CN109041084A - A kind of method of radio network optimization - Google Patents
A kind of method of radio network optimization Download PDFInfo
- Publication number
- CN109041084A CN109041084A CN201811060613.9A CN201811060613A CN109041084A CN 109041084 A CN109041084 A CN 109041084A CN 201811060613 A CN201811060613 A CN 201811060613A CN 109041084 A CN109041084 A CN 109041084A
- Authority
- CN
- China
- Prior art keywords
- base station
- communication base
- drive test
- module
- information
- 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.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/02—Arrangements for optimising operational condition
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The invention proposes a kind of methods of radio network optimization, including drive test terminal, communication base station and a network optimizer, the network optimizer includes receiving module, sending module, neural study module and memory module, learnt using test information and location information of the neural study module to drive test terminal location and obtains optimization data set, the optimized parameter of communication base station is obtained by optimization data set, optimize cumbersome Optimization Steps the present invention overcomes conventional Wi-Fi, reduces the human cost and material resources cost of optimization.
Description
Technical field
The present invention relates to network communication technology field more particularly to a kind of methods of radio network optimization.
Background technique
Existing radio network optimization technology be usually used manually carry out data transmission and configured transmission adjustment, so
And the arriving of big data era makes the transmission quantity explosive growth of data.This also allows the current network optimization to face problem, especially
It is the optimization of wireless network, conventional wireless network optimization needs the equipment by profession, by large-scale drive test, counts and divides
The drive test result on test route is analysed, to analyze network problem.
Conventional drive test mode and optimization method needs to devote a tremendous amount of time using a large amount of human and material resources to logical
Letter base station is adjusted and adjusts, and the test mode is not only passive, but also efficiency is extremely low.Particularly, for adjacent base station it
Between signal switch position at, the determination of signal source and the switching of base station can all be influenced by network optimization problem.
Summary of the invention
In view of this, the invention proposes one kind can be improved working efficiency, optimization cost is reduced, and base can be overcome
The method of the radio network optimization of signal assignment problem between standing.
The technical scheme of the present invention is realized as follows: the present invention provides a kind of methods of radio network optimization, including
Following steps:
Step 1: drive test terminal uploads the location information in drive test region to network optimizer, network optimizer passes through position
Information judges the optimal communication base station of the position and optimal communication base station information is sent to drive test terminal;
Step 2: the drive test result of the position is sent to network optimizer by drive test terminal, network optimizer is according to drive test
As a result a parameter feedback information is obtained, network optimizer is according to parameter feedback information to the ginseng of optimal communication base station in step 1
Number is adjusted.
On the basis of above technical scheme, it is preferred that the network optimizer includes receiving module, sending module, mind
Through study module and memory module;
The receiving module is used to receive the data information of drive test terminal and communication base station;
The sending module is for sending data information to drive test terminal and communication base station;
The nerve study module is electrically connected with receiving module, sending module and memory module respectively, the neurology
Location information, drive test result that module receives receiving module by artificial neural network is practised to be associated study and form position
Confidence breath-drive test result optimization data set, the optimization data set storage is in a storage module.
On the basis of above technical scheme, it is preferred that the working method of the network optimizer includes: that the drive test is whole
The location information at end, the data information of drive test result are sent to the receiving module of network optimizer, and receiving module is by data information
It is sent to neural study module, the nerve study module is artificial neural network system, using artificial neural network to data
Information carries out study conclusion, and obtains optimization data set, and the storage of optimization data set is in a storage module, excellent when needing to carry out network
When change, neural study module is called according to optimization data set of the data information received to storage, and is obtained corresponding
Parameter feedback information, parameter feedback information are sent to communication base station by sending module, and communication base station carries out the parameter of communication
Modification.
On the basis of above technical scheme, it is preferred that the corresponding optimization data set of each communication base station, the optimization
Data set is the messaging parameter set at each position in the communication range of the communication base station.
On the basis of above technical scheme, it is preferred that location information described in step 1 is drive test terminal position
Coordinate in the global coordinate system of map.
On the basis of above technical scheme, it is preferred that the method for the judgement optimal communication base station is to calculate drive test end
End and adjacent the distance between communication base station, utilize the coordinate of coordinate and drive test terminal of the communication base station in global coordinate system
It is calculated, is exactly optimal communication base station apart from shortest communication base station.
On the basis of above technical scheme, it is preferred that be no less than when apart from the shortest communication base station quantity of drive test terminal
At two, drive test terminal sends test information to the communication base station with the identical shortest distance simultaneously, according to different communication base station
Optimal communication base station is determined to the feedback information intensity of same test information, the communication base station with most strong feedback information is optimal
Communication base station.
On the basis of above technical scheme, it is preferred that the acquisition pattern of drive test result described in step 2 includes: drive test
The transmission power and tranmitting frequency that terminal uses multiple groups different simultaneously send signal, optimal communication base station to optimal communication base station
To the feedback letter with the signal of different transmission power and different tranmitting frequencies feedback multiple groups with different capacity and different frequency
Number, by each group of transmitting signal with particular transmission power and tranmitting frequency with particular transmission power and tranmitting frequency
Feedback signal is wanted to match, and is organized into data packet, and the data packet is exactly drive test result.
A kind of method for optimizing wireless network of the invention has the advantages that compared with the existing technology
(1) technical solution of the present invention handle using network optimizer road test data and utilizes network optimizer pair
Communication base station carries out parameter regulation, eliminates the tedious steps of manual adjustment, secondly using with deep learning energy in the present invention
The neural network module road test data and adjustment parameter of power are learnt, and obtain optimization data set, just by a drive test
Can directly by the parameter regulation of communication base station to compared with the figure of merit, avoid in conventional wireless networks optimization process it is multiple adjusting with
Drive test process, and it can be directly applied to using the optimization data set of a communication base station or the communication base station of limited quantity
The radio network optimization of his communication base station substantially increases the efficiency of radio network optimization, reduces the cost of optimization;
(2) communication point that the present invention will also be between adjacent base station distinguishes conclusion, accurately manages each communication
The base station distribution of point, avoids the occurrence of in base station handoff position signal deletion.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is the flow chart of method for optimizing wireless network of the invention;
Fig. 2 is the structural schematic diagram of network optimizer of the invention.
Specific embodiment
Below in conjunction with embodiment of the present invention, the technical solution in embodiment of the present invention is carried out clearly and completely
Description, it is clear that described embodiment is only some embodiments of the invention, rather than whole embodiments.Base
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts all
Other embodiments shall fall within the protection scope of the present invention.
As shown in Figure 1, a kind of method of radio network optimization of the invention, detailed process include:
Drive test terminal satisfy the need measuring point carry out coordinate setting, and by positioning coordinate be sent to network optimizer;
Network optimizer is carried out according to the coordinate of the communication base station near the positioning coordinate and drive test terminal of drive test terminal
Distance calculates, and judges apart from nearest communication base station;
If apart from nearest communication base station one and only one, drive test terminal to the communication base station send multiple groups have not
The test signal of same frequency different capacity, communication base station carry out each with the signal of specific frequency and certain power anti-
Feedback, the signal of feedback also have specific frequency and power.
It is above to confirm that communication base station should be sent out in the position for the point using the primary multiple groups test signal that sends
The signal of which kind of attribute is given, therefore drive test terminal and communication base station can all be sent together using multiple groups signal.
Drive test terminal is interrelated by the signal of the signal of transmission and feedback after receiving feedback signal, has same frequency
The transmission signal and feedback signal of rate and power information are as a signal group, seat to each signal group and at this location
Mark information carries out packing integration, then is sent to network optimizer by drive test terminal, and network optimizer utilizes neural study module
Deep learning is carried out to the data of packing, and forms optimization data set.
Last network optimizer joins the communication base station using including location information-drive test information optimization data set
Number adjustment, specifically, network optimizer is learnt using different location informations, drive test information, and calculates each correspondence
At location information, while there is the minimum base station parameter for sending power and highest information strength, which is the optimal of base station
Parameter, the optimized parameter of comprehensive different location, summing up has the widest parameter of real applicability, using the parameter to communication base
Station is adjusted.
If apart from drive test terminal with same distance communication base station have it is multiple, drive test terminal simultaneously to multiple communications
Base station sends signal, is compared using the intensity of the identical feedback signal of multiple communication base stations, the intensity highest of feedback signal
Communication base station as apart from nearest communication base station.
As shown in Fig. 2, the workflow of network optimizer includes: that receiving module is received from drive test terminal and communication base
The data information stood, and give data information transfer to neural study module, neural study module will come from road by deep learning
It surveys the location information of terminal, drive test information and the parameter feedback information from communication base station is associated and deep learning, most
Optimization data set is obtained eventually, and it is defeated to feed back an optimal base station by location information and drive test information of the optimization data set to input
Parameter information out, the information are sent to drive test terminal and communication base station, communication base station by the parameter information to base station into
The adjustment of row parameter.
In one embodiment, the optimization data set that network optimizer can also comprehensively utilize multiple communication base stations carries out
Deep learning.
It in one embodiment, can be using nearest communication base station as the origin of relative coordinate system, to calculate drive test
The coordinate of terminal and the distance of relative communication base station.
In one embodiment, the optimization data set of the communication base station with similar landform is merged, and in mind
Through deep learning again in study module, merging optimization data set is finally obtained, merging optimization data set has similar landform
Communication base station in can directly apply.
The foregoing is merely better embodiments of the invention, are not intended to limit the invention, all of the invention
Within spirit and principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.
Claims (8)
1. a kind of method of radio network optimization, which is characterized in that the described method includes:
Step 1: drive test terminal uploads the location information in drive test region to network optimizer, network optimizer passes through location information
Judge the optimal communication base station of the position and optimal communication base station information is sent to drive test terminal;
Step 2: the drive test result of the position is sent to network optimizer by drive test terminal, network optimizer is according to drive test result
A parameter feedback information is obtained, network optimizer is according to parameter feedback information to the parameter of the optimal communication base station in step 1
It is adjusted.
2. a kind of method of radio network optimization as described in claim 1, which is characterized in that the network optimization described in step 1
Device includes receiving module, sending module, neural study module and memory module;
The receiving module is used to receive the data information of drive test terminal and communication base station;
The sending module is for sending data information to drive test terminal and communication base station;
The nerve study module is electrically connected with receiving module, sending module and memory module respectively, the nerve study mould
The location information and drive test result that block receives receiving module by artificial neural network are associated study and forming position
Information-drive test result optimization data set, the optimization data set storage is in a storage module.
3. a kind of method of radio network optimization as claimed in claim 2, which is characterized in that the work of the network optimizer
Mode includes:
The data information of the location information of the drive test terminal, drive test result is sent to connecing for network optimizer by the drive test terminal
Module is received, data information is sent to neural study module by receiving module, and the nerve study module is artificial neural network system
System, carries out study conclusion to location information and drive test result using artificial neural network, and obtain optimization data set, optimizes data
In a storage module, when needing to carry out the network optimization, neural study module is according to the data information received to depositing for collection storage
The optimization data set of storage is called, and obtains corresponding parameter feedback information, and parameter feedback information is sent by sending module
To communication base station, communication base station modifies to parameter using parameter feedback information.
4. a kind of method of radio network optimization as claimed in claim 2, which is characterized in that each communication base station is one corresponding
Optimize data set.
5. a kind of method of radio network optimization as claimed in claim 4, which is characterized in that in step 1, the position letter
Breath is coordinate of the drive test terminal position in the global coordinate system of map.
6. a kind of method of radio network optimization as claimed in claim 5, which is characterized in that in step 1, the judgement is most
The method of excellent communication base station is to calculate drive test terminal and adjacent the distance between communication base station, just apart from shortest communication base station
It is optimal communication base station.
7. a kind of method of radio network optimization as claimed in claim 6, which is characterized in that when shortest apart from drive test terminal
When communication base station quantity is no less than two, drive test terminal sends test letter to the communication base station with the identical shortest distance simultaneously
Breath, determines optimal communication base station according to feedback information intensity of the different communication base station to same test information, has most strong feedback
The communication base station of information is optimal communication base station.
8. a kind of method of radio network optimization as described in claim 1, which is characterized in that drive test result described in step 2
Acquisition pattern include: that drive test terminal while the transmission power that uses multiple groups different and frequency send optimal communication base station and believe
Number, and the feedback signal from optimal communication base station is received, by that will have the hair of different transmission power and frequency to each group
The number of delivering letters and feedback signal want to match and be organized into data packet, and the data packet is drive test result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811060613.9A CN109041084B (en) | 2018-09-11 | 2018-09-11 | Wireless network optimization method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811060613.9A CN109041084B (en) | 2018-09-11 | 2018-09-11 | Wireless network optimization method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109041084A true CN109041084A (en) | 2018-12-18 |
CN109041084B CN109041084B (en) | 2021-10-26 |
Family
ID=64621589
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811060613.9A Active CN109041084B (en) | 2018-09-11 | 2018-09-11 | Wireless network optimization method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109041084B (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2020178266A (en) * | 2019-04-19 | 2020-10-29 | ソフトバンク株式会社 | Creation method of estimation program, creation method of learning data set, estimation device, estimation program, estimation method, and communication quality improvement system |
CN111988799A (en) * | 2020-08-27 | 2020-11-24 | 几维通信技术(深圳)有限公司 | Automatic network optimization method, terminal equipment and access network equipment |
CN113179527A (en) * | 2020-08-27 | 2021-07-27 | 几维通信技术(深圳)有限公司 | Wireless communication network optimization method and computer-readable storage medium |
CN115086972A (en) * | 2022-07-19 | 2022-09-20 | 深圳市华曦达科技股份有限公司 | Distributed wireless signal quality optimization method and system |
WO2022237568A1 (en) * | 2021-05-10 | 2022-11-17 | 中兴通讯股份有限公司 | Base station performance optimization method and apparatus, base station, and storage medium |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102202421A (en) * | 2011-04-27 | 2011-09-28 | 宇龙计算机通信科技(深圳)有限公司 | Signal connection prompting method and mobile terminal |
CN103533565A (en) * | 2013-11-06 | 2014-01-22 | 北京北方烽火科技有限公司 | Wireless network optimization method and optimizer |
CN103796252A (en) * | 2012-11-02 | 2014-05-14 | 北京三星通信技术研究有限公司 | Method for automatic adjustment of mobile parameters |
US20150245259A1 (en) * | 2014-02-27 | 2015-08-27 | Cellco Partnership D/B/A Verizon Wireless | Optimizing mobile device handoff parameters |
US20150312813A1 (en) * | 2014-04-29 | 2015-10-29 | Samsung Electronics Co., Ltd. | Method and apparatus for transmitting a handover report and an rlf report |
WO2017071828A1 (en) * | 2015-10-30 | 2017-05-04 | Telecom Italia S.P.A. | Method and system for dynamically varying reference signals' power in a mobile radio network |
CN107437100A (en) * | 2017-08-08 | 2017-12-05 | 重庆邮电大学 | A kind of picture position Forecasting Methodology based on the association study of cross-module state |
CN107770719A (en) * | 2017-09-27 | 2018-03-06 | 无锡神探电子科技有限公司 | A kind of object localization method based on drive test data and machine learning |
CN107948919A (en) * | 2017-11-28 | 2018-04-20 | 维沃移动通信有限公司 | A kind of shared method for processing information and mobile terminal |
US20180176792A1 (en) * | 2016-12-18 | 2018-06-21 | Dell Products, Lp | Method and apparatus for optimizing selection of radio channel frequency and adaptive clear channel assessment threshold for wlan access points |
CN108207005A (en) * | 2016-12-20 | 2018-06-26 | 中国移动通信集团设计院有限公司 | A kind of appraisal procedure and server of LTE wireless networks |
-
2018
- 2018-09-11 CN CN201811060613.9A patent/CN109041084B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102202421A (en) * | 2011-04-27 | 2011-09-28 | 宇龙计算机通信科技(深圳)有限公司 | Signal connection prompting method and mobile terminal |
CN103796252A (en) * | 2012-11-02 | 2014-05-14 | 北京三星通信技术研究有限公司 | Method for automatic adjustment of mobile parameters |
CN103533565A (en) * | 2013-11-06 | 2014-01-22 | 北京北方烽火科技有限公司 | Wireless network optimization method and optimizer |
US20150245259A1 (en) * | 2014-02-27 | 2015-08-27 | Cellco Partnership D/B/A Verizon Wireless | Optimizing mobile device handoff parameters |
US20150312813A1 (en) * | 2014-04-29 | 2015-10-29 | Samsung Electronics Co., Ltd. | Method and apparatus for transmitting a handover report and an rlf report |
WO2017071828A1 (en) * | 2015-10-30 | 2017-05-04 | Telecom Italia S.P.A. | Method and system for dynamically varying reference signals' power in a mobile radio network |
US20180176792A1 (en) * | 2016-12-18 | 2018-06-21 | Dell Products, Lp | Method and apparatus for optimizing selection of radio channel frequency and adaptive clear channel assessment threshold for wlan access points |
CN108207005A (en) * | 2016-12-20 | 2018-06-26 | 中国移动通信集团设计院有限公司 | A kind of appraisal procedure and server of LTE wireless networks |
CN107437100A (en) * | 2017-08-08 | 2017-12-05 | 重庆邮电大学 | A kind of picture position Forecasting Methodology based on the association study of cross-module state |
CN107770719A (en) * | 2017-09-27 | 2018-03-06 | 无锡神探电子科技有限公司 | A kind of object localization method based on drive test data and machine learning |
CN107948919A (en) * | 2017-11-28 | 2018-04-20 | 维沃移动通信有限公司 | A kind of shared method for processing information and mobile terminal |
Non-Patent Citations (3)
Title |
---|
MOHAMMAD J. ABDEL-RAHMAN等: "Robust Controller Placement and Assignment in Software-Defined Cellular Networks", 《2017 26TH INTERNATIONAL CONFERENCE ON COMPUTER COMMUNICATION AND NETWORKS (ICCCN)》 * |
宋青: "大规模网络最短路径的分层优化算法研究", 《中国优秀硕士学位论文库》 * |
张宏君: "基于BP神经网络的无线定位算法研究", 《中国优秀硕士学位论文库》 * |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2020178266A (en) * | 2019-04-19 | 2020-10-29 | ソフトバンク株式会社 | Creation method of estimation program, creation method of learning data set, estimation device, estimation program, estimation method, and communication quality improvement system |
CN111988799A (en) * | 2020-08-27 | 2020-11-24 | 几维通信技术(深圳)有限公司 | Automatic network optimization method, terminal equipment and access network equipment |
CN111988799B (en) * | 2020-08-27 | 2021-05-28 | 几维通信技术(深圳)有限公司 | Automatic network optimization method, terminal equipment and access network equipment |
CN113179527A (en) * | 2020-08-27 | 2021-07-27 | 几维通信技术(深圳)有限公司 | Wireless communication network optimization method and computer-readable storage medium |
CN113179526A (en) * | 2020-08-27 | 2021-07-27 | 几维通信技术(深圳)有限公司 | Terminal equipment and access network equipment for optimizing wireless communication network |
CN113179527B (en) * | 2020-08-27 | 2023-02-24 | 几维通信技术(深圳)有限公司 | Wireless communication network optimization method and computer-readable storage medium |
CN113179526B (en) * | 2020-08-27 | 2023-02-24 | 几维通信技术(深圳)有限公司 | Terminal equipment and access network equipment for optimizing wireless communication network |
WO2022237568A1 (en) * | 2021-05-10 | 2022-11-17 | 中兴通讯股份有限公司 | Base station performance optimization method and apparatus, base station, and storage medium |
CN115086972A (en) * | 2022-07-19 | 2022-09-20 | 深圳市华曦达科技股份有限公司 | Distributed wireless signal quality optimization method and system |
Also Published As
Publication number | Publication date |
---|---|
CN109041084B (en) | 2021-10-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109041084A (en) | A kind of method of radio network optimization | |
US20130343212A1 (en) | Method for self organizing network operation | |
CN106465328B (en) | For estimating method and system, mobile communications network and the user equipment of the range of geographic distance or geographic distance between at least two user equipmenies | |
CN103179580A (en) | Method and device for self-adaptively optimizing coverage | |
CN108064075B (en) | Method and apparatus for adjusting reference signal transmit power of one or more cells | |
CN108462965B (en) | Iron tower demand site sharing planning method | |
CN108476061A (en) | Underwater communications system | |
WO2020173324A1 (en) | Method and device for acquiring location of terminal, network device and storage medium | |
CN108738151A (en) | A kind of wireless prediction resource allocation methods based on coarse information | |
CN110896565B (en) | Short wave intelligent channel selection method | |
US11201649B2 (en) | Base station device, terminal device, communication system, and communication control method | |
CN104125608B (en) | A kind of method and system and its network equipment of network control shunting | |
CN104661296A (en) | Device and method for deciding transmission power of user device | |
CN112702713B (en) | Low-altitude unmanned-machine communication deployment method under multi-constraint condition | |
CN113596936A (en) | Method, device, equipment and medium for switching beams in satellite communication system | |
CN105334493A (en) | WLAN-based indoor positioning method | |
CN112612000A (en) | Intelligent configuration platform suitable for rapidly laying UWB positioning system | |
CN103533565A (en) | Wireless network optimization method and optimizer | |
CN102006654A (en) | Method and system for power allocation in multi-relay cooperative communication | |
CN107920387A (en) | A kind of method that receiver difference is realized using WIFI LANs | |
CN105453646B (en) | A kind of control method and device of activating set updating | |
CN108419245B (en) | Subnet division method and device | |
CN112203285B (en) | Multi-cell joint cooperative transmission control method, device and system | |
CN110493793B (en) | Method and system for planning new station building based on capacity LTE | |
CN110519812B (en) | ANR measurement configuration method, device, access network equipment and readable storage medium |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |