5G communication network base station node management system based on cloud computing

Abstract

The invention discloses a 5G communication network base station node management system based on cloud computing, which relates to the technical field of communication networks and comprises a distributed base station node cluster, a cloud resource computing unit, an edge computing unit and a resource scheduling unit. According to the invention, through setting the distributed base station node cluster, demand evaluation is carried out according to the pedestrian flow data and the traffic flow data of the distribution area, the 5G communication network base stations are densely deployed to improve the total capacity of the network, and the operation data of all the 5G communication network base stations in the area range are acquired; three-dimensional pooling management is performed on base station calculation, storage and spectrum resources, a traffic prediction model is constructed based on historical data, resource demands of real-time traffic are predicted, calculation, storage and network resources are dynamically allocated to base station nodes based on resource demand values, communication resource links are obtained, and corresponding communication data of the base station nodes are obtained. Link transmission evaluation is carried out based on communication data, and the safety and stability in the transmission process are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of communication networks, and particularly to a 5G communication network base station node management system based on cloud computing. Background Art

[0002] The 5G communication network base station node is a key component in the 5G wireless communication system, responsible for providing wireless access services, forwarding data, and supporting communication between user equipment (such as mobile phones, Internet of Things devices, etc.) and the network. In the 5G network, the functions and architectures of the base station nodes have changed significantly compared to 4G to support higher speeds, lower latency, and larger capacities; The base station node provides wireless signal coverage and access services to ensure that user equipment can communicate with the network. In 5G, the base station provides higher transmission rates and lower latency through new technologies; at the same time, with the gradual maturity of vehicle networking technology and the advent of the big data era, more and more vehicles have intelligent services such as autonomous driving and environmental perception. These services have a sharp increase in communication resource requirements, resulting in a decline in the utilization efficiency of the spectrum resources of the vehicle networking. The existing network base station management requirements do not consider the traffic usage requirements of vehicles, which is likely to cause network latency in the actual application process; In view of the above technical defects, a solution is proposed. Summary of the Invention

[0003] The purpose of the present invention is to: by setting up a distributed base station node cluster, conduct demand assessment based on the pedestrian flow data and vehicle flow data in the distribution area, densely deploy 5G communication network base stations to improve the total capacity of the network, and obtain the operation data of all 5G communication network base stations within the regional scope, perform three-dimensional pooling management on the computing, storage, and spectrum resources of the base stations, and conduct link transmission assessment based on communication data, which can not only meet the traffic demand but also ensure the security and stability during the transmission process.

[0004] To achieve the above purpose, the present invention adopts the following technical solutions: a 5G communication network base station node management system based on cloud computing, including a distributed base station node cluster, a cloud resource computing unit, an edge computing unit, and a resource scheduling unit; The distributed base station node cluster is composed of multiple radio access units supporting the 5G NR standard, conducts demand assessment based on the pedestrian flow data and vehicle flow data in the distribution area, and densely deploys 5G communication network base stations according to the demand assessment results to improve the total capacity of the network; The cloud resource computing unit includes a resource management module and a demand acquisition module. The resource management module is used to obtain the operation data of all 5G communication network base stations within the regional scope and perform three-dimensional pooling management on the computing, storage, and spectrum resources of the base stations; The demand acquisition module is used to obtain real-time vehicle flow data and real-time pedestrian flow data within a region, and at the same time obtain the peak factor within the region. Based on historical data, a traffic prediction model is constructed to predict the resource demand for real-time traffic, and the resource demand value is sent to the resource scheduling unit; The resource scheduling unit is used to obtain and process the resource demand value, and dynamically allocate computing, storage, and network resources to each base station node based on the resource demand value to obtain each communication resource link; The edge computing node is used to obtain each communication resource link, and obtain the communication data of the corresponding base station nodes. Based on the communication data, link transmission evaluation is performed, local traffic shaping and fault pre-judgment are executed according to the evaluation results, and a warning instruction is generated according to the fault pre-judgment result.

[0005] Furthermore, the specific process of densely deploying 5G communication network base stations according to the demand evaluation results is as follows: S101. Obtain the distribution area of the 5G communication network base station and calculate the area of the region; S102. Obtain the normal pedestrian flow and normal vehicle flow in the distribution area. The pedestrian flow data is specifically the maximum pedestrian flow, normal pedestrian flow, and their corresponding time periods, and the vehicle flow data is specifically the maximum vehicle flow, normal vehicle flow, and their corresponding time periods; S103. Calculate the maximum traffic demand according to the maximum pedestrian flow data and maximum vehicle flow data, set the large traffic demand area according to the corresponding time period, set the number of 5G communication network base stations according to the maximum traffic demand, and perform uniform density distribution setting according to the area of the region to obtain the coordinates of each traffic base station node; S104. Calculate the normal traffic demand according to the normal pedestrian flow data and normal vehicle flow data, set the normal traffic demand area according to the corresponding time period, and select normal base station nodes and peak standby base station nodes according to the regional distribution in the coordinates of each traffic base station node.

[0006] Furthermore, the base station node is also provided with a breathing control module, which is used for the adaptive adjustment mechanism according to the state switching threshold, and at the same time follows the power coordination control protocol with neighboring base stations.

[0007] Furthermore, the specific process of obtaining the resource demand value is as follows: S201. Obtain historical data, which is historical vehicle flow data, historical pedestrian flow data, and corresponding time nodes. Calculate the real-time traffic demand according to the base station traffic demand calculation formula, and integrate the real-time traffic demand and time nodes as training samples. According to the ratio of 8:2, the generated training samples are divided into a training set and a test set; The specific formula for calculating the base station traffic demand is: Base station traffic demand = (real-time vehicle flow data + real-time pedestrian flow data) × average traffic per user × peak factor; S202. Download the weight file and load it onto the corresponding network to initialize the migration network parameters, and determine the number of hidden layer nodes of the BP neural network model according to the number of samples in the training set; S203. Modify the last fully connected layer of the network, keep the input unchanged, set the output to the resource demand value, initialize the weights of the last layer, use the gradient descent algorithm for learning, and use fixed-step decay to optimize the training parameters, and retrain the entire network to obtain the traffic prediction model; S204. During the training process, randomly and non-repeatedly extract small batches of training samples from the training set. After extracting all the training samples in the training set, it is a training cycle. Iterate to a certain number of cycles to complete the training, and then use the test set to evaluate the effect of the traffic prediction model; S205. Substitute the real-time vehicle flow data and the real-time pedestrian flow data into the traffic prediction model to obtain the resource demand value.

[0008] Furthermore, the specific process of obtaining each communication resource link is as follows: S301. Obtain the status information of each communication base node, and generate a base station status prediction matrix through the digital twin engine; S302. Use the federated learning engine to aggregate the multi-base station local models to generate a global policy; S303. Solve the constrained optimization problem through the resource scheduling unit: , where U i is the user utility function, N is the number of users, that is, the sum of the real-time vehicle flow data and the real-time pedestrian flow data, r i is the preset allocated resource amount, and R total is the maximum traffic limit value of the base station.

[0009] Furthermore, the specific process of evaluating the link transmission based on the communication data is as follows: S401. Collect the communication data of the base station nodes. The communication data includes the signal strength Ei, the traffic value Qi, and the signal-to-noise ratio dBi. Calculate the interference influence index Ui according to the communication data: , i = 1, 2, 3,..., n, where n is the number of communication data, and among them is the standard signal strength, is the standard traffic value, is the standard signal-to-noise ratio, α, β, and γ are preset proportionality coefficients, and the communication quality of the link is evaluated through the interference influence index. The larger the interference influence index, the worse the communication quality of the link. Conversely, the smaller the interference influence index, the better the communication quality of the link; S402. Collect the link operation stability information, where the link operation stability information includes the transmitted signal power Wi, the packet loss rate Hi, and the throughput Di; S403. Obtain the interference influence index and the link operation stability information, and calculate the communication link operation fluctuation coefficient Yi according to the following formula: , where e1, e2, and e3 are preset weight coefficients, and the communication link operation fluctuation coefficient is used to reflect the stability of the communication link; S404. Obtain the preset fluctuation judgment threshold. If the communication link operation fluctuation coefficient is less than the fluctuation judgment threshold, the link is marked as an available link; If the communication link operation fluctuation coefficient is greater than or equal to the fluctuation judgment threshold, the link is marked as a faulty link. When the number of faulty links is greater than the preset fault threshold, a warning instruction is generated.

[0010] In summary, due to the adoption of the above technical solutions, the beneficial effects of the present invention are: The 5G communication network base station node management system based on cloud computing sets up a distributed base station node cluster, densely deploys 5G communication network base stations according to the pedestrian flow data and vehicle flow data in the distribution area for demand assessment to improve the total network capacity, obtains the operation data of all 5G communication network base stations within the regional scope, performs three-dimensional pooling management on the computing, storage, and spectrum resources of the base stations, and simultaneously constructs a traffic prediction model based on historical data to predict the resource requirements of real-time traffic. Based on the resource demand values, computing, storage, and network resources are dynamically allocated to each base station node to obtain each communication resource link, the communication data of the corresponding base station nodes is obtained, and link transmission evaluation is performed based on the communication data to ensure the security and stability during the transmission process. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 Shows the overall module structure diagram of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0012] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0013] Embodiment AsFigure 1 As shown in Figure 1 , the 5G communication network base station node management system based on cloud computing includes a distributed base station node cluster, a cloud resource computing unit, an edge computing unit, and a resource scheduling unit; The distributed base station node cluster is composed of multiple radio access units that support the 5G NR standard, and conducts demand assessment based on the pedestrian flow data and vehicle flow data in the distribution area. According to the demand assessment results, 5G communication network base stations are densely deployed to improve the total capacity of the network; The specific process of densely deploying 5G communication network base stations according to the demand assessment results is as follows: S101. Obtain the distribution area of the 5G communication network base station and calculate the area of the region; S102. Obtain the normal pedestrian flow and normal vehicle flow in the distribution area. The pedestrian flow data specifically includes the maximum pedestrian flow, normal pedestrian flow, and their corresponding time periods. The vehicle flow data specifically includes the maximum vehicle flow, normal vehicle flow, and their corresponding time periods; S103. Calculate the maximum traffic demand based on the maximum pedestrian flow data and maximum vehicle flow data, set the large traffic demand area according to the corresponding time period, set the number of 5G communication network base stations according to the maximum traffic demand, and perform uniform density distribution setting according to the area of the region to obtain the coordinates of each traffic base station node; S104. Calculate the normal traffic demand based on the normal pedestrian flow data and normal vehicle flow data, set the normal traffic demand area according to the corresponding time period, and select normal base station nodes and peak standby base station nodes from the coordinates of each traffic base station node according to the regional distribution.

[0014] The base station node is also provided with a breathing control module, which is used for the adaptive adjustment mechanism according to the state switching threshold, and at the same time follows the power coordination control protocol with neighboring base stations.

[0015] The cloud resource computing unit includes a resource management module and a demand acquisition module. The resource management module is used to obtain the operation data of all 5G communication network base stations within the regional scope and perform three-dimensional pooling management of the base station computing, storage, and spectrum resources; The demand acquisition module is used for the real-time vehicle flow data and real-time pedestrian flow data within the regional scope, and at the same time obtains the peak factor within the region, constructs a traffic prediction model based on historical data, predicts the resource demand for real-time traffic, and sends the resource demand value to the resource scheduling unit; The specific process of obtaining the resource demand value is as follows: S201. Obtain historical data, including historical vehicle flow data, historical pedestrian flow data, and corresponding time nodes. Calculate the real-time traffic demand according to the base station traffic demand calculation formula, and integrate the real-time traffic demand and time nodes as training samples. Divide the generated training samples into a training set and a test set according to a ratio of 8:2. The base station traffic demand calculation formula is specifically: Base station traffic demand = (Real-time vehicle flow data + Real-time pedestrian flow data) × Average traffic per user × Peak factor. S202. Download the weight file and load it onto the corresponding network to initialize the transfer network parameters, and determine the number of hidden layer nodes of the BP neural network model according to the number of samples in the training set. S203. Modify the last fully connected layer of the network, keep the input unchanged, set the output to the resource demand value, initialize the weights of the last layer, use the gradient descent algorithm for learning, and adopt fixed-step decay to optimize the training parameters. Retrain the entire network to obtain the traffic prediction model. S204. During the training process, randomly and non-repeatedly extract small batches of training samples from the training set. Completing the extraction of all training samples in the training set is one training cycle. Iterate to a certain number of cycles to complete the training, and then use the test set to evaluate the effect of the traffic prediction model. S205. Substitute the real-time vehicle flow data and real-time pedestrian flow data into the traffic prediction model to obtain the resource demand value.

[0016] The resource scheduling unit is used to obtain and process the resource demand value, and dynamically allocate computing, storage, and network resources to each base station node based on the resource demand value to obtain each communication resource link. The specific process of obtaining each communication resource link is as follows: S301. Obtain the status information of each communication base node, and generate a base station status prediction matrix through the digital twin engine. S302. Use the federated learning engine to aggregate multi-base station local models to generate a global policy. S303. Solve the constrained optimization problem through the resource scheduling unit: , where U i is the user utility function, N is the number of users, that is, the sum of the real-time vehicle flow data and real-time pedestrian flow data, r i is the preset allocated resource amount, and R total is the maximum traffic limit value of the base station.

[0017] The edge computing node is used to obtain each communication resource link, obtain the communication data of the corresponding base station nodes, perform link transmission evaluation based on the communication data, execute local traffic shaping and fault pre-judgment according to the evaluation results, and generate a warning instruction according to the fault pre-judgment result.

[0018] The specific process of performing link transmission evaluation based on communication data is as follows: S401. Collect the communication data of the base station node. The communication data includes signal strength Ei, traffic value Qi, and signal-to-noise ratio dBi. Calculate the interference influence index Ui according to the communication data: , where i = 1, 2, 3,..., n, and n is the number of communication data. Among them is the standard signal strength, is the standard traffic value, is the standard signal-to-noise ratio, and α, β, and γ are preset proportionality coefficients. Evaluate the communication quality of the link through the interference influence index. The larger the interference influence index, the worse the communication quality of the link. On the contrary, the smaller the interference influence index, the better the communication quality of the link; S402. Collect the link operation stability information. The link operation stability information includes transmit signal power Wi, packet loss rate Hi, and throughput Di; S403. Obtain the interference influence index and the link operation stability information, and calculate the communication link operation fluctuation coefficient Yi according to the following formula: , where e1, e2, and e3 are preset weight coefficients. The communication link operation fluctuation coefficient is used to reflect the stability of the communication link; S404. Obtain the preset fluctuation judgment threshold. If the communication link operation fluctuation coefficient is less than the fluctuation judgment threshold, the link is marked as an available link; If the communication link operation fluctuation coefficient is greater than or equal to the fluctuation judgment threshold, the link is marked as a faulty link. When the number of faulty links is greater than the preset fault threshold, a warning instruction is generated.

[0019] By setting up a distributed base station node cluster, the present invention densely deploys 5G communication network base stations according to the demand evaluation based on the pedestrian flow data and vehicle flow data in the distribution area to improve the total network capacity, obtains the operation data of all 5G communication network base stations within the regional scope, performs three-dimensional pooling management of the base station computing, storage, and spectrum resources, and at the same time constructs a traffic prediction model based on historical data to predict the resource requirements of real-time traffic, dynamically allocates computing, storage, and network resources to each base station node based on the resource demand value, obtains each communication resource link, obtains the communication data of the corresponding base station nodes, and performs link transmission evaluation based on the communication data, which can not only meet the traffic demand but also ensure the security and stability during the transmission process.

[0020] The setting of the threshold value is for the convenience of comparison. Regarding the size of the threshold value, it depends on the amount of sample data and the number of base values set by those skilled in the art for each group of sample data; as long as the proportional relationship between the parameter and the quantized value is not affected.

[0021] The above formulas are all dimensionless and take their numerical calculations. The formulas are obtained by collecting a large amount of data for software simulation to get a formula closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation. The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution and inventive concept of the present invention, makes equivalent substitutions or changes, and should be covered within the protection scope of the present invention.

Claims

1. A 5G communication network base station node management system based on cloud computing, characterized in that: It includes a distributed base station node cluster, a cloud resource computing unit, an edge computing unit, and a resource scheduling unit; The distributed base station node cluster consists of multiple wireless access units that support the 5G NR standard. It conducts demand assessment based on the pedestrian and vehicle traffic data in the distribution area, and densely deploys 5G communication network base stations based on the demand assessment results to increase the total capacity of the network. The cloud resource computing unit includes a resource management module and a demand acquisition module. The resource management module is used to obtain the operating data of all 5G communication network base stations within the region and to perform three-dimensional pooling management of base station computing, storage, and spectrum resources. The demand acquisition module is used to obtain the real-time vehicle flow data and real-time pedestrian flow data within the area, and at the same time obtain the peak factor in the area, build a flow prediction model based on historical data, predict the resource demand of real-time flow, and obtain the resource demand value and send it to the resource scheduling unit; The resource scheduling unit is used to obtain and process resource demand values, dynamically allocate computing, storage and network resources to each base station node based on the resource demand values, and obtain each communication resource link; The edge computing node is used to obtain each communication resource link and the communication data of each corresponding base station node, perform link transmission evaluation based on the communication data, perform local traffic shaping and fault pre-judgment according to the evaluation results, and generate early warning instructions based on the fault pre-judgment results.

2. The 5G communication network base station node management system based on cloud computing according to claim 1 is characterized in that: The specific process of densely deploying 5G communication network base stations based on the demand assessment results is as follows: S101, obtaining the distribution area of ​​5G communication network base stations and calculating the area of ​​the area; S102, obtaining normal pedestrian flow and normal vehicle flow in the distribution area, wherein the pedestrian flow data specifically includes the maximum pedestrian flow and normal pedestrian flow and their corresponding time segments, and the vehicle flow data specifically includes the maximum vehicle flow and normal vehicle flow and their corresponding time segments; S103, calculating the maximum flow demand according to the maximum pedestrian flow data and the maximum vehicle flow data, and setting the high flow demand area according to the corresponding time segment, setting the number of 5G communication network base stations according to the maximum flow demand, and setting the average density distribution according to the area to obtain the coordinates of each flow base station node; S104. Calculate normal traffic demand based on normal pedestrian traffic data and normal vehicle traffic data, set normal traffic demand area according to its corresponding time segment, and select normal base station nodes and peak standby base station nodes in the coordinates of each traffic base station node according to the regional distribution.

3. The 5G communication network base station node management system based on cloud computing according to claim 1, characterized in that: The base station node is also provided with a breathing control module, which is used to adaptively adjust the mechanism according to the state switching threshold and follow the power coordination control protocol with the adjacent base stations.

4. The 5G communication network base station node management system based on cloud computing according to claim 1, characterized in that: The specific process of obtaining the resource demand value is as follows: S201, obtaining historical data, including historical vehicle flow data and historical pedestrian flow data and corresponding time nodes, calculating real-time flow demand according to the base station flow demand calculation formula, integrating the real-time flow demand and time node crop training samples, and dividing the generated training samples into a training set and a test set according to a ratio of 8:2; S202, download the weight file and load it to the corresponding network to initialize the migration network parameters, and determine the number of hidden layer nodes of the BP neural network model according to the number of samples in the training set; S203, modify the last fully connected layer of the network, keep the input unchanged, set the output to the resource demand value, initialize the weight of the last layer, use the gradient descent algorithm for learning, and use fixed step size decay to optimize the training parameters, retrain the entire network, and obtain a traffic prediction model; S204, during the training process, randomly and non-repeatedly extract small batches of training samples from the training set, extracting all the training samples in the training set as one training cycle, iterate to a certain cycle to complete the training, and then use the test set to evaluate the effect of the traffic prediction model; S205: Substitute the real-time vehicle flow data and the real-time pedestrian flow data into the flow prediction model to obtain the resource demand value.

5. The 5G communication network base station node management system based on cloud computing according to claim 1, characterized in that: The specific process of obtaining each communication resource link is as follows: S301. Obtain status information of each communication base node, and generate a base station status prediction matrix through a digital twin engine; S302, using a federated learning engine to aggregate local models of multiple base stations to generate a global strategy; S303, solving the constrained optimization problem through the resource scheduling unit: , where U i is the user utility function, N is the number of users, i.e. the sum of real-time vehicle flow data and real-time pedestrian flow data, r i is the preset amount of allocated resources, R total is the maximum flow limit value of the base station.

6. The 5G communication network base station node management system based on cloud computing according to claim 1, characterized in that: The specific process of link transmission evaluation based on communication data is as follows: S401, collect communication data of the base station node, the communication data includes signal strength Ei, flow value Qi and signal-to-noise ratio dBi, and calculate interference impact index Ui according to the communication data: , i=1, 2, 3, ..., n, n is the number of communication data, where is the standard signal strength, is the standard flow value, is the standard signal-to-noise ratio, α, β and γ are preset proportional coefficients, and the communication quality of the link is evaluated by the interference impact index; S402, collecting link operation stability information, where the link operation stability information includes transmission signal power Wi, packet loss rate Hi and throughput Di; S403, obtaining the interference impact index and link operation stability information, and calculating the communication link operation fluctuation coefficient Yi according to the following formula: , where e1, e2 and e3 are preset weight coefficients, and the communication link operation fluctuation coefficient is used to reflect the stability of the communication link; S404, obtaining a preset fluctuation judgment threshold, and if the communication link operation fluctuation coefficient is less than the fluctuation judgment threshold, marking the link as an available link; If the communication link operation fluctuation coefficient is greater than or equal to the fluctuation judgment threshold, the link is marked as a faulty link. When the number of faulty links is greater than the preset fault threshold, an early warning instruction is generated.

Images