CN114422003B - Method, device and storage medium for detecting influence on MIMO data transmission ratio - Google Patents

Method, device and storage medium for detecting influence on MIMO data transmission ratio Download PDF

Info

Publication number
CN114422003B
CN114422003B CN202210327648.4A CN202210327648A CN114422003B CN 114422003 B CN114422003 B CN 114422003B CN 202210327648 A CN202210327648 A CN 202210327648A CN 114422003 B CN114422003 B CN 114422003B
Authority
CN
China
Prior art keywords
data transmission
floor
transmission ratio
mimo data
floors
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
CN202210327648.4A
Other languages
Chinese (zh)
Other versions
CN114422003A (en
Inventor
寇红侠
卢军
闫兴秀
黄聿辰
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.)
Orange Frame Technology Jiangsu Co ltd
Original Assignee
Orange Frame Technology Jiangsu Co ltd
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 Orange Frame Technology Jiangsu Co ltd filed Critical Orange Frame Technology Jiangsu Co ltd
Priority to CN202210327648.4A priority Critical patent/CN114422003B/en
Publication of CN114422003A publication Critical patent/CN114422003A/en
Application granted granted Critical
Publication of CN114422003B publication Critical patent/CN114422003B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B7/00—Radio transmission systems, i.e. using radiation field
    • H04B7/02—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas
    • H04B7/04—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
    • H04B7/0413—MIMO systems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/048—Activation functions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/08—Testing, supervising or monitoring using real traffic

Abstract

The invention relates to a detection method, a device and a storage medium for influencing the MIMO data transmission ratio, belonging to the technical field of mobile communication. The invention comprises the following steps: step one, collecting training data; step two, processing training data; step three, modeling; step four, training; step five, calculating; step six, evaluating; step seven, adjustment; the invention adopts RFID or Bluetooth to collect the floor line loss value, and the authenticity of the data source is reliable; by adopting the Resnet convolutional neural network, the data fitting performance is strong, the output result is accurate, and the MIMO data transmission ratio can be obtained by rectifying and modifying according to the standard line loss tensor.

Description

Method, device and storage medium for detecting influence on MIMO data transmission ratio
Technical Field
The invention relates to a detection method, a device and a storage medium for influencing the MIMO data transmission ratio, belonging to the technical field of mobile communication.
Background
With the further popularization of the application of the mobile internet and the internet of things, people have stronger and stronger requirements on mobile communication networks. According to data traffic statistics of network parts of various large operators, a large amount of traffic of mobile applications occurs indoors, the data percentage of the traffic is almost over 75%, and therefore coverage of indoor scenes becomes a necessary place for mobile operators.
At present, a split-level coverage scheme is adopted to enable a floor where a terminal device (the RRU1 of a cell) is located and an upper floor and a lower floor (the RRU 2) of the terminal device to form MIMO, so that the download rate of a user is improved, and the user experience is improved.
ResNet is a network structure proposed by Rekaming in 2015, and obtains the first name of ILSVRC-2015 classification tasks, and also obtains the first names of ImageNet detection, ImageNet localization, COCO detection, COCO segmentation and other tasks.
Resnet, also known as residual neural network, refers to the idea of adding residual learning (residual learning) to the conventional convolutional neural network, which solves the problems of gradient dispersion and accuracy reduction (training set) in the deep network, so that the network can be deeper and deeper, not only the accuracy is ensured, but also the speed is controlled.
The Residual block Residual module is a common module of a Residual neural network ResNet, and 8 Residual block structures are additionally arranged in the invention.
In the paper Deep Residual Learning for Image registration, the principle of a Residual neural network and a Residual module is explained in detail, and the invention is to apply the Residual neural network and the Residual module in the field of calculating the MIMO data transmission ratio under an indoor coverage scene.
At present, MIMO data transmission ratio is uneven under various indoor coverage scenes, and monitoring is not easy. And generally, under the scene that the indoor division of the building is installed to be staggered floor coverage, the MIMO cannot be carried out on the first floor of the building floor, and the first floor generally interacts with the macro station outside the building floor. The top floor of the same building floor is also inconvenient to apply the MIMO technology. There is generally no need to consider MIMO situations for the first and top of a building floor.
The existing patent cn201611086093.x is a same-layer branch interleaving method for realizing an FDD-LTE dual-stream data transmission mode indoors, which realizes the dual-stream data transmission mode by designing a system backbone as a dual backbone, designing an antenna feeder branch of each floor as a single-path antenna feeder, and respectively connecting an odd-numbered antenna feeder branch and an even-numbered antenna feeder branch in each floor with one of the two backbones. Because double-trunk wiring is carried out on the same layer and antenna ports are required to be arranged alternately according to the double trunks, the requirement on the on-site construction accuracy is high, and the actual on-site deployment environment is difficult to guarantee to be consistent with the ideal requirement; the wiring cost of the double trunks is high, two trunk feeders need to be arranged, and the installation time is approximately doubled.
Disclosure of Invention
The invention aims to solve the technical problem that the MIMO data transmission ratio under various indoor coverage scenes is difficult to monitor. The invention applies the residual error neural network and the residual error module to
The invention provides a detection method for influencing the MIMO data transmission ratio, which is characterized in that a plurality of floors covered by staggered floors are installed based on the indoor division of a building, and the first floor and the top floor of the building are not considered, wherein a Keras framework is adopted to construct a convolutional neural network with a Resnet50 Residual error structure, and the convolutional neural network is added with 8 Residual error blocks, namely a Residual block structure, and the detection method comprises the following steps:
step one, collecting training data:
collecting a plurality of floors F = { F1，f2，f3，…fi… } of the line loss values a = { a =11，a12，a12，…amn…, and collecting the proportion R of the MIMO data transmission with the granularity of minutes in one hour of a plurality of floors1，r2，r3，…r60}; wherein m is a floor, n is the nth antenna port of the m floor, amnThe line loss value of the nth antenna port of the mth floor is referred to.
Step two, processing training data:
a plurality of floors F = { F1，f2，f3，…fi… } of any three consecutive floors (f)i-1，fi，fi+1) As a basic sample, a tensor formed by arranging the line loss values of all antenna ports of any continuous three floors is used as sample data mode (A);
wherein mode (A) =
[a（m+1）1 a（m+1）2 a（m+1）3 … a（m+1）n]
[am1 am2 am3 … amn]
[a（m-1）1 a（m-1）2 a（m-1）3 …a（m-1）n]；
Taking a MIMO data transmission occupation mode of minute granularity within one hour of each floor of any continuous three floors as a sample label;
step three, modeling:
inputting the sample data obtained in the second step into the convolutional neural network, wherein the adopted convolutional kernel is 3 x 3, and the output of the convolutional neural network is the MIMO data transmission ratio of the middle floor of any three continuous floors;
step four, training:
adopting K-fold cross validation, inputting sample data into the convolutional neural network for training according to the sample data collected in the step one and in a mode of a training set and a validation set 8:2, and after training is finished, adding and averaging a training result model to obtain a final model; finally, outputting the model to obtain the standard MIMO data transmission ratio;
step five, calculating:
if the MIMO data transmission ratio of a certain floor of a certain building needs to be calculated;
taking a certain floor as an intermediate floor, collecting line loss values of all antenna ports of three continuous floors, and arranging the line loss values to form tensors as calculation data;
inputting the calculated data into the convolutional neural network trained in the fourth step to obtain the MIMO data transmission ratio of a certain floor;
Step six, evaluation:
and C, evaluating according to the MIMO data transmission ratio of the middle floor obtained in the step five:
the higher the MIMO data transmission of the middle floor is, the better the network effect of the floor is;
the lower the MIMO data transmission occupied value of the middle floor is, the poorer the network effect of the floor is;
when the MIMO data transmission ratio of the floor is lower than the standard MIMO data transmission ratio in the fourth step, the antenna ports of three consecutive floors, in which a certain floor is used as a middle floor, need to be adjusted;
step seven, adjustment:
taking an average number of all line loss values of three continuous floors with a certain floor as an intermediate floor, marking the line loss values with larger relative average difference in all line loss values, rectifying the antenna ports corresponding to the marked line loss values, and inputting the rectified calculation data into the convolutional neural network again for verification until the obtained MIMO data transmission ratio of the intermediate floor is close to the standard MIMO data transmission ratio.
The scheme is further improved in that: the line loss value is obtained through RFID or Bluetooth; and the MIMO data transmission ratio is acquired through DPI data.
Further, a detection apparatus for influencing the occupation ratio of MIMO data transmission includes: the data acquisition module is used for acquiring line loss values of a plurality of antenna ports of a plurality of floors and acquiring the MIMO data transmission ratio of minute granularity in one hour of each floor of the plurality of floors;
the neural network building module is used for building a convolutional neural network with a Resnet50 residual error structure;
and the model training module is used for inputting the sample data into the convolutional neural network for training according to a training set and a verification set 8: 2. The steps of the method for detecting the influence of the MIMO data transmission ratio under the staggered layer coverage scene are realized.
Further, an electronic device includes: a processor, a memory, and a communication bus;
the communication bus is used for realizing connection communication between the processor and the memory;
the processor is configured to execute one or more programs stored in the memory to implement steps of a detection method that affects MIMO data transmission duty cycle.
Further, a computer readable storage medium stores one or more programs which are executable by one or more processors to implement steps of a method of affecting detection of MIMO data transmission duty cycle in a wrong-layer coverage scenario.
The invention has the advantages that the installation is simpler, the requirement on constructors is lower, and the site environment can be seen as an ideal environment; synthesizing sample data for training by collecting line loss value data of a large number of antennas and MIMO data transmission ratio data of each layer of DPI data, thereby obtaining a model for predicting the MIMO data transmission ratio according to the line loss value; after obtaining the model, or when the MIMO data transmission ratio of a certain building floor is required to be obtained, only the line loss value of the antenna of the building floor is required to be acquired; when the antennas of the building floor with low MIMO data transmission occupation are required to be adjusted, the corresponding antennas required to be adjusted are found according to the line loss value, and the MIMO data transmission occupation data of each layer is not required to be slowly acquired; and a tensor splicing mode of continuous 3-layer line loss values is adopted, understanding of the principle of MIMO bottom layer formation under staggered layer coverage is reflected, and the data relation between the continuous 3-layer line loss values is extracted, so that mapping of the line loss values and the MIMO data transmission ratio is realized.
Drawings
The invention is further described below with reference to the accompanying drawings.
FIG. 1 is a schematic flow chart of an embodiment of the present invention.
FIG. 2 is a schematic diagram of a neural network according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments with reference to the accompanying drawings will provide further detailed description of the embodiments of the present invention, such as the mutual positions and connection relationships between the related parts, the functions and working principles of the parts, and the operation and use methods, to help those skilled in the art to more completely, accurately and deeply understand the concept and technical solutions of the present invention.
As shown in fig. 1, the present embodiment provides a method, an apparatus and a storage medium for detecting the influence on the MIMO data transmission ratio according to the present invention. The building-based room is installed into a plurality of floors covered in staggered floors, wherein a Keras framework is adopted to build a convolutional neural network with a Resnet50 Residual error structure, and 8 Residual error block joints are added into the convolutional neural network, namely the Residual block structure.
And generally, in the indoor coverage scene of the building, the first floor and the top floor basically do not generate split-level coverage with the rooms in the building. There is no need to consider the case of floor 1 and the roof.
The embodiment comprises the following steps:
step one, collecting training data:
collecting a plurality of floors F = { F1，f2，f3，…fi… } of the line loss values a = { a =11，a12，a12，…amn…, and collecting the proportion R of the MIMO data transmission with the granularity of minutes in one hour of a plurality of floors 1，r2，r3，…r60}; wherein m is a floor, n is the nth antenna port of the m floor, amnThe line loss value of the nth antenna port of the mth floor is referred to.
Step two, processing training data:
a plurality of floors F = { F1，f2，f3，…fi… any three consecutive floors (f)i-1，fi，fi+1) As a basic sample, taking tensor formed by arranging line loss values of all antenna ports of any continuous three floors as sample data mode (A);
wherein mode (A) =
[a（m+1）1 a（m+1）2 a（m+1）3 … a（m+1）n]
[am1 am2 am3 … amn]
[a（m-1）1 a（m-1）2 a（m-1）3 …a（m-1）n]；
Taking a MIMO data transmission occupation mode of minute granularity within one hour of each floor of any continuous three floors as a sample label;
step three, modeling:
inputting the sample data obtained in the second step into a convolutional neural network, wherein the adopted convolutional kernel is 3 x 3, and the output of the convolutional neural network is the MIMO data transmission ratio of the middle floor of any three continuous floors;
step four, training:
adopting K-fold cross validation, inputting the sample data into a convolutional neural network for training according to the sample data acquired in the step one and the modes of a training set and a validation set 8:2, and after the training is finished, adding and averaging a training result model to obtain a final model; finally, outputting the model to obtain the standard MIMO data transmission ratio;
Step five, calculating:
if the MIMO data transmission ratio of a certain floor of a certain building needs to be calculated;
collecting line loss values of all antenna ports of three continuous floors by taking a certain floor as an intermediate floor, and arranging the line loss values to form tensors as calculation data;
inputting the calculated data into the convolutional neural network trained in the fourth step to obtain the MIMO data transmission ratio of a certain floor;
step six, evaluation:
and D, evaluating according to the MIMO data transmission ratio of the middle floor obtained in the step five:
the higher the MIMO data transmission of the middle floor takes up, the better the network effect of the floor is;
the lower the value occupied by the MIMO data transmission of the middle floor is, the poorer the network effect of the floor is;
when the MIMO data transmission duty ratio of a floor is lower than the standard MIMO data transmission duty ratio in step four, the antenna ports of three consecutive floors, in which a certain floor is used as a middle floor, need to be adjusted;
step seven, adjustment:
taking an average number of all line loss values of three continuous floors with a certain floor as an intermediate floor, marking the line loss value with a larger difference relative to the average number in all the line loss values, rectifying an antenna port corresponding to the marked line loss value, and inputting the rectified calculation data into a convolutional neural network again for verification until the obtained MIMO data transmission ratio of the intermediate floor is close to the standard MIMO data transmission ratio.
A detection apparatus that affects a MIMO data transmission duty cycle, comprising: the data acquisition module is used for acquiring line loss values of a plurality of antenna ports of a plurality of floors and acquiring the MIMO data transmission ratio of minute granularity in one hour of each floor of the plurality of floors;
the neural network building module is used for building a convolutional neural network with a Resnet50 residual error structure;
and the model training module is used for inputting the sample data into the convolutional neural network for training according to the mode of 8:2 of the training set and the verification set. The steps of the method for detecting the influence of the MIMO data transmission ratio under the staggered layer coverage scene are realized.
An electronic device, comprising: a processor, a memory, and a communication bus;
the communication bus is used for realizing connection communication between the processor and the memory;
the processor is configured to execute one or more programs stored in the memory to implement the steps of the detection method that affect the MIMO data transmission duty cycle.
A computer readable storage medium having one or more programs stored thereon which are executable by one or more processors to perform the steps of a method for affecting detection of a MIMO data transmission duty cycle in a split-layer coverage scenario.
Fig. 2 is a schematic diagram of the Resnet structure of the present invention. Residual learning can be understood as a block, which contains two branches or two mappings:
1. identity mapping refers to the curve on the right hand side of the upper graph. As the name implies, the identity mapping refers to the mapping of itself, i.e. itself;
2. residual mapping refers to another branch, namely, F (x) part, which is called residual mapping and is regarded as a convolution calculation part by the habit of I
Finally, the block outputs the convolution computing part plus its own mapping, and relu is activated.
The present invention is not limited to the above embodiments, and any technical solutions formed by equivalent substitutions fall within the scope of the claims of the present invention.

Claims (5)

1. A method for detecting the influence of MIMO data transmission ratio,
the building-based indoor partition is installed as a plurality of floors covered by staggered floors, wherein a Keras framework is adopted to construct a convolutional neural network with a Resnet50 Residual error structure, and the convolutional neural network is added with 8 Residual error blocks, namely a Residual block structure, and the building-based indoor partition is characterized by comprising the following steps of:
step one, collecting training data:
acquiring line loss values of a plurality of antenna ports of a plurality of floors, and acquiring the MIMO data transmission ratio of minute granularity in one hour of each floor of the plurality of floors;
Step two, processing training data:
taking any continuous three floors of the multiple floors as a basic sample, taking a tensor formed by arranging line loss values of all antenna ports of the any continuous three floors as sample data, and taking a MIMO data transmission ratio mode of minute granularity within one hour of each floor of the any continuous three floors as a sample label;
step three, modeling:
inputting the sample data obtained in the second step into the convolutional neural network, wherein the adopted convolutional kernel is 3 x 3, and the output of the convolutional neural network is the MIMO data transmission ratio of the middle floor of any three continuous floors;
step four, training:
adopting K-fold cross validation, inputting sample data into the convolutional neural network for training according to the sample data collected in the step one and in a mode of a training set and a validation set 8:2, and after training is finished, adding and averaging a training result model to obtain a final model; finally, outputting the model to obtain the standard MIMO data transmission ratio;
step five, calculating:
if the MIMO data transmission ratio of a certain floor of a certain building needs to be calculated;
taking a certain floor as an intermediate floor, collecting line loss values of all antenna ports of three continuous floors, and arranging the line loss values to form tensors as calculation data;
Inputting the calculated data into the convolutional neural network trained in the fourth step to obtain the MIMO data transmission ratio of a certain floor;
step six, evaluation:
and evaluating according to the MIMO data transmission ratio of the middle floor obtained in the fifth step:
the higher the value occupied by the MIMO data transmission of the middle floor is, the better the network effect of the floor is;
the lower the value occupied by the MIMO data transmission of the middle floor is, the poorer the network effect of the floor is;
when the MIMO data transmission ratio of the floor is lower than the standard MIMO data transmission ratio in the fourth step, the antenna ports of three consecutive floors, in which a certain floor is used as a middle floor, need to be adjusted;
step seven, adjustment:
taking an average number of all line loss values of three continuous floors with a certain floor as an intermediate floor, marking the line loss values with larger relative average difference in all line loss values, rectifying the antenna ports corresponding to the marked line loss values, and inputting the rectified calculation data into the convolutional neural network again for verification until the obtained MIMO data transmission ratio of the intermediate floor is close to the standard MIMO data transmission ratio.
2. The method of claim 1, wherein the method further comprises: the line loss value is obtained through RFID or Bluetooth; and the MIMO data transmission ratio is acquired through DPI data.
3. A detection apparatus for affecting MIMO data transmission duty cycle, comprising:
the data acquisition module is used for acquiring line loss values of a plurality of antenna ports of a plurality of floors and acquiring the MIMO data transmission ratio of minute granularity in one hour of each floor of the plurality of floors;
the neural network construction module is used for constructing a convolutional neural network with a Resnet50 residual error structure;
the model training module is used for inputting sample data into the convolutional neural network for training in a mode of a training set and a verification set 8: 2;
to implement the steps of the method of detecting a contribution to the MIMO data transmission duty as claimed in any one of claims 1 and 2.
4. An electronic device, comprising: a processor, a memory, and a communication bus;
the communication bus is used for realizing connection communication between the processor and the memory;
the processor is configured to execute one or more programs stored in the memory;
To implement the steps of the method of detecting a contribution to the MIMO data transmission duty as claimed in any one of claims 1 and 2.
5. A computer-readable storage medium, wherein the computer-readable storage medium stores one or more programs, the one or more programs being executable by one or more processors;
to implement the steps of the method of detecting a contribution to the MIMO data transmission duty as claimed in any one of claims 1 and 2.
CN202210327648.4A 2022-03-31 2022-03-31 Method, device and storage medium for detecting influence on MIMO data transmission ratio Active CN114422003B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210327648.4A CN114422003B (en) 2022-03-31 2022-03-31 Method, device and storage medium for detecting influence on MIMO data transmission ratio

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210327648.4A CN114422003B (en) 2022-03-31 2022-03-31 Method, device and storage medium for detecting influence on MIMO data transmission ratio

Publications (2)

Publication Number Publication Date
CN114422003A CN114422003A (en) 2022-04-29
CN114422003B true CN114422003B (en) 2022-06-14

Family

ID=81264537

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210327648.4A Active CN114422003B (en) 2022-03-31 2022-03-31 Method, device and storage medium for detecting influence on MIMO data transmission ratio

Country Status (1)

Country Link
CN (1) CN114422003B (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105050120A (en) * 2015-08-18 2015-11-11 深圳市科虹通信有限公司 MIMO (Multiple Input Multiple Output) performance diagnostic method and system of LTE (Long Term Evolution) network
CN109151750A (en) * 2018-09-06 2019-01-04 哈尔滨工业大学 A kind of LTE indoor positioning floor method of discrimination based on Recognition with Recurrent Neural Network model
CN112333753A (en) * 2020-11-27 2021-02-05 中国联合网络通信集团有限公司 Method and device for evaluating number of accessible users
CN113133022A (en) * 2019-12-31 2021-07-16 中国移动通信集团重庆有限公司 Download rate improving method and system based on MIMO multipath construction
CN113177553A (en) * 2021-05-31 2021-07-27 哈尔滨工业大学（深圳） Method and device for identifying floor buttons of inner panel of elevator

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105050120A (en) * 2015-08-18 2015-11-11 深圳市科虹通信有限公司 MIMO (Multiple Input Multiple Output) performance diagnostic method and system of LTE (Long Term Evolution) network
CN109151750A (en) * 2018-09-06 2019-01-04 哈尔滨工业大学 A kind of LTE indoor positioning floor method of discrimination based on Recognition with Recurrent Neural Network model
CN113133022A (en) * 2019-12-31 2021-07-16 中国移动通信集团重庆有限公司 Download rate improving method and system based on MIMO multipath construction
CN112333753A (en) * 2020-11-27 2021-02-05 中国联合网络通信集团有限公司 Method and device for evaluating number of accessible users
CN113177553A (en) * 2021-05-31 2021-07-27 哈尔滨工业大学（深圳） Method and device for identifying floor buttons of inner panel of elevator

Also Published As

Publication number Publication date
CN114422003A (en) 2022-04-29

Similar Documents

Publication Publication Date Title
US20230134964A1 (en) A distributed network traffic data decomposition method
DE60220812T2 (en) POSITION DETECTION AND LOCAL TRACKING IN A WIRELESS NETWORK
CN109302712A (en) Determine the method, apparatus and storage medium of intelligent base station position
CN1951027A (en) Location determination and location tracking in wireless networks
DE102011081188A1 (en) Analysis and address assignment of wireless building networks
CN101742545A (en) Positioning method and system in WiFi environment
CN1666111A (en) Probabilistic model for a positioning technique
CN104780606A (en) Indoor positioning system and method based on WLAN (wireless local area network)
CN104039008B (en) A kind of hybrid locating method
CN104581749A (en) A method and device for predicting service amount of data service of mobile network
CN114422003B (en) Method, device and storage medium for detecting influence on MIMO data transmission ratio
CN111143769B (en) Travel mode sharing rate prediction method and prediction device based on big data
CN103139804A (en) Energy-saving transmission self-adaption recursive least squares (RLS) distributed-type detection method of wireless sensor network
CN103345552A (en) Method and device for assessing reliability of power ICT communication network
WO2018147502A1 (en) Method and device for network design in wireless communication system
CN111263295B (en) WLAN indoor positioning method and device
CN102692241B (en) Error compensation method of wireless positioning system
CN103152751B (en) Energy-saving transmission adaptive LMS (Least-Mean Squares) distributed detection method for wireless sensor network
CN116709249A (en) Management method for edge calculation in Internet of vehicles
CN116379505A (en) System and method for optimizing control based on household metering heat balance
CN102195724B (en) Channel estimation method for Zigbee in indoor environment
Zhang et al. Fusing received signal strength from multiple access points for WLAN user location estimation
CN115119297A (en) Indoor dynamic ranging method based on LoRa signal path attenuation model
CN115002703A (en) Passive indoor people number detection method based on Wi-Fi channel state information
CN112492636B (en) Method and device for determining propagation loss

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