CN108199792A - A kind of WCDMA base stations electromagnetic radiation Forecasting Methodology - Google Patents
A kind of WCDMA base stations electromagnetic radiation Forecasting Methodology Download PDFInfo
- Publication number
- CN108199792A CN108199792A CN201810104417.0A CN201810104417A CN108199792A CN 108199792 A CN108199792 A CN 108199792A CN 201810104417 A CN201810104417 A CN 201810104417A CN 108199792 A CN108199792 A CN 108199792A
- Authority
- CN
- China
- Prior art keywords
- base station
- distance
- electromagnetic radiation
- base stations
- wcdma
- 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
- H04B—TRANSMISSION
- H04B17/00—Monitoring; Testing
- H04B17/30—Monitoring; Testing of propagation channels
- H04B17/391—Modelling the propagation channel
- H04B17/3913—Predictive models, e.g. based on neural network models
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/06—Testing, 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 kind of WCDMA base stations electromagnetic radiation Forecasting Methodologies, and its step are as follows:With reference to base station call amount and future position and the distance of base station, establish a WCDMA base stations electromagnetic radiation prediction model based on telephone traffic and with base station different distance point, employ telephone traffic variation coefficient and distance change coefficient, prediction model is trained by WCDMA base stations history traffic data and with the history electromagnetic radiation value corresponding to the distance of base station difference position and these point positions again, determine the variation coefficient and correction parameter of prediction model, again by the trained prediction model of distance input of the base station call amount and future position and base station of prediction period, the electromagnetic radiation value of WCDMA base stations different distance point is predicted.The present invention considers telephone traffic variation coefficient and distance change coefficient, and comparatively fast and accurately the electromagnetic radiation value of WCDMA base stations different distance point can be predicted by this method, has certain social benefit.
Description
Technical field
The present invention relates to a kind of WCDMA base stations electromagnetic radiation Forecasting Methodologies.
Background technology
Electromagnetic radiation value around base station is to change with telephone traffic and with the variation of base station distance distance, and base station week
It encloses the variation of electromagnetic radiation value and the size of base station call amount and has certain regularity with the distance of base station, distance can be established and become
Change coefficient and telephone traffic variation coefficient to be predicted, but disclosed document and patent at present, be not based on this rule and provide
To electromagnetic radiation value Forecasting Methodology around the electricity of base station, for assessing the electromagnetic radiation value of base station different distance point.
For the deficiencies in the prior art, this patent by combine base station call amount and future position and base station away from
From establishing a WCDMA base stations electromagnetic radiation prediction model based on telephone traffic and with base station different distance point, employ traffic
Measure variation coefficient and distance change coefficient, then by WCDMA base stations history traffic data and with the distance of base station difference position with
And the history electromagnetic radiation value corresponding to these point positions is trained prediction model, determines variation coefficient and the school of prediction model
Positive parameter, then the trained prediction model of distance input by the base station call amount and future position and base station of prediction period are right
The electromagnetic radiation value of WCDMA base stations different distance point is predicted.It is shown experimentally that, the prediction model that this patent proposes can be compared with
Electromagnetic radiation value that is fast and accurately predicting WCDMA base stations different distance point.
Invention content
In order to solve the above technical problem, the present invention provides a kind of WCDMA base stations electromagnetic radiation Forecasting Methodologies.
The present invention solves above-mentioned technical problem, and the technical scheme comprises the following steps:
1) the distance base station electromagnetic radiation as input for, establishing WCDMA base station calls amount and future position and base station is predicted
Model, prediction model are as follows:
Eij=b+cHj+kYi (1)
Wherein, EijIn telephone traffic it is H for WCDMA base stationsjIt is Y with base station distanceiThe electromagnetic radiation predicted value of point, unit are
V/m, HjFor telephone traffic of the base station in the j periods, unit Erl, YiFor i points and the distance of base station, unit m, b join for correction
Number, c are telephone traffic variation coefficient, and k is distance change coefficient;
2), by WCDMA base stations history traffic data and with base station difference position distance and these point positions corresponding to
History electromagnetic radiation value, the prediction model in step 1 is trained, passes through the determining prediction model correction parameter b of training, words
The value of business amount variation coefficient c, distance change coefficient k;
3) telephone traffic of WCDMA base stations prediction period and the distance of future position and base station, are substituted into the determining prediction of step 2
Model predicts the electromagnetic radiation value of WCDMA base stations different distance point.
Above-mentioned a kind of WCDMA base stations electromagnetic radiation Forecasting Methodology, in the step 2), by WCDMA base stations history traffic
Measure data and with the history electromagnetic radiation value corresponding to the distance of base station difference position and these point positions to the prediction in step 1
Model is trained, and the training mode of model is as follows:
Wherein, prediction model is trained by historical data in the training process, by the historical data m periods
WCDMA base station call amounts Hm, the distance Y with base station difference positionl, l=1,2 ..., n input training pattern, take different ginsengs
Array b, c, k obtain different trained valuesCalculate trained valuesWith electromagnetic radiation history value ElmError, error
Calculation is:
As ε < 0.01n, with regard to deconditioning, prediction model correction parameter b, telephone traffic variation coefficient c, distance change are determined
The value of coefficient k.
The beneficial effects of the present invention are:By combining base station call amount and the distance of future position and base station, one is established
WCDMA base stations electromagnetic radiation prediction model based on telephone traffic and with base station different distance point, distance change coefficient and telephone traffic
Variation coefficient predicted, the Forecasting Methodology that this patent proposes can predict quickly and accurately WCDMA base stations difference away from
Electromagnetic radiation value from point, this method have base station construction and environmental protection larger reference value, have certain society's effect
Benefit.
Specific embodiment
The present embodiment is carried out lower premised on the content of present invention, gives detailed implementation steps, but the guarantor of the present invention
Shield range is not limited to following embodiments.
This sample plot implemented is in spacious flat region, and objective for implementation is school teaching building roof base station, laboratory apparatus
For spectrum analyzer AT6030D, measurement object is WCDMA base stations.
With reference to specific embodiment, the present invention is described further, the specific steps are:
Step 1:Establish the distance base station electromagnetic radiation as input of WCDMA base station calls amount and future position and base station
Prediction model, prediction model are as follows:
Eij=b+cHj+kYi (4)
Wherein, EijIn telephone traffic it is H for WCDMA base stationsjIt is Yi with base station distanceiThe electromagnetic radiation predicted value of point, unit
For v/m, HjFor telephone traffic of the base station in the j periods, unit Erl, YiFor i points and the distance of base station, unit m, b are correction
Parameter, c are telephone traffic variation coefficient, and k is distance change coefficient.
Step 2:By WCDMA base stations history traffic data and with base station difference position distance and these point position institutes
Corresponding history electromagnetic radiation value, is trained the prediction model in step 1, passes through the determining prediction model correction parameter of training
B, telephone traffic variation coefficient c, distance change coefficient k value.
In this embodiment, by WCDMA base stations the m periods telephone traffic and with base station distance be 10m, 15m,
The point of 20m ..., 55m distances and its corresponding history electromagnetic radiation value are trained prediction model, the training mould of model
Formula is as follows:
Wherein, prediction model is trained by historical data in the training process, by the historical data m periods
WCDMA base station call amounts Hm=6.316, the distance Y with base station difference positionl, l=1,2 ..., 10, wherein Y1=10m, Y2=
15m, Y3=20m ..., Y10=55m inputs training pattern, takes different parameter group b, c, k, obtain different trained valuesCalculate trained valuesWith electromagnetic radiation history value ElmError, wherein E1m=1.222, E2m=1.211 ...,
E10m=0.854, unit v/m, error calculation mode are:
As ε < 0.01 × 10, i.e., when ε < 0.1 are with regard to deconditioning, determine prediction model parameters, correction parameter b=0.356,
Telephone traffic variation coefficient c=0.1476, distance change coefficient k=- 0.006583.
Step 3:The telephone traffic of WCDMA base stations prediction period and the distance of future position and base station are substituted into what step 2 determined
Prediction model predicts the electromagnetic radiation value of WCDMA base stations different distance point.
In this embodiment, by base station call amount Hj=7.216, unit Erl and the distance Y of base station differencei,
Middle YiValue be 10,20,30 ..., 60, unit m input trained prediction model and are predicted, as follows:
Eij=0.356+0.1476Hj-0.006583Yi (7)
By input value H when predictingjAnd YiTrained prediction model formula (7) is substituted into, wherein predicted value and measured value is as follows
Shown in table:
1 predicted value E of tableijWith the displaying of measured value
It as can be seen that can be compared with by base station call amount and future position and the distance input prediction model of base station from prediction result
The electromagnetic radiation value by WCDMA base stations different distance point soon is predicted, while can be seen that WCDMA from experimental result
The electromagnetic radiation predicted value and measured value of base station difference position are all more close, illustrates to utilize the method can quickly and accurately
The electromagnetic radiation value of WCDMA base stations different distance point predicted, while experiment show method used herein
Validity.
Claims (2)
1. a kind of WCDMA base stations electromagnetic radiation Forecasting Methodology, which is characterized in that include the following steps:
1) the distance electromagnetic radiation prediction model in base station as input of WCDMA base station calls amount and future position and base station, is established,
Prediction model is as follows:
Eij=b+cHj+kYi (1)
Wherein, EijIn telephone traffic it is H for WCDMA base stationsjIt is Y with base station distanceiThe electromagnetic radiation predicted value of point, unit v/m,
HjFor telephone traffic of the base station in the j periods, unit Erl, YiFor i points and the distance of base station, unit m, b are correction parameter, c
For telephone traffic variation coefficient, k is distance change coefficient;
2), by WCDMA base stations history traffic data and with base station difference position distance and these point positions corresponding to going through
History electromagnetic radiation value, is trained the prediction model in step 1, passes through the determining prediction model correction parameter b of training, telephone traffic
The value of variation coefficient c, distance change coefficient k;
3) telephone traffic of WCDMA base stations prediction period and the distance of future position and base station, are substituted into the determining prediction mould of step 2
Type predicts the electromagnetic radiation value of WCDMA base stations different distance point.
2. a kind of WCDMA base stations electromagnetic radiation Forecasting Methodology as described in claim 1, in the step 2), which is characterized in that
History electromagnetism spoke by WCDMA base stations history traffic data and corresponding to the distance of base station difference position and these point positions
It penetrates value to be trained the prediction model in step 1, the training mode of model is as follows:
Wherein, prediction model is trained by historical data in the training process, by the WCDMA of historical data m periods
Base station call amount Hm, the distance Y with base station difference positionl, l=1,2 ..., n, input training pattern, take different parameter group b,
C, k obtain different trained valuesCalculate trained valuesWith electromagnetic radiation history value ElmError, error calculation side
Formula is:
As ε < 0.01n, with regard to deconditioning, prediction model correction parameter b, telephone traffic variation coefficient c, distance change coefficient k are determined
Value.
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 true CN108199792A (en) | 2018-06-22 |
CN108199792B 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) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111065109A (en) * | 2020-01-16 | 2020-04-24 | 湘潭大学 | Method for predicting electromagnetic radiation of base station of heterogeneous cellular network in rural area |
CN115243271A (en) * | 2022-07-14 | 2022-10-25 | 中国联合网络通信集团有限公司 | Radiation evaluation method, device and storage medium |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103440428A (en) * | 2013-09-12 | 2013-12-11 | 重庆大学 | Method for determining self-adaption dynamic weight of combined prediction model for wind electricity power |
CN103874090A (en) * | 2014-03-31 | 2014-06-18 | 湘潭大学 | GSM communication base station electromagnetic radiation prediction 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 |
-
2018
- 2018-02-02 CN CN201810104417.0A patent/CN108199792B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103440428A (en) * | 2013-09-12 | 2013-12-11 | 重庆大学 | Method for determining self-adaption dynamic weight of combined prediction model for wind electricity power |
CN103874090A (en) * | 2014-03-31 | 2014-06-18 | 湘潭大学 | GSM communication base station electromagnetic radiation prediction 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 |
Non-Patent Citations (1)
Title |
---|
何晴晴: "移动通信基站电磁辐射预测方法研究", 《湘潭大学硕士学位论文》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111065109A (en) * | 2020-01-16 | 2020-04-24 | 湘潭大学 | Method for predicting electromagnetic radiation of base station of heterogeneous cellular network in rural area |
CN111065109B (en) * | 2020-01-16 | 2023-08-22 | 湘潭大学 | Rural area heterogeneous cellular network base station electromagnetic radiation prediction method |
CN115243271A (en) * | 2022-07-14 | 2022-10-25 | 中国联合网络通信集团有限公司 | Radiation evaluation method, device and storage medium |
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 |
Also Published As
Publication number | Publication date |
---|---|
CN108199792B (en) | 2021-04-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106507372A (en) | A kind of wireless network zone-skipping coverage detection method, device and communication system | |
CN107390524B (en) | A kind of blast-melted quality optimization control method based on bilinearity Subspace Identification | |
CN108199792A (en) | A kind of WCDMA base stations electromagnetic radiation Forecasting Methodology | |
CN104462808A (en) | Method for fitting safe horizontal displacement and dynamic data of variable sliding window of water level | |
CN104598155B (en) | A kind of smoothing processing method and device for touch-screen curve of output | |
CN112541613B (en) | Multi-layer ConvLSTM sea surface temperature prediction calculation method based on remote sensing data | |
CN106021698B (en) | The UKFNN aluminium electroloysis power consumption model construction method updated based on iteration | |
CN104254083B (en) | Predict the method and device of traffic hotspots | |
CN114329347B (en) | Method and device for predicting metering error of electric energy meter and storage medium | |
CN111079993A (en) | Traffic flow prediction method and device, electronic equipment and storage medium | |
CN116862079B (en) | Enterprise pollutant emission prediction method and prediction system | |
CN111126550B (en) | Neural network molten steel temperature forecasting method based on Monte Carlo method | |
CN115880101B (en) | Water conservancy data management system based on big data | |
CN117388951A (en) | Plum rain prediction method, apparatus and equipment | |
CN111622274A (en) | Method and system for predicting settlement of foundation of high-fill foundation of large grained soil in mountainous area | |
CN114875196B (en) | Method and system for determining converter tapping quantity | |
CN110442930A (en) | Virtual measurement method and virtual measurement device | |
CN108062435B (en) | Fatigue life calibration method based on nominal stress method | |
CN114486821B (en) | Metallurgical spectral feature regression method, device, electronic equipment and storage medium | |
CN115049116A (en) | Method and device for predicting container terminal throughput, terminal device and medium | |
CN109632649A (en) | SF based on artificial neural network6Gas fiber laser arrays quantitative analysis method | |
CN114879042A (en) | Method and device for predicting partial capacity and discharge capacity of battery cell and electronic equipment | |
JP2015168870A (en) | Rephosphorization amount prediction method and device, and converter dephosphorization control method | |
CN103743362B (en) | The measuring method of electrical sheet surface insulation coating applications amount | |
CN108229757B (en) | Electromagnetic radiation prediction method for CDMA base station |
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 |