CN109996274B - Method, device, equipment and medium for adjusting LTE cell parameters - Google Patents

Method, device, equipment and medium for adjusting LTE cell parameters Download PDF

Info

Publication number
CN109996274B
CN109996274B CN201711492379.2A CN201711492379A CN109996274B CN 109996274 B CN109996274 B CN 109996274B CN 201711492379 A CN201711492379 A CN 201711492379A CN 109996274 B CN109996274 B CN 109996274B
Authority
CN
China
Prior art keywords
cell
neural network
parameters
data
layer
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
CN201711492379.2A
Other languages
Chinese (zh)
Other versions
CN109996274A (en
Inventor
赵明宇
简晨
雷鹤
赵杰卫
罗小勇
蔡远来
刁枫
杨波
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.)
China Mobile Communications Group Co Ltd
China Mobile Group Sichuan Co Ltd
Original Assignee
China Mobile Communications Group Co Ltd
China Mobile Group Sichuan 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 China Mobile Communications Group Co Ltd, China Mobile Group Sichuan Co Ltd filed Critical China Mobile Communications Group Co Ltd
Priority to CN201711492379.2A priority Critical patent/CN109996274B/en
Publication of CN109996274A publication Critical patent/CN109996274A/en
Application granted granted Critical
Publication of CN109996274B publication Critical patent/CN109996274B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • 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
    • G06N3/044—Recurrent networks, e.g. Hopfield 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
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • 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
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W28/00—Network traffic management; Network resource management
    • H04W28/16—Central resource management; Negotiation of resources or communication parameters, e.g. negotiating bandwidth or QoS [Quality of Service]
    • H04W28/18—Negotiating wireless communication parameters

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Molecular Biology (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Quality & Reliability (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

The invention discloses a method, a device, equipment and a medium for adjusting LTE cell parameters. The method comprises the following steps: carrying out normalization processing on data related to cell operation parameters to generate standard data units with different dimensions; carrying out sample training on the standard data units with different dimensions to generate a simulation model; acquiring current operation parameters of a cell, and inputting the current operation parameters into the simulation model for simulation; and adjusting the cell parameters according to the simulation result. The technical scheme of the invention can be used for effectively adjusting the parameters of the cell.

Description

Method, device, equipment and medium for adjusting LTE cell parameters
Technical Field
The present invention relates to the field of communications technologies, and in particular, to a method, an apparatus, a device, and a medium for adjusting LTE cell parameters
Background
The LTE cell operating parameters are the engines and components that make up various operating mechanisms in the LTE network. The configuration and effective utilization of resources are concerned, and the method has great influence on network coverage, signaling traffic load, service load distribution, network performance indexes and the like, and finally influences on network quality and user satisfaction. Therefore, correctly setting the cell operation parameters is the basis for the normal operation of the LTE network.
The existing adjusting method needs to operate for a period of time after adjustment, and the adjusting effect can be obtained by collecting network indexes. Problems possibly occurring in adjustment are difficult to predict, the adjustment result is difficult to predict, and effective suggestions cannot be given to parameter adjustment. The network quality is the most important factor for the user to select the communication operator, and is directly related to the operation performance and profit of the communication operator. Therefore, new ideas and methods are urgently needed to be developed for establishing an effective simulation method for the LTE parameter adjustment effect and providing support for the LTE parameter adjustment.
Disclosure of Invention
The embodiment of the invention provides a method, a device, equipment and a medium for adjusting LTE (Long term evolution) cell parameters, which are used for effectively adjusting the cell parameters.
In a first aspect, an embodiment of the present invention provides a method for adjusting LTE cell parameters, where the method includes:
carrying out normalization processing on data related to cell operation parameters to generate standard data units with different dimensions;
carrying out sample training on the standard data units with different dimensions to generate a simulation model;
acquiring current operation parameters of a cell, and inputting the current operation parameters into the simulation model for simulation;
and adjusting the cell parameters according to the simulation result.
Preferably, the data related to the cell operation parameters includes: the data processing method comprises the following steps of cell performance statistical data, MR data, complaint data, base station cell configuration data and GIS layer data.
Preferably, the step of normalizing the data related to the cell operation parameters to generate standard data units with different dimensions specifically includes:
determining a normalization dimension according to the category and the characteristics of the data related to the cell operation parameters;
processing the data according to the normalization dimension;
and generating a standard data unit according to the processed data.
Preferably, the step of performing sample training on the standard data units of different dimensions to generate a simulation model specifically includes:
a forward propagation stage: inputting the standard data units with different dimensions into an initial neural network, processing layer by layer through an input layer of the initial neural network and a hidden layer, and transmitting the processed data units to an output layer to obtain output values; if the error between the output value and the target output value is larger than a threshold value, performing a back propagation stage;
and (3) a back propagation stage: establishing an objective function according to the square sum of the error of the output value and a target output value, calculating the partial derivative of the objective function to each neuron weight value layer by layer to form the gradient of the objective function to the weight value vector, and modifying the weight value of the initial neural network according to the gradient to obtain a modified neural network;
repeating the forward propagation stage and the backward propagation stage, wherein the initial neural network of the current forward propagation stage is a modified neural network generated in the last backward propagation stage; and obtaining a simulation model until the error between the output value of the initial neural network in the current forward propagation stage and the target output value is smaller than a threshold value.
Preferably, the initial neural network in the first forward propagation phase is trained by the following steps:
extracting historical parameter adjustment information of the cell, wherein the historical parameter adjustment information comprises adjustment time, the cell, the name of an adjustment parameter, parameter values before and after adjustment and cell coverage grids;
according to the time, the cell and the grid information, searching a standard data unit corresponding to the adjustment information in the data after normalization processing;
establishing an initial neural network; and the searched standard data unit corresponding to the adjustment information is used as the input characteristic of the initial neural network.
Preferably, the counter-propagating stage specifically includes:
defining an objective function for the input features and the target output values of the initial neural network;
obtaining an adjustment characteristic value according to the error allowable range and the target function;
and according to the adjustment characteristic value, forming a gradient of the target function to the weight vector, and according to the gradient, modifying the weight of the initial neural network to obtain the modified neural network.
Preferably, the step of obtaining the current operating parameters of the cell and inputting the current operating parameters into the simulation model for simulation specifically includes:
inputting one or more characteristic values into the simulation model according to data related to the cell operation parameters;
analyzing the characteristic value according to the simulation model, and predicting the index condition;
and outputting a prediction conclusion.
Preferably, before the step of normalizing the data related to the cell operation parameters to generate standard data units with different dimensions, the method further includes:
and acquiring data related to cell operation parameters.
In a second aspect, an embodiment of the present invention provides an apparatus for adjusting LTE cell parameters, where the apparatus includes:
the normalization processing module is used for normalizing the data related to the cell operation parameters to generate standard data units with different dimensions;
the training module is used for carrying out sample training on the standard data units with different dimensions to generate a simulation model;
the simulation module is used for acquiring the current operation parameters of the cell and inputting the current operation parameters into the simulation model for simulation;
and the adjusting module is used for adjusting the cell parameters according to the simulation result.
In a third aspect, an embodiment of the present invention provides an apparatus for adjusting LTE cell parameters, including: at least one processor, at least one memory, and computer program instructions stored in the memory, which when executed by the processor, implement the method of the first aspect of the embodiments described above.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which computer program instructions are stored, which, when executed by a processor, implement the method of the first aspect in the foregoing embodiments.
The method, the device, the equipment and the medium for adjusting the LTE cell parameters provided by the embodiment of the invention set the LTE cell parameters based on a Back Propagation (BP), fully consider the characteristics of various data, fully consider the change conditions of cell operation parameters and the like before and after the parameter adjustment, and provide scientific and quantitative standards and guidance for the adjustment of the LTE cell operation parameters by utilizing a neural network algorithm.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required to be used in the embodiments of the present invention will be briefly described below, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart of an LTE cell parameter adjustment method according to embodiment 1 of the present invention;
fig. 2 is a flowchart of an LTE cell parameter adjustment method according to embodiment 2 of the present invention;
fig. 3 is a flowchart of step S12 of the method for adjusting LTE cell parameters according to embodiment 2 of the present invention;
fig. 4 is a flowchart of the forward propagation phase of step S13 of the method for adjusting LTE cell parameters according to embodiment 2 of the present invention;
fig. 5 is a flowchart of the back propagation stage of step S13 of the method for adjusting LTE cell parameters according to embodiment 2 of the present invention;
fig. 6 is a flowchart of step S14 of the method for adjusting LTE cell parameters according to embodiment 2 of the present invention;
fig. 7 is a schematic structural diagram of an apparatus for adjusting LTE cell parameters according to embodiment 3 of the present invention;
fig. 8 is a schematic structural diagram of an LTE cell parameter adjustment device according to embodiment 4 of the present invention.
Detailed Description
Features and exemplary embodiments of various aspects of the present invention will be described in detail below, and in order to make objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not to be construed as limiting the invention. It will be apparent to one skilled in the art that the present invention may be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the present invention by illustrating examples of the present invention. It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
With reference to fig. 1, an embodiment of the present invention provides a method for adjusting LTE cell parameters, which includes the following steps:
and S01, carrying out normalization processing on the data related to the cell operation parameters to generate standard data units with different dimensions.
And S02, performing sample training on the standard data units with different dimensions to generate a simulation model, wherein the simulation model is a neural network.
And S03, acquiring the current operation parameters of the cell, and inputting the parameters into the simulation model for simulation.
And S04, adjusting the cell parameters according to the simulation result.
The method for adjusting the LTE cell parameters in the embodiment of the invention sets the LTE cell parameters by a Back Propagation (BP) based neural network, fully considers the characteristics of various data, fully considers the change conditions of cell operation parameters and the like before and after parameter adjustment, and provides scientific and quantitative standard and guidance for the adjustment of the LTE cell operation parameters by utilizing a neural network algorithm.
In order to make clearer the specific implementation of the embodiment of the present invention, the method for adjusting LTE cell parameters in this embodiment is specifically described with reference to embodiment 2.
Referring to fig. 2, an embodiment 2 of the present invention provides a method for adjusting LTE cell parameters, which specifically includes the following steps:
s11, importing comprehensive data: and acquiring data related to cell operation parameters, including cell performance statistical data, MR data, complaint data, base station cell configuration data, GIS layer data and the like.
S12, normalization processing: and carrying out normalization processing on the data related to the cell operation parameters to generate standard data units with different dimensions.
As shown in fig. 3, the steps specifically include the following steps:
s121, determining a normalization dimension according to the category and the characteristics of the data related to the cell operation parameters; for example: the MR data normalization dimension is a grid, the cell performance data normalization dimension is a network element, and the complaint data normalization dimension is a call and grid.
And S122, processing the data according to the normalization dimension.
And S123, generating a standard data unit according to the processed data.
And S13, performing sample training on the standard data units with different dimensions to generate a simulation model. The simulation model may be generated for this step in the following manner.
A forward propagation stage: inputting the standard data units with different dimensions into an initial neural network, processing layer by layer through an input layer of the initial neural network and a hidden layer, and transmitting the processed data units to an output layer to obtain output values; and if the error between the output value and the target output value is larger than a threshold value, performing a back propagation stage.
And (3) a back propagation stage: and establishing an objective function according to the square sum of the error of the output value and the target output value, calculating the partial derivative of the objective function to the weight of each neuron layer by layer to form the gradient of the objective function to the weight vector, and modifying the weight of the initial neural network according to the gradient to obtain the modified neural network.
Repeating the forward propagation stage and the backward propagation stage, wherein the initial neural network of the current forward propagation stage is a modified neural network generated in the last backward propagation stage; and obtaining a simulation model until the error between the output value of the initial neural network in the current forward propagation stage and the target output value is smaller than a threshold value.
As shown in fig. 4, the initial neural network in the first forward propagation stage is obtained by training through the following steps:
s1311, extracting historical parameter adjustment information of the cell, wherein the historical parameter adjustment information comprises adjustment time, the cell, the name of the adjustment parameter, the parameter value before and after adjustment and a cell coverage grid.
S1312, according to the time, cell, and grid information, a standard data unit corresponding to the adjustment information is searched for in the normalized data.
S1313, establishing an initial neural network; and the searched standard data unit corresponding to the adjustment information is used as the input characteristic of the initial neural network.
The purpose of establishing the initial neural network is to input the adjustment characteristics into the neural network model to obtain a prediction result. And comparing the predicted result with the actual result, and finally judging whether the current neural network model is complete enough.
For the backward propagation stage, the initial neural network parameters are adjusted according to the comparison between the predicted result and the actual result obtained in the forward propagation stage. As shown in fig. 5, the back propagation stage may specifically include the following steps:
s1321, the neural network algorithm is based on gradient descent, and the energy function of the expected error is minimum. For the input features and the target output values of the initial neural network, a squared error energy function is defined, that is, an objective function is defined as follows:
Figure BDA0001535810600000071
wherein, the input vector x is each data unit found according to the time, cell, and grid information in S1312, and the label y is an output value of the initial neural network, that is, a prediction result.
And S1322, calculating an adjustment characteristic value according to the error allowable range and the objective function.
In this step, to find a proper value of W and B (where W is a set of weight values, and is the weight value of each standard data unit in the neural network model in record S1312, i.e. the data importance, and B is a set of threshold values, and is the boundary value of each standard data unit in record S1312 for obtaining the corresponding prediction result, i.e. the judgment basis), J (W, B; x, y) is minimized, i.e.:
minimizeW，bJ(W，b；x，y) (1)；
using a gradient descent method:
Figure BDA0001535810600000072
Figure BDA0001535810600000073
α is a learning rate.
By derivation
Figure BDA0001535810600000081
Figure BDA0001535810600000082
Figure BDA0001535810600000083
The error term is:
Figure BDA0001535810600000084
substituting into the formulas (4) and (5), the following are provided:
Figure BDA0001535810600000085
Figure BDA0001535810600000086
or vectorized form:
Figure BDA0001535810600000087
Figure BDA0001535810600000088
wherein:
Figure BDA0001535810600000089
if l layers are output layers, then:
Figure BDA0001535810600000091
then:
Figure BDA0001535810600000092
or:
δ(l)＝(a(l)-y)·f′(Z(l)) (13)；
if the layer is a hidden layer, the derivation formula of the composite function is used for solving the J
Figure BDA0001535810600000093
The partial derivatives of (a) have:
Figure BDA0001535810600000094
substituting into formula (6) as follows:
Figure BDA0001535810600000095
after vectorization:
δ(l)＝((W(l+1))Tδ(l+1))·f′(Z(l)) (16)；
and finishing the calculation of the characteristic values of the neural network, namely the weight W and the threshold B after the modification.
S1323, according to the neural network model, establishing a corresponding relation between the adjustment value and the neural network, and when the adjustment value is given, calculating a parameter adjustment simulation result. That is, according to the adjusted characteristic value, the gradient of the objective function to the weight vector is formed, and the weight of the initial neural network is modified according to the gradient to obtain the modified neural network.
S14, simulating and predicting and outputting the result: acquiring current operation parameters of a cell, and inputting the current operation parameters into the simulation model for simulation; as shown in fig. 6, this step may be specifically implemented by the following method:
and S141, inputting one or more characteristic values to the simulation model according to the data related to the cell operation parameters.
And S142, analyzing the characteristic values according to the simulation model, and predicting the index condition.
And S143, outputting a prediction conclusion.
Next, the cell parameters may be set according to the predicted conclusion. For example, when the predicted conclusion is that the adjustment effect is better, the cell parameters are adjusted; the predicted conclusion is that the cell parameters are not adjusted when the adjustment effect is worse than the current parameters.
The LTE cell parameter adjusting method of the embodiment of the invention sufficiently integrates various data of network optimization analysis, including cell performance data, MR data, complaint data and the like, and establishes a parameter adjusting neural network model according to the network index change situation before and after the existing parameter adjustment, thereby solving the problem that the network index situation after the parameter adjustment cannot be predicted. The method effectively improves the parameter adjustment efficiency and provides scientific and quantitative standards and guidance for setting the network optimization parameters.
Referring to fig. 7, an embodiment of the present invention provides an apparatus for adjusting LTE cell parameters, which may set cell parameters by using the method for adjusting LTE cell parameters in embodiment 1 or 2. The device specifically includes: a normalization processing module 301, a training module 302, a simulation module 303 and an adjustment module 304.
The normalization processing module 301 is configured to perform normalization processing on data related to cell operation parameters to generate standard data units with different dimensions; the training module 302 is configured to perform sample training on the standard data units with different dimensions to generate a simulation model; the simulation module 303 is configured to obtain a current operation parameter of the cell, and input the current operation parameter to the simulation model for simulation; the adjusting module 304 is configured to adjust the cell parameter according to the simulation result.
Preferably, the device for adjusting LTE cell parameters in the embodiment of the present invention further includes an acquisition module, configured to acquire data related to cell operation parameters, where the data specifically includes cell performance statistics data, MR data, complaint data, base station cell configuration data, GIS layer data, and the like.
Preferably, the normalization processing module 301 includes: the device comprises a normalization dimension determining unit, a processing unit and a generating unit; the normalization dimension determining unit is used for determining a normalization dimension according to the category and the characteristics of the data related to the cell operation parameters; for example: the MR data normalization dimension is a grid, the cell performance data normalization dimension is a network element, and the complaint data normalization dimension is a call and a grid; the processing unit is used for processing the data according to the normalization dimension; the generating unit is used for generating a standard data unit according to the processed data.
Preferably, the training module 302 specifically includes a forward propagation training unit and a backward propagation training unit; the forward propagation training unit is used for inputting the standard data units with different dimensions into an initial neural network, processing layer by layer through an input layer of the initial neural network and a hidden layer, and transmitting the processed data units to an output layer to obtain an output value; if the error between the output value and the target output value is larger than a threshold value, performing a back propagation stage; and the back propagation training unit is used for establishing an objective function according to the square sum of the error of the output value and the target output value, calculating the partial derivative of the objective function to the weight of each neuron layer by layer to form the gradient of the objective function to the weight vector, and modifying the weight of the initial neural network according to the gradient to obtain the modified neural network.
The simulation module 303 is specifically configured to input one or more feature values to the simulation model according to data related to the cell operation parameters; and analyzing the characteristic values according to the simulation model, predicting the index condition and outputting a prediction conclusion.
The LTE cell parameter adjusting device according to the embodiment of the present invention may adopt the LTE cell parameter adjusting method according to embodiment 1 or 2, fully integrates various types of data of network optimization analysis, including cell performance data, MR data, complaint data, and the like, and establishes a parameter adjustment neural network model according to the network index change before and after the existing parameter adjustment, thereby solving the problem that the network index situation after the parameter adjustment cannot be predicted. The method effectively improves the parameter adjustment efficiency and provides scientific and quantitative standards and guidance for setting the network optimization parameters.
The embodiment of the present invention provides an LTE cell parameter adjusting device, and the LTE cell parameter adjusting method according to the embodiment of the present invention described in conjunction with fig. 1 and 2 may be implemented by the LTE cell parameter adjusting device. Fig. 8 shows a schematic hardware structure diagram of an LTE cell parameter adjustment device according to an embodiment of the present invention.
The apparatus for adjustment of LTE cell parameters may include a processor 401 and a memory 402 having stored computer program instructions.
Specifically, the processor 401 may include a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or may be configured as one or more Integrated circuits implementing embodiments of the present invention.
Memory 402 may include mass storage for data or instructions. By way of example, and not limitation, memory 402 may include a Hard Disk Drive (HDD), floppy Disk Drive, flash memory, optical Disk, magneto-optical Disk, tape, or Universal Serial Bus (USB) Drive or a combination of two or more of these. Memory 402 may include removable or non-removable (or fixed) media, where appropriate. The memory 402 may be internal or external to the data processing apparatus, where appropriate. In a particular embodiment, the memory 402 is a non-volatile solid-state memory. In a particular embodiment, the memory 402 includes Read Only Memory (ROM). Where appropriate, the ROM may be mask-programmed ROM, Programmable ROM (PROM), Erasable PROM (EPROM), Electrically Erasable PROM (EEPROM), electrically rewritable ROM (EAROM), or flash memory or a combination of two or more of these.
The processor 401 reads and executes the computer program instructions stored in the memory 402 to implement any one of the methods for adjusting LTE cell parameters in the above embodiments.
In one example, the apparatus for adjusting LTE cell parameters may also include a communication interface 403 and a bus 410. As shown in fig. 4, the processor 401, the memory 402, and the communication interface 403 are connected via a bus 410 to complete communication therebetween.
The communication interface 403 is mainly used for implementing communication between modules, apparatuses, units and/or devices in the embodiments of the present invention.
The bus 410 comprises hardware, software, or both, coupling the components of the LTE cell parameter adjustment device to each other. By way of example, and not limitation, a bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hypertransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an infiniband interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a video electronics standards association local (VLB) bus, or other suitable bus or a combination of two or more of these. Bus 410 may include one or more buses, where appropriate. Although specific buses have been described and shown in the embodiments of the invention, any suitable buses or interconnects are contemplated by the invention.
Embodiments of the present invention may be implemented by providing a computer-readable storage medium. The computer readable storage medium having stored thereon computer program instructions; the computer program instructions, when executed by a processor, implement any one of the methods for adjusting LTE cell parameters in the above embodiments.
It is to be understood that the invention is not limited to the specific arrangements and instrumentality described above and shown in the drawings. A detailed description of known methods is omitted herein for the sake of brevity. In the above embodiments, several specific steps are described and shown as examples. However, the method processes of the present invention are not limited to the specific steps described and illustrated, and those skilled in the art can make various changes, modifications and additions or change the order between the steps after comprehending the spirit of the present invention.
The functional blocks shown in the above-described structural block diagrams may be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, it may be, for example, an electronic circuit, an Application Specific Integrated Circuit (ASIC), suitable firmware, plug-in, function card, or the like. When implemented in software, the elements of the invention are the programs or code segments used to perform the required tasks. The program or code segments may be stored in a machine-readable medium or transmitted by a data signal carried in a carrier wave over a transmission medium or a communication link. A "machine-readable medium" may include any medium that can store or transfer information. Examples of a machine-readable medium include electronic circuits, semiconductor memory devices, ROM, flash memory, Erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, Radio Frequency (RF) links, and so forth. The code segments may be downloaded via computer networks such as the internet, intranet, etc.
It should also be noted that the exemplary embodiments mentioned in this patent describe some methods or systems based on a series of steps or devices. However, the present invention is not limited to the order of the above-described steps, that is, the steps may be performed in the order mentioned in the embodiments, may be performed in an order different from the order in the embodiments, or may be performed simultaneously.
As described above, only the specific embodiments of the present invention are provided, and it can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the system, the module and the unit described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again. It should be understood that the scope of the present invention is not limited thereto, and any equivalent modifications or substitutions can be easily made by those skilled in the art within the technical scope of the present invention.

Claims (10)

1. A method for adjusting LTE cell parameters, the method comprising:
carrying out normalization processing on data related to cell operation parameters to generate standard data units with different dimensions;
carrying out sample training on the standard data units with different dimensions to generate a simulation model;
acquiring current operation parameters of the cell, and inputting the current operation parameters into the simulation model for simulation;
adjusting the cell parameters according to the simulation result;
the step of performing sample training on the standard data units with different dimensions to generate a simulation model comprises the following steps:
a forward propagation stage: inputting the standard data units with different dimensions into an initial neural network, processing layer by layer through an input layer of the initial neural network and a hidden layer, and transmitting the processed data units to an output layer to obtain output values; if the error between the output value and the target output value is larger than a threshold value, performing a back propagation stage;
and (3) a back propagation stage: establishing an objective function according to the square sum of the error of the output value and a target output value, calculating the partial derivative of the objective function to each neuron weight value layer by layer to form the gradient of the objective function to the weight value vector, and modifying the weight value of the initial neural network according to the gradient to obtain a modified neural network;
repeating the forward propagation stage and the backward propagation stage, wherein the initial neural network of the current forward propagation stage is a modified neural network generated in the last backward propagation stage; and obtaining a simulation model until the error between the output value of the initial neural network in the current forward propagation stage and the target output value is smaller than a threshold value.
2. The method of claim 1, wherein the data related to the cell operation parameters comprises at least one of: the data processing method comprises the following steps of cell performance statistical data, MR data, complaint data, base station cell configuration data and GIS layer data.
3. The method according to claim 1, wherein the step of normalizing the data related to the cell operation parameters to generate standard data units with different dimensions comprises:
determining a normalization dimension according to the category and the characteristics of the data related to the cell operation parameters;
processing the data according to the normalization dimension;
and generating a standard data unit according to the processed data.
4. The method of claim 1, wherein the initial neural network in a first forward propagation phase is trained using the following steps:
extracting historical parameter adjustment information of the cell, wherein the historical parameter adjustment information comprises adjustment time, the cell, the name of an adjustment parameter, parameter values before and after adjustment and cell coverage grids;
according to the time, the cell and the grid information, searching a standard data unit corresponding to the adjustment information in the data after normalization processing;
establishing an initial neural network; and the searched standard data unit corresponding to the adjustment information is used as the input characteristic of the initial neural network.
5. The method of claim 4, wherein the back propagation phase comprises:
defining an objective function for the input features and the target output values of the initial neural network;
obtaining an adjustment characteristic value according to the error allowable range and the target function;
and according to the adjustment characteristic value, forming a gradient of the target function to the weight vector, and according to the gradient, modifying the weight of the initial neural network to obtain the modified neural network.
6. The method of claim 5, wherein the step of obtaining the current operating parameters of the cell and inputting the current operating parameters into the simulation model for simulation comprises:
inputting one or more characteristic values into the simulation model according to data related to the cell operation parameters;
analyzing the characteristic value according to the simulation model, and predicting the index condition;
and outputting a prediction conclusion.
7. The method according to claim 1, wherein before the step of normalizing the data related to the cell operation parameters to generate the standard data units with different dimensions, the method further comprises:
and acquiring data related to the cell operation parameters.
8. An apparatus for adjusting LTE cell parameters, the apparatus comprising:
the normalization processing module is used for normalizing the data related to the cell operation parameters to generate standard data units with different dimensions;
the training module is used for carrying out sample training on the standard data units with different dimensions to generate a simulation model;
the simulation module is used for acquiring the current operation parameters of the cell and inputting the current operation parameters into the simulation model for simulation;
the adjusting module is used for adjusting the cell parameters according to the simulation result;
the training module specifically comprises:
the forward propagation training unit is used for inputting the standard data units with different dimensions into an initial neural network, processing layer by layer through an input layer of the initial neural network and a hidden layer, and transmitting the processed data units to an output layer to obtain an output value; if the error between the output value and the target output value is larger than a threshold value, performing a back propagation stage;
the back propagation training unit is used for establishing an objective function according to the square sum of the error of the output value and a target output value, calculating the partial derivative of the objective function to the weight of each neuron layer by layer to form the gradient of the objective function to the weight vector, and modifying the weight of the initial neural network according to the gradient to obtain a modified neural network;
repeating the forward propagation stage and the backward propagation stage, wherein the initial neural network of the current forward propagation stage is a modified neural network generated in the last backward propagation stage; and obtaining a simulation model until the error between the output value of the initial neural network in the current forward propagation stage and the target output value is smaller than a threshold value.
9. An apparatus for adjusting LTE cell parameters, comprising: at least one processor, at least one memory, and computer program instructions stored in the memory that, when executed by the processor, implement the method of any of claims 1-7.
10. A computer-readable storage medium having computer program instructions stored thereon, which when executed by a processor implement the method of any one of claims 1-7.
CN201711492379.2A 2017-12-30 2017-12-30 Method, device, equipment and medium for adjusting LTE cell parameters Active CN109996274B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201711492379.2A CN109996274B (en) 2017-12-30 2017-12-30 Method, device, equipment and medium for adjusting LTE cell parameters

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201711492379.2A CN109996274B (en) 2017-12-30 2017-12-30 Method, device, equipment and medium for adjusting LTE cell parameters

Publications (2)

Publication Number Publication Date
CN109996274A CN109996274A (en) 2019-07-09
CN109996274B true CN109996274B (en) 2022-06-03

Family

ID=67111106

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201711492379.2A Active CN109996274B (en) 2017-12-30 2017-12-30 Method, device, equipment and medium for adjusting LTE cell parameters

Country Status (1)

Country Link
CN (1) CN109996274B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111314926B (en) * 2020-01-15 2021-02-09 徐康庭 Coverage relation determination method and device and computer readable storage medium

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102098689B (en) * 2009-12-14 2013-03-27 中国联合网络通信集团有限公司 Antenna automatic-distribution method and device for indoor distributed wireless network
WO2014085957A1 (en) * 2012-12-03 2014-06-12 华为技术有限公司 Network simulation method and server
CN103338468A (en) * 2012-12-27 2013-10-02 上海华为技术有限公司 Method and device for enhancing mobility performance
CN107113635B (en) * 2014-12-17 2020-02-14 华为技术有限公司 Method and apparatus for determining cell status to adjust antenna configuration parameters
CN106851671A (en) * 2015-12-07 2017-06-13 中国联合网络通信集团有限公司 Determine the method and device of network condition

Also Published As

Publication number Publication date
CN109996274A (en) 2019-07-09

Similar Documents

Publication Publication Date Title
CN108280542B (en) User portrait model optimization method, medium and equipment
CN109951306B (en) Alarm processing method, device, equipment and medium
CN109874104B (en) User position positioning method, device, equipment and medium
CN109684851A (en) Evaluation of Software Quality, device, equipment and computer storage medium
CN108596398B (en) Time sequence prediction method and device based on conditional random field and Stacking algorithm
CN109993183B (en) Network fault evaluation method and device, computing equipment and storage medium
CN111835537A (en) Method, device and equipment for identifying nodes in communication network cascade fault
CN109362092B (en) Network parameter adjusting method, device, equipment and medium
CN117580090B (en) Mobile terminal communication stability testing method and system
CN109996274B (en) Method, device, equipment and medium for adjusting LTE cell parameters
CN115174355A (en) Generation method of fault root cause positioning model, and fault root cause positioning method and device
CN115291108A (en) Data generation method, device, equipment and computer program product
CN114564370A (en) Method, device and equipment for determining alarm threshold value and computer storage medium
CN108377508B (en) User perception classification method and device based on measurement report data
CN115545533A (en) Data processing method, device, equipment, medium and product
CN114417830A (en) Risk evaluation method, device, equipment and computer readable storage medium
CN112749998A (en) Income information output method and device, electronic equipment and computer storage medium
CN109993388B (en) Method, device, equipment and medium for judging cause of deteriorated cell
CN113112102A (en) Priority determination method, device, equipment and storage medium
CN110602652A (en) Complaint model training method, and user complaint prediction method, device and equipment
CN111310959A (en) Wind generating set damage prediction analysis method, device, equipment and storage medium
CN114547101B (en) Data quality evaluation method, device, equipment and storage medium for data center
CN111091284A (en) Training method, device, equipment and storage medium of communication accident recognition model
CN114158060B (en) Cell network optimization method and device
CN114630356A (en) Base station determination method, device, equipment and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant