scale of the Access Point (AP) device is huge, and other variable or unknown radio frequency signals exist in the network, in the aspect of channel planning, a large amount of labor cost needs to be consumed by only depending on manual planning, and interference caused by other variable or unknown radio frequency signals is difficult to predict.

The existing tuning technology for network resource configuration is based on a tuning domain of a network device, the tuning range only performs resource optimization configuration for a single Access Controller (AC) or a network device in a certain tuning domain, and network devices between different ACs or tuning domains may have relatively large communication interference, so that the problem of resource configuration optimization of the whole network is difficult to solve.

Disclosure of Invention

The application provides a method and a device for configuring network resources, which solve the problems that the tuning range and the tuning effect of network resource configuration in the prior art are limited and the network resource optimal configuration of the whole network cannot be solved.

In order to achieve the purpose, the following technical scheme is adopted in the application:

in a first aspect, a method for configuring network resources is provided, which is applied to a communication device, such as an analyzer device. The method comprises the following steps: acquiring detection data of a plurality of network devices, wherein the detection data comprises air interface data of the network devices; obtaining path loss among the network devices according to the detection data of the network devices; obtaining network health scores corresponding to a plurality of network configurations through a neural network algorithm and a deep learning algorithm, wherein the plurality of network configurations are determined according to path loss among a plurality of network devices; and selecting the network configuration with the highest network health score to configure the plurality of network devices.

According to the technical scheme, the path loss among the network devices is obtained according to the detection data of the plurality of network devices, and the network configuration with the highest network health score under the optimized configuration is obtained through repeated iterative computation through a neural network algorithm and a deep learning algorithm, so that the resource configuration optimization problem of the whole network is realized at one time, and the network resource optimization efficiency is improved.

In a possible design manner, the detection data of the multiple network devices includes state information and neighbor network device information corresponding to the multiple network devices. In the possible implementation manner, the state information and the like of the network equipment and the neighbor network equipment are obtained by obtaining the air interface data of the plurality of network equipment, so that the network health degree is evaluated, the data collection is convenient and fast, the real-time user communication network quality data is not relied on, and the tuning efficiency of the network resources is improved.

In a possible design mode, network health scores corresponding to a plurality of network configurations are obtained through a neural network algorithm and a deep learning algorithm, and the method specifically comprises the following steps: acquiring first network configuration through path loss among a plurality of network devices, and acquiring a first network health score corresponding to the first network configuration according to a neural network algorithm and a deep learning algorithm; updating the first network configuration through a neural network algorithm according to the priority of the network equipment to obtain a second network configuration; and obtaining a corresponding second network health score of the second network configuration according to the neural network algorithm and the deep learning algorithm.

In the possible implementation mode, the optimization scheme of the network configuration is simulated through the neural network algorithm, the network health score corresponding to the optimized network configuration is estimated through the deep learning algorithm modeling, so that the configuration is repeatedly modified, the network health score is calculated, and the optimization scheme of the network configuration with the most target network health score is obtained through traction. The problem of optimizing the resource allocation of the whole network at one time is solved by acquiring the detection data at one time, and the adjusting and optimizing efficiency of network resources is improved.

In one possible design, the network health score is associated with interference conflicts between the plurality of network devices; and/or, the network health score is associated with network load, user communication latency, or packet loss data of the plurality of network devices. In the possible implementation manners, the network health score may be abstracted through interference collision values among a plurality of network devices, or the network health score may be abstracted according to parameters such as network load of the network devices, user communication delay or packet loss data. The network health score is reflected according to the interference conflict value between the network devices, the algorithm is simple, the data processing complexity can be reduced, and the network resource tuning efficiency is improved.

In one possible design, the network configuration includes at least one of configuration information of channels, bandwidths, or powers of the plurality of network devices. In the possible implementation manner, configuration updating of channels, bandwidths or powers of a plurality of network devices is realized by optimizing configuration, tuning of network resources of the whole network can be realized, and user experience is improved.

In a possible design, acquiring detection data of a plurality of network devices specifically includes: receiving detection data sent by a plurality of network devices; or, receiving detection data of a plurality of network devices transparently transmitted by at least one intermediate forwarding device; or, accessing a plurality of network devices to obtain the detection data of the plurality of network devices. In the possible implementation manners, the detection data of the plurality of network devices are passively or actively acquired through several manners of directly reporting by the network devices, forwarding by the intermediate forwarding device or actively accessing the network devices to acquire the detection data, so that the flexibility of detection data acquisition is improved, and the resource occupation of the overall data acquisition and processing is reduced.

In one possible design, selecting a network configuration with the highest network health score to configure the plurality of network devices includes: and sending configuration information to a plurality of network devices through a Simple Network Management Protocol (SNMP) or a network device configuration management protocol (NETCONF), wherein the configuration information comprises network configuration with the highest network health score. In the possible implementation manner, the configuration with the optimal network health can be sent to a plurality of network devices through an SNMP or NETCONF protocol, so as to implement the configuration of network tuning.

In a second aspect, an apparatus for configuring a network resource is provided, the apparatus including: the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring detection data of a plurality of network devices, and the detection data comprises air interface data of the network devices; the processing module is used for obtaining the path loss among the network devices according to the detection data of the network devices; obtaining network health scores corresponding to a plurality of network configurations through a neural network algorithm and a deep learning algorithm, wherein the plurality of network configurations are determined according to path loss among a plurality of network devices; and the configuration module is used for selecting the network configuration with the highest network health score to configure the plurality of network devices.

In a possible design, the detection data of the multiple network devices includes at least one of state information, neighbor network device information, and network configuration information corresponding to the multiple network devices.

In a possible design, the processing module is specifically configured to: obtaining network health scores corresponding to various network configurations through a neural network algorithm and a deep learning algorithm, and specifically comprising the following steps of: acquiring first network configuration through path loss among a plurality of network devices, and acquiring a first network health score corresponding to the first network configuration according to a neural network algorithm and a deep learning algorithm; updating the first network configuration through a neural network algorithm according to the priority of the network equipment to obtain a second network configuration; and obtaining a corresponding second network health score of the second network configuration according to the neural network algorithm and the deep learning algorithm.

In one possible design, the network health score is associated with interference conflicts between the plurality of network devices; and/or, the network health score is associated with network load, user communication latency, or packet loss data of the plurality of network devices.

In one possible design, the network configuration includes at least one of configuration information of channels, bandwidths, or powers of the plurality of network devices.

In one possible design, the obtaining module is specifically configured to: receiving detection data sent by a plurality of network devices; or, receiving detection data of a plurality of network devices transparently transmitted by at least one intermediate forwarding device; or, accessing a plurality of network devices to obtain the detection data of the plurality of network devices.

In one possible design, the configuration module is specifically configured to: and sending configuration information to a plurality of network devices through a Simple Network Management Protocol (SNMP) or a network device configuration management protocol (NETCONF), wherein the configuration information comprises network configuration with the highest network health score.

In a third aspect, a communication apparatus is provided, which includes: at least one processor, a memory; the at least one memory stores program instructions and data, the program instructions being executable on the at least one processor, the at least one processor executing the program instructions in the memory to cause the communication device to perform the method for configuring network resources as set forth in any one of the possible designs of the first aspect.

In a fourth aspect, a computer-readable storage medium is provided, where instructions are stored in the computer-readable storage medium, and when the computer-readable storage medium is run on a device, the device is caused to perform the method for configuring network resources described in any one of the possible design manners of the first aspect.

In a fifth aspect, a computer program product is provided, which when running on a computer, causes the computer to perform the method for configuring network resources as described in any one of the possible designs of the first aspect.

It is understood that any one of the above-provided network resource configuration method, network resource configuration device, communication device, computer-readable storage medium and computer program product can be implemented by the corresponding method provided above, and therefore, the beneficial effects achieved by the method can refer to the beneficial effects in the corresponding method provided above, and are not described herein again.

Drawings

Fig. 1 is a system architecture diagram of a communication network according to an embodiment of the present application;

fig. 2 is a schematic flowchart of a method for configuring network resources according to an embodiment of the present application;

fig. 3 is a schematic processing module diagram of a method for configuring network resources according to an embodiment of the present disclosure;

fig. 4 is a schematic processing flow diagram of a method for configuring network resources according to an embodiment of the present application;

fig. 5 is a schematic structural diagram of a device for configuring network resources according to an embodiment of the present application;

fig. 6 is a schematic structural diagram of a communication device according to an embodiment of the present application.

Detailed Description

In the following, the terms "first", "second" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present embodiment, "a plurality" means two or more unless otherwise specified.

The embodiment of the application provides a method for configuring Network resources, which can be applied to the optimal configuration of Network resources of a Local Area Network (LAN) and can also be applied to other cellular networks.

The Local Area Network is a Local Area Network formed in a Local Area, and is divided into a wired Local Area Network (lan) and a Wireless Local Area Network (WLAN), and the WLAN is a Network system which is formed by interconnecting computer devices by using a Wireless communication technology and can communicate with each other and realize resource sharing. Currently, WLANs are widely used due to their convenience. In the embodiments of the present application, the WLAN is merely used as an example for description, and the present application is not limited thereto.

Before introducing the method embodiment of the present application, a network structure of a WLAN is briefly introduced, as shown in fig. 1, a WLAN system generally includes an Access Controller (AC) and a Wireless Access Point (AP), and may include multiple network devices such as an AP1, an AP2, and an AP3 shown in fig. 1, for example.

The AP is a wireless switch for the wireless network and is also the core of the wireless network. Wireless APs are access points for mobile computer users to access wired networks, primarily for broadband homes, inside buildings and inside parks, typically covering distances from tens to hundreds of meters. Most wireless APs also have an AP client mode, and can wirelessly connect with other APs to extend the coverage of the network.

The AC is an access control device of the wireless lan, and is responsible for aggregating data from different APs and accessing the data to the network, and simultaneously performing control functions such as configuration management of the AP device, authentication and management of wireless users, broadband access, security, and the like.

The WLAN system may further include a switch, which may be configured to supply power to the plurality of wireless APs and may also provide a data forwarding function, for example, for forwarding data of the network device AP and the network device AC.

The WLAN system may further comprise an analyzer, which may be connected to the switch or to the network device AC, for planning, managing and controlling the network resources of the WLAN system. For example, the analyzer may be a campus network analyzer (campussignt) for parameter configuration, management, troubleshooting, and the like of all ACs and APs within the WLAN network.

The reasonable channel planning is carried out on a plurality of APs in the wireless network WLAN, and the method plays an important role in reducing interference and conflict among wireless communication and improving network quality and transmission efficiency.

Wherein the channel determines which frequency range the wireless AP is communicating in. A wireless channel is a wireless "frequency band (channel)" which is a data signal transmission channel using a wireless signal as a transmission medium. There may be different degrees of co-frequency or adjacent-frequency interference between network devices located adjacent to each other.

The embodiment of the application can be used for reasonably planning the channels of a plurality of network devices in the wireless network WLAN, so that interference conflict among the network devices of the whole network is minimum, and the network experience of a user is best, thereby realizing the optimal configuration of network resources of the whole network and improving the user experience.

The embodiment of the present application provides a method for configuring network resources based on a neural network and a deep learning algorithm, and the method may be applied to a communication device, for example, the communication device may be an analyzer. The analyzer can quickly simulate better network resource allocation through a neural network algorithm according to neighbor detection information collected by all network equipment in a wireless network, and obtain the network resource allocation with the highest network health score aiming at the whole network through a reinforcement learning algorithm, so that the analyzer is issued to the network equipment according to the network resource allocation, and the resource optimization allocation of the network equipment in the whole local area network is realized.

Referring to fig. 1, an embodiment of the present application will be described in detail, and as shown in fig. 2, the method may include the following steps:

201: detection data for a plurality of network devices is obtained.

The network device in the WLAN network may be an AP, or may be another network device, for example, a network device such as an access point control AC, a Switch (SW), or a Firewall (FW). In the embodiments of the present application, the AP is merely used as an example to describe the present application, and the present application is not limited thereto.

The detection data of the multiple network devices may be air interface data acquired by the network devices, and may also be referred to as air interface detection data. The air interface is a wireless link between a network device and a terminal device, and the wireless transmission specification of the wireless link defines the use frequency, bandwidth, access timing, coding method, handover and other data of each wireless channel. In mobile communication, a user's terminal equipment and a base station communicate with each other over the air interface.

The air interface data may include state information of multiple network devices, neighbor network device information, and network configuration information. For example, after the AP1 device is powered on, it may detect surrounding environment information, such as neighbor devices AP2 and AP3 around the AP1, and may also detect other interference sources, such as a mobile phone hotspot, a microwave oven microwave signal, or a bluetooth signal.

The state information refers to the inherent attributes of the network device, the current operating state information, and the like, and such information can only be queried and cannot be modified and configured. The configuration data refers to data that is issued by a professional technician or an analyzer device and configured on the network device, for example, attributes such as available channels and bandwidths for data transmission of the network device.

Illustratively, the air interface detection data detected by the AP may include radio frequency data of the AP itself, and may also include radio frequency data of surrounding neighbors detected by the AP. For example, the radio frequency data of the AP itself may include: the Media Access Control Address (MAC) of the AP, the radio ID, and the channel on which it is located. For example, the radio frequency data of the neighbors may include: MAC addresses of the neighbor devices, types of the neighbor devices, channels where the neighbor devices are located, and Signal Strength indicators (RSSI) of the neighbor devices, and the like.

The type of the neighbor device may include type one: manageable or modifiable configured network devices of the same WLAN network, such as APs. Type two may also be included: unmanageable and unmodifiable network signals, i.e. other interference source signals, such as e.g. mobile phone hotspots, microwave signals of microwave ovens or bluetooth signals, etc.

In an embodiment, the analyzer obtains air interface data of a plurality of network devices, and may use an active acquisition mode and a passive reception mode, for example, taking a network device as an AP as an example for description.

In the first mode, the analyzer receives detection data sent by a plurality of APs.

When multiple APs and the analyzer system can communicate with each other, the multiple APs can directly report their own air interface detection data to the analyzer. For example, a plurality of APs may report to the analyzer through a wired network by using a transmission channel such as a hypertext Transfer Protocol over secure session Layer (HTTPS) or a User Datagram Protocol (UDP). That is, the AP may send a data message, for example, a UDP message, to the analyzer, where the data message is encapsulated with air interface detection data, and the analyzer analyzes the UDP message after receiving the UDP message reported by the AP, so as to obtain the air interface detection data of each AP.

The AP equipment can provide a data transmission channel between the AP and the analyzer by reporting, a large amount of detection data does not need to be forwarded by the intermediate forwarding equipment in a centralized manner, and the resource occupation of the centralized forwarding processing on the equipment processor and the network working bandwidth can be reduced.

And secondly, receiving detection data of a plurality of APs transparently transmitted by at least one access AC or forwarding equipment.

When the APs and the analyzer system cannot communicate directly, the air interface detection data acquired by the network devices may be reported to the analyzer through the intermediate forwarding device.

If the network between the AP and the analyzer system cannot be connected, a centralized forwarding device needs to be deployed, for example, forwarding through an AC device, or a server is deployed as a centralized forwarding device at the exit of the local network. The air interface detection data detected by the AP is firstly reported to the AC or the centralized forwarding equipment by the AP and then reported to the analyzer by the AC or the centralized forwarding equipment.

For example, the AP may send a data packet encapsulating air interface detection data to the AC, and after receiving the packet reported by the AP, the AC forwards the packet to the analyzer, and the analyzer analyzes the received packet, so as to obtain the air interface detection data of each AP.

And in the third mode, the analyzer actively accesses the plurality of APs so as to acquire the detection data of the plurality of APs.

If the plurality of APs do not have the capability of reporting the message, the analyzer can also request the AP device to acquire the probe data through an active polling mechanism. For example, the analyzer sends request information to the AP, where the request information is used to instruct to acquire air interface data of the AP device, and the analyzer may acquire air interface detection data from multiple APs.

Furthermore, the AC can compress and pack a plurality of AP detection data detected for many times and then uniformly upload the data to the analyzer, so that the data transmission efficiency is improved.

If the analyzer only obtains the air interface detection data of the multiple APs, the analyzer only needs to poll once to obtain the air interface detection data of the multiple APs under the condition that the configuration of the network environment is not changed. If the analyzer is to obtain user experience data of multiple APs during operation, it is necessary to obtain real-time AP detection data, and the polling mechanism of the analyzer may be configured to be timed or periodic. After the analyzer acquires the detection data of the AP, the actively detected detection data may be timestamped and stored in a database or a file.

In particular embodiments, the analyzer may collect the detection data through a configured acquisition module.

The acquisition module can check the validity of the network device reporting the detection data and the reported detection data, for example, if the detection data is lost or the detection data has data integrity defect, the acquisition module can record the log or send an alarm prompt in time. In addition, the acquisition module of the analyzer may have a certain flow control and management capability, and if it is detected that a single acquisition module cannot meet the requirement of receiving a large amount of detection data, a plurality of acquisition modules may be configured to collect the detection data at multiple points.

After the acquisition module of the analyzer acquires the report message of the detection data of the network equipment, the acquisition module can dial away the message header to acquire the data carrier, and the data carrier is processed into the pre-configured formatted data through the data analysis capability. As shown in fig. 3, the acquisition module may directly upload the formatted data generated by the processing to the network simulation module, or may upload the formatted data to the network simulation module after storing the formatted data, thereby improving the reliability of the data. The generated formatted data may be stored, for example, in the form of a database or file.

202: and obtaining the path loss among the network devices according to the detection data of the network devices.

Here, the path loss, also called propagation loss, may be referred to as path loss for short. The loss generated by the spatial propagation of the electric signal is caused by the radiation diffusion of the transmitting power and the propagation characteristic of a channel, and reflects the change of the average value of the power of the received signal in a macroscopic range. Refers to the loss in received power of the network device as compared to the transmitted power.

After the analyzer obtains the air interface detection data of the plurality of network devices, the analyzer may calculate the path loss between the adjacent network devices among the plurality of network devices according to the air interface detection data of the plurality of network devices, so as to obtain the neighbor relation of the plurality of network devices.

Specifically, the analyzer may calculate the path loss between the APs according to the detection data of the plurality of network devices, for example, the path loss between the APs is calculated according to the transmission power of the AP, the reception power of the AP, or the information strength detected by the APs, and the unit of the path loss is decibel-milliwatt (dbm). The specific way of calculating the path loss between APs may be obtained according to an existing algorithm, which is not specifically limited in the present application.

The path loss between the APs is related to the position relationship between the APs and the obstacles between the APs, so that the path loss between the APs is relatively stable even though the surrounding environment (such as obstacles) is not changed after the installation points of the APs are fixed.

The neighbor relations of the network devices do not refer to physical relations of the network devices, but are used for representing the neighbor relations of radio frequency signals of other network devices around which the network devices can detect.

203: and acquiring network health scores corresponding to various network configurations through a neural network algorithm and a deep learning algorithm.

Wherein the plurality of network configurations are determined based on path losses between the plurality of network devices.

The analyzer calculates the current path loss between the plurality of network devices according to the air interface detection data reported by the plurality of current network devices, and abstracts the network health score of the current network configuration according to the path loss between the plurality of network devices.

Referring to fig. 3, after acquiring the detection data of the plurality of network devices, the acquisition module reports the detection data to the network simulation module, and the network simulation module calculates the path loss between the plurality of network devices by acquiring the data. Interference collision values between the plurality of network devices may then be calculated based on the path losses between the plurality of network devices.

For example, the network health score may be represented by an interference collision value of the whole network, where the interference collision value between APs is used to represent a network interference situation between two APs, and the interference collision value of the whole network may be obtained by the interference collision value of a single AP, for example, an algorithm that performs weighted average on the interference collision values of the single APs, or an algorithm that calculates an average value is used to obtain the interference collision value of the whole network, which is used to represent the network health score of the whole network. For example, the lower the interference collision value of the whole network, the higher the network health score; the higher the interference conflict value of the whole network, the lower the network health score.

In one embodiment, the network health score may also be represented by other parameters, such as network load, terminal access experience, traffic data of network devices, packet loss data, communication latency or other user experience data, and so on.

As shown in fig. 4, after the detection data of the network device is obtained, network simulation is performed through a neural network algorithm, a plurality of different network configuration models are simulated, a network health score corresponding to each network configuration is predicted through a deep learning algorithm, and a network configuration with the highest network health score is obtained through repeated iteration.

The iterative process may specifically include:

obtaining network health scores corresponding to various network configurations through a neural network algorithm and a deep learning algorithm, and specifically comprising the following steps of: acquiring first network configuration through path loss among a plurality of network devices, and acquiring a first network health score corresponding to the first network configuration according to a neural network algorithm and a deep learning algorithm; updating the first network configuration through a neural network algorithm according to the priority of the network equipment to obtain a second network configuration; and obtaining a corresponding second network health score of the second network configuration according to the neural network algorithm and the deep learning algorithm.

The iterative processing process of the neural network combined with the deep learning algorithm can be realized by different computing modules, and as shown in fig. 3, the iterative processing process can include a network simulation module, an optimization action generation module, an evaluation module, and an optimization execution module. The function of each module in the above-described process will be described separately below.

And the network simulation module acquires the label data corresponding to the current network configuration according to the current network health score calculated by the evaluation module. For example, the tag data may be enumerated tags of health, normal, abnormal, and the like, which respectively correspond to network health scores with different scores; or the tag data may be a specific score, corresponding to a network health score. And calculating probability distribution under each optimization action by combining the distributable actions provided by the optimization action generation module, and giving the optimal network configuration under the current network equipment through neural network prediction according to the priority of the network equipment. The evaluation module calculates corresponding network health scores, finally outputs the predicted configuration and scores to the evaluation module, and finally decides whether the network configuration is optimal or not by the evaluation module.

An evaluation module: network health assessment is performed in combination with online data (real-time acquired detection data) and offline data (simulation information). The evaluation module is mainly used for providing two evaluation processing capacities: firstly, network health assessment, namely acquiring detection data from an acquisition module, calculating to obtain path loss among a plurality of network devices, and obtaining the network health assessment through modeling on the premise of no change of environment. The network health score can be simulated according to a single index, for example, the interference conflict value of the same frequency or adjacent frequency between network devices; or simulation can be performed according to the comprehensive indexes, such as a calculation model for abstractly calculating the network health score by comprehensively considering network load, terminal access experience and the like. And obtaining the whole network health score by the network health score among the single network devices through weighted average calculation, and determining whether the whole network health score is the highest by using the whole network health score as a target value traction algorithm. And secondly, decision evaluation of whether the optimal network configuration is achieved or not is carried out, and the optimal network configuration is decided by utilizing a reinforcement learning algorithm based on mass data samples including a network simulation module and real running online data (detection data acquired in real time).

An optimization action generation module: based on the detection data of the plurality of network devices, the network health assessment of the assessment module, such as interference conflict value, is combined to perform the priority ranking of the network devices. Therefore, when the configuration action is optimized, the network resource allocation of the high-priority equipment, such as the configuration of network channels, power and bandwidth, is preferentially ensured. If the collected detection data is rich enough, other factors can be used as the factors for generating actions, such as the channel utilization rate of radio frequency, the service load or the comprehensive factors of user experience data and the like. And after the optimization action generation module gives an optimizable action, the output distributable action is provided for the network simulation module for the decision of the network simulation module.

An optimization execution module: and after the optimal network configuration is determined through the steps, the configuration adjustment of the plurality of network devices is completed.

204: and selecting the network configuration with the highest network health score to configure the plurality of network devices.

Specifically, The analyzer may send Configuration information to The plurality of Network devices through a Simple Network Management Protocol (SNMP) or a Network device Configuration Management Protocol (NETCONF), where The Configuration information includes a Network Configuration with a highest Network health score.

The SNMP is an application layer protocol of a TCP/IP protocol cluster, works at a UDP 161 port, and is used for monitoring software and hardware information such as an operating system, hardware equipment, service application, software and hardware configuration, a network protocol state, equipment performance and resource utilization rate, equipment error reporting event information, an application program state and the like of network equipment.

Through the optimization execution module, a plurality of network devices can be configured through a general network device management protocol, such as SNMP or NETCONF, and also can be configured through a customized private interaction protocol.

The analyzer issues the network configuration of the multiple network devices, and may directly issue the network configuration to the multiple network devices, for example, the analyzer sends a configuration packet to the multiple APs. It may also be forwarded through an intermediate proxy, e.g., through the AC to the AP. The network configuration with the highest network health score is issued once, and the optimal network configuration is realized by one-time configuration.

The above embodiments of the present application are implemented by matching a plurality of

The detection data collected by the network equipment is subjected to analog simulation of network resource allocation, network health scores of the network resource allocation are optimized through a deep learning algorithm, and the optimal network resource allocation is calculated through repeated iteration of a neural network and deep learning, so that the optimal network resource allocation is issued to each network equipment. The effects of generating optimal network resource allocation and optimizing the quality of the wireless network at one time are achieved according to the detection data at one time, and the efficiency and the accuracy of network resource optimization are improved.

The present application further provides an apparatus for configuring a network resource, as shown in fig. 5, the apparatus 500 may include: an acquisition module 501, a processing module 502 and a configuration module 503.

An obtaining module 501, configured to obtain detection data of multiple network devices, where the detection data includes air interface data of the network devices.

A processing module 502, configured to obtain path loss between multiple network devices according to detection data of the multiple network devices; and acquiring network health scores corresponding to a plurality of network configurations through a neural network algorithm and a deep learning algorithm, wherein the plurality of network configurations are determined according to path loss among a plurality of network devices.

The configuration module 503 is configured to select a network configuration with the highest network health score to configure a plurality of network devices.

In one possible design, the detection data of the multiple network devices includes state information and neighbor network device information corresponding to the multiple network devices.

In a possible design, the processing module 502 may be further configured to: obtaining a first network configuration through a neural network algorithm, and obtaining a first network health score corresponding to the first network configuration according to a deep learning algorithm; according to the priority of the network equipment, updating the configuration of the network equipment configured by the first network through a neural network algorithm to obtain second network configuration; and obtaining a corresponding second network health score of the second network configuration according to the deep learning algorithm, and repeatedly iterating through the neural network algorithm and the deep learning algorithm until the network configuration with the highest network health score is obtained.

In a possible design manner, the obtaining module 501 may be specifically configured to: receiving detection data sent by a plurality of network devices; or, receiving detection data of a plurality of network devices transparently transmitted by at least one intermediate forwarding device; or, accessing a plurality of network devices to obtain the detection data of the plurality of network devices.

In a possible design, the configuration module 503 may be specifically configured to: and sending configuration information to the plurality of APs through a Simple Network Management Protocol (SNMP) or a network equipment configuration management protocol (NETCONF), wherein the configuration information comprises network configuration with the highest network health score.

In addition, the present application also provides a communication apparatus, as shown in fig. 6, the communication apparatus 600 may be used to implement the method described in the above method embodiment, and specifically, refer to the description in the above method embodiment. The communication device 600 may be a chip, a network device (e.g., a base station).

The communication device 600 includes one or more processors 601. The processor 601 may be a general purpose processor, a special purpose processor, or the like. For example, a baseband processor, or a central processor. The baseband processor may be used to process communication protocols and communication data, and the central processor may be used to control a device (e.g., a base station, a terminal, or a chip, etc.), execute a software program, and process data of the software program. The apparatus may include a transceiving unit to enable input (reception) and output (transmission) of signals. For example, the apparatus may be a chip, and the transceiving unit may be an input and/or output circuit of the chip, or a communication interface. The chip can be used for terminal equipment or network equipment (such as a base station). As another example, the apparatus may be a terminal device or a network device (e.g., a base station), and the transceiver unit may be a transceiver, a radio frequency chip, or the like.

Optionally, in one design, the processor 601 may also include instructions 603, which may be executed on the processor, so that the communication device 600 performs the method described in the above method embodiment.

In yet another possible design, the communication apparatus 600 may also include a circuit, which may implement the functions of the network device or the terminal device in the foregoing method embodiments.

In yet another possible design, the communication device 600 may include one or more memories 602 having instructions 604 stored thereon, which are executable on the processor to cause the communication device 600 to perform the methods described in the above method embodiments. Optionally, the memory may further store data therein. Instructions and/or data may also be stored in the optional processor. For example, the one or more memories 602 may store the moving active area described in the above embodiments, or the related parameters or tables and the like referred to in the above embodiments. The processor and the memory may be provided separately or may be integrated together.

In yet another possible design, the communication device 600 may further include a transceiver 605 and an antenna 606, or a communication interface. The transceiver 605 may be referred to as a transceiver, a transceiving circuit, a transceiver, or the like, and is used for implementing transceiving functions of the apparatus through the antenna 606. The communication interface (not shown) may be used for communication between a core network device and a network device, or between a network device and a network device. Alternatively, the communication interface may be an interface for wired communication, such as an interface for fiber-optic communication.

The processor 601 may be referred to as a processing unit and controls devices (such as a terminal or a base station).

In addition, since the transceiver 605 performs transmission or reception under the control of the processing unit (the processor 601) in the embodiment of the present application, the transmission or reception may also be described as being performed by the processing unit (the processor 601) in the embodiment of the present application, which does not affect the understanding of the solution by those skilled in the art.

The terminal device and the network device in the above-mentioned various apparatus embodiments may completely correspond to the terminal device or the network device in the method embodiment, and the corresponding module or unit performs the corresponding steps, for example, when the apparatus is implemented in the form of a chip, the receiving unit may be an interface circuit of the chip for receiving signals from other chips or apparatuses. The above unit for transmitting is an interface circuit of the apparatus for transmitting a signal to other apparatuses, for example, when the apparatus is implemented in the form of a chip, the transmitting unit is an interface circuit of the chip for transmitting a signal to other chips or apparatuses.

It should be understood that the processor in the embodiments of the present application may be a CPU, and the processor may also be other general purpose processors, DSPs, ASICs, FPGAs, or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like.

It will also be appreciated that the memory in the embodiments of the subject application can be either volatile memory or nonvolatile memory, or can include both volatile and nonvolatile memory. The non-volatile memory may be a read-only memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable PROM (EEPROM), or a flash memory. Volatile memory can be Random Access Memory (RAM), which acts as external cache memory. By way of example, but not limitation, many forms of Random Access Memory (RAM) are available, such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), Enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM), and direct bus RAM (DR RAM).

The network device in the above-mentioned various apparatus embodiments may completely correspond to the network device in the method embodiment, and the corresponding steps are performed by corresponding modules or units, for example, when the apparatus is implemented in the form of a chip, the receiving unit may be an interface circuit of the chip for receiving signals from other chips or apparatuses. The above unit for transmitting is an interface circuit of the apparatus for transmitting a signal to another apparatus, for example, when the apparatus is implemented in the form of a chip, the transmitting unit is an interface circuit of the chip for transmitting a signal to another chip or apparatus.

It should be understood that, in the various embodiments of the present application, the sequence numbers of the above-mentioned processes do not mean the execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

In the several embodiments provided in the present application, it should be understood that the disclosed system, communication device and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one position, or may be distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.

The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method for configuring network resources, the method comprising:

acquiring detection data of a plurality of network devices, wherein the detection data comprises air interface data of the network devices;

obtaining path loss among the network devices according to the detection data of the network devices;

performing network simulation through a neural network algorithm to obtain a plurality of network configurations;

obtaining a plurality of network health scores, wherein the plurality of network health scores comprise a network health score corresponding to at least one of the plurality of network configurations, and wherein the plurality of network configurations are determined according to path loss among the plurality of network devices;

and configuring the plurality of network devices according to network configuration corresponding to a target network health score, wherein the target network health score is a network health score which meets preset conditions of the network health scores.

2. The method of claim 1, wherein the detection data of the plurality of network devices comprises state information and neighbor network device information corresponding to the plurality of network devices.

3. The method of claim 1 or 2, wherein obtaining a plurality of network health scores comprises:

acquiring a first network configuration through path loss among the plurality of network devices, and acquiring a first network health score corresponding to the first network configuration according to the neural network algorithm and the deep learning algorithm;

updating the first network configuration through a neural network algorithm according to the priority of the network equipment to obtain a second network configuration;

and obtaining a corresponding second network health score of the second network configuration according to the neural network algorithm and the deep learning algorithm.

4. The method of claim 3, wherein the network health score is associated with interference conflicts between the plurality of network devices; and/or, the network health score is associated with network load, user communication delay or packet loss data of the plurality of network devices.

5. The method of claim 4, wherein the network configuration comprises at least one of channel, bandwidth, or power configuration information of the plurality of network devices.

6. The method according to claim 1 or 2, wherein the acquiring the detection data of the plurality of network devices specifically includes:

receiving detection data sent by a plurality of network devices; or, receiving detection data of a plurality of network devices transparently transmitted by at least one intermediate forwarding device; or, accessing a plurality of network devices to obtain the detection data of the plurality of network devices.

7. The method of any one of claims 1, 2, 4, or 5, wherein configuring the plurality of network devices according to the network configuration corresponding to the target network health score comprises:

and sending configuration information to the plurality of network devices through a Simple Network Management Protocol (SNMP) or a network device configuration management protocol (NETCONF), wherein the configuration information comprises network configuration corresponding to the target network health score.

8. An apparatus for configuring network resources, the apparatus comprising:

the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring detection data of a plurality of network devices, and the detection data comprises air interface data of the network devices;

the processing module is used for obtaining the path loss among the plurality of network devices according to the detection data of the plurality of network devices; performing network simulation through a neural network algorithm to obtain a plurality of network configurations; obtaining a plurality of network health scores, wherein the plurality of network health scores comprise a network health score corresponding to at least one of the plurality of network configurations, and wherein the plurality of network configurations are determined according to path loss among the plurality of network devices;

and the configuration module is used for configuring the plurality of network devices by network configuration corresponding to the target network health scores, wherein the target network health scores are the network health scores meeting preset conditions of the network health scores in the plurality of network health scores.

9. The apparatus of claim 8, wherein the detection data of the plurality of network devices comprises state information and neighbor network device information corresponding to the plurality of network devices.

10. The apparatus according to claim 8 or 9, wherein the processing module is specifically configured to:

11. The apparatus of claim 10, wherein the network health score is associated with interference conflicts between the plurality of network devices; and/or the network health score is associated with network load, user communication delay or packet loss data of the plurality of network devices.

12. The apparatus of claim 11, wherein the network configuration comprises at least one of configuration information of channel, bandwidth, or power of the plurality of network devices.

13. The apparatus according to claim 8 or 9, wherein the obtaining module is specifically configured to:

14. The apparatus according to any one of claims 8, 9, 11 or 12, wherein the configuration module is specifically configured to:

15. A communication apparatus, characterized in that the communication apparatus comprises: at least one processor, a memory;

the at least one memory stores program instructions and data, the program instructions being executable on the at least one processor, the at least one processor executing the program instructions in the memory to cause the communications device to perform the method of configuring a network resource of any of claims 1 to 7.

16. A computer-readable storage medium having stored therein instructions which, when run on a device, cause the device to perform the method of configuring a network resource of any one of claims 1-7.