An intelligent optimization system and method based on 5G micro-cellular base station

Abstract

The present invention discloses an intelligent optimization system and method based on 5G microcellular pico base stations, and specifically relates to the technical field of 5G microcellular pico base station management. Based on the base station coverage, base station signal quality, base station capacity and packet loss rate, a base station network performance evaluation index is obtained; based on the base station voltage and equipment temperature, a base station equipment operation fault evaluation index is obtained; the network communication demand coefficient of the geographical area and the network communication demand coefficient of the time period are obtained; based on the network communication demand coefficient of each time period and the base station network performance evaluation index of each time period, the time load balancing optimization coefficient of each time period is calculated, and the base station configuration is adjusted in real time based on the time load balancing optimization coefficient of each time period; based on the comprehensive network performance anomaly index of each geographical area and the network communication demand coefficient of each geographical area, the regional load balancing optimization coefficient of each geographical area is calculated.

Description

Technical Field

[0001] The present invention relates to the technical field of 5G micro-cellular pico base station management, and more specifically, the present invention relates to an intelligent optimization system, method and system based on 5G micro-cellular pico base stations. Background Art

[0002] The operating principle of 5G micro-cell pico base stations mainly involves the reception and transmission of signals. Specifically, the pico base station receives signals from mobile phones. When the mobile phone makes a call, sends text messages or surfs the Internet, it sends wireless signals to nearby base stations. These signals will be received and decoded by the pico base station to obtain the information sent by the mobile phone user and transmit this information to the core network; in terms of transmission, the pico base station will encode and modulate the information from the core network and then send it out via radio waves. These radio waves will cover a certain range of areas, forming a so-called "cell" to transmit signals to nearby mobile phones. When the mobile phone receives these signals, it will decode and demodulate them to convert the signals into voice, text or images that people understand.

[0003] However, the current problems with the operation of 5G microcellular base stations mainly include: with the increase in the number of users, the capacity of the microcellular base stations may not be able to meet the demand, and communication congestion is prone to occur; in a multi-base station environment, there may be interference between the microcellular base stations, affecting the communication quality; there is a lack of monitoring of the operating status of the base stations, resulting in failure to timely discover abnormal base station operations; there is a lack of load optimization of base station network resources from the time dimension and geographical area dimension, resulting in uneven distribution of network resources in the time dimension and space dimension. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, the present invention provides an intelligent optimization system and method based on 5G micro-cellular base stations, which monitors the operating status of the base stations and obtains the operating performance of the base stations to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solution: an intelligent optimization system based on 5G micro-cellular pico base station, comprising:

[0006] The base station performance collection module is used to collect the network performance and operation performance of the base station and transmit the collected data to the base station status analysis module. The network performance includes signal coverage, signal quality, capacity and throughput, delay and packet loss rate, and security; the operation performance includes base station equipment temperature and voltage fluctuation coefficient;

[0007] The base station status analysis module is used to analyze the collected data and obtain the base station network performance evaluation index based on the base station coverage, base station signal quality, base station capacity and packet loss rate; and obtain the base station equipment operation fault evaluation index based on the base station voltage and equipment temperature;

[0008] The data partitioning module is used to divide the collected data into several intervals according to the area of ​​the geographical area, i represents the number of the geographical area, the number of the geographical areas is recorded as n, and j represents the number of the time period;

[0009] A demand coefficient calculation module, used for obtaining the network communication demand coefficient qdi of the i-th geographical area;

[0010] The intelligent optimization decision module is used to generate a base station optimization strategy, including a base station equipment optimization unit and a geographical area load balancing optimization unit. The base station equipment optimization unit optimizes the base station equipment based on the base station network performance evaluation index and the base station equipment operation fault evaluation index; the geographical area base station optimization unit optimizes the base station distribution and quality in the geographical area based on the comprehensive network performance anomaly index ZPi.

[0011] Preferably, the base station performance description parameters are obtained through testing, and the base station performance description parameters include signal coverage, signal quality, packet loss rate, and transmission speed. Get the base station network performance evaluation index wp, where fg, xz, dbl, and cs represent the signal coverage, signal quality, packet loss rate, and transmission rate of the base station, respectively. 0≤δ≤1, 0≤θ≤1, and δ+θ=1. δ and θ are weights, and their specific values ​​are adjusted and set by the user.

[0012] Preferably, the voltage and temperature of the base station are monitored to obtain the voltage dispersion coefficient, power dispersion coefficient, maximum device temperature value, and average device temperature value of the base station; The base station equipment operation fault evaluation index gp of each base station is obtained, where dy_dis, wd_max, wd_avg, and wd0 represent the voltage dispersion coefficient, the maximum equipment temperature, the average equipment temperature, and the preset equipment temperature of the base station, respectively; and ε1 and ε2 represent the proportional coefficients of each item, respectively.

[0013] Preferably, the comprehensive network performance anomaly index of a geographical area is obtained in the following manner:

[0014] Assume that there are k base stations in the i-th geographical area, and the base station network performance evaluation index and base station equipment operation failure evaluation index of the s-th base station are recorded as wp_s and gp_s respectively;

[0015] Compare the obtained base station network performance evaluation index with the preset value thb1, divide the base stations into base stations with normal network performance and base stations with abnormal network performance, and obtain the proportion of base stations with abnormal network performance zb1 in each geographical area;

[0016] Compare the obtained base station equipment operation fault evaluation index with the preset value thb2, divide the base stations into normal operation base stations and abnormal operation base stations, and obtain the proportion of abnormal operation base stations in each geographical area zb2;

[0017] By formula The comprehensive network performance anomaly index ZPi of the ith geographical area is calculated.

[0018] Preferably, the intelligent optimization decision module includes a geographic area load balancing optimization unit, which obtains a comprehensive network performance anomaly index ZPi for each geographic area based on a joint analysis of the base station network performance evaluation index and the base station equipment operation fault evaluation index, and obtains the regional load balancing optimization coefficient of the geographic area based on the comprehensive network performance anomaly index ZPi of the geographic area.

[0019] Preferably, based on the average value of mobile device density, population density, and data transmission efficiency in each geographic area, the formula The network communication demand coefficient qdi of the ith geographical area is calculated, where ysi, rmi, and sci_avg represent the mobile device density, population density, and data transmission efficiency average of the ith geographical area, respectively; based on the average data transmission efficiency, network load, and throughput in each time period, the formula The network communication demand coefficient tdj of the j-th time period is calculated, where csj_avg, wfj_avg, and tlj_avg represent the average data transmission efficiency, average network load, and average throughput of the base station in the j-th time period, respectively, 0≤ρ1≤1, 0≤ρ2≤1, and ρ1+ρ2=1.0, and ρ1 and ρ2 are weight coefficients.

[0020] Preferably, the average value of the comprehensive network performance anomaly index of the geographical area is obtained, denoted as ZP_avg, and the formula The regional load balancing optimization coefficient Qyi of the i-th geographical area is calculated, and the management personnel adjust the base station performance and operation status of the geographical area based on the regional load balancing optimization coefficient of the geographical area.

[0021] Preferably, the intelligent optimization decision module includes a time load balancing optimization unit, which calculates the time load balancing optimization coefficient of each time period based on the network communication demand coefficient tdj of each time period and the base station network performance evaluation index of each time period, records the network signal evaluation index of all base stations in the jth time period as wpj, and records the average value of the network signal evaluation index of all base stations in m time periods as wpj_avg. The time load balancing optimization coefficient Tyj of each time period is calculated.

[0022] To achieve the above object, the present invention provides the following technical solution: an intelligent optimization method based on 5G micro-cellular pico base station, comprising the following steps:

[0023] Step S001, base station performance collection: used to collect the network performance and operation performance of the base station, and transmit the collected data to the base station status analysis step;

[0024] Step S002, base station status analysis step, is used to analyze the collected data, and obtain the base station network performance evaluation index based on the base station coverage, base station signal quality, base station capacity and packet loss rate; obtain the base station equipment operation fault evaluation index based on the base station voltage and equipment temperature; obtain the comprehensive network performance anomaly index ZPi of each geographical area based on the joint analysis of the base station network performance evaluation index and the base station equipment operation fault evaluation index;

[0025] Step S003, data division step, for dividing the collected data into several intervals according to geographical areas and time periods;

[0026] Step S004, a regional weight coefficient calculation step, based on the mobile device density, population density, and data transmission efficiency average value of each geographical area, obtain the network communication demand coefficient of the ith geographical area; based on the mobile device density, population density, and data transmission efficiency average value of each geographical area, obtain the network communication demand coefficient of the ith geographical area;

[0027] Step S005, base station equipment optimization step: optimizing the base station equipment based on the relationship between the base station network performance evaluation index and the base station equipment operation fault evaluation index and the preset value, and allocating the base station equipment optimization resources;

[0028] Step S006, base station performance optimization step with time period: based on the network communication demand coefficient of each time period and the base station network performance evaluation index of each time period, the time load balancing optimization coefficient of each time period is calculated, and the base station configuration is adjusted in real time based on the time load balancing optimization coefficient of each time period, such as increasing the number of channels and adjusting the antenna direction, to balance the load of each time period and improve network performance;

[0029] Step S007, base station performance optimization step with geographical area: based on the comprehensive network performance anomaly index of each geographical area and the network communication demand coefficient of each geographical area, the regional load balancing optimization coefficient of each geographical area is calculated.

[0030] Technical effects and advantages of the present invention:

[0031] (1) The intelligent optimization system and method based on 5G micro-cellular base stations provided by the present invention collect the network performance and operating performance of the base stations and analyze them to obtain the base station network performance evaluation index wp and the base station equipment operation fault evaluation index gp. Based on the analysis results, the faulty base station equipment can be quickly located, helping managers to optimize the base station equipment in a timely manner.

[0032] (2) The intelligent optimization system and method based on 5G microcellular base stations provided by the present invention calculates the time load balancing optimization coefficient of each time period based on the network communication demand coefficient of each time period and the base station network performance evaluation index of each time period, and adjusts the base station configuration in real time based on the time load balancing optimization coefficient of each time period, so as to help management personnel to timely understand the load status of the network in each time period, and adjust the configuration of the base station accordingly to achieve load balancing in the time dimension.

[0033] (3) The intelligent optimization system and method based on 5G micro-cellular base stations provided by the present invention calculates the regional load balancing optimization coefficient of each geographical area based on the comprehensive network performance anomaly index of each geographical area and the network communication demand coefficient of each geographical area, so as to help management personnel to timely understand the load status of the network in each geographical area and adjust the configuration of the base station accordingly to achieve load balancing in the spatial dimension. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 This is a structural block diagram of the intelligent optimization system based on 5G micro-cellular base stations of the present invention.

[0035] Figure 2 This is a structural block diagram of the intelligent optimization decision module of the present invention.

[0036] Figure 3 This is a flow chart of the intelligent optimization method based on 5G micro-cellular base stations of the present invention. DETAILED DESCRIPTION

[0037] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0038] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0039] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the present application, its application, or uses.

[0040] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered as part of the specification.

[0041] Example 1

[0042] See also Figure 1 The intelligent optimization system structure block diagram of the micro-cellular pico base station is provided in the embodiment of the present invention. Figure 1 An intelligent optimization system based on a 5G micro-cellular pico base station is shown, comprising:

[0043] The base station performance collection module is used to collect the network performance and operation performance of the base station and transmit the collected data to the base station status analysis module. The network performance includes signal coverage, signal quality, capacity and throughput, delay and packet loss rate, and security; the operation performance includes base station equipment temperature and voltage fluctuation coefficient;

[0044] The base station status analysis module is used to analyze the collected data and obtain the base station network performance evaluation index based on the base station coverage, base station signal quality, base station capacity and packet loss rate; and obtain the base station equipment operation fault evaluation index based on the base station voltage and equipment temperature;

[0045] The data partitioning module is used to divide the collected data into several intervals according to the area of ​​the geographical area, i represents the number of the geographical area, the number of the geographical areas is recorded as n, and j represents the number of the time period;

[0046] A demand coefficient calculation module, used for obtaining the network communication demand coefficient qdi of the i-th geographical area;

[0047] The intelligent optimization decision module is used to generate a base station optimization strategy, including a base station equipment optimization unit and a geographical area load balancing optimization unit. The base station equipment optimization unit optimizes the base station equipment based on the base station network performance evaluation index and the base station equipment operation fault evaluation index; the geographical area base station optimization unit optimizes the base station distribution and quality in the geographical area based on the comprehensive network performance anomaly index ZPi.

[0048] Furthermore, the geographic area load balancing optimization unit obtains a comprehensive network performance anomaly index ZPi of each geographic area based on a joint analysis of the base station network performance evaluation index and the base station equipment operation fault evaluation index, and obtains a regional load balancing optimization coefficient of the geographic area based on the comprehensive network performance anomaly index ZPi of the geographic area;

[0049] For example, preset values ​​are set for the base station network performance evaluation index and the base station equipment operation fault evaluation index, and the base station equipment is optimized based on the preset values; the comprehensive network performance anomaly index of each geographical area is evenly distributed, the obtained comprehensive network performance anomaly index ZPi is compared with the preset value, and the base station distribution of the geographical area that does not meet the preset value requirements is adjusted.

[0050] It is necessary to further explain in the embodiment of the present invention that the base station performance description parameters are obtained by testing, and the base station performance description parameters include signal coverage, signal quality, packet loss rate, and transmission speed. Get the base station network performance evaluation index wp, where fg, xz, dbl, and cs represent the signal coverage, signal quality, packet loss rate, and transmission rate of the base station, respectively. 0≤δ≤1, 0≤θ≤1, and δ+θ=1. δ and θ are weights, and their specific values ​​are adjusted and set by the user.

[0051] It is necessary to further explain in the embodiment of the present invention that the voltage and temperature of the base station are monitored to obtain the voltage dispersion coefficient, power dispersion coefficient, maximum value of the equipment temperature, and average value of the equipment temperature of the base station; by formula The base station equipment operation fault evaluation index gp of each base station is obtained, where dy_dis, wd_max, wd_avg, and wd0 represent the voltage dispersion coefficient, the maximum equipment temperature, the average equipment temperature, and the preset equipment temperature of the base station, respectively; and ε1 and ε2 represent the proportional coefficients of each item, respectively.

[0052] It needs to be further explained in the embodiment of the present invention that the comprehensive network performance anomaly index of a geographical area is obtained in the following manner:

[0053] Assume that there are k base stations in the i-th geographical area, and the base station network performance evaluation index and base station equipment operation failure evaluation index of the s-th base station are recorded as wp_s and gp_s respectively;

[0054] Compare the obtained base station network performance evaluation index with the preset value thb1, divide the base stations into base stations with normal network performance and base stations with abnormal network performance, and obtain the proportion of base stations with abnormal network performance zb1 in each geographical area;

[0055] Compare the obtained base station equipment operation fault evaluation index with the preset value thb2, divide the base stations into normal operation base stations and abnormal operation base stations, and obtain the proportion of abnormal operation base stations in each geographical area zb2;

[0056] By formula The comprehensive network performance anomaly index ZPi of the ith geographical area is calculated.

[0057] It needs to be further explained in the embodiment of the present invention that the intelligent optimization decision module includes a geographic area load balancing optimization unit, which calculates the regional load balancing optimization coefficient of each geographic area based on the comprehensive network performance anomaly index of each geographic area and the network communication demand coefficient of each geographic area.

[0058] Based on the average values ​​of mobile device density, population density, and data transmission efficiency in each geographic area, the formula The network communication demand coefficient qdi of the i-th geographical area is calculated, where ysi, rmi, and sci_avg represent the average values ​​of mobile device density, population density, and data transmission efficiency of the i-th geographical area, respectively;

[0059] Get the average value of the comprehensive network performance anomaly index of the geographical area, denoted as ZP_avg, through the formula The regional load balancing optimization coefficient Qyi of the i-th geographical area is calculated, and the management personnel adjust the base station performance and operation status of the geographical area based on the regional load balancing optimization coefficient of the geographical area.

[0060] It is explained that the regional load balancing optimization coefficient of each geographical area is calculated based on the comprehensive network performance anomaly index of each geographical area and the network communication demand coefficient of each geographical area. The regional load balancing optimization coefficient reflects the network load status in the geographical area and the performance of the base station. By real-time monitoring and calculating these coefficients, the operator can timely understand the network load status of each geographical area and adjust the configuration of the base station accordingly to achieve regional load balancing. Specifically, when the comprehensive network performance anomaly index of a certain geographical area is high and the network communication demand coefficient is also high, it means that the network load in the area is heavy and the base station performance cannot meet the demand. At this time, the operator improves the network performance by increasing the number of base stations in the area, improving the performance of base stations, optimizing the network structure, etc., so as to better meet the needs of users. On the contrary, when the comprehensive network performance anomaly index of a certain geographical area is low and the network communication demand coefficient is also low, it means that the network load in the area is light and the base station performance is sufficient. At this time, the operator appropriately adjusts the configuration of base stations in the area, such as reducing the number of base stations and reducing the transmission power of base stations, so as to achieve energy saving and network optimization. Through this regional load balancing optimization method based on geographical areas, operators can manage network resources more finely, improve network performance and user experience. At the same time, this method also helps operators achieve more reasonable network planning and layout, and improve network coverage and signal quality.

[0061] Example 2

[0062] See also Figure 1 The intelligent optimization system structure block diagram of the micro-cellular pico base station is provided in the embodiment of the present invention. Figure 2 An intelligent optimization system based on a 5G micro-cellular pico base station is shown, comprising:

[0063] The base station performance collection module is used to collect the network performance and operation performance of the base station and transmit the collected data to the base station status analysis module. The network performance includes signal coverage, signal quality, capacity and throughput, delay and packet loss rate, and security; the operation performance includes base station equipment temperature and voltage fluctuation coefficient;

[0064] The base station status analysis module is used to analyze the collected data and obtain the base station network performance evaluation index based on the base station coverage, base station signal quality, base station capacity and packet loss rate; and obtain the base station equipment operation fault evaluation index based on the base station voltage and equipment temperature;

[0065] The data partitioning module is used to divide the collected data into several intervals according to the area of ​​the geographical area, i represents the number of the geographical area, the number of the geographical areas is recorded as n, and j represents the number of the time period;

[0066] A demand coefficient calculation module, used to obtain the network communication demand coefficient qdi of the i-th geographical area and the network communication demand coefficient tdj of the j-th time period;

[0067] It is necessary to further explain in the embodiment of the present invention that based on the average data transmission efficiency, the average network load, and the average throughput in each time period, the formula The network communication demand coefficient tdj of the j-th time period is calculated, where csj_avg, wfj_avg, and tlj_avg represent the average data transmission efficiency, average network load, and average throughput of the base station in the j-th time period, respectively, 0≤ρ1≤1, 0≤ρ2≤1, and ρ1+ρ2=1.0, and ρ1 and ρ2 are weight coefficients.

[0068] See also Figure 2 The intelligent optimization decision module structure block diagram of the embodiment of the present invention needs to be further explained that the intelligent optimization decision module includes a base station equipment optimization unit, a geographic area load balancing optimization unit, and a time load balancing optimization unit. The time load balancing optimization unit calculates the time load balancing optimization coefficient of each time period based on the network communication demand coefficient tdj of each time period and the base station network performance evaluation index of each time period, including the following contents:

[0069] Based on the average data transmission efficiency, network load, and throughput in each time period, the formula The network communication demand coefficient tdj of the jth time period is calculated, where csj_avg, wfj_avg, and tlj_avg represent the average data transmission efficiency, network load, and throughput of the base station in the jth time period, respectively. 0≤ρ1≤1, 0≤ρ2≤1, and ρ1+ρ2=1.0. ρ1 and ρ2 are weight coefficients. The network signal evaluation index of all base stations in the jth time period is recorded as wpj, and the average value of the network signal evaluation index of all base stations in the m time periods is recorded as wpj_avg. The formula The time load balancing optimization coefficient Tyj of each time period is calculated.

[0070] It is explained that the time load balancing optimization coefficient of each time period is calculated based on the network communication demand coefficient of each time period and the base station network performance evaluation index of each time period. The time load balancing optimization coefficient reflects the network load status and the performance of the base station in the time period. By real-time monitoring and calculating the time load balancing optimization coefficient, it helps managers to timely understand the network load status of each time period and adjust the configuration of the base station accordingly to achieve load balancing in the time dimension. The time load balancing optimization coefficient can help managers formulate time optimization strategies and help managers understand which time periods require large floating base station performance adjustments. Specifically, when the network communication demand coefficient of a certain time period is high and the base station network performance evaluation index is low, it means that the network load in this time period is heavy and the base station performance cannot meet the demand. At this time, the operator improves the base station performance by increasing the number of channels, adjusting the antenna direction, and increasing the transmission power to better meet user needs. On the contrary, when the network communication demand coefficient of a certain time period is low and the base station network performance evaluation index is high, it means that the network load in this time period is light and the base station performance is sufficient. At this time, the operator appropriately reduces the base station configuration, such as reducing the number of channels and adjusting the antenna direction, to achieve energy saving and network optimization. Through this time period-based time load balancing optimization method, operators can manage network resources more finely, improve network performance and user experience. At the same time, this method also helps operators achieve the goal of energy conservation and emission reduction and reduce operating costs. The intelligent optimization decision module includes a base station equipment optimization unit and a geographical area load balancing optimization unit. The base station equipment optimization unit optimizes the base station equipment based on the base station network performance evaluation index and the base station equipment operation fault evaluation index; the geographical area base station optimization unit optimizes the base station distribution and quality in the geographical area based on the comprehensive network performance anomaly index ZPi.

[0071] Example 3

[0072] To achieve the above purpose, see Figure 3 The flow chart of the intelligent optimization method based on 5G micro-cellular pico base station is provided. The embodiment of the present invention provides the following technical solution: an intelligent optimization method based on 5G micro-cellular pico base station comprises the following steps:

[0073] Step S001, base station performance collection: used to collect the network performance and operation performance of the base station, and transmit the collected data to the base station status analysis step;

[0074] Step S002, base station status analysis step, for analyzing the collected data to obtain a base station network performance evaluation index and a base station equipment operation fault evaluation index; based on the base station network performance evaluation index and the base station equipment operation fault evaluation index, a combined analysis is performed to obtain a comprehensive network performance anomaly index ZPi for each geographical area;

[0075] Furthermore, based on the base station coverage, base station signal quality, base station capacity and packet loss rate, the base station network performance evaluation index is obtained; based on the base station voltage and equipment temperature, the base station equipment operation fault evaluation index is obtained;

[0076] Step S003, data division step, for dividing the collected data into several intervals according to geographical areas and time periods;

[0077] Step S004, a regional weight coefficient calculation step, for obtaining a network communication demand coefficient of the ith geographical area and a network communication demand coefficient of the ith geographical area;

[0078] Furthermore, based on the average values ​​of mobile device density, population density, and data transmission efficiency of each geographical area, the network communication demand coefficient of the ith geographical area is obtained; based on the average values ​​of mobile device density, population density, and data transmission efficiency of each geographical area, the network communication demand coefficient of the ith geographical area is obtained.

[0079] Step S005, base station equipment optimization step: optimizing the base station equipment based on the relationship between the base station network performance evaluation index and the base station equipment operation fault evaluation index and the preset value, and allocating the base station equipment optimization resources;

[0080] Step S006, base station performance optimization step according to time period: calculate the time load balancing optimization coefficient of each time period, and adjust the base station configuration in real time based on the time load balancing optimization coefficient of each time period;

[0081] Furthermore, based on the network communication demand coefficient of each time period and the base station network performance evaluation index of each time period, the time load balancing optimization coefficient of each time period is calculated, and the base station configuration is adjusted in real time based on the time load balancing optimization coefficient of each time period, such as increasing the number of channels and adjusting the antenna direction, to balance the load of each time period and improve network performance.

[0082] Step S007, base station performance optimization step with geographical area: based on the comprehensive network performance anomaly index of each geographical area and the network communication demand coefficient of each geographical area, the regional load balancing optimization coefficient of each geographical area is calculated.

[0083] It shows that by calculating the regional load balancing optimization coefficient, it can help managers understand the distribution of network resources in the region and make corresponding adjustments according to the actual situation. For example, for those areas with high comprehensive network performance anomaly index or large network communication demand coefficient, the network performance and stability of the area can be improved by increasing the corresponding network resource investment.

[0084] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent optimization system based on 5G micro-cellular base stations, characterized in that: include: The base station performance collection module is used to collect the network performance and operation performance of the base station and transmit the collected data to the base station status analysis module. The network performance includes signal coverage, signal quality, capacity and throughput, delay and packet loss rate, and security; the operation performance includes base station equipment temperature and voltage fluctuation coefficient; The base station status analysis module is used to analyze the collected data and obtain the base station network performance evaluation index based on the base station coverage, base station signal quality, base station capacity and packet loss rate; and obtain the base station equipment operation fault evaluation index based on the base station voltage and equipment temperature; The data partitioning module is used to divide the collected data into several intervals according to the area of ​​the geographical area, i represents the number of the geographical area, the number of the geographical areas is recorded as n, and j represents the number of the time period; A demand coefficient calculation module, used for obtaining the network communication demand coefficient qdi of the i-th geographical area; By formula The network communication demand coefficient qdi of the i-th geographical area is calculated, where ysi, rmi, and sci_avg represent the average values ​​of mobile device density, population density, and data transmission efficiency in the i-th geographical area, respectively; it is used to obtain the network communication demand coefficient tdj of the j-th time period, through the formula The network communication demand coefficient tdj of the j-th time period is calculated, where csj_avg, wfj_avg, and tlj_avg represent the average data transmission efficiency, network load, and throughput of the base station in the j-th time period, respectively, 0≤ρ1≤1, 0≤ρ2≤1, and ρ1+ρ2=1.0, ρ1 and ρ2 are weight coefficients; An intelligent optimization decision module is used to generate a base station optimization strategy, including a base station equipment optimization unit, a geographic area load balancing optimization unit and a time load balancing optimization unit. The base station equipment optimization unit optimizes the base station equipment based on the base station network performance evaluation index and the base station equipment operation fault evaluation index; the geographic area load balancing optimization unit optimizes the base station distribution and quality in the geographic area based on the comprehensive network performance anomaly index ZPi; The geographical area load balancing optimization unit obtains the average value of the comprehensive network performance anomaly index of the geographical area, recorded as ZP_avg, and uses the formula The regional load balancing optimization coefficient Qyi of the i-th geographical area is calculated, and the management personnel adjust the base station performance and operation status of the geographical area based on the regional load balancing optimization coefficient of the geographical area; The time load balancing optimization unit records the network signal evaluation index of all base stations in the jth time period as wpj, and records the average value of the network signal evaluation index of all base stations in the m time periods as wpj_avg. The time load balancing optimization coefficient Tyj of each time period is calculated.

2. According to claim 1, an intelligent optimization system based on a 5G micro-cellular pico base station is characterized in that: The base station performance description parameters are obtained through testing. The base station performance description parameters include signal coverage, signal quality, packet loss rate, and transmission speed. Get the base station network performance evaluation index wp, where fg, xz, dbl, and cs represent the signal coverage, signal quality, packet loss rate, and transmission rate of the base station, respectively. 0≤δ≤1, 0≤θ≤1, and δ+θ=1. δ and θ are weights, and their specific values ​​are adjusted and set by the user.

3. According to claim 2, an intelligent optimization system based on a 5G micro-cellular pico base station is characterized in that: Monitor the voltage and temperature of the base station to obtain the voltage dispersion coefficient, power dispersion coefficient, maximum equipment temperature, and average equipment temperature of the base station; The base station equipment operation fault evaluation index gp of each base station is obtained, where dy_dis, wd_max, wd_avg, and wd0 represent the voltage dispersion coefficient, the maximum equipment temperature, the average equipment temperature, and the preset equipment temperature of the base station, respectively; and ε1 and ε2 represent the proportional coefficients of each item, respectively.

4. The intelligent optimization system based on 5G micro-cellular pico base station according to claim 3 is characterized in that: The comprehensive network performance anomaly index of a geographic area is obtained as follows: Assume that there are k base stations in the i-th geographical area, and the base station network performance evaluation index and base station equipment operation failure evaluation index of the s-th base station are recorded as wp_s and gp_s respectively; Compare the obtained base station network performance evaluation index with the preset value thb1, divide the base stations into base stations with normal network performance and base stations with abnormal network performance, and obtain the proportion of base stations with abnormal network performance zb1 in each geographical area; Compare the obtained base station equipment operation fault evaluation index with the preset value thb2, divide the base stations into normal operation base stations and abnormal operation base stations, and obtain the proportion of abnormal operation base stations in each geographical area zb2; By formula The comprehensive network performance anomaly index ZPi of the ith geographical area is calculated.

Images