CN117440407A - LTE wireless network evaluation method and server - Google Patents
LTE wireless network evaluation method and server Download PDFInfo
- Publication number
- CN117440407A CN117440407A CN202311632981.7A CN202311632981A CN117440407A CN 117440407 A CN117440407 A CN 117440407A CN 202311632981 A CN202311632981 A CN 202311632981A CN 117440407 A CN117440407 A CN 117440407A
- Authority
- CN
- China
- Prior art keywords
- data
- lte
- network
- wireless network
- lur
- 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.)
- Withdrawn
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 19
- 238000004891 communication Methods 0.000 claims abstract description 29
- 238000012544 monitoring process Methods 0.000 claims abstract description 19
- 238000007781 pre-processing Methods 0.000 claims abstract description 11
- 230000000903 blocking effect Effects 0.000 claims abstract description 4
- 238000013468 resource allocation Methods 0.000 claims abstract description 4
- 210000002569 neuron Anatomy 0.000 claims description 25
- 238000012502 risk assessment Methods 0.000 claims description 24
- 238000012549 training Methods 0.000 claims description 18
- 238000004422 calculation algorithm Methods 0.000 claims description 14
- 238000004088 simulation Methods 0.000 claims description 14
- 230000005540 biological transmission Effects 0.000 claims description 12
- 238000000034 method Methods 0.000 claims description 12
- 238000012795 verification Methods 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 9
- 238000005516 engineering process Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 7
- 230000002159 abnormal effect Effects 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 6
- 230000006835 compression Effects 0.000 claims description 4
- 238000007906 compression Methods 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 4
- 238000013500 data storage Methods 0.000 claims description 4
- 238000005457 optimization Methods 0.000 claims description 4
- 230000004913 activation Effects 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 238000012806 monitoring device Methods 0.000 claims description 3
- 230000001681 protective effect Effects 0.000 claims description 3
- 238000001228 spectrum Methods 0.000 claims description 3
- 230000001131 transforming effect Effects 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 claims description 3
- 238000009499 grossing Methods 0.000 claims description 2
- 238000012216 screening Methods 0.000 claims description 2
- 238000012163 sequencing technique Methods 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 abstract description 3
- 238000011161 development Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/02—Arrangements for optimising operational condition
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W28/00—Network traffic management; Network resource management
- H04W28/02—Traffic management, e.g. flow control or congestion control
- H04W28/08—Load balancing or load distribution
- H04W28/09—Management thereof
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W40/00—Communication routing or communication path finding
- H04W40/02—Communication route or path selection, e.g. power-based or shortest path routing
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The invention discloses an evaluation method and a server of an LTE wireless network, which belong to the technical field of network communication, wherein the evaluation method comprises the following specific steps: (1) Monitoring and preprocessing various data of an LTE wireless network in real time; (2) Constructing a LUR linked list of the LTE wireless network to store each group of data; (3) Searching an optimal communication path in the LTE network through iterative search; (4) Carrying out security assessment and risk protection on the LTE network; (5) Dynamically adjusting resource allocation to balance load in the LTE network; (6) Optimizing LTE network service and storing various data in a blocking way; the invention can improve the efficiency of data access, ensure the rapid access of data, provide good performance with lower calculation cost, simultaneously can rapidly adapt to the change of access hot spots, maintain the high efficiency of a linked list, dynamically adapt to the change of network state, reduce the possibility of network congestion, improve the quality of communication signals and reduce the communication error rate.
Description
Technical Field
The present invention relates to the field of network communications technologies, and in particular, to an evaluation method and a server for an LTE wireless network.
Background
With the rapid development of technologies such as the internet of things, big data and cloud computing, the LTE wireless network has significantly progressed in the aspects of connection performance, data transmission speed, coverage range and the like. The popularity of mobile terminals and the widespread use of wireless applications have created a higher desire for high quality, high reliability LTE networks by users. However, with the increase in network load and diversification of user demands, management and maintenance of LTE networks face increasingly complex challenges. The continued development of LTE networks brings about higher data transmission speeds and lower delays, which enable better utilization of wireless communication technologies in various industries. In this digital age, the LTE network is not only an infrastructure for communication, but also supports innovative developments in numerous fields such as smart cities, smart transportation, industrial internet of things, and the like.
Through retrieval, chinese patent number CN108207005A discloses an evaluation method and a server of an LTE wireless network, and the evaluation method and the server of the invention improve the evaluation accuracy of the LTE wireless network, but have lower data access efficiency and can not provide good performance with lower calculation cost; in addition, the existing LTE wireless network evaluation method has the defects of high possibility of network congestion of the server, low quality of communication signals and high communication error rate; therefore, we propose an evaluation method and server for LTE wireless network.
Disclosure of Invention
The invention aims to solve the defects in the prior art, and provides an evaluation method and a server of an LTE wireless network.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
an evaluation method of an LTE wireless network comprises the following specific steps:
(1) Monitoring and preprocessing various data of an LTE wireless network in real time;
(2) Constructing a LUR linked list of the LTE wireless network to store each group of data;
(3) Searching an optimal communication path in the LTE network through iterative search;
(4) Carrying out security assessment and risk protection on the LTE network;
(5) Dynamically adjusting resource allocation to balance load in the LTE network;
(6) And optimizing LTE network service and storing various data in a blocking mode.
As a further aspect of the present invention, the specific steps of the LTE wireless network data preprocessing in step (1) are as follows:
step one: collecting LTE wireless network data in real time by using monitoring equipment, removing noise of all collected data by Gaussian filtering and smoothing the data, unifying all the data after denoising into the same data set, calculating standard deviation of the data set, detecting the data according to the calculated standard deviation, screening out abnormal data, detecting whether repeated data records exist or not, and deleting the repeated data if the repeated data exist;
step two: detecting missing values in each group of data, marking the positions of the missing values in the corresponding data, carrying out statistics and visual analysis on the missing values in each group of data to obtain the distribution condition and the influence range of the missing values, and replacing the abnormal values or the missing values by the average value or the median of the corresponding K groups of data points found by the KNN algorithm.
As a further aspect of the present invention, the monitoring device in step one specifically includes a sensor, a signal intensity detector, a data transmission rate monitor, a spectrum analyzer, a camera, and a network traffic analyzer.
As a further scheme of the present invention, the storing data of the LUR linked list in the step (2) specifically includes the following steps:
step 1: collecting data related to a user in an LTE network, preprocessing the collected data, identifying the position of the user by using geographic information in the collected data, recording the connection state of user equipment, and extracting a communication quality index from the collected data;
step 2: constructing a LUR linked list according to each collected group of data, initializing the LUR linked list, setting the size of the linked list according to a system memory, recording each collected group of data into each group of nodes of the LUR linked list in real time, and sequencing the data in the LUR linked list according to the sequence from new to old of each data timestamp;
step 3: establishing an index in the LUR chain table, reducing the space occupied by data storage in the LUR chain table by using a compression algorithm, carrying out inert loading on data in the chain table, and simultaneously carrying out parallelization processing on the construction and optimization process of the chain table by using a parallel computing technology, and updating the use frequency of a node and moving the node to the head of the chain table to indicate that the node is recently used when accessing a group of nodes each time;
step 4: when new data is added into the LUR linked list, whether the size of the LUR linked list exceeds the set maximum capacity is automatically checked, and if the size of the linked list exceeds the maximum capacity, nodes at the tail of the linked list are deleted.
As a further aspect of the present invention, the LTE network communication path searching in step (3) specifically includes the following steps:
step (1): taking the current LTE network state as a root node of a tree, initializing a group of Monte Carlo trees, adding the root node into the tree, initializing related statistical information, starting from the root node, selecting a child node by using a selection algorithm until a leaf node is found, and stopping selecting;
step (2): adding new child nodes to the selected leaf node expansion tree structure, generating corresponding paths by simulation or random simulation for the new expanded nodes, calculating the quality or cost of the paths, transmitting reward values of simulation results back to the selected paths, and updating statistical information of the corresponding nodes;
step (3): and repeating the selecting, expanding, simulating and backtracking stages until the preset iteration times or time limit is reached, selecting an optimal path in the child nodes of the root node according to the statistical information of the Monte Carlo tree, and then applying the selected optimal path to data transmission or communication of the LTE network.
As a further aspect of the present invention, the specific steps of risk protection in the step (4) are as follows:
step I: extracting past monitoring data of an LTE network, preprocessing each group of data, extracting characteristic information of each group of monitoring data through characteristic engineering, and dividing the extracted characteristic information into a training set, a verification set and a test set;
step II: constructing a risk assessment model, determining the number of neurons of the risk assessment model according to the characteristic information, initializing the weights of the neurons to be random values or preset initial values, determining the learning rate and the step length according to the preset information, dividing training sets into small batches, transmitting the training sets to the risk assessment model in batches through forward propagation, and calculating the output of each neuron;
step III: comparing the difference between the output of the risk assessment model and the actual target value by using the loss function, calculating the gradient of the weight according to the gradient of the loss function, updating the weight of each neuron by using a gradient descent algorithm, and repeatedly training the risk assessment model until all training sets are used;
step IV: the performance of the trained model is estimated by using a verification set, the learning rate of the risk estimation model which does not meet the preset condition is adjusted by a cross verification method, when the performance of the model on the verification set is no longer improved or starts to deteriorate, training is stopped in advance, and the performance of the final risk estimation model is estimated by using a test set;
step V: receiving real-time monitoring data, linearly transforming the same input real-time monitoring data from different angles through a plurality of groups of attention layers of the risk assessment model to extract characteristic information, fusing the outputs of the plurality of groups of attention layers, and importing the fused characteristic information into a subsequent hidden layer;
step VI: and calculating the weighted input of each layer of neurons through each hidden layer, calculating the output of each layer of neurons through an activation function, transmitting the output of each layer of neurons as input to the next layer until the output of each layer of neurons is transmitted to the output layer, and then outputting each group of risk assessment results by the output layer according to the weight proportion of each neuron, and taking preset protective measures.
An evaluation server of an LTE wireless network comprises a processor, a memory, a communication bus, a main board, a graphic processor, a power supply unit, a radiator, a clock generator, a BIOS chip and a network interface;
the processor is used for executing various computing tasks on the server; the memory is used for storing various data of the server; the communication bus is used for connecting the server components and providing a data transmission channel among the components; the main board is used for providing a framework and integrating all the server components together;
the graphics processor is used for assisting the processor to perform parallel computing tasks when graphics processing is performed or massive parallel computing is required; the power supply unit is used for providing power required by the server; the radiator is used for keeping the internal temperature of the server within a safe range and preventing overheat from damaging electronic elements; the clock generator is used for providing clock signals of all components in the server; the BIOS chip is used for providing a basic input/output system required by the starting of the server and assisting the system to perform self-checking and initialization; the network interface is used for exchanging data with the LTE base station and the user equipment through wireless or wired connection.
Compared with the prior art, the invention has the beneficial effects that:
1. the evaluation method of the LTE wireless network collects data related to users in the LTE network, preprocesses the collected data, builds a LUR chain table according to the collected data of each group, records the collected data of each group in each group of nodes of the LUR chain table in real time, orders the data in the LUR chain table according to the sequence from new to old of each data timestamp, builds an index in the LUR chain table, reduces the space occupied by data storage in the LUR chain table by using a compression algorithm, carries out inertia loading on the data in the chain table, simultaneously carries out parallelization processing on the construction and optimization process of the chain table by using a parallel computing technology, updates the use frequency of the node and moves the node to the head of the chain table to indicate that the node is used recently, and when new data is added into the LUR chain table, automatically checks whether the size of the LUR chain table exceeds the set capacity, if the size exceeds the maximum capacity, deletes the node at the tail of the chain table, can improve the efficiency of data access, ensure the quick access of the chain table, can provide good performance with lower calculation cost, and simultaneously can adapt to the change of the hot point quickly and keep the high efficiency of access.
2. The invention takes the current LTE network state as the root node of the tree, initializes a group of Monte Carlo trees, adds the root node into the tree, initializes related statistical information, starts from the root node, selects one sub-node by using a selection algorithm until finding a leaf node, stops selecting, expands the tree structure for the selected leaf node, adds a new sub-node, then generates a corresponding path by simulation or random simulation for the newly expanded node, calculates the quality or cost of the path, propagates the reward value of the simulation result back to the selected path, updates the statistical information of the corresponding node, repeatedly performs the selection, expansion, simulation and backtracking stages until reaching the preset iteration times or time limit, selects the optimal path in the sub-node of the root node according to the statistical information of the Monte Carlo tree, then applies the selected optimal path to data transmission or communication of the LTE network, can dynamically adapt to the change of the network state, reduces the possibility of network congestion, improves the quality of communication signals, and reduces the communication error rate.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention.
Fig. 1 is a flow chart of an evaluation method of an LTE wireless network according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments.
Example 1
Referring to fig. 1, the embodiment discloses an evaluation method of an LTE wireless network, which specifically includes the following steps:
and monitoring and preprocessing various data of the LTE wireless network in real time.
Specifically, the monitoring equipment is utilized to collect LTE wireless network data in real time, noise of all collected data is removed through Gaussian filtering, the collected data is smoothed, all the data after denoising are unified into the same data set, standard deviation of the data set is calculated, data are detected and abnormal data are screened out according to the calculated standard deviation, whether repeated data records exist or not is detected, if the repeated data exist, missing values exist in all the data are detected, positions of all the missing values in corresponding data are marked, statistics and visual analysis are conducted on the missing values in all the data to obtain distribution conditions and influence ranges of the missing values, and average values or median values of corresponding K groups of data points found through a KNN algorithm replace the abnormal values or the missing values.
It should be further noted that the monitoring device specifically includes a sensor, a signal strength detector, a data transmission rate monitor, a spectrum analyzer, a camera, and a network traffic analyzer.
Building a LUR linked list of the LTE wireless network stores the sets of data.
Specifically, data related to a user in an LTE network is collected, the collected data is preprocessed, geographic information in the collected data is utilized to identify the position of the user and record the connection state of user equipment, meanwhile, communication quality indexes are extracted from the collected data, a LUR (line list) is built according to the collected data of each group, the LUR list is initialized, the size of the list is set according to a system memory, the collected data of each group are recorded in each group of nodes of the LUR list in real time respectively, the data in the LUR list is ordered according to the sequence from new to old according to the time stamp of each data, an index is built in the LUR list, the space occupied by data storage in the LUR list is reduced by utilizing a compression algorithm, inert loading is carried out on the data in the list, parallel computing technology is used to carry out parallel processing on the construction and optimization process of the list, the use frequency of the node is updated each time when the node is accessed to the head part to represent that the node is used recently, when new data is added into the LUR list, whether the size of the LUR list exceeds the set maximum capacity is checked by itself, and if the size of the LUR list exceeds the set maximum capacity, the node is deleted.
And searching the optimal communication path in the LTE network through iterative search.
Specifically, the current LTE network state is taken as a root node of a tree, a set of monte carlo trees is initialized, the root node is added into the tree, relevant statistical information is initialized, starting from the root node, a child node is selected by using a selection algorithm until a leaf node is found, selection is stopped, a tree structure is expanded for the selected leaf node, a new child node is added, then for the newly expanded node, a corresponding path is generated through simulation or random simulation, the quality or cost of the path is calculated, a reward value of a simulation result is propagated back to the selected path, statistical information of the corresponding node is updated, the selection, expansion, simulation and backtracking stages are repeatedly performed until a predetermined iteration number or time limit is reached, an optimal path is selected among the child nodes of the root node according to the statistical information of the monte carlo tree, and then the selected optimal path is applied to data transmission or communication of the LTE network.
And carrying out security assessment and risk protection on the LTE network.
Specifically, the past monitoring data of the LTE network are extracted, after preprocessing each group of data, each group of monitoring data characteristic information is extracted through characteristic engineering, the extracted characteristic information is divided into a training set, a verification set and a test set, a risk assessment model is constructed, then the number of neurons of the risk assessment model is determined according to the characteristic information, each neuron weight is initialized to a random value or a preset initial value, a learning rate and a step length are determined according to the preset information, the training set is divided into small batches, each group of training set is transmitted to the risk assessment model in batches through forward propagation, the output of each neuron is calculated, the difference between the output of the risk assessment model and an actual target value is compared by using a loss function, the gradient of the weight is calculated according to the gradient of the loss function, each neuron weight is updated through a gradient descent algorithm, training the risk assessment model repeatedly until all training sets are used, assessing the performance of the trained model by using a verification set, adjusting the learning rate of the risk assessment model which does not meet preset conditions by using a cross verification method, when the performance of the model on the verification set is no longer improved or begins to deteriorate, selecting to stop training in advance, assessing the performance of a final risk assessment model by using a test set, receiving real-time monitoring data, linearly transforming the real-time monitoring data which are input in the same way from different angles by using multiple groups of attention layers of the risk assessment model to extract characteristic information, fusing the outputs of the multiple groups of attention layers, importing the fused characteristic information into a subsequent hidden layer, calculating the weighted input of each layer of neurons by using each hidden layer, calculating the output of each layer of neurons by using an activation function and transmitting the output to the next layer as input, and the output layer outputs each group of risk assessment results according to the weight proportion of each neuron until the risk assessment results are transmitted to the output layer, and preset protective measures are adopted.
The resource allocation is dynamically adjusted to balance the load in the LTE network.
And optimizing LTE network service and storing various data in a blocking mode.
Example 2
The embodiment discloses an evaluation server of an LTE wireless network, which comprises a processor, a memory, a communication bus, a main board, a graphic processor, a power supply unit, a radiator, a clock generator, a BIOS chip and a network interface.
The processor is used for executing various computing tasks on the server; the memory is used for storing various data of the server; the communication bus is used for connecting the server components and providing a data transmission channel among the components; the motherboard is used to provide a framework for integrating the server components together.
The graphics processor is used for assisting the processor in carrying out parallel computing tasks when graphics processing is carried out or massive parallel computing is needed; the power supply unit is used for providing power required by the server; the radiator is used for keeping the internal temperature of the server within a safe range and preventing overheat from damaging the electronic element; the clock generator is used for providing clock signals of all components in the server; the BIOS chip is used for providing a basic input/output system required by the starting of the server and assisting the system to perform self-checking and initialization; the network interface is used for exchanging data with the LTE base station and the user equipment through wireless or wired connection.
Claims (7)
1. An evaluation method of an LTE wireless network is characterized by comprising the following specific steps:
(1) Monitoring and preprocessing various data of an LTE wireless network in real time;
(2) Constructing a LUR linked list of the LTE wireless network to store each group of data;
(3) Searching an optimal communication path in the LTE network through iterative search;
(4) Carrying out security assessment and risk protection on the LTE network;
(5) Dynamically adjusting resource allocation to balance load in the LTE network;
(6) And optimizing LTE network service and storing various data in a blocking mode.
2. The method for evaluating an LTE wireless network according to claim 1, wherein the data preprocessing of the LTE wireless network in step (1) specifically comprises the following steps:
step one: collecting LTE wireless network data in real time by using monitoring equipment, removing noise of all collected data by Gaussian filtering and smoothing the data, unifying all the data after denoising into the same data set, calculating standard deviation of the data set, detecting the data according to the calculated standard deviation, screening out abnormal data, detecting whether repeated data records exist or not, and deleting the repeated data if the repeated data exist;
step two: detecting missing values in each group of data, marking the positions of the missing values in the corresponding data, carrying out statistics and visual analysis on the missing values in each group of data to obtain the distribution condition and the influence range of the missing values, and replacing the abnormal values or the missing values by the average value or the median of the corresponding K groups of data points found by the KNN algorithm.
3. The method according to claim 2, wherein the monitoring device comprises a sensor, a signal strength detector, a data transmission rate monitor, a spectrum analyzer, a camera, and a network traffic analyzer.
4. The method for evaluating an LTE wireless network according to claim 2, wherein the storing data in the LUR linked list in step (2) specifically comprises the steps of:
step 1: collecting data related to a user in an LTE network, preprocessing the collected data, identifying the position of the user by using geographic information in the collected data, recording the connection state of user equipment, and extracting a communication quality index from the collected data;
step 2: constructing a LUR linked list according to each collected group of data, initializing the LUR linked list, setting the size of the linked list according to a system memory, recording each collected group of data into each group of nodes of the LUR linked list in real time, and sequencing the data in the LUR linked list according to the sequence from new to old of each data timestamp;
step 3: establishing an index in the LUR chain table, reducing the space occupied by data storage in the LUR chain table by using a compression algorithm, carrying out inert loading on data in the chain table, and simultaneously carrying out parallelization processing on the construction and optimization process of the chain table by using a parallel computing technology, and updating the use frequency of a node and moving the node to the head of the chain table to indicate that the node is recently used when accessing a group of nodes each time;
step 4: when new data is added into the LUR linked list, whether the size of the LUR linked list exceeds the set maximum capacity is automatically checked, and if the size of the linked list exceeds the maximum capacity, nodes at the tail of the linked list are deleted.
5. The method for evaluating an LTE wireless network according to claim 4, wherein the LTE network communication path searching in step (3) specifically includes the steps of:
step (1): taking the current LTE network state as a root node of a tree, initializing a group of Monte Carlo trees, adding the root node into the tree, initializing related statistical information, starting from the root node, selecting a child node by using a selection algorithm until a leaf node is found, and stopping selecting;
step (2): adding new child nodes to the selected leaf node expansion tree structure, generating corresponding paths by simulation or random simulation for the new expanded nodes, calculating the quality or cost of the paths, transmitting reward values of simulation results back to the selected paths, and updating statistical information of the corresponding nodes;
step (3): and repeating the selecting, expanding, simulating and backtracking stages until the preset iteration times or time limit is reached, selecting an optimal path in the child nodes of the root node according to the statistical information of the Monte Carlo tree, and then applying the selected optimal path to data transmission or communication of the LTE network.
6. The method for evaluating an LTE wireless network according to claim 4, wherein the risk protection in step (4) specifically comprises the steps of:
step I: extracting past monitoring data of an LTE network, preprocessing each group of data, extracting characteristic information of each group of monitoring data through characteristic engineering, and dividing the extracted characteristic information into a training set, a verification set and a test set;
step II: constructing a risk assessment model, determining the number of neurons of the risk assessment model according to the characteristic information, initializing the weights of the neurons to be random values or preset initial values, determining the learning rate and the step length according to the preset information, dividing training sets into small batches, transmitting the training sets to the risk assessment model in batches through forward propagation, and calculating the output of each neuron;
step III: comparing the difference between the output of the risk assessment model and the actual target value by using the loss function, calculating the gradient of the weight according to the gradient of the loss function, updating the weight of each neuron by using a gradient descent algorithm, and repeatedly training the risk assessment model until all training sets are used;
step IV: the performance of the trained model is estimated by using a verification set, the learning rate of the risk estimation model which does not meet the preset condition is adjusted by a cross verification method, when the performance of the model on the verification set is no longer improved or starts to deteriorate, training is stopped in advance, and the performance of the final risk estimation model is estimated by using a test set;
step V: receiving real-time monitoring data, linearly transforming the same input real-time monitoring data from different angles through a plurality of groups of attention layers of the risk assessment model to extract characteristic information, fusing the outputs of the plurality of groups of attention layers, and importing the fused characteristic information into a subsequent hidden layer;
step VI: and calculating the weighted input of each layer of neurons through each hidden layer, calculating the output of each layer of neurons through an activation function, transmitting the output of each layer of neurons as input to the next layer until the output of each layer of neurons is transmitted to the output layer, and then outputting each group of risk assessment results by the output layer according to the weight proportion of each neuron, and taking preset protective measures.
7. The evaluation server of the LTE wireless network is characterized by comprising a processor, a memory, a communication bus, a main board, a graphic processor, a power supply unit, a radiator, a clock generator, a BIOS chip and a network interface;
the processor is used for executing various computing tasks on the server; the memory is used for storing various data of the server; the communication bus is used for connecting the server components and providing a data transmission channel among the components; the main board is used for providing a framework and integrating all the server components together;
the graphics processor is used for assisting the processor to perform parallel computing tasks when graphics processing is performed or massive parallel computing is required; the power supply unit is used for providing power required by the server; the radiator is used for keeping the internal temperature of the server within a safe range and preventing overheat from damaging electronic elements; the clock generator is used for providing clock signals of all components in the server; the BIOS chip is used for providing a basic input/output system required by the starting of the server and assisting the system to perform self-checking and initialization; the network interface is used for exchanging data with the LTE base station and the user equipment through wireless or wired connection.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311632981.7A CN117440407A (en) | 2023-11-30 | 2023-11-30 | LTE wireless network evaluation method and server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311632981.7A CN117440407A (en) | 2023-11-30 | 2023-11-30 | LTE wireless network evaluation method and server |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117440407A true CN117440407A (en) | 2024-01-23 |
Family
ID=89546224
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311632981.7A Withdrawn CN117440407A (en) | 2023-11-30 | 2023-11-30 | LTE wireless network evaluation method and server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117440407A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117998448A (en) * | 2024-04-07 | 2024-05-07 | 广州华生网络科技股份有限公司 | Wireless network quality data collection method and system |
| CN118870473A (en) * | 2024-08-19 | 2024-10-29 | 重庆杰速高科技有限公司 | Embedded wireless network system and method for accessing wireless network |
-
2023
- 2023-11-30 CN CN202311632981.7A patent/CN117440407A/en not_active Withdrawn
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117998448A (en) * | 2024-04-07 | 2024-05-07 | 广州华生网络科技股份有限公司 | Wireless network quality data collection method and system |
| CN117998448B (en) * | 2024-04-07 | 2024-06-07 | 广州华生网络科技股份有限公司 | Wireless network quality data acquisition method and system |
| CN118870473A (en) * | 2024-08-19 | 2024-10-29 | 重庆杰速高科技有限公司 | Embedded wireless network system and method for accessing wireless network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113159615B (en) | An intelligent determination system and method for information security risk of industrial control systems | |
| CN114325405A (en) | Battery pack consistency analysis method, modeling method, device, equipment and medium | |
| CN113204716B (en) | Method and device for determining transaction relationship of suspicious money laundering users | |
| WO2020215783A1 (en) | Locating method and apparatus, and storage medium | |
| CN111526119A (en) | Abnormal flow detection method and device, electronic equipment and computer readable medium | |
| CN116489038A (en) | Network traffic prediction method, device, equipment and medium | |
| CN116467759A (en) | Method, device, equipment and storage medium for determining data storage strategy | |
| CN120389938B (en) | Communication equipment fault prediction method and system based on big data and optical fiber sensor | |
| CN107679626A (en) | Machine learning method, device, system, storage medium and equipment | |
| CN117422031B (en) | Method and device for generating and simplifying test vector of ATPG (automatic Teller machine) system | |
| CN118627914B (en) | Iron tower installation risk assessment method and system based on communication network | |
| CN112861123A (en) | Bit currency malicious address identification method and device | |
| CN119294924B (en) | A method and system for analyzing reliability of power system | |
| CN121301071B (en) | Intelligent Diagnosis and Recovery Method and System for System Anomalies Integrating Time-Series Logs | |
| CN118869511A (en) | Network energy consumption assessment method, device, equipment, storage medium and program product | |
| CN120144971A (en) | A method and system for processing electronic component detection data | |
| CN118606218A (en) | Test case selection method and device | |
| CN118536243A (en) | A vulnerability assessment method, system and electronic equipment for urban rail pipeline network | |
| CN114116417B (en) | Capacity prediction model training method, capacity prediction method, device and equipment | |
| CN118051506A (en) | Missing flow data completion method, terminal device and storage medium | |
| CN116150191B (en) | A method and system for accelerating data processing in cloud data architecture | |
| CN118174296B (en) | Output prediction method and system for novel power distribution system | |
| CN120499049A (en) | High concurrency scene-oriented government affair system automation performance test method and system | |
| CN119829953A (en) | Processing intelligent evaluation method and system based on mobile phone connector | |
| CN120547603B (en) | WiFi signal data processing method and device |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20240123 |
|
| WW01 | Invention patent application withdrawn after publication |