Intelligent wireless network optimization system based on data analysis

Abstract

The invention discloses an intelligent wireless network optimization system based on data analysis, which belongs to the field of network optimization systems and comprises an environment information acquisition module, a data analysis module, a data import module, a frequency optimization module and a parameter optimization module. The environment information acquisition module is used for acquiring environment information of a target area and transmitting the acquired environment information to the data analysis module, and the environment information comprises weather information, temperature information, humidity information, wind speed information, precipitation information, illumination information and noise information; the data import module is used for importing preset data into the data analysis module; and the data analysis module is used for receiving and analyzing all the collected information and outputting an analysis result to the frequency optimization module and the parameter optimization module. According to the invention, the collected environment data is more comprehensive, and the optimization effect of the wireless network can be effectively improved.

Description

Technical Field

[0001] The invention relates to the field of network optimization systems, in particular to an intelligent wireless network optimization system based on data analysis. Background Art

[0002] Intelligent wireless network optimization system is an important direction of modern communication technology development. It realizes the intelligent management of wireless network self-perception, self-analysis, self-decision-making and self-execution by introducing artificial intelligence technology. Such system can significantly improve network performance, reduce operation and maintenance costs, and improve user experience.

[0003] The network transmission speed of a wireless network is an important indicator for detecting the performance of a wireless network. Its speed will change with the changes in the weather and environment of the target area. The most obvious is rainy days. Rain will increase the humidity of the air, absorb and scatter the radio waves, resulting in increased signal attenuation, shortened transmission distance, and reduced signal-to-noise ratio. However, in rainy weather, lower-frequency radio waves have longer wavelengths and relatively stronger penetration, making them more suitable for wireless network transmission. Therefore, it is possible to consider reducing the carrier frequency of the signal. In addition, increasing the transmission power can compensate for the attenuation of the signal by rain to a certain extent.

[0004] Although the existing wireless network optimization system can also adjust and optimize the wireless network by collecting environmental data for analysis, the collected environmental data is not comprehensive enough, and the optimization effect of the wireless network is not ideal. Therefore, those skilled in the art provide an intelligent wireless network optimization system based on data analysis to solve the problems raised in the above background technology. Summary of the invention

[0005] The purpose of the present invention is to provide an intelligent wireless network optimization system based on data analysis, which collects more comprehensive environmental data and can effectively improve the optimization effect of the wireless network to solve the problems raised in the above background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] An intelligent wireless network optimization system based on data analysis, including an environmental information acquisition module, a data analysis module, a data import module, a frequency optimization module and a parameter optimization module;

[0008] The environmental information acquisition module is used to collect environmental information of the target area and transmit the collected environmental information to the data analysis module, wherein the environmental information includes weather information as well as temperature information, humidity information, wind speed information, precipitation information, light information, and noise information; the data import module is used to import preset data to the data analysis module; the data analysis module is used to receive all collected information and analyze it, and output the analysis results to the frequency optimization module and the parameter optimization module; the frequency optimization module is used to adjust and optimize the carrier frequency of the wireless network signal according to the analysis results; the parameter optimization module is used to adjust and optimize the transmission power and network parameters of the wireless network according to the analysis results.

[0009] As a further solution of the present invention: the specific process of the data analysis module analyzing the environmental information is as follows:

[0010] Step 1: mark the weather information collected in real time as A, mark the temperature information collected in real time as B1, mark the humidity information collected in real time as B2, mark the wind speed information collected in real time as B3, mark the precipitation information collected in real time as B4, mark the light information collected in real time as B5, and mark the noise information collected in real time as B6;

[0011] Step 2: Generate a radar map P based on the temperature information B1, humidity information B2, wind speed information B3, precipitation information B4, light information B5, and noise information B6;

[0012] Step 3: retrieve the weather information of the target area in previous time periods from the preset data, and then select the time period that matches the weather information A;

[0013] Step 4: extract the temperature information, humidity information, wind speed information, precipitation information, light information, and noise information corresponding to the selected time period, and generate a radar map pi of the previous time period based on the extracted information, where i=1···n, where n is a positive integer;

[0014] Step 5: Build a real-time optimization analysis model and output real-time optimization analysis results;

[0015] Step 6: Build a predictive optimization analysis model and output the predictive optimization analysis results.

[0016] As a further solution of the present invention: the specific analysis process of the real-time optimization analysis model is:

[0017] S501: perform similarity matching between P and pi. If the similarity between P and pi is greater than a preset value, pi is planned to the first sequence. If the similarity between P and pi is less than or equal to the preset value, pi is planned to the second sequence.

[0018] S502: extracting the wireless network transmission speed corresponding to the time period pi in the first sequence, and then selecting the time period with the fastest wireless network transmission speed;

[0019] S503: extracting the carrier frequency of the wireless network signal, the transmission power of the wireless network and the network parameters within the selected time period, and outputting them as real-time optimization analysis results.

[0020] As a further solution of the present invention: the specific analysis process of the prediction optimization analysis model is:

[0021] S601: Mark the time period that matches the weather information A selected in step 3 as ti, where i=1...n;

[0022] S602: Filter out a time period that matches the current network time from ti, and then mark the next time period of the filtered time period as Ti, where i=1...k, where k is a positive integer and k≤n;

[0023] S603: extracting weather information of Ti, filtering out weather information with the most repetitions, and then planning Ti corresponding to the filtered weather information into a third sequence;

[0024] S604: extracting temperature information, humidity information, wind speed information, precipitation information, light information, and noise information corresponding to each Ti time period in the third sequence, and generating a radar chart corresponding to each Ti time period in the third sequence based on the extracted information;

[0025] S605: Select the radar chart with the highest similarity to radar chart P from the radar charts corresponding to the Ti time period in the third sequence and mark it as P 预测 ;

[0026] S606: P 预测 Perform similarity matching with pi, if P 预测 The similarity with pi is greater than the preset value, then pi is planned to the fourth sequence. 预测 If the similarity with pi is less than or equal to the preset value, pi is planned to the fifth sequence;

[0027] S607: extracting the wireless network transmission speed corresponding to the time period where pi is located in the fourth sequence, and then selecting the time period with the fastest wireless network transmission speed;

[0028] S608: extracting the carrier frequency of the wireless network signal, the transmission power of the wireless network and the network parameters within the selected time period, and outputting them as the prediction optimization analysis result.

[0029] As a further solution of the present invention: after receiving the real-time optimization analysis result, the frequency optimization module adjusts the carrier frequency of the wireless network signal to be consistent with the carrier frequency of the wireless network signal in the real-time optimization analysis result; after receiving the predictive optimization analysis result, the frequency optimization module adjusts the carrier frequency of the wireless network signal to be consistent with the carrier frequency of the wireless network signal in the predictive optimization analysis result at the beginning of the next time period.

[0030] As a further solution of the present invention: after receiving the real-time optimization analysis results, the parameter optimization module adjusts the transmission power and network parameters of the wireless network to be consistent with the transmission power and network parameters of the wireless network in the real-time optimization analysis results; after receiving the predictive optimization analysis results, the parameter optimization module adjusts the transmission power and network parameters of the wireless network to be consistent with the transmission power and network parameters of the wireless network in the real-time optimization analysis results at the beginning of the next time period.

[0031] As a further solution of the present invention: it also includes an early warning module, which is used to issue an early warning when an abnormality occurs in the adjustment and optimization process of the frequency optimization module and the parameter optimization module.

[0032] As a further solution of the present invention: the specific process of whether the early warning module issues an early warning is:

[0033] The acquisition frequency optimization module previously adjusted the response time of the carrier frequency each time, marked as Ci, i = 1···n;

[0034] The acquisition parameter optimization module previously adjusted the response time of the transmission power and network parameters each time, marked as Di, i = 1···n;

[0035] The response time of the frequency optimization module to adjust the carrier frequency this time is marked as c, and the response time of the parameter optimization module to adjust the transmission power and network parameters this time is marked as d;

[0036] Match c with Ci. If any one of Ci matches with c, it means that the adjustment process of the frequency optimization module is normal. If c does not match with any one of Ci, compare c with the preset value C preset. If c < C preset, it means that the adjustment process of the frequency optimization module is normal. If c ≥ C preset, it means that the adjustment process of the frequency optimization module is abnormal.

[0037] Match d with Di. If any Di matches d, it means that the adjustment process of the parameter optimization module is normal. If d does not match any Di, compare d with the preset value D preset. If d < D preset, it means that the adjustment process of the parameter optimization module is normal. If d ≥ D preset, it means that the adjustment process of the parameter optimization module is abnormal.

[0038] If the adjustment process of the frequency optimization module and the adjustment process of the parameter optimization module are both abnormal, the warning module issues a second-level warning;

[0039] If any of the adjustment processes of the frequency optimization module and the parameter optimization module is abnormal, the early warning module issues a first-level early warning.

[0040] Compared with the prior art, the present invention has the following beneficial effects:

[0041] 1. The environmental data collected by this application is more comprehensive, and can effectively improve the optimization effect of the wireless network. After collecting the current environmental information, the records of the same weather are first screened out from the previous records, and then a radar map is constructed for similarity comparison. Finally, the real-time optimization analysis model and the predictive optimization analysis model are constructed to output the real-time optimization analysis results and the predictive optimization analysis results. The real-time optimization analysis results can be used to adjust the carrier frequency of the current wireless network signal, the transmission power of the wireless network and the network parameters in real time, and the predictive optimization analysis results can be used as the preset values ​​of the carrier frequency of the wireless network signal, the transmission power of the wireless network and the network parameters in the next time period, thereby ensuring that the values ​​changed during the subsequent real-time adjustment of the wireless network are small, saving workload and shortening response time. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 The structure diagram of an intelligent wireless network optimization system based on data analysis is shown in FIG. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] As mentioned in the background technology of this application, research has found that although the existing wireless network optimization system can also adjust and optimize the wireless network by collecting environmental data for analysis, the collected environmental data is not comprehensive enough, and the optimization effect on the wireless network is not ideal, and there are certain defects.

[0045] In order to solve the above-mentioned defects, the present application discloses an intelligent wireless network optimization system based on data analysis, which collects more comprehensive environmental data and can effectively improve the optimization effect of the wireless network.

[0046] The following will describe in detail how the solution of the present application solves the above technical problems in conjunction with the accompanying drawings.

[0047] See also Figure 1 In an embodiment of the present invention, an intelligent wireless network optimization system based on data analysis includes an environmental information acquisition module, a data analysis module, a data import module, a frequency optimization module and a parameter optimization module; the environmental information acquisition module is used to collect environmental information of the target area and transmit the collected environmental information to the data analysis module, wherein the environmental information includes weather information and temperature information, humidity information, wind speed information, precipitation information, light information, and noise information; the data import module is used to import preset data to the data analysis module; the data analysis module is used to receive all collected information and analyze it, and output the analysis results to the frequency optimization module and the parameter optimization module; the frequency optimization module is used to adjust and optimize the carrier frequency of the wireless network signal according to the analysis results; the parameter optimization module is used to adjust and optimize the transmission power and network parameters of the wireless network according to the analysis results. The environmental data collected by this application is more comprehensive, which can effectively improve the optimization effect of the wireless network.

[0048] In this embodiment, the specific process of the data analysis module analyzing the environmental information is as follows: Step 1: mark the weather information collected in real time as A, mark the temperature information collected in real time as B1, mark the humidity information collected in real time as B2, mark the wind speed information collected in real time as B3, mark the precipitation information collected in real time as B4, mark the light information collected in real time as B5, and mark the noise information collected in real time as B6; Step 2: based on the temperature information B1, humidity information B2, wind speed information B3, precipitation information B4, light information B5, noise information Information B6 generates a radar chart P; Step three: retrieve the weather information of the target area in previous time periods from the preset data, and then filter out the time period matching the weather information A; Step four: extract the temperature information, humidity information, wind speed information, precipitation information, light information, and noise information corresponding to the filtered time period, and generate a radar chart pi of the previous time period based on the extracted information, i=1···n, where n is a positive integer; Step five: construct a real-time optimization analysis model and output the real-time optimization analysis results; Step six: construct a predictive optimization analysis model and output the predictive optimization analysis results. After collecting the current environmental information, we first filter out records of the same weather from previous records, and then use this to construct a radar map for similarity comparison. Finally, through the constructed real-time optimization analysis model and predictive optimization analysis model, we output the real-time optimization analysis results and predictive optimization analysis results. The real-time optimization analysis results can be used to adjust the carrier frequency, transmission power and network parameters of the current wireless network signal in real time, while the predictive optimization analysis results can be used as the preset values ​​of the carrier frequency, transmission power and network parameters of the wireless network signal in the next time period, thereby ensuring that the values ​​changed during subsequent real-time adjustments to the wireless network are small, saving workload and shortening response time.

[0049] In this embodiment, the specific analysis process of the real-time optimization analysis model is as follows: S501: P and pi are matched for similarity. If the similarity between P and pi is greater than a preset value, pi is planned to the first sequence. If the similarity between P and pi is less than or equal to a preset value, pi is planned to the second sequence; S502: The wireless network propagation speed corresponding to the time period where pi is located in the first sequence is extracted, and then the time period with the fastest wireless network propagation speed is selected; S503: The carrier frequency of the wireless network signal, the transmission power of the wireless network and the network parameters in the selected time period are extracted, and the results are output as real-time optimization analysis results. This setting can quickly analyze the real-time optimization analysis results, and then facilitate the real-time adjustment and optimization of the wireless network.

[0050] In this embodiment, the specific analysis process of the prediction optimization analysis model is as follows: S601: mark the time period that matches the weather information A selected in step three as ti, i=1···n; S602: select the time period that matches the current network time from ti, and then mark the next time period of the selected time period as Ti, i=1···k, where k is a positive integer and k≤n; S603: extract the weather information of Ti, select the weather information with the most repetitions, and then plan the Ti corresponding to the selected weather information to the third sequence; S604: extract the temperature information, humidity information, wind speed information, precipitation information, light information, and noise information corresponding to each Ti time period in the third sequence, and generate a radar chart corresponding to each Ti time period in the third sequence based on the extracted information; S605: select the radar chart with the highest similarity to the radar chart P from the radar chart corresponding to the Ti time period in the third sequence and mark it as P 预测 ; S606: P 预测 Perform similarity matching with pi. If P 预测 The similarity with pi is greater than the preset value, then pi is planned to the fourth sequence. 预测 If the similarity with pi is less than or equal to the preset value, pi is planned to the fifth sequence; S607: extract the wireless network propagation speed corresponding to the time period where pi is located in the fourth sequence, and then select the time period with the fastest wireless network propagation speed; S608: extract the carrier frequency of the wireless network signal, the transmission power of the wireless network and the network parameters in the selected time period, and output them as the prediction optimization analysis results. Radar chart (also known as spider web chart, star chart, polar coordinate chart or network chart) is a graphical representation method for displaying multiple quantitative variables, which allows multiple attributes or variables of different categories to be compared in the same chart. Each variable has an axis extending outward from the center, and these axes are usually distributed on the circumference at the same angle interval. The attribute value of each category is represented by a line segment connecting the points on these axes to form a polygon, so that the performance of different categories on each variable can be intuitively compared.

[0051] In this embodiment, after receiving the real-time optimization analysis result, the frequency optimization module adjusts the carrier frequency of the wireless network signal to be consistent with the carrier frequency of the wireless network signal in the real-time optimization analysis result; after receiving the prediction optimization analysis result, the frequency optimization module adjusts the carrier frequency of the wireless network signal to be consistent with the carrier frequency of the wireless network signal in the prediction optimization analysis result at the beginning of the next time period. This setting ensures that the frequency optimization module can successfully complete the optimization adjustment of the wireless network.

[0052] In this embodiment, after receiving the real-time optimization analysis result, the parameter optimization module adjusts the transmission power and network parameters of the wireless network to be consistent with the transmission power and network parameters of the wireless network in the real-time optimization analysis result; after receiving the prediction optimization analysis result, the parameter optimization module adjusts the transmission power and network parameters of the wireless network to be consistent with the transmission power and network parameters of the wireless network in the real-time optimization analysis result at the beginning of the next time period. This setting ensures that the parameter optimization module can successfully complete the optimization adjustment of the wireless network.

[0053] In this embodiment, an early warning module is also included, which is used to issue an early warning when an abnormality occurs in the adjustment and optimization process of the frequency optimization module and the parameter optimization module. This setting can promptly warn the backstage staff when an abnormality occurs.

[0054] In this embodiment, the specific process of whether the early warning module issues an early warning is as follows: collect the response time of the frequency optimization module to adjust the carrier frequency each time in the past, marked as Ci, i=1···n; collect the response time of the parameter optimization module to adjust the transmission power and network parameters each time in the past, marked as Di, i=1···n; mark the response time of the frequency optimization module to adjust the carrier frequency this time as c, and then mark the response time of the parameter optimization module to adjust the transmission power and network parameters this time as d; match c with Ci, if any one Ci matches with c, it means that the adjustment process of the frequency optimization module is normal; if c does not match with any one Ci, compare c with the preset value C preset, if c<C preset, it means The adjustment process of the frequency optimization module is normal. If c≥C preset, it means that the adjustment process of the frequency optimization module is abnormal; match d with Di. If any Di matches d, it means that the adjustment process of the parameter optimization module is normal; if d does not match any Di, compare d with the preset value D preset. If d<D preset, it means that the adjustment process of the parameter optimization module is normal. If d≥D preset, it means that the adjustment process of the parameter optimization module is abnormal; if the adjustment process of the frequency optimization module and the adjustment process of the parameter optimization module are both abnormal, the early warning module issues a second-level early warning; if any of the adjustment process of the frequency optimization module and the adjustment process of the parameter optimization module are abnormal, the early warning module issues a first-level early warning. Different early warning levels can help staff understand the importance of things.

[0055] The environmental data collected by the present invention is more comprehensive, and can effectively improve the optimization effect of the wireless network. After collecting the current environmental information, the records of the same weather are first screened out from the previous records, and then a radar chart is constructed to compare the similarities. Finally, the real-time optimization analysis model and the predictive optimization analysis model are constructed to output the real-time optimization analysis results and the predictive optimization analysis results. The real-time optimization analysis results can be used to adjust the carrier frequency of the current wireless network signal, the transmission power of the wireless network and the network parameters in real time, and the predictive optimization analysis results can be used as the preset values ​​of the carrier frequency of the wireless network signal, the transmission power of the wireless network and the network parameters in the next time period, thereby ensuring that the values ​​changed during the subsequent real-time adjustment of the wireless network are small, saving workload and shortening response time.

[0056] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

[0057] What is described above is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. An intelligent wireless network optimization system based on data analysis, characterized in that: It includes environmental information acquisition module, data analysis module, data import module, frequency optimization module and parameter optimization module; The environmental information acquisition module is used to collect environmental information of the target area and transmit the collected environmental information to the data analysis module, wherein the environmental information includes weather information as well as temperature information, humidity information, wind speed information, precipitation information, light information, and noise information; the data import module is used to import preset data to the data analysis module; the data analysis module is used to receive all collected information and analyze it, and output the analysis results to the frequency optimization module and the parameter optimization module; the frequency optimization module is used to adjust and optimize the carrier frequency of the wireless network signal according to the analysis results; the parameter optimization module is used to adjust and optimize the transmission power and network parameters of the wireless network according to the analysis results.

2. The intelligent wireless network optimization system based on data analysis according to claim 1 is characterized in that: The specific process of the data analysis module analyzing the environmental information is as follows: Step 1: mark the weather information collected in real time as A, mark the temperature information collected in real time as B1, mark the humidity information collected in real time as B2, mark the wind speed information collected in real time as B3, mark the precipitation information collected in real time as B4, mark the light information collected in real time as B5, and mark the noise information collected in real time as B6; Step 2: Generate a radar map P based on the temperature information B1, humidity information B2, wind speed information B3, precipitation information B4, light information B5, and noise information B6; Step 3: retrieve the weather information of the target area in previous time periods from the preset data, and then select the time period that matches the weather information A; Step 4: extract the temperature information, humidity information, wind speed information, precipitation information, light information, and noise information corresponding to the selected time period, and generate a radar map pi of the previous time period based on the extracted information, where i=1···n, where n is a positive integer; Step 5: Build a real-time optimization analysis model and output real-time optimization analysis results; Step 6: Build a predictive optimization analysis model and output the predictive optimization analysis results.

3. The intelligent wireless network optimization system based on data analysis according to claim 2 is characterized in that: The specific analysis process of the real-time optimization analysis model is as follows: S501: perform similarity matching between P and pi. If the similarity between P and pi is greater than a preset value, pi is planned to the first sequence. If the similarity between P and pi is less than or equal to the preset value, pi is planned to the second sequence. S502: extracting the wireless network transmission speed corresponding to the time period pi in the first sequence, and then selecting the time period with the fastest wireless network transmission speed; S503: extracting the carrier frequency of the wireless network signal, the transmission power of the wireless network and the network parameters within the selected time period, and outputting them as real-time optimization analysis results.

4. The intelligent wireless network optimization system based on data analysis according to claim 3 is characterized in that: The specific analysis process of the prediction optimization analysis model is as follows: S601: Mark the time period that matches the weather information A selected in step 3 as ti, where i=1...n; S602: Filter out a time period that matches the current network time from ti, and then mark the next time period of the filtered time period as Ti, where i=1...k, where k is a positive integer and k≤n; S603: extracting weather information of Ti, screening out weather information with the most repetitions, and then planning Ti corresponding to the screened weather information into a third sequence; S604: extracting temperature information, humidity information, wind speed information, precipitation information, light information, and noise information corresponding to each Ti time period in the third sequence, and generating a radar chart corresponding to each Ti time period in the third sequence based on the extracted information; S605: Select the radar chart with the highest similarity to radar chart P from the radar charts corresponding to the Ti time period in the third sequence and mark it as P 预测 ; S606: P 预测 Perform similarity matching with pi. If P 预测 The similarity with pi is greater than the preset value, then pi is planned to the fourth sequence. 预测 If the similarity with pi is less than or equal to the preset value, pi is planned to the fifth sequence; S607: extracting the wireless network transmission speed corresponding to the time period where pi is located in the fourth sequence, and then selecting the time period with the fastest wireless network transmission speed; S608: extracting the carrier frequency of the wireless network signal, the transmission power of the wireless network and the network parameters within the selected time period, and outputting them as the prediction optimization analysis result.

5. The intelligent wireless network optimization system based on data analysis according to claim 4 is characterized in that: After receiving the real-time optimization analysis result, the frequency optimization module adjusts the carrier frequency of the wireless network signal to be consistent with the carrier frequency of the wireless network signal in the real-time optimization analysis result; after receiving the predictive optimization analysis result, the frequency optimization module adjusts the carrier frequency of the wireless network signal to be consistent with the carrier frequency of the wireless network signal in the predictive optimization analysis result at the beginning of the next time period.

6. The intelligent wireless network optimization system based on data analysis according to claim 5, characterized in that: After receiving the real-time optimization analysis result, the parameter optimization module adjusts the transmission power and network parameters of the wireless network to be consistent with the transmission power and network parameters of the wireless network in the real-time optimization analysis result; After receiving the prediction optimization analysis result, the parameter optimization module adjusts the transmission power and network parameters of the wireless network to be consistent with the transmission power and network parameters of the wireless network in the real-time optimization analysis result at the beginning of the next time period.

7. The intelligent wireless network optimization system based on data analysis according to claim 6, characterized in that: It also includes an early warning module for issuing an early warning when an abnormality occurs in the adjustment and optimization process of the frequency optimization module and the parameter optimization module.

8. The intelligent wireless network optimization system based on data analysis according to claim 7 is characterized in that: The specific process of whether the early warning module issues an early warning is as follows: The acquisition frequency optimization module previously adjusted the response time of the carrier frequency each time, marked as Ci, i = 1···n; The acquisition parameter optimization module previously adjusted the response time of the transmission power and network parameters each time, marked as Di, i = 1···n; The response time of the frequency optimization module to adjust the carrier frequency this time is marked as c, and the response time of the parameter optimization module to adjust the transmission power and network parameters this time is marked as d; Match c with Ci. If any one of Ci matches with c, it means that the adjustment process of the frequency optimization module is normal. If c does not match with any one of Ci, compare c with the preset value C preset. If c < C preset, it means that the adjustment process of the frequency optimization module is normal. If c ≥ C preset, it means that the adjustment process of the frequency optimization module is abnormal. Match d with Di. If any Di matches d, it means that the adjustment process of the parameter optimization module is normal. If d does not match any Di, compare d with the preset value D preset. If d < D preset, it means that the adjustment process of the parameter optimization module is normal. If d ≥ D preset, it means that the adjustment process of the parameter optimization module is abnormal. If the adjustment process of the frequency optimization module and the adjustment process of the parameter optimization module are both abnormal, the warning module issues a second-level warning; If any of the adjustment processes of the frequency optimization module and the parameter optimization module is abnormal, the early warning module issues a first-level early warning.

Images