CN108093418B - Call bill information mining call prediction and dynamic base station access method based on K nearest neighbor algorithm - Google Patents

Call bill information mining call prediction and dynamic base station access method based on K nearest neighbor algorithm Download PDF

Info

Publication number
CN108093418B
CN108093418B CN201711366689.XA CN201711366689A CN108093418B CN 108093418 B CN108093418 B CN 108093418B CN 201711366689 A CN201711366689 A CN 201711366689A CN 108093418 B CN108093418 B CN 108093418B
Authority
CN
China
Prior art keywords
base station
call
access
nearest neighbor
nearby
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.)
Active
Application number
CN201711366689.XA
Other languages
Chinese (zh)
Other versions
CN108093418A (en
Inventor
曹万鹏
罗云彬
李鹏
李�浩
徐青
史辉
林绍福
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing University of Technology
Original Assignee
Beijing University of Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing University of Technology filed Critical Beijing University of Technology
Priority to CN201711366689.XA priority Critical patent/CN108093418B/en
Publication of CN108093418A publication Critical patent/CN108093418A/en
Application granted granted Critical
Publication of CN108093418B publication Critical patent/CN108093418B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
    • G06F18/24147—Distances to closest patterns, e.g. nearest neighbour classification
    • 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
    • H04L41/14—Network analysis or design
    • H04L41/142—Network analysis or design using statistical or mathematical methods
    • 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
    • H04L41/14—Network analysis or design
    • H04L41/147—Network analysis or design for predicting network behaviour
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W72/00—Local resource management
    • H04W72/50—Allocation or scheduling criteria for wireless resources
    • H04W72/52—Allocation or scheduling criteria for wireless resources based on load

Landscapes

  • Engineering & Computer Science (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Algebra (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Mathematical Physics (AREA)
  • Probability & Statistics with Applications (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

The invention discloses a call bill information mining call prediction and dynamic base station access method based on a K nearest neighbor algorithm, which comprises the following steps: step 1, searching fixed call information with relative regularity of time points and the maximum mobile terminal access amount which can be borne by a base station in a period of time in call bill big data; 2. for the telephone numbers with regularity, parameters such as conversation time points, access continuity, variance of different conversation times and the like are taken as statistical information to be used as characteristics, and each number is accurately classified based on a K nearest neighbor algorithm; 3. when the base station predicts that the saturation degree is reached, planning in advance to inform a nearby base station, and actively introducing other temporary access mobile terminal connection applications into other nearby base stations; 4. and judging the busy and idle degrees of the base station every day, and determining whether to expand the capacity of the base station and deploy a new fixed or temporary base station nearby, or temporarily close and remove the surrounding base stations.

Description

Call bill information mining call prediction and dynamic base station access method based on K nearest neighbor algorithm
Technical Field
The invention relates to a data statistical method, in particular to a call bill information mining call prediction and dynamic base station access method based on a K nearest neighbor algorithm (KNN).
Background
The number and frequency of base stations accessing the telephone on a daily basis is variable and non-uniform. The access information of different base stations and different time period telephones is mastered, so that the capacity design of the base stations and the construction layout of the base stations are guided, under the condition of minimum investment, each base station device is fully utilized, the waste of design layout is avoided, the base station connection and telephone communication experience of users is ensured, and the intelligent channel service is realized.
Obviously, if accurate prediction of the access telephone quantity and the access time of each base station can be realized, the dynamic adjustment and the overall planning of the telephone access base station are undoubtedly facilitated, and meanwhile, the planning of the construction and the layout of the base stations is facilitated. In addition, the preparation and prediction of the connection of the telephone in advance are beneficial to realizing the access of the mobile phone more quickly and rapidly, quickening the connection speed of the user and improving the connection experience of the user base station.
Disclosure of Invention
Aiming at the requirements and the defects of the traditional base station capacity design, the base station planning layout, the telephone base station connection and the like, a call bill information mining call prediction and dynamic base station access method based on the K nearest neighbor algorithm is provided, and regular characteristic quantities are mined through statistics of big data of call bills connected with the base station, so that guidance for base station layout planning and telephone access preparation is formed, and an intelligent telecommunication service mode is realized.
A call bill information mining conversation prediction and dynamic base station access method based on a K nearest neighbor algorithm comprises the following steps:
1. starting from the communication habits of people and the working rules of base stations in different areas and at different time points, searching fixed call information (or telephone access volume) of the base stations at certain time points in a period of time and the maximum mobile terminal access volume which can be borne by the base stations in the call bill big data;
2. the regular telephone numbers are characterized in that parameters such as call time points, access continuity, variance of different call time and the like are taken as statistical information, and each number is accurately classified based on a K nearest neighbor algorithm. In the subsequent operation, different scheduling means and flow control rules are adopted for different classified numbers, the conversation and the like are accurately predicted, when the time point or the time period is about to be reached, the saturation degree of the base station is checked, and according to the situation, a space is reserved for the class numbers of the mobile terminals which are relatively fixedly connected with the base station;
3. when the base station predicts that the saturation degree is reached, planning in advance to inform a nearby base station, and actively introducing other temporary access mobile terminal connection applications into other nearby base stations;
4. the busy and idle degrees of the base station every day are judged, whether the base station is expanded and a new fixed or temporary base station is deployed nearby or surrounding base stations are temporarily closed and removed is determined, the utilization rate of the base station is improved, and dynamic and self-adaptive intelligent operation and scheduling of communication equipment are realized.
Compared with the prior art, the invention has the following obvious advantages and beneficial effects:
(1) the method is based on base station connection information in call ticket data, provides call ticket information mining call prediction and dynamic base station access method based on K nearest neighbor algorithm, and predicts and prepares intervention application (access quantity) of a relatively fixed number of a user in advance by mining base station connection data in call ticket big data and based on base station capacity and connection prediction, so that a telecom operator can save cost and make full use of the existing built base station, can better serve the mobile user, and improve user experience.
(2) The dynamic scheduling of the base station is guided, and the relative fixed access numbers are classified based on the relevant difference information quoting K nearest neighbor algorithm, so that a base station dynamic scheduling mode which not only fully utilizes each base station device, saves the control cost, but also ensures better base station connection and telephone communication experience of users is realized.
Drawings
Fig. 1 is a flow chart of a call bill information mining call prediction and dynamic base station access method based on a K nearest neighbor algorithm.
Detailed Description
The invention is further described with reference to the following figures and detailed description.
The flow chart of the method of the invention is shown in figure 1 and comprises the following steps:
1. starting from the communication habits of people and the working rules of base stations in different areas and at different time points, searching fixed call information (or telephone access volume) of the base stations at certain time points in a period of time and the maximum mobile terminal access volume which can be borne by the base stations in the call bill big data;
2. for the regular telephone numbers, taking statistical information such as the call time point, the access continuity, the variance of different call times and the like as characteristics, accurately classifying each number based on the K nearest neighbor algorithm, and the specific flow is as follows:
given a training set of data, each training set of data is already classified.
Setting an initial test data DtCalculating DtEuclidean distances to all data in the training set and sorting.
Selecting training set separation DtK training set data closest to.
Comparing K training set data, and selecting the classification type with the most occurrence in the training set data, wherein the classification type is the final test data DtClassification of (3).
In the subsequent operation, different scheduling means and flow control rules are adopted for different classified numbers, the conversation and the like are accurately predicted, when the time point or the time period is about to be reached, the saturation degree of the base station is checked, and according to the situation, a space is reserved for the class numbers of the mobile terminals which are relatively fixedly connected with the base station;
3. when the base station predicts that the saturation degree is reached, planning in advance to inform a nearby base station, and actively introducing other temporary access mobile terminal connection applications into other nearby base stations;
4. the busy and idle degrees of the base station every day are judged, whether the base station is expanded and a new fixed or temporary base station is deployed nearby or surrounding base stations are temporarily closed and removed is determined, the utilization rate of the base station is improved, and dynamic and self-adaptive intelligent operation and scheduling of communication equipment are realized.

Claims (1)

1. A call bill information mining conversation prediction and dynamic base station access method based on a K nearest neighbor algorithm is characterized by comprising the following steps:
step 1, searching fixed call information with relative regularity of time points and the maximum mobile terminal access amount which can be borne by a base station in a period of time in call bill big data;
step 2, accurately classifying each number based on a K nearest neighbor algorithm by taking the call time point, access continuity and different call time variances of the call information which is relatively regular and fixed at the time point as statistical information; when the time point or the time period is about to arrive, checking the saturation degree of the base station, and reserving space for the mobile terminal category numbers which are relatively fixed and connected with the base station;
step 3, when the base station predicts that the saturation degree is reached, planning in advance and informing the nearby base station, and actively introducing other temporary access mobile terminal connection applications into other nearby base stations;
and 4, judging the daily busy and idle degrees of the base station, and determining whether to expand the capacity of the base station and deploy a new fixed or temporary base station nearby, or to temporarily close and remove the surrounding base stations.
CN201711366689.XA 2017-12-18 2017-12-18 Call bill information mining call prediction and dynamic base station access method based on K nearest neighbor algorithm Active CN108093418B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201711366689.XA CN108093418B (en) 2017-12-18 2017-12-18 Call bill information mining call prediction and dynamic base station access method based on K nearest neighbor algorithm

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201711366689.XA CN108093418B (en) 2017-12-18 2017-12-18 Call bill information mining call prediction and dynamic base station access method based on K nearest neighbor algorithm

Publications (2)

Publication Number Publication Date
CN108093418A CN108093418A (en) 2018-05-29
CN108093418B true CN108093418B (en) 2021-03-02

Family

ID=62177316

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201711366689.XA Active CN108093418B (en) 2017-12-18 2017-12-18 Call bill information mining call prediction and dynamic base station access method based on K nearest neighbor algorithm

Country Status (1)

Country Link
CN (1) CN108093418B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108810911B (en) * 2018-06-04 2021-09-14 南京邮电大学 Low-power-consumption wide area network planning method based on data mining

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102056210A (en) * 2009-11-09 2011-05-11 中国移动通信集团甘肃有限公司 Network quality monitoring method and device
CN103188645A (en) * 2011-12-29 2013-07-03 北京信威通信技术股份有限公司 Base station data service charging method used for flat network architecture
CN103796227A (en) * 2012-10-31 2014-05-14 中国电信股份有限公司 Method and system for performing wireless signal coverage analysis
CN105337753A (en) * 2014-08-06 2016-02-17 中国移动通信集团广东有限公司 Method and device for monitoring Internet real quality
CN106162749A (en) * 2015-04-15 2016-11-23 电信科学技术研究院 A kind of load-balancing method and equipment
CN107480307A (en) * 2017-09-25 2017-12-15 南京科拓软件科技有限公司 Analysing system for movable termination calling area distribution density

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3099046B1 (en) * 2015-05-25 2018-07-04 EXFO Oy Arrangement, computer program code and method for call data record processing

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102056210A (en) * 2009-11-09 2011-05-11 中国移动通信集团甘肃有限公司 Network quality monitoring method and device
CN103188645A (en) * 2011-12-29 2013-07-03 北京信威通信技术股份有限公司 Base station data service charging method used for flat network architecture
CN103796227A (en) * 2012-10-31 2014-05-14 中国电信股份有限公司 Method and system for performing wireless signal coverage analysis
CN105337753A (en) * 2014-08-06 2016-02-17 中国移动通信集团广东有限公司 Method and device for monitoring Internet real quality
CN106162749A (en) * 2015-04-15 2016-11-23 电信科学技术研究院 A kind of load-balancing method and equipment
CN107480307A (en) * 2017-09-25 2017-12-15 南京科拓软件科技有限公司 Analysing system for movable termination calling area distribution density

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
尹丹丹.移动通信网用户流失预测.《中国优秀硕士学位论文全文数据库 信息科技辑》.2017, *
池州移动基站话务统计及分析系统的应用;张辉;《万方数据知识服务平台》;20090429;全文 *
移动通信网用户流失预测;尹丹丹;《中国优秀硕士学位论文全文数据库 信息科技辑》;20170115;第三章、第3.1节 *

Also Published As

Publication number Publication date
CN108093418A (en) 2018-05-29

Similar Documents

Publication Publication Date Title
CN109195170B (en) Cell capacity expansion method and device and storage medium
CN103077718B (en) Method of speech processing, system and terminal
US10917315B2 (en) Network service quality evaluation method and system, and network device
AU730545B2 (en) Selective broadcasting of charge rates
US9451473B2 (en) Analyzing and forecasting network traffic
CN110430583B (en) SSB beam optimization configuration method and device
CN109379736B (en) Method and device for adjusting cell network quality
US20130173947A1 (en) Device and method for calculating battery usable time period for mobile station
WO2015014246A1 (en) Method and apparatus for monitoring service usage of a mobile terminal
CN112689329A (en) Beam configuration method and device, electronic equipment and computer storage medium
CN102932862A (en) Method for selecting network connection mode based on business use condition of user
CN108093418B (en) Call bill information mining call prediction and dynamic base station access method based on K nearest neighbor algorithm
CN104349426A (en) Method and device for establishing conversation connection
CN108632088B (en) Method for processing business, device and server
CN106686668B (en) method and device for selecting voice fallback cell
CN103916870B (en) Four net coordination with the synthesis analysis systems and method
CN101247612B (en) Video telephone traffic prediction method and capacity scale estimation method
CN105517021A (en) Mobile communication network user perception initiative optimized analysis method based on abnormal cell
CN102131000A (en) Method and device for providing quick contact list and mobile terminal
CN105323828A (en) Multi-mode terminal network access selection method and terminal
CN114980234A (en) Pilot frequency switching method, device and storage medium
CN107294672B (en) Scheduling method and device for cell carrier aggregation
CN108495345A (en) Access the methods, devices and systems of cell
CN105611569B (en) A kind of report method and mobile terminal of channel quality information
CN110557817B (en) Control method and device of multi-card mobile terminal, storage medium and computer equipment

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