CN117641367A - Clustering algorithm-based planning method for communication base stations in distributed area - Google Patents
Clustering algorithm-based planning method for communication base stations in distributed area Download PDFInfo
- Publication number
- CN117641367A CN117641367A CN202311602424.0A CN202311602424A CN117641367A CN 117641367 A CN117641367 A CN 117641367A CN 202311602424 A CN202311602424 A CN 202311602424A CN 117641367 A CN117641367 A CN 117641367A
- Authority
- CN
- China
- Prior art keywords
- clustering algorithm
- algorithm
- base station
- data
- clustering
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 133
- 238000004891 communication Methods 0.000 title claims abstract description 58
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000005516 engineering process Methods 0.000 claims description 29
- 238000005457 optimization Methods 0.000 claims description 15
- 238000003064 k means clustering Methods 0.000 claims description 14
- 238000005259 measurement Methods 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 11
- 238000007405 data analysis Methods 0.000 claims description 6
- 230000006872 improvement Effects 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000010295 mobile communication Methods 0.000 claims description 4
- 238000005192 partition Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000007619 statistical method Methods 0.000 claims description 3
- 238000012800 visualization Methods 0.000 claims description 3
- 239000000835 fiber Substances 0.000 claims description 2
- 238000013433 optimization analysis Methods 0.000 claims description 2
- 230000002776 aggregation Effects 0.000 abstract description 2
- 238000004220 aggregation Methods 0.000 abstract description 2
- 238000012360 testing method Methods 0.000 description 49
- 238000010276 construction Methods 0.000 description 19
- 230000000694 effects Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 9
- 238000012423 maintenance Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 9
- 238000012544 monitoring process Methods 0.000 description 8
- 238000003745 diagnosis Methods 0.000 description 6
- 238000011056 performance test Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 230000010354 integration Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000000638 solvent extraction Methods 0.000 description 2
- 241000282326 Felis catus Species 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000010420 art technique Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000004064 recycling Methods 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W16/00—Network planning, e.g. coverage or traffic planning tools; Network deployment, e.g. resource partitioning or cells structures
- H04W16/18—Network planning tools
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/16—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using machine learning or artificial intelligence
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W16/00—Network planning, e.g. coverage or traffic planning tools; Network deployment, e.g. resource partitioning or cells structures
- H04W16/22—Traffic simulation tools or models
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The invention discloses a method for constructing communication base stations in a distributed area based on a clustering algorithm, which belongs to the technical field of aggregation algorithms, adopts the clustering algorithm to group users in the area, reasonably arranges the positions and the number of the base stations according to the mobility and the communication requirements of the users, and specifically comprises the following steps: constructing a signal attenuation prediction model based on a clustering algorithm; optimizing a signal coverage area based on a clustering algorithm; detecting and establishing an interference signal library based on a clustering algorithm, and detecting an interference signal source; the location and number of base stations are arranged reasonably according to the mobility of the users and the communication requirements. The method for constructing the communication base station in the distributed area based on the clustering algorithm reduces the coverage area of the base station through a plurality of clustering algorithms, thereby realizing the communication capability of high density, high capacity and low time delay.
Description
Technical Field
The invention relates to the technical field of clustering algorithms, in particular to a method for planning communication base stations in a distributed area based on a clustering algorithm.
Background
Along with the continuous development of mobile communication technology, people have increasingly increased demands for communication, and in areas with larger coverage areas, such as cities, highways, high-speed rails and the like, the traditional base station construction cannot meet the communication demands of high density, high capacity and low time delay, so that a novel method for constructing the communication base station in the distributed area is researched to have important practical significance.
When the communication base station is built, the coverage area is large, so that the signal attenuation is serious, the communication quality is affected, advanced mechanical equipment and an automation technology are inconvenient to use, the coverage area and the communication efficiency of the communication base station are affected, and the communication system is inconvenient to test and evaluate, so that the scheme cannot meet the actual requirements and cannot reach the expected performance index.
Disclosure of Invention
The invention aims to provide a clustering algorithm-based planning method for communication base stations in a distributed area, which aims to solve the problems in the background art.
In order to achieve the above purpose, the present invention provides a method for planning communication base stations in a distributed area based on a clustering algorithm, wherein the clustering algorithm is used for grouping users in the area, and the positions and the number of the base stations are arranged according to the mobility and the communication requirements of the users, and the method specifically comprises the following steps:
(1) Constructing a signal attenuation prediction model based on a clustering algorithm;
(2) Optimizing a signal coverage area based on a clustering algorithm;
(3) Detecting and establishing an interference signal library based on a clustering algorithm, and detecting an interference signal source;
(4) Arranging the positions and the number of the base stations according to the mobility and the communication requirements of users;
the clustering algorithm comprises a DBSCAN clustering algorithm, a K-Means clustering algorithm and a Mean-Shift clustering algorithm.
Preferably, the step (1) specifically includes: a plurality of signal attenuation prediction models based on a clustering algorithm are established through the clustering algorithm, a measuring point is established around each communication base station, signal attenuation data of the measuring points are collected through regular measurement of the measuring points, and the clustering algorithm clusters the data to obtain signal attenuation conditions in different areas;
preferably, the step (2) specifically includes: partitioning the severe signal coverage area by using a DBSCAN clustering algorithm, a K-Means clustering algorithm and a Mean-Shift clustering algorithm, optimizing the signal coverage in each partition, selecting a proper clustering algorithm by using a plurality of signal attenuation prediction models based on the clustering algorithm, and finding a coverage area with optimal signal coverage;
preferably, the planning the communication base station consideration includes:
user demand changes, including user flow differences in different scenarios of office, business and home;
multimode signals, mobile communications, fiber optic communications and satellite communications.
Preferably, the DBSCAN clustering algorithm includes:
selecting appropriate parameters, wherein the parameters comprise neighbor relation metrics and minimum cluster sizes;
improving neighbor relation measurement, adopting Euclidean distance and Manhattan distance measurement mode to reflect similarity between data points, and adopting Euclidean distance three-dimensional formula
d＝sqrt(x 1 -x 2 )^+(y 1 -y 2 )^+(z 1 -z 2 )^)
Generalized to n-dimensional space, the Euclidean distance formula is
d＝sqrt(∑(i 1 -i 2 )^)
Where i=1, 2..n, xi1 denotes the i-th dimensional coordinate of the first point, x i 2 represents the i-th dimensional coordinates of the second point;
manhattan distance calculation formula d (i, j) = |X 1 -X 2 |+|Y 1 -Y 2 |；
Selecting a proper density value, and adjusting the size of the minimum cluster according to a specific data set and a task;
processing noise and missing data, wherein the data comprises signal data by adopting a data preprocessing, feature selection and missing value filling mode according to a corresponding processing strategy;
and (3) realizing an optimization algorithm, and optimizing the DBSCAN algorithm in a dynamic programming mode.
Preferably, the K-Means clustering algorithm includes selecting a suitable cluster size, calculating a distance between points inside the cluster, selecting a suitable cluster center, updating cluster boundaries, and initializing the cluster center with random, the cluster size should be not less than 3.
Preferably, the Mean-Shift clustering algorithm comprises parameter adjustment, algorithm improvement, application optimization and data analysis;
adjusting parameters, adjusting values of $k_max$ and $min_p$;
an improved algorithm, wherein a Hopf-Lindberg and Mahalanobis clustering algorithm is used for processing locally nearest data points;
optimizing the application, namely optimizing a Mean-Shift clustering algorithm by adopting a randomization technology and a self-adaptive learning rate;
and (3) data analysis, namely, using a visualization technology to display a clustering result, and using a statistical analysis technology to evaluate performance indexes such as the mean value, the standard deviation and the like of the algorithm.
Preferably, the construction and maintenance of the communication base station
Advanced mechanical equipment and automation technology are adopted to realize efficient construction and maintenance of the base station; through the intelligent monitoring and fault diagnosis system, the high-efficiency stable operation of the base station is ensured;
and (3) real-time monitoring: and a fault diagnosis and early warning system is introduced, so that the real-time monitoring of the running state of the base station is realized, and the base station is simplified: the modularized and integrated design is adopted, so that the base station construction process is simplified;
an automation technology: and the base station construction cost is reduced by utilizing an automation technology.
Preferably, the automation techniques include determining automation targets and requirements, evaluating prior art techniques, designing automation solutions, implementing automation, verifying automation effects, and continuously improving automation.
Preferably, system integration and testing
The clustering algorithm and the construction and maintenance of the communication base station are integrated into a complete communication system, and strict test and performance evaluation are carried out, so that the proposed scheme is ensured to meet the actual requirements, and the expected performance index can be achieved.
(1) Designing an expandable system architecture so as to be updated and expanded according to the requirement later;
(2) developing an optimization algorithm aiming at different scenes and application scenes to improve the system performance;
(3) third party test services are introduced, including functional testing, performance testing, and compatibility testing.
Therefore, the method for planning the communication base station in the distributed area based on the clustering algorithm has the following beneficial effects:
(1) Grouping users in the area through a DBSCAN clustering algorithm, a K-Means clustering algorithm and a Mean-Shift clustering algorithm, reasonably arranging the positions and the number of base stations according to the mobility and the communication requirements of the users, and reducing the coverage area of the base stations, thereby realizing the communication capability of high density, high capacity and low time delay;
(2) The method comprises the steps of adopting advanced mechanical equipment and an automation technology to realize efficient construction and maintenance of a base station, simultaneously ensuring efficient and stable operation of the base station through an intelligent monitoring and fault diagnosis system, then introducing a fault diagnosis and early warning system to realize real-time monitoring of the operation state of the base station, ensuring timely discovery and processing of faults, then adopting modularized and integrated design to simplify the construction process of the base station, improving the construction efficiency, recycling the automation technology, reducing manual intervention, reducing the construction cost of the base station, and adopting the advanced mechanical equipment and the automation technology to realize efficient construction and maintenance of the base station and improve the efficient and stable operation of the base station;
(3) The clustering algorithm is combined with base station construction and maintenance, so that the reliability and stability of the proposed scheme for constructing the communication base station in the distributed area are ensured.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
FIG. 1 is a schematic diagram of an embodiment of the present invention;
FIG. 2 is a schematic diagram of a base station planning consideration in accordance with an embodiment of the present invention;
FIG. 3 is a schematic diagram of a DBSCAN clustering algorithm according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of Manhattan distance according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a K-Means clustering algorithm according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of a Mean-Shift clustering algorithm according to an embodiment of the present invention;
FIG. 7 is a schematic diagram of an automated technique according to an embodiment of the invention;
FIG. 8 is a schematic diagram of a performance test according to an embodiment of the present invention;
fig. 9 is a schematic diagram of a compatibility test according to an embodiment of the present invention.
Detailed Description
Example 1
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention.
Referring to fig. 1 to 9, a method for planning communication base stations in a distributed area based on a clustering algorithm, groups users in the area by a DBSCAN clustering algorithm, a K-Means clustering algorithm and a Mean-Shift clustering algorithm, and reasonably arranges positions and numbers of the base stations according to mobility and communication requirements of the users, wherein the method specifically comprises the following steps:
(1) A signal attenuation prediction model is built, a plurality of signal attenuation prediction models based on a clustering algorithm are built through a DBSCAN clustering algorithm, a K-Means clustering algorithm and a Mean-Shift clustering algorithm, a measuring point is built around each communication base station, signal attenuation data of the measuring points are collected through regular measurement of the measuring points, and the data are clustered through the clustering algorithm to obtain signal attenuation conditions in different areas;
(2) Optimizing a signal coverage area based on a clustering algorithm, after determining a signal attenuation serious area, partitioning the signal coverage serious area by using a DBSCAN clustering algorithm, a K-Means clustering algorithm and a Mean-Shift clustering algorithm, optimizing the signal coverage in each partition, selecting a proper clustering algorithm through a plurality of signal attenuation prediction models based on the clustering algorithm, and finding a coverage area with optimal signal coverage;
(3) When a communication base station is built, interference of other signal sources is generated, communication quality is affected, a DBSCAN clustering algorithm, a K-Means clustering algorithm and a Mean-Shift clustering algorithm are adopted to establish an interference signal library for detecting the interference signal sources;
(4) The location and number of base stations are arranged reasonably according to the mobility of the users and the communication requirements.
Planning communication base station considerations includes:
user demand changes, including user flow differences in different scenarios of office, business and home;
multimode signal: the mobile communication achieves the application purpose after being received by a signal processor in the smart phone through cdma, 4G800m base station and 4G5G network; optical fiber communication runs the light source signals of signal packages sent by switches such as SDH, GPON and the like, and the light source signals are processed and applied by gateways (optical cats), routers and the like; the satellite communication is directly connected with the satellite through the mobile phone terminal, is another signal, and takes the hardware required by the three scenes into consideration during construction.
The DBSCAN clustering algorithm includes selecting appropriate parameters, improving neighbor relation metrics, selecting appropriate density values, processing noise and missing data, and optimizing algorithm implementation.
a. Selecting appropriate parameters: many parameters in the DBSCAN clustering algorithm need to be adjusted, including neighbor relation measurement and minimum cluster size, and different parameters have important influence on the clustering result and need to be adjusted according to specific data sets and tasks.
b. Improving neighbor relation metrics: the neighbor relation measurement in the DBSCAN clustering algorithm is one of the most critical parameters, the traditional neighbor relation measurement mode only considers the space distance between data points, but ignores the similarity between the data points, the improved neighbor relation measurement can adopt a more complex measurement mode, the Euclidean distance and the Manhattan distance to better reflect the similarity between the data points, and the three-dimensional formula of the Euclidean distance is as follows: d=sqrt (x 1 -x 2 )^+(y 1 -y 2 )^+(z 1 -z 2 )^)
Generalizing to n-dimensional space, the formula of Euclidean distance is: d=sqrt (Σ (i) 1 -i 2 )^)
Where i=1, 2..n, xi1 denotes the i-th dimensional coordinate of the first point, and xi2 denotes the i-th dimensional coordinate of the second point;
manhattan distance calculation formula d (i, j) = |X 1 -X 2 |+|Y 1 -Y 2 |；
See fig. 4, where: a represents the manhattan distance, B represents the euclidean distance, i.e., the straight line distance, and C and D represent the equivalent manhattan distance, the distance between two points of the manhattan distance in the north-south direction plus the distance in the east-west direction, i.e., D (i, j) = |x i -x j |+|y i -y j For a town street with regular arrangement in the north-south direction and the east-west direction, the distance from one point to the other is exactly the distance travelled in the north-south direction plus the distance in the east-west direction, and the formal meaning of manhattan distance is defined as the distance or city block distance, i.e. the sum of the distances of the projections of the line segments formed by two points on a fixed rectangular coordinate system of euclidean space to the axes.
c. Selecting an appropriate density value: the minimum cluster size in the DBSCAN clustering algorithm is also a parameter to be adjusted, and too small results in too sparse clustering results, while too large results in too tight clustering results, and proper density values need to be selected according to specific data sets and tasks.
d. Processing noise and missing data: noise and missing data in the DBSCAN clustering algorithm are unavoidable, and the data are processed by adopting a data preprocessing mode, a feature selection mode and a missing value filling mode according to a corresponding processing strategy.
e. The optimization algorithm is realized: the DBSCAN clustering algorithm is realized in a dynamic programming mode, so that the calculation complexity of the algorithm is reduced.
The K-Means clustering algorithm includes selecting a suitable cluster size, calculating distances between points within the cluster, selecting a suitable cluster center, updating cluster boundaries, and initializing the cluster center with random.
a. Selecting an appropriate cluster size: the cluster size has great influence on the clustering effect, the cluster size is more than or equal to 3, smaller clusters are easily influenced by external points and are difficult to divide clearly, but the cluster size cannot be too large, otherwise, the clustering result is not obvious enough.
b. Calculating the distance between points inside the cluster: the distance between the points in the cluster is an important index for measuring the clustering effect, and common distance measurement methods comprise Euclidean distance, manhattan distance and Chebyshev distance.
c. Selecting a proper clustering center: the choice of cluster centers has also a great influence on the effect of the clusters, which are located in the central position of the data sets, or for some data sets, using centroids as cluster centers.
d. Updating cluster boundaries: in the process of using the K-Means clustering algorithm, the cluster boundary needs to be updated continuously to ensure the clustering effect, however, when updating the cluster boundary, attention needs to be paid, if a new cluster center coincides with the original cluster center, it is indicated that the current cluster cannot accurately divide the data set, and the cluster center needs to be reselected to perform clustering again.
e. Adopting random initialization clustering center: in some cases, the points in the data set are denser or noise exists, so that the clustering center is inaccurate, and a method for randomly initializing the clustering center is adopted, and one clustering center is randomly selected during each clustering, so that the clustering accuracy is improved.
The Mean-Shift clustering algorithm comprises parameter adjustment, algorithm improvement, application optimization, data analysis and ensemble learning.
a. Adjusting parameters: for the Mean-Shift clustering algorithm, the selection of parameters is critical, the clustering effect of the algorithm can be effectively improved by adjusting the parameters, and the values of $k_max$ and $min_p$ are adjusted, so that the clustering result is more remarkable.
b. Improved algorithm: the Mean-Shift algorithm has some limitations in processing the locally nearest data points, and other clustering algorithms such as Hopf-Lindberg and Mahalanobis, which are more efficient in computing the locally nearest data points, can be considered.
c. Application optimization: in application, optimization technology is adopted to improve the performance of the algorithm, randomization technology is used to reduce the dependence of the algorithm on a data set, and adaptive learning rate is used
d. Data analysis: in order to more comprehensively evaluate the performance of the algorithm, a visualization technology is used for displaying the clustering result, and a statistical analysis technology is used for evaluating performance indexes such as the mean value, the standard deviation and the like of the algorithm.
e. And (3) ensemble learning: in order to further improve the performance of the algorithm, the clustering results of the K-Means or PySALM aggregation algorithm are fused to obtain better results.
Construction and maintenance of communication base station
Advanced mechanical equipment and automation technology are adopted to realize efficient construction and maintenance of the base station; through the intelligent monitoring and fault diagnosis system, the high-efficiency stable operation of the base station is ensured;
and (3) real-time monitoring: and a fault diagnosis and early warning system is introduced to realize real-time monitoring of the running state of the base station, so that the faults are timely found and processed.
Simplifying the base station: and the modularized and integrated design is adopted, so that the base station construction process is simplified, and the construction efficiency is improved.
An automation technology: and the manual intervention is reduced by utilizing an automation technology. And the construction cost of the base station is reduced.
Automation techniques include determining automation goals and demands, evaluating existing technologies, designing automation solutions, implementing automation, verifying automation effects, and continuing improvements.
a. Determining automation targets and requirements: before introducing automation technology, specific automation targets are defined and problems to be solved, such as improving production efficiency, reducing cost or enhancing safety, the specific targets can help a team to select appropriate automation technology more specifically.
b. Evaluation of prior art: prior to introducing new automation technology, the prior art should be evaluated for its performance, limitations, and compatibility with new technology, which helps teams reduce risk in implementing automation.
c. And (3) designing an automation scheme: according to the aim and technical requirements, a suitable automation scheme is designed. This may include selecting appropriate tools, software or hardware, and determining the network and resource configuration required.
d. And (3) implementing automation: before automation is implemented, sufficient training and guidance are needed to ensure that team members are familiar with the automation technology, and in the implementation process, the automation effect is closely focused and the strategy is timely adjusted.
e. Verifying an automation effect: after automated implementation, the effects are validated, the equipment performance is checked regularly, the parameters are optimized, and the actual production data is collected, and the validation results help the team to know the performance of the new technology and decide whether further optimization is needed.
f. Continuous improvement: the automation technology is continuously developed and perfected, and teams continuously pay attention to industry dynamic and technical changes, and timely adjust and optimize an automation scheme.
Integration and testing of systems
The two technical schemes of clustering algorithm and communication base station construction and maintenance are integrated into a complete communication system, and strict test and performance evaluation are carried out, so that the proposed scheme is ensured to meet actual requirements, and expected performance indexes can be achieved.
(1) Designing an expandable system architecture so as to be updated and expanded according to the requirement later;
(2) developing an optimization algorithm aiming at different scenes and application scenes to improve the system performance;
(3) third party test services are introduced, including functional testing, performance testing, and compatibility testing.
Performance testing can discover and resolve performance bottlenecks, the testing including:
a. selecting an appropriate performance testing tool: and selecting a proper performance testing tool according to project requirements and testing targets.
b. Writing a performance test plan: the detailed performance test plan is written, the test targets, the test scenes, the test data, the test methods and the test standards are defined, and the smooth performance of the test process is ensured, and the test efficiency is improved.
c. And (3) data collection: in the performance test process, a large amount of performance data needs to be collected, some common loads (such as a CPU, a memory, a disk IO and a network) can be set in a test environment so as to simulate an actual application scene, and meanwhile, log information of a test tool needs to be collected so as to analyze the problem.
d. Analysis data: after the performance data is collected, the data needs to be analyzed and processed, and an analysis tool can help quickly identify the performance bottleneck and provide a corresponding solution.
e. Writing a test report: and (3) arranging the analysis results into a test report, and describing the problems, the solutions and the test results in the test process. This helps deliver performance problems to the project team and test team and guides the subsequent optimization work.
f. Performance optimization: according to the test result, a targeted performance optimization measure is formulated, and for example, the test environment, the test script, the optimization code or the optimization tool can be adjusted.
Compatibility testing can ensure that software performs well on different devices and operating systems:
a. test cases are added: based on the original test cases, new test cases aiming at different devices, operating systems and browsers are added to ensure wider coverage.
b. Making a test plan: according to project requirements, a detailed test plan is formulated, the range, the target and the time schedule of the test are defined, and the test work is ensured to be orderly carried out.
c. Selecting a suitable test tool: and a testing tool with strong functions and simple and convenient operation is selected, so that the testing efficiency can be improved.
d. Simulating a real scene: in the testing process, the actual application scene is simulated, and the performance of the software on different devices and operating systems is better checked.
e. Making a testing strategy: corresponding test strategies are formulated for different devices and operating systems, such as finer screen size and resolution strategies for cell phone devices.
Example 2
Unlike embodiment 1, the method for planning a communication base station in a distributed area according to the present embodiment includes the following steps:
s1, base station planning method based on clustering algorithm
And grouping users in the area through a K-Medians clustering algorithm, and reasonably arranging the positions and the number of the base stations according to the mobility and the communication requirements of the users.
S2, improving distance measurement
Similarity in the data set is measured with finer granularity, and Chebyshev distance or least square distance is used, so that the distance between data points can be measured more accurately, and the clustering accuracy is improved.
S3, improving initial cluster center selection
And a more flexible clustering center is selected by adopting a random initialization mode or a self-adaptive initialization mode and the like, so that the degree of freedom of clustering is improved.
S4, improved algorithm
Other clustering algorithms, such as hierarchical clustering and density clustering, have been attempted to be used, which are in some ways more excellent than the K-Medians clustering algorithm.
The K-Medians clustering algorithm determines the center point of a cluster by computing the median, rather than the average, of all the vectors in the class.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention and not for limiting it, and although the present invention has been described in detail with reference to the preferred embodiments, it will be understood by those skilled in the art that: the technical scheme of the invention can be modified or replaced by the same, and the modified technical scheme cannot deviate from the spirit and scope of the technical scheme of the invention.
Claims (7)
1. A method for planning communication base stations in a distributed area based on a clustering algorithm is characterized in that the clustering algorithm is adopted to group users in the area, and the positions and the number of the base stations are arranged according to the mobility and the communication requirements of the users, and the method specifically comprises the following steps:
(1) Constructing a signal attenuation prediction model based on a clustering algorithm;
(2) Optimizing a signal coverage area based on a clustering algorithm;
(3) Detecting and establishing an interference signal library based on a clustering algorithm, and detecting an interference signal source;
(4) Arranging the positions and the number of the base stations according to the mobility and the communication requirements of users;
the clustering algorithm comprises a DBSCAN clustering algorithm, a K-Means clustering algorithm and a Mean-Shift clustering algorithm.
2. The method for planning a communication base station in a distributed area based on a clustering algorithm according to claim 1, wherein the step (1) specifically includes: a plurality of signal attenuation prediction models based on a clustering algorithm are established through the clustering algorithm, a measuring point is established around each communication base station, signal attenuation data of the measuring points are collected through regular measurement of the measuring points, and the clustering algorithm clusters the data to obtain signal attenuation conditions in different areas.
3. The method for planning a communication base station in a distributed area based on a clustering algorithm according to claim 1, wherein the step (2) specifically comprises: after the serious signal attenuation area is determined, the serious signal coverage area is partitioned by using a DBSCAN clustering algorithm, a K-Means clustering algorithm and a Mean-Shift clustering algorithm, signal coverage optimization is carried out in each partition, and a proper clustering algorithm is selected through a plurality of signal attenuation prediction models based on the clustering algorithm to find the coverage area with optimal signal coverage.
4. The method for planning a communication base station in a distributed area based on a clustering algorithm according to claim 1, wherein the planning the consideration of the communication base station comprises:
user demand changes, including user flow differences in different scenarios of office, business and home;
multimode signals, mobile communications, fiber optic communications and satellite communications.
5. The method for planning a communication base station in a distributed area based on a clustering algorithm as claimed in claim 1, wherein the DBSCAN clustering algorithm comprises:
selecting appropriate parameters, wherein the parameters comprise neighbor relation metrics and minimum cluster sizes;
improving neighbor relation measurement, adopting Euclidean distance and Manhattan distance measurement mode to reflect similarity between data points, and adopting Euclidean distance three-dimensional formula
d＝sqrt(x 1 -x 2 )^+(y 1 -y 2 )^+(z 1 -z 2 )^)
Generalized to n-dimensional space, the Euclidean distance formula is
d＝sqrt(∑(i 1 -i 2 )^)
Wherein i=1, 2..n, i 1 I-th dimensional coordinates representing the first point, i 2 An ith dimensional coordinate representing a second point;
manhattan distance calculation formula d (i, j) = |X 1 -X 2 |+|Y 1 -Y 2 |；
Selecting a proper density value, and adjusting the size of the minimum cluster according to a specific data set and a task;
processing noise and missing data, wherein the data comprises signal data by adopting a data preprocessing, feature selection and missing value filling mode according to a corresponding processing strategy;
and (3) realizing an optimization algorithm, and optimizing the DBSCAN algorithm in a dynamic programming mode.
6. The method for planning a communication base station in a distributed area based on a clustering algorithm according to claim 1, wherein the method comprises the following steps: the K-Means clustering algorithm comprises selecting a proper cluster size, calculating the distance between points in the cluster, selecting a proper cluster center, updating the cluster boundary and adopting a random initialization cluster center, wherein the cluster size is not less than 3.
7. The method for planning a communication base station in a distributed area based on a clustering algorithm according to claim 1, wherein the method comprises the following steps: the Mean-Shift clustering algorithm comprises parameter adjustment, algorithm improvement, application optimization and data analysis;
adjusting parameters, adjusting values of $k_max$ and $min_p$;
an improved algorithm, wherein a Hopf-Lindberg and Mahalanobis clustering algorithm is used for processing locally nearest data points;
optimizing the application, namely optimizing a Mean-Shift clustering algorithm by adopting a randomization technology and a self-adaptive learning rate;
data analysis, using visualization technology to show clustering results, and using statistical analysis technology to evaluate the mean and standard deviation performance index of the algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311602424.0A CN117641367A (en) | 2023-11-28 | 2023-11-28 | Clustering algorithm-based planning method for communication base stations in distributed area |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311602424.0A CN117641367A (en) | 2023-11-28 | 2023-11-28 | Clustering algorithm-based planning method for communication base stations in distributed area |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117641367A true CN117641367A (en) | 2024-03-01 |
Family
ID=90035142
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311602424.0A Pending CN117641367A (en) | 2023-11-28 | 2023-11-28 | Clustering algorithm-based planning method for communication base stations in distributed area |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117641367A (en) |
-
2023
- 2023-11-28 CN CN202311602424.0A patent/CN117641367A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111867049B (en) | Positioning method, positioning device and storage medium | |
| CN106970353B (en) | Tracking and tracing method based on three-dimensional positioning of communication base station | |
| CN114338418B (en) | Virtual-real combined information network verification platform | |
| CN113821332B (en) | Method, device, equipment and medium for optimizing efficiency of automatic machine learning system | |
| CN101650687A (en) | Large-scale parallel program property-predication realizing method | |
| CN112601173B (en) | 5G positioning truth value detection and attack tracing method, system, equipment and application | |
| CN117078048A (en) | Digital twinning-based intelligent city resource management method and system | |
| CN115905450B (en) | Water quality anomaly tracing method and system based on unmanned aerial vehicle monitoring | |
| CN110909804B (en) | Method, device, server and storage medium for detecting abnormal data of base station | |
| CN115426710A (en) | Indoor fingerprint positioning-oriented sparse feature completion method | |
| CN114339913A (en) | Method, device, medium and electronic device for updating neighbor cell of wireless network | |
| CN117641367A (en) | Clustering algorithm-based planning method for communication base stations in distributed area | |
| CN118468186A (en) | Wind power data anomaly detection method and system based on federal learning mechanism | |
| CN112910699A (en) | Intelligent fault detection method and device for power internet of things | |
| CN112488343B (en) | Smart city intelligent perception terminal address selection method based on hyper-heuristic algorithm | |
| CN114205238B (en) | Network resource optimization and model training method and device, storage medium and equipment | |
| CN115454787A (en) | Alarm classification method and device, electronic equipment and storage medium | |
| CN113055111B (en) | Channel modeling method and system based on Bayesian optimization | |
| CN114462225A (en) | Rapid construction system for hybrid traffic simulation supporting environment under vehicle-road cooperation | |
| CN114564523A (en) | Big data vulnerability analysis method and cloud AI system for intelligent virtual scene | |
| Jesus et al. | A dependability-aware approach for dynamic mobile sink repositioning in smart cities applications | |
| CN112188388A (en) | Hybrid indoor positioning method based on machine learning | |
| CN111046321A (en) | Photovoltaic power station operation and maintenance strategy optimization method and device | |
| CN113068194A (en) | Method, device, equipment and medium for determining anchor point | |
| CN117424791B (en) | Large-scale power communication network fault diagnosis system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |