CN108199792B - WCDMA base station electromagnetic radiation prediction method - Google Patents

WCDMA base station electromagnetic radiation prediction method Download PDF

Info

Publication number
CN108199792B
CN108199792B CN201810104417.0A CN201810104417A CN108199792B CN 108199792 B CN108199792 B CN 108199792B CN 201810104417 A CN201810104417 A CN 201810104417A CN 108199792 B CN108199792 B CN 108199792B
Authority
CN
China
Prior art keywords
base station
distance
electromagnetic radiation
traffic
prediction
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
CN201810104417.0A
Other languages
Chinese (zh)
Other versions
CN108199792A (en
Inventor
杨万春
吴涛
谭平安
张园
彭艳芬
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.)
Xiangtan University
Original Assignee
Xiangtan University
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 Xiangtan University filed Critical Xiangtan University
Priority to CN201810104417.0A priority Critical patent/CN108199792B/en
Publication of CN108199792A publication Critical patent/CN108199792A/en
Application granted granted Critical
Publication of CN108199792B publication Critical patent/CN108199792B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04BTRANSMISSION
    • H04B17/00Monitoring; Testing
    • H04B17/30Monitoring; Testing of propagation channels
    • H04B17/391Modelling the propagation channel
    • H04B17/3913Predictive models, e.g. based on neural network models
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W24/00Supervisory, monitoring or testing arrangements
    • H04W24/06Testing, supervising or monitoring using simulated traffic

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Physics & Mathematics (AREA)
  • Electromagnetism (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

The invention discloses a WCDMA base station electromagnetic radiation prediction method, which comprises the following steps: combining the telephone traffic of the base station and the distance between the prediction point and the base station, establishing a WCDMA base station electromagnetic radiation prediction model based on the telephone traffic and the points with different distances from the base station, adopting a telephone traffic variation coefficient and a distance variation coefficient, training the prediction model according to the historical telephone traffic data of the WCDMA base station, the distances between the data and different points of the base station and the historical electromagnetic radiation values corresponding to the points, determining the variation coefficient and the correction parameters of the prediction model, inputting the telephone traffic of the base station and the distance between the prediction point and the base station in the prediction period into the trained prediction model, and predicting the electromagnetic radiation values of the different points of the WCDMA base station. The invention considers the traffic change coefficient and the distance change coefficient, can quickly and accurately predict the electromagnetic radiation values of different distance points of the WCDMA base station by the method, and has certain social benefit.

Description

WCDMA base station electromagnetic radiation prediction method
Technical Field
The invention relates to a WCDMA base station electromagnetic radiation prediction method.
Background
The electromagnetic radiation value around the base station is changed along with the change of telephone traffic and the distance between the base station and the electromagnetic radiation value, and the change of the electromagnetic radiation value around the base station has certain regularity with the size of the telephone traffic of the base station and the distance between the base station and the electromagnetic radiation value, and a distance change coefficient and a telephone traffic change coefficient can be established for prediction.
Aiming at the defects in the prior art, the method establishes a WCDMA base station electromagnetic radiation prediction model based on telephone traffic and different distance points from a base station by combining the telephone traffic of the base station and the distance between the prediction point and the base station, adopts the telephone traffic variation coefficient and the distance variation coefficient, trains the prediction model according to historical telephone traffic data of the WCDMA base station, the distance between the data and different point positions of the base station and the historical electromagnetic radiation values corresponding to the point positions, determines the variation coefficient and the correction parameter of the prediction model, inputs the telephone traffic of the base station and the distance between the prediction point and the base station in a prediction time period into the trained prediction model, and predicts the electromagnetic radiation values of the different distance points of the WCDMA base station. Experiments show that the prediction model provided by the patent can quickly and accurately predict the electromagnetic radiation values of different distance points of the WCDMA base station.
Disclosure of Invention
In order to solve the above technical problems, the present invention provides a method for predicting electromagnetic radiation of a WCDMA base station.
The technical scheme for solving the technical problems comprises the following steps:
1) establishing a base station electromagnetic radiation prediction model taking the traffic of the WCDMA base station and the distance between the prediction point and the base station as input, wherein the prediction model is as follows:
Eij=b+cHj+kYi (1)
wherein E isijFor WCDMA base station at traffic volume of HjAt a distance of Y from the base stationiThe predicted value of the electromagnetic radiation of the point is in the unit of v/m and HjThe unit is Erl, Y for the traffic of the base station in j time periodiThe unit is m, b is a correction parameter, c is a traffic change coefficient, and k is a distance change coefficient;
2) training the historical traffic data of the WCDMA base station, the distances between the historical traffic data and different point locations of the base station and the historical electromagnetic radiation values corresponding to the point locations, training the prediction model in the step 1, and determining the values of a correction parameter b, a traffic change coefficient c and a distance change coefficient k of the prediction model through training;
3) and substituting the telephone traffic of the WCDMA base station in the prediction time period and the distance between the prediction point and the base station into the prediction model determined in the step 2, and predicting the electromagnetic radiation values of different distance points of the WCDMA base station.
In the above method for predicting electromagnetic radiation of a WCDMA base station, in step 2), the prediction model in step 1 is trained according to historical traffic data of the WCDMA base station, distances between different point locations of the base station and historical electromagnetic radiation values corresponding to the point locations, and the training mode of the model is as follows:
Figure BDA0001567381520000021
wherein, in the training process, the prediction model is trained through historical data, and the traffic H of the WCDMA base station in the time period of the historical data m is usedmDistance Y from different points of the base stationl1,2, n, inputting training model, and taking different parameter sets b, cK, obtaining different training values
Figure BDA0001567381520000022
Calculating a training value
Figure BDA0001567381520000023
And electromagnetic radiation history value ElmThe error calculation method is as follows:
Figure BDA0001567381520000024
and when the epsilon is less than 0.01n, stopping training, and determining values of a prediction model correction parameter b, a telephone traffic change coefficient c and a distance change coefficient k.
The invention has the beneficial effects that: the method has the advantages that the electromagnetic radiation values of different distance points of the WCDMA base station can be predicted quickly and accurately by the prediction method provided by the patent, and the method has a high reference value for base station construction and environmental protection and has certain social benefits.
Detailed Description
The present embodiment is performed on the premise of the present disclosure, and detailed implementation procedures are given, but the scope of the present disclosure is not limited to the following embodiments.
In the experiment place, in an open and flat area, the implementation object is a teaching building roof base station, the experimental instrument is a spectrum analyzer AT6030D, and the measurement object is a WCDMA base station.
The invention is further described with reference to specific examples, which include the following steps:
the method comprises the following steps: establishing a base station electromagnetic radiation prediction model taking the traffic of the WCDMA base station and the distance between the prediction point and the base station as input, wherein the prediction model is as follows:
Eij=b+cHj+kYi (4)
wherein E isijFor WCDMA base station at traffic volume of HjAt a distance Yi from the base stationiThe predicted value of the electromagnetic radiation of the point is in the unit of v/m and HjThe unit is Erl, Y for the traffic of the base station in j time periodiThe unit is m, b is a correction parameter, c is a traffic change coefficient, and k is a distance change coefficient.
Step two: and (3) training the historical traffic data of the WCDMA base station, the distances between the historical traffic data and different point positions of the base station and the historical electromagnetic radiation values corresponding to the point positions, training the prediction model in the step (1), and determining the values of a correction parameter b, a traffic change coefficient c and a distance change coefficient k of the prediction model through training.
In this embodiment, a prediction model is trained on traffic of a WCDMA base station in an m time period, points at distances of 10m, 15m, 20m, and 55m from the base station, and historical electromagnetic radiation values corresponding to the points, and a training mode of the model is as follows:
Figure BDA0001567381520000031
wherein, in the training process, the prediction model is trained through historical data, and the traffic H of the WCDMA base station in the time period of the historical data m is usedm6.316, distance Y from different points of the base stationl1,2, 10, wherein Y is1=10m,Y2=15m,Y3=20m,…,Y10Inputting the training model at 55m, taking different parameter groups b, c and k, and obtaining different training values
Figure BDA0001567381520000032
Calculating a training value
Figure BDA0001567381520000033
And electromagnetic radiation history value ElmError of (2), wherein E1m=1.222,E2m=1.211,...,E10m0.854, unit is v/m, and error calculation mode is as follows:
Figure BDA0001567381520000034
when epsilon is less than 0.01 multiplied by 10, namely when epsilon is less than 0.1, the training is stopped, the prediction model parameters are determined, the correction parameter b is 0.356, the traffic volume change coefficient c is 0.1476, and the distance change coefficient k is-0.006583.
Step three: and (3) substituting the telephone traffic of the WCDMA base station in the prediction time period and the distance between the prediction point and the base station into the prediction model determined in the step (2), and predicting the electromagnetic radiation values of different distance points of the WCDMA base station.
In this embodiment, the base station traffic H is setj7.216 in Erl units, and distance Y from a different point of the base stationiWherein Y isiIs 10,20,30, …,60, and the unit is m, and the prediction is input into the trained prediction model, as follows:
Eij=0.356+0.1476Hj-0.006583Yi (7)
will predict the input value HjAnd YiSubstituting into the trained prediction model equation (7), wherein the predicted values and the measured values are shown in the following table:
TABLE 1 prediction value EijAnd presentation of measured values
Figure BDA0001567381520000035
Figure BDA0001567381520000041
The prediction result shows that the electromagnetic radiation values of different distance points of the WCDMA base station can be rapidly predicted by inputting the telephone traffic of the base station and the distance between the prediction point and the base station into the prediction model, and meanwhile, the experimental result shows that the predicted value and the measured value of the electromagnetic radiation of different point positions of the WCDMA base station are relatively similar, which shows that the electromagnetic radiation values of different distance points of the WCDMA base station can be rapidly and accurately predicted by using the method, and the effectiveness of the method used by the invention is verified by the experimental result.

Claims (1)

1. A WCDMA base station electromagnetic radiation prediction method is characterized by comprising the following steps:
1) establishing a base station electromagnetic radiation prediction model taking the traffic of the WCDMA base station and the distance between the prediction point and the base station as input, wherein the prediction model is as follows:
Eij=b+cHj+kYi (1)
wherein E isijFor WCDMA base station at traffic volume of HjAt a distance of Y from the base stationiThe predicted value of the electromagnetic radiation of the point is in the unit of v/m and HjThe unit is Erl, Y for the traffic of the base station in j time periodiThe unit is m, b is a correction parameter, c is a traffic change coefficient, and k is a distance change coefficient;
2) training the historical traffic data of the WCDMA base station, the distances between the historical traffic data and different point locations of the base station and the historical electromagnetic radiation values corresponding to the point locations, training the prediction model in the step 1, and determining the values of a correction parameter b, a traffic change coefficient c and a distance change coefficient k of the prediction model through training;
the training pattern of the model is as follows:
Figure FDA0002909285030000011
wherein, in the training process, the prediction model is trained through historical data, and the traffic H of the WCDMA base station in the time period of the historical data m is usedmDistance Y from different points of the base stationlAnd l 1,2, n, inputting the training model, taking different parameter groups b, c and k, and obtaining different training values
Figure FDA0002909285030000012
Calculating a training value
Figure FDA0002909285030000013
And history of electromagnetic radiationValue ElmThe error calculation method is as follows:
Figure FDA0002909285030000014
when epsilon is less than 0.01n, stopping training, and determining values of a prediction model correction parameter b, a telephone traffic change coefficient c and a distance change coefficient k;
3) and substituting the telephone traffic of the WCDMA base station in the prediction time period and the distance between the prediction point and the base station into the prediction model determined in the step 2, and predicting the electromagnetic radiation values of different distance points of the WCDMA base station.
CN201810104417.0A 2018-02-02 2018-02-02 WCDMA base station electromagnetic radiation prediction method Active CN108199792B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810104417.0A CN108199792B (en) 2018-02-02 2018-02-02 WCDMA base station electromagnetic radiation prediction method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810104417.0A CN108199792B (en) 2018-02-02 2018-02-02 WCDMA base station electromagnetic radiation prediction method

Publications (2)

Publication Number Publication Date
CN108199792A CN108199792A (en) 2018-06-22
CN108199792B true CN108199792B (en) 2021-04-23

Family

ID=62591937

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810104417.0A Active CN108199792B (en) 2018-02-02 2018-02-02 WCDMA base station electromagnetic radiation prediction method

Country Status (1)

Country Link
CN (1) CN108199792B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111065109B (en) * 2020-01-16 2023-08-22 湘潭大学 Rural area heterogeneous cellular network base station electromagnetic radiation prediction method
CN115243271B (en) * 2022-07-14 2023-09-05 中国联合网络通信集团有限公司 Radiation evaluation method, device and storage medium

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103874090A (en) * 2014-03-31 2014-06-18 湘潭大学 GSM communication base station electromagnetic radiation prediction method

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103440428B (en) * 2013-09-12 2016-05-04 重庆大学 The self adaptation changeable weight of wind power combination forecasting is determined method
CN105184421A (en) * 2015-09-28 2015-12-23 南方电网科学研究院有限责任公司 Electromagnetic environment parameter prediction method based on data segmentation and model calibration

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103874090A (en) * 2014-03-31 2014-06-18 湘潭大学 GSM communication base station electromagnetic radiation prediction method

Also Published As

Publication number Publication date
CN108199792A (en) 2018-06-22

Similar Documents

Publication Publication Date Title
CN107124238B (en) Novel TD-SCDMA communication base station electromagnetic radiation prediction method
CN108199792B (en) WCDMA base station electromagnetic radiation prediction method
CN106878955B (en) A kind of interior floor location method and positioning device
CN104732296A (en) Modeling method for distributed photovoltaic output power short-term prediction model
CN105421173A (en) Method for improving double-line operation railway track control network
MX2022000808A (en) Method for generating quality prediction model, quality prediction model, quality prediction method, method for manufacturing metal material, device for generating quality prediction model, and quality prediction device.
CN104239742A (en) Transformer far-field noise prediction method and system
CN104050380A (en) LF furnace final temperature forecasting method based on Adaboost-PLS-ELM
CN110334406A (en) It is a kind of consider the especially big value of wind speed the Maximum wind speed return period determine method and apparatus
CN104598155A (en) Smoothing method and device
CN106412817B (en) A kind of localization method and its device of mobile terminal
CN108183754B (en) Electromagnetic radiation prediction method for GSM base station
CN104850746A (en) Equivalent salt deposit density prediction method based on fourth-order Runge-Kutta and simulated annealing
CN104091090A (en) Calculating method for equivalent sound level A of any point in transformer substation sound field
CN114083770A (en) Method, device, equipment and storage medium for adjusting process parameters and training models
CN107167658B (en) A kind of jamproof electric system fundamental frequency of high-precision and Method for Phase Difference Measurement
CN105336637A (en) Method for measuring wafer deformation
MX2021010455A (en) Method for tin bath monitoring and control.
CN103870656A (en) Method for determining downburst crosswind profile
CN114996959B (en) CT test piece service life prediction method based on crack propagation
CN109583112A (en) A kind of aerial condutor based on ABAQUS finite element software looks for shape method
CN106840130A (en) A device and method is put in high accuracy engineering survey setting-out
KR102209587B1 (en) METHOD FOR DETERMINING INTRODUCTION AMOUNT OF Fe-Ti
CN107632639B (en) The method and device of temperature index dynamic regulation
Dong et al. Control and optimization of quality cost based on discrete grey forecasting model

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