CN109511144B - Network access type decision method, device, switching control device and storage medium - Google Patents

Network access type decision method, device, switching control device and storage medium Download PDF

Info

Publication number
CN109511144B
CN109511144B CN201811605468.8A CN201811605468A CN109511144B CN 109511144 B CN109511144 B CN 109511144B CN 201811605468 A CN201811605468 A CN 201811605468A CN 109511144 B CN109511144 B CN 109511144B
Authority
CN
China
Prior art keywords
lifi
access type
rate
wifi
user side
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
CN201811605468.8A
Other languages
Chinese (zh)
Other versions
CN109511144A (en
Inventor
王昭诚
吉开轩
权进国
金爽
董宇涵
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.)
Shenzhen Graduate School Tsinghua University
Original Assignee
Shenzhen Graduate School Tsinghua University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenzhen Graduate School Tsinghua University filed Critical Shenzhen Graduate School Tsinghua University
Priority to CN201811605468.8A priority Critical patent/CN109511144B/en
Publication of CN109511144A publication Critical patent/CN109511144A/en
Application granted granted Critical
Publication of CN109511144B publication Critical patent/CN109511144B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W36/00—Hand-off or reselection arrangements
    • H04W36/0005—Control or signalling for completing the hand-off
    • H04W36/0055—Transmission or use of information for re-establishing the radio link
    • H04W36/0066—Transmission or use of information for re-establishing the radio link of control information between different types of networks in order to establish a new radio link in the target network
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B17/00—Monitoring; Testing
    • H04B17/30—Monitoring; Testing of propagation channels
    • H04B17/391—Modelling the propagation channel
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W36/00—Hand-off or reselection arrangements
    • H04W36/0005—Control or signalling for completing the hand-off
    • H04W36/0083—Determination of parameters used for hand-off, e.g. generation or modification of neighbour cell lists
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W36/00—Hand-off or reselection arrangements
    • H04W36/24—Reselection being triggered by specific parameters
    • H04W36/30—Reselection being triggered by specific parameters by measured or perceived connection quality data
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B10/00—Transmission systems employing electromagnetic waves other than radio-waves, e.g. infrared, visible or ultraviolet light, or employing corpuscular radiation, e.g. quantum communication
    • H04B10/11—Arrangements specific to free-space transmission, i.e. transmission through air or vacuum
    • H04B10/114—Indoor or close-range type systems
    • H04B10/116—Visible light communication
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/30—Services specially adapted for particular environments, situations or purposes
    • H04W4/33—Services specially adapted for particular environments, situations or purposes for indoor environments, e.g. buildings
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/80—Services using short range communication, e.g. near-field communication [NFC], radio-frequency identification [RFID] or low energy communication

Abstract

A method for network access type decision making, comprising: and acquiring the data transmission rate of the user side when the visible light communication channel is not shielded in the current state, and determining the access type with the maximum equivalent data rate as the access type of the user side in the current state according to the known channel blocking parameter in the previous state and the known data transmission rate of the user side when the visible light communication channel is not shielded in the current state and a pre-trained nonlinear support vector machine model. The invention also provides a network access type decision device, a network switching control device and a computer readable storage medium. In a mixed indoor wireless communication network environment consisting of visible light communication and traditional radio frequency communication, the invention enables a user to more accurately select the access type with the maximum equivalent data rate in the current state under the condition that the actual channel blocking parameter is unknown, effectively deals with the negative influence caused by frequent switching and blocking shielding, and meets the requirements of the user on the transmission rate and the communication quality.

Description

Network access type decision method, device, switching control device and storage medium
Technical Field
The invention relates to the technical field of indoor wireless communication, in particular to a network access type decision method and device, a switching control device and a computer readable storage medium in a mixed indoor wireless communication network environment consisting of visible light communication and traditional radio frequency communication.
Background
Visible Light Communication (VLC) technology is considered as one of the important technologies of future indoor wireless Communication systems, and has attracted extensive attention in both academic and industrial fields. Due to the increasing number of mobile terminals and the increasing demand for services, the data traffic of indoor wireless networks is increasing rapidly, and the drawback of limited available Frequency spectrum for Radio Frequency (RF) communication is gradually emerging. In recent years, VLC technology has been rapidly developed, which communicates via an indoor-covered Light Emitting Diode (LED) facility, uses high-frequency visible light waves emitted by the LED as a communication information carrier to perform intensity modulation and transmission of information, and detects a received light carrier signal at a user end by a photodetection device. VLC systems, which support data communications and lighting in indoor environments, can transmit light signals in the air using a large amount of unrestricted free spectrum, has become a viable means to overcome the radio spectrum congestion of highly localized communication systems. Compared with the traditional radio frequency communication technology, the visible light communication has the advantages of high data rate, greenness, low carbon, convenience in arrangement and high confidentiality, and can meet the requirement of an indoor wireless communication scene on high access rate.
However, the visible light communication technology still has some problems to be solved in the application of practical systems. Compared with the penetrability of other wireless communications, the visible light communication is easily affected by the shielding object, which causes the instability of the optical communication link and can not ensure that the mobile user obtains continuous and effective communication service. In addition, the visible light wavelength is too short, so that the influence of scattering, reflection and multipath is large, and therefore the technology has certain limitations and application scenes. In summary, the bottleneck problem to be broken through by VLC technology is how to effectively deal with the blockage of the light beam by the obstacle, which is also a hot issue of current research.
At present, a reasonable solution is to combine VLC technology with other wireless access modes to provide better network service for mobile users in actual environments. In an indoor place, Wireless Fidelity (WiFi) is generally adopted for full coverage, so that the continuity of user access is ensured, and aiming at the defect of insufficient bandwidth of the WiFi technology, a VLC technology is introduced to form an indoor heterogeneous communication network. The VLC-WiFi hybrid network can combine the high-speed transmission characteristics of Light Fidelity (LiFi) and ubiquitous WiFi coverage characteristics to provide users in indoor environments with better access options to improve transmission performance and improve user experience.
In a VLC-WiFi hybrid network, LiFi is susceptible to channel blockage due to Line of Sight (LoS) channels obstructed by opaque obstacles, and switching a LiFi user to WiFi provides alternative access in order to prevent long-term interruption of communications. However, frequent switching of users between the two networks can significantly reduce the time for transmitting data and reduce the equivalent transmission rate. To avoid the ping-pong effect, the user should selectively switch to WiFi when the LiFi connection is lost. In an indoor scene, the frequency and duration of channel blockage caused by movement of an obstacle are difficult to determine, and switching overhead and shielding effect are both problems to be considered, so that the difficulty of selecting a proper access type by a user is greatly increased.
For the sake of simplicity, the indoor visible light communication channel can be modeled as a LoS channel model, and the optical channel gain can be expressed as:
Figure BDA0001923482280000021
wherein the Lambertian index m is the half-intensity radiation angle θ1/2Can be expressed by the formula m-1/log2(cos(θ1/2) Is represented by APIs the receiving end physical area of the photodiode, d is the distance from the LiFi Access Point (AP) to the user light receiver, ψ is the illumination angle, θ is the incident angle; thetaFIs the half angle of the receiver Field of View (FoV), TS(θ) is the gain of the optical filter, and the concentrator gain g (θ) can be expressed as:
Figure BDA0001923482280000031
where n is the refractive index.
When the ue μ is connected to the LiFi AP α, its signal to interference plus noise ratio (SINR) can be expressed as:
Figure BDA0001923482280000032
where γ is the photoelectric conversion efficiency, PtIs the emitted optical power, N, of each LiFi AP0Is the noise power spectral density, B is the modulation bandwidth of the LED lamp, Hμ,αIs the optical channel gain, H, between the user side mu and LiFi AP alphaμ,elseIs the optical channel gain between the user side mu and other interfering LiFi APs.
Orthogonal Frequency Division Multiplexing (OFDM) is commonly used in visible light communications, and because of the intensity modulation and direct detection used in LiFi transmission, only real-valued signals can be transmitted to the receiver, and at least half of the subcarriers are used to implement hermitian conjugation of the modulated complex symbols. The data rate achievable with half the bandwidth between the ue μ and the other interfering LiFi APs is therefore expressed as:
Figure BDA0001923482280000033
in machine learning, a Support Vector Machine (SVM) is a supervised learning model related to a related learning algorithm, is widely applied to data analysis and pattern recognition, and is mainly used for solving the problems of classification, regression and the like. When the training samples are linearly divisible, learning is performed by hard interval maximization, and for samples which are approximately linearly divisible, learning can be performed according to soft interval maximization. In practical application, a linear inseparable sample set is more common, and at the moment, nonlinear transformation is performed through a kernel function, so that a nonlinear problem is converted into a linear problem. The kernel function can map the training samples from the original space to a high-dimensional space, so that the training samples can be linearly divided in the space, and therefore, an appropriate kernel function needs to be selected when solving the non-linear problem.
Disclosure of Invention
In view of the above problems, the present invention provides a network access type decision method, a device, a handover control device, and a computer readable storage medium, which enable a user to select an access type with the maximum equivalent data rate more accurately in a mixed indoor wireless communication network environment composed of visible light communication and conventional radio frequency communication, effectively cope with the negative impact caused by frequent handover and blocking, and meet the requirements of the user on transmission rate and communication quality.
A first aspect of the present application provides a network access type decision method, applied to a hybrid indoor wireless communication system composed of visible light communication and conventional radio frequency communication, where the indoor wireless communication system includes at least one network switching control device, at least one visible light communication device, at least one wireless radio frequency communication device, and at least one user end, and the method includes:
continuously monitoring visible light communication channel blocking parameters of a user terminal in each time interval at fixed time intervals, wherein each time interval is defined as a state, the channel blocking parameters comprise channel blocking occurrence rate and occupancy rate, the occurrence rate corresponds to the channel blocking times occurring in the time interval, and the occupancy rate is the proportion of the time of the user terminal encountering channel blocking to the time interval;
and acquiring the data transmission rate of the user side when the visible light communication channel is not shielded in the current state, and determining the access type with the maximum equivalent data rate as the access type of the user side in the current state according to the known channel blocking parameter in the previous state and the data transmission rate of the user side when the visible light communication channel is not shielded in the current state and a pre-trained nonlinear support vector machine model.
Preferably, the training method of the pre-trained nonlinear support vector machine model includes:
establishing an initial data set of a user side access type decision, wherein the initial data set comprises the channel blocking occurrence rate and the occupancy rate of a user side in a previous state and the data transmission rate when a visible light communication channel is not blocked in a current state;
training the nonlinear support vector machine model by adopting a radial basis kernel function on the initial data set, wherein a training sample data set is the initial data set, and tags are three user network access types, wherein a first tag type y is 1 for only connecting WiFi, a second tag type y is 2 for only connecting LiFi, and a third tag type y is 3 for LiFi/WiFi, namely, when a visible light channel is blocked, a user end switches from LiFi to WiFi to ensure data transmission, and when LiFi connection is recovered, the user end switches back to LiFi;
and obtaining a test sample data set, and testing the decision effect of the trained nonlinear support vector machine model, wherein the test sample data set comprises the channel blockage occurrence rate and the occupancy rate of the user terminal in the previous state and the data transmission rate when the visible light communication channel is not blocked in the current state.
Preferably, the tag calculation method includes:
and calculating the equivalent rate of the user terminal in the current state by using the measured current actual channel blocking parameters within the preset time length, and selecting the network access type with the maximum equivalent rate as a training sample data set label.
Preferably, the calculating the equivalent rate of the current state user side and selecting the network access type with the maximum equivalent rate as the training sample data set label includes:
1) calculating the equivalent rate of the current state user side:
let kappa denote the access type, T, of the user sideHThe vertical switching time representing network switching of the user side accounts for the time interval proportion, and the data transmission efficiency of the user side using WiFi in the current state is as follows:
Figure BDA0001923482280000051
the access type of the user side represented by κ ═ WiFi is only WiFi connected, the access type of the user side represented by κ ═ LiFi is only LiFi connected, the access type of the user side represented by κ ═ LiFi/WiFi is that the user side switches from LiFi to WiFi when a visible light channel is blocked to ensure data transmission, and switches back to LiFi when the LiFi connection is restored;
the data transmission efficiency of the user side using the LiFi is as follows:
Figure BDA0001923482280000052
the access type of the user side represented by κ ═ WiFi is only WiFi connected, the access type of the user side represented by κ ═ LiFi is only LiFi connected, the access type of the user side represented by κ ═ LiFi/WiFi is that the user side switches from LiFi to WiFi when a visible light channel is blocked to ensure data transmission, and switches back to LiFi when the LiFi connection is restored;
rLiFiis the actual received current state LiFi transmission rate, r of the user terminalWiFiFor a WiFi constant transmission rate, the ue equivalent rate r is:
Figure BDA0001923482280000053
2) and selecting the network access type with the maximum equivalent rate from the equivalent rates of the user side as a training sample data set label.
A second aspect of the present application provides a network access type decision apparatus, the apparatus comprising:
a visible light communication channel blocking parameter monitoring module, configured to continuously monitor, at fixed time intervals, a visible light communication channel blocking parameter of a user terminal at each time interval, where each time interval is defined as a state, the channel blocking parameter includes a channel blocking occurrence rate and an occupancy rate, the occurrence rate corresponds to the number of channel blocking occurring in the time interval, and the occupancy rate is a proportion of time during which the user terminal encounters channel blocking to the time interval;
the data transmission rate acquisition module is used for acquiring the data transmission rate when the visible light communication channel is not shielded in the current state of the user side; and
and the network access type decision module is used for determining the access type with the maximum equivalent data rate as the access type of the user terminal in the current state according to the known channel blocking parameter in the previous state and the data transmission rate when the visible light communication channel in the current state is not blocked and a pre-trained nonlinear support vector machine model.
Preferably, the apparatus further comprises a model training module for training the nonlinear support vector machine model, the model training module training the nonlinear support vector machine model comprising:
establishing an initial data set of a user side access type decision, wherein the initial data set comprises the channel blocking occurrence rate and the occupancy rate of a user side in a previous state and the data transmission rate when a visible light communication channel is not blocked in a current state;
training the nonlinear support vector machine model on the initial data set by adopting a radial basis kernel function, wherein a training sample is the initial data set, and tags are three user network access types, wherein a first tag type y is 1 for only connecting WiFi, a second tag type y is 2 for only connecting LiFi, and a third tag type y is 3 for LiFi/WiFi, that is, when a visible light channel is blocked, a user end switches from LiFi to WiFi to ensure data transmission, and when LiFi connection is recovered, the user end switches back to LiFi;
and obtaining a test sample data set, and testing the decision effect of the trained nonlinear support vector machine model, wherein the test sample data set comprises the channel blockage occurrence rate and the occupancy rate of the user terminal in the previous state and the data transmission rate when the visible light communication channel is not blocked in the current state.
Preferably, the tag calculation method includes:
calculating the equivalent rate of a user terminal in the current state by using the measured current actual channel blocking parameter within a preset time length, and selecting the network access type with the maximum equivalent rate as a training sample data set label;
wherein, the calculating the equivalent rate of the current state user terminal and selecting the network access type with the maximum equivalent rate as the training sample data set label includes:
1) calculating the equivalent rate of the current state user side:
let kappa denote the access type, T, of the user sideHThe vertical switching time representing network switching of the user side accounts for the time interval proportion, and the data transmission efficiency of the user side using WiFi in the current state is as follows:
Figure BDA0001923482280000071
the access type of the user side represented by κ ═ WiFi is only WiFi connected, the access type of the user side represented by κ ═ LiFi is only LiFi connected, the access type of the user side represented by κ ═ LiFi/WiFi is that the user side switches from LiFi to WiFi when a visible light channel is blocked to ensure data transmission, and switches back to LiFi when the LiFi connection is restored;
the data transmission efficiency of the user side using the LiFi is as follows:
Figure BDA0001923482280000072
the access type of the user side represented by κ ═ WiFi is only WiFi connected, the access type of the user side represented by κ ═ LiFi is only LiFi connected, the access type of the user side represented by κ ═ LiFi/WiFi is that the user side switches from LiFi to WiFi when a visible light channel is blocked to ensure data transmission, and switches back to LiFi when the LiFi connection is restored;
rLiFiis the actual received current state LiFi transmission rate, r of the user terminalWiFiFor a WiFi constant transmission rate, the ue equivalent rate r is:
Figure BDA0001923482280000073
2) and selecting the network access type with the maximum equivalent rate from the equivalent rates of the user side as a training sample data set label.
A third aspect of the present application provides a handover control apparatus comprising a processor for implementing the network access type decision method when executing a computer program stored in a memory.
A fourth aspect of the present application provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the network access type decision method.
According to the VLC channel blocking parameters (incidence rate and occupancy rate) in the last state known by the user and the LiFi data transmission rate, the access type with the maximum equivalent data rate is selected through the trained SVM model, and the user can accurately select the access type with the maximum equivalent data rate in the hybrid network through the method, so that the negative effects caused by frequent switching and blocking can be effectively coped with, the overall rate performance of the user is improved, the requirements of the user on the transmission rate and the communication quality are met, and the long-time interruption of communication is avoided. In addition, after the classification data set and the model are established, the network access type can be quickly decided by directly utilizing the current known information of the user side, and the additional overhead of network switching decision is reduced.
Drawings
Fig. 1 is a schematic diagram of a network application environment of a network access type decision method according to an embodiment of the present invention.
Fig. 2 is a flowchart of a network access type decision method according to an embodiment of the present invention.
Fig. 3 is a flowchart of an SVM model training method for network access type decision according to an embodiment of the present invention.
Fig. 4 is a functional block diagram of a network access type decision device according to an embodiment of the present invention.
Fig. 5 is a schematic diagram of a network handover control apparatus according to an embodiment of the present invention.
Detailed Description
In order that the above objects, features and advantages of the present invention can be more clearly understood, a detailed description of the present invention will be given below with reference to the accompanying drawings and specific embodiments. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.
In the following description, numerous specific details are set forth to provide a thorough understanding of the present invention, and the described embodiments are merely a subset of the embodiments of the present invention, rather than a complete embodiment. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.
Fig. 1 is a schematic diagram of an application environment of a network access type decision method according to an embodiment of the present invention. In this embodiment, the network access type decision method is applied to a hybrid indoor wireless communication system 100 (hereinafter referred to as an indoor wireless communication system 100) composed of visible light communication and conventional radio frequency communication. The indoor wireless communication system 100 at least comprises at least one network switching control device 10, at least one visible light communication device 20, at least one radio frequency communication device 30, and at least one user terminal 40. The network switching control device 10 establishes communication connection with the visible light communication device 20 and the radio frequency communication device 30 by means of wired connection. The at least one user terminal 40 implements network data transmission through the visible light communication network provided by the visible light communication device 20 or the wireless radio frequency communication network provided by the radio frequency communication device 30. The network switching control device 10 is used for controlling the switching of the user terminal 40 between the visible light communication network and the wireless radio frequency communication network.
In the present embodiment, the visible Light communication device 20 is an indoor lighting device, such as an indoor lighting Light emitting diode (LED lamp), a fluorescent lamp, and the like, and is used for providing Light Fidelity (LiFi) communication. In the present embodiment, the radio frequency communication device 30 is a Wireless Fidelity (WiFi) communication device installed indoors. In other embodiments, the wireless rf communication device 30 may also be a communication device of other wireless communication methods. The user terminal 40 of the present invention is an electronic device such as a smart phone and a tablet computer.
Fig. 2 is a flowchart of a network access type decision method according to an embodiment of the present invention. The order of the steps in the flow chart may be changed and some steps may be omitted according to different needs. For convenience of explanation, only portions related to the embodiments of the present invention are shown.
As shown in fig. 2, the network access type decision method specifically includes the following steps:
step S1: the network switching control device continuously monitors VLC channel blockage parameters of the user terminal at each time interval T at fixed time intervals T, wherein each time interval T is defined as a state, and the VLC channel blockage parameters comprise channel blockage occurrence rate lambda and occupancy rate eta.
In this embodiment, the time interval T may be set to an appropriate time length value as needed. For example, the network switching control device continuously monitors the VLC channel blocking parameter of the user terminal at a time interval T of 60 seconds, the first 60 seconds is defined as the first state, the second 60 seconds is defined as the second state, and so on, the nth 60 seconds is defined as the nth state. The natural number n indicates the sequence number of each state.
The occurrence rate λ corresponding to a state (i.e. a time interval T) refers to the number of VLC channel blocking occurring in the time interval T, and the occupancy rate η is the proportion of the time during which the user terminal encounters channel blocking to the time interval T. Since the occupancy η of congestion is an arbitrary number between 0 and 1, η is discretized with an accuracy of 0.1 for ease of analysis.
In the monitoring process, due to the movement of the user end and the obstacle, the VLC channel blockage parameter between two adjacent states changes correspondingly, and the VLC channel blockage parameter is nextThe state will change to a new value. In an actual application scenario, a user cannot know VLC channel blocking parameters in a current n-state time period, and the information known by the user is n-1 state blocking occurrence rate lambdan-1And occupancy rate ηn-1。
Step S2, the network switching control device obtains the LiFi data transmission rate at which the visible light communication channel is not blocked in the current n state of the user end, and determines the access type with the maximum equivalent data rate as the access type of the user end in the current state according to the known VLC channel blocking parameter in the previous state and the LiFi data transmission rate in the current state and the pre-trained nonlinear SVM model.
The training method of the non-linear SVM model will be described in detail later with reference to fig. 3.
In each state, the network switching control device decides the network access type for all the user terminals in the wireless communication system. In a VLC-WiFi hybrid network of a hybrid indoor wireless communication system, VLC channel blockage parameters change to new values in the next state due to the movement of a user terminal and an obstacle, the time interval between two adjacent states is T, and a network switching control device updates the network access type of each user terminal at the time interval T as a period.
Step S3, the network switching control device sends the determined access type of the current state user end to the user end, and controls the user end to access the network with the determined access type.
When the network switching control device determines that the network type accessed by the user terminal in the current state is only WiFi connection, the user terminal accesses the WiFi network according to the Access type determined by the network switching control device, and does not perform switching between AP (Wireless Access Point). And when the network switching control device determines that the network type accessed by the user side in the current state is only LiFi connection, the user side is accessed into the LiFi network according to the access type determined by the network switching control device, and the AP is not switched. When the network switching control device determines that the network type accessed by the user side in the current state is LiFi/WiFi, the user side can switch between the LiFi network and the WiFi network according to the access type determined by the network switching control device, switch from LiFi to WiFi when channel blockage occurs, and switch back to the original AP when LiFi connection is recovered. The network access type decision method in the invention utilizes an SVM model to select the access type with the maximum equivalent data rate according to the last state VLC channel blocking parameters (including the occurrence rate and the occupancy rate) known by a user terminal and the LiFi data transmission rate in the current state, thereby improving the overall rate performance of the user.
Please refer to fig. 3, which is a flowchart illustrating a method for training an SVM model according to an embodiment of the present invention. The order of the steps in the flow chart may be changed and some steps may be omitted according to different needs. For convenience of explanation, only portions related to the embodiments of the present invention are shown.
Step S21, establishing an initial data set of user terminal access type decision, wherein the initial data set comprises VLC channel blockage occurrence rate lambda of the user terminal in n-1 staten-1And occupancy rate ηn-1And the transmission rate of unshielded LiFi in the current n state
Figure BDA0001923482280000111
I.e. the initial data set
Figure BDA0001923482280000112
Wherein n is a natural number.
In this embodiment, the initial data set is obtained by collecting information within a preset time period from the user side. The preset time length is information within a long period of time, and the preset time length can be set as required, for example, one month. In an actual scene, a user cannot know VLC channel blocking parameters in a current n-state time period, and the known information of the user side is the n-1 state occurrence rate lambdan-1And occupancy rate ηn-1And the current n-state unshielded LiFi transmission rate
Figure BDA0001923482280000113
Thus the initial data set of the sample input is made up of the above three parameters
Figure BDA0001923482280000114
The VLC channel blocking parameters (incidence and occupancy rate) of the user terminal in each state are kept unchanged, when the state changes, the VLC channel blocking parameters of the user terminal also change, and the incidence rate lambda of the current state changesnAnd occupancy rate ηnOnly with respect to the last state. In the embodiment, the SVM model is trained to make a decision by utilizing the correlation between the LiFi channel blocking parameters of the states before and after the actual indoor scene.
Step S22, training a nonlinear SVM model on the initial data set by using a radial basis function, where the training sample data set is the initial data set x, and the labels are three user network access types y, where a first label type y is 1 for only connecting WiFi, a second label type y is 2 for only connecting LiFi, and a third label type y is 3 for LiFi/WiFi, that is, when a visible light channel is blocked, the user terminal switches from LiFi to WiFi to ensure data transmission, and when the LiFi connection is restored, switches back to LiFi.
In this embodiment, the current actual channel blocking occurrence rate λ measured within the preset time length is usednAnd occupancy rate ηnAnd calculating the equivalent rate of the current state user side and selecting the network access type with the maximum equivalent rate as the training sample data set label y.
Specifically, for a ue, the effective transmission time in one state is the time ratio of the time interval T minus the channel blocking time and the time occupied by the network handover. Let kappa denote the access type, T, of the user sideHThe vertical switching time representing network switching of the user side accounts for the time interval proportion, and the data transmission efficiency of the user side using WiFi in the current state is as follows:
Figure BDA0001923482280000121
the access type of the user side represented by κ ═ WiFi is only WiFi connected, the access type of the user side represented by κ ═ LiFi is only LiFi connected, the access type of the user side represented by κ ═ LiFi/WiFi is that the user side switches from LiFi to WiFi when a visible light channel is blocked to ensure data transmission, and switches back to LiFi when the LiFi connection is restored;
the data transmission efficiency of the user side using the LiFi is as follows:
Figure BDA0001923482280000122
the access type of the user side represented by κ ═ WiFi is only WiFi connected, the access type of the user side represented by κ ═ LiFi is only LiFi connected, the access type of the user side represented by κ ═ LiFi/WiFi is that the user side switches from LiFi to WiFi when a visible light channel is blocked to ensure data transmission, and switches back to LiFi when the LiFi connection is restored;
rLiFiis the actual received current state LiFi transmission rate, r of the user terminalWiFiFor a WiFi constant transmission rate, the ue equivalent rate r is:
Figure BDA0001923482280000131
and calculating equivalent rates of different access types by using actual parameter values of the current state, and selecting the access type with the maximum equivalent rate as the training sample data set label y.
The user terminal with the tag type y being 1 is always connected to the WiFi, and the switching between APs is not performed; the ue with tag type y 2 is always connected to LiFi, and no switching between APs is performed. When the LiFi channel blocking occurs, the client with tag type y 3 switches from LiFi to WiFi and switches back to the original AP when the LiFi connection is restored. The classification is as follows, not every LiFi user terminal experiencing VLC channel blockage should switch to WiFi, considering the handover overhead. When the user equipment has a high channel blocking occurrence rate, switching it to WiFi may result in frequent switching. In this case, if the congestion occupancy is high, the ue is preferably always connected to WiFi, otherwise the ue should remain in the LiFi network. For a user terminal with low occurrence rate but high occupancy rate, the user terminal should be switched to WiFi when channel blocking occurs, in this case, the user terminal is switched infrequently between APs, and robust transmission of data during the blocked occupancy period is also ensured.
In this embodiment, the trained nonlinear SVM model is denoted as y ═ f (x), where the x vector includes the n-1 state occurrence rate λn-1And occupancy rate ηn-1And the current n-state unshielded LiFi transmission rate
Figure BDA0001923482280000132
y is the network access type.
And S23, acquiring a test sample data set, and testing the decision effect of the trained nonlinear SVM model, wherein the test sample data set comprises the VLC channel blockage occurrence rate and occupancy rate of a user terminal in an n-1 state and the unoccluded LiFi transmission rate in the current n state.
In this embodiment, the method for obtaining the test sample data set is the same as the method for obtaining the initial data set, that is, the test sample data set is obtained by collecting statistical information of the user terminal for a long time.
In this embodiment, the training of the SVM model is performed by the network switching control device, and the network switching control device obtains the initial data set from the user side and trains the nonlinear SVM model, and stores the model parameters of the trained nonlinear SVM model to a preset storage location of the network switching control device.
After the nonlinear SVM model training is finished, the network switching control device carries out state incidence lambda of n-1 vector according to the known information x of the current user terminaln-1And occupancy rate ηn-1And the current n state does not obscure the LiFi transmission rate) to decide the appropriate network access type y for the user.
In other embodiments of the present invention, the training of the SVM model may also be performed by other computer devices such as a cloud server, for example, after the network switching control device obtains the initial data set by a user side, the initial data set is sent to the cloud server, after the cloud server trains the nonlinear SVM model by using a radial basis kernel function according to the initial data set and completes the test, the cloud server sends the trained model of the nonlinear SVM model to the network switching control device, and the network switching control device directly uses the trained nonlinear SVM model to make a decision on a suitable network access type for the user.
The invention decides the proper user network access type through the trained SVM model, and the user can more accurately select the access type with the maximum equivalent data rate in the hybrid network through the method, thereby effectively coping with the negative effects caused by frequent switching and blocking shielding, meeting the requirements of the user on the transmission rate and the communication quality and avoiding the long-time interruption of communication. The main overhead of the system is the collection and establishment of the sample data set and the training process of the nonlinear SVM model, so that after the classification data set and the model are established by the central processing unit, the network access type can be quickly decided by directly utilizing the currently known information of the user terminal, and the additional overhead is reduced.
Fig. 4 is a block diagram of a network access type decision device according to an embodiment of the present invention.
In some embodiments, the network access type decision device 200 may include a plurality of functional modules composed of program code segments. The program codes of the program segments in the network access type decision device 200 can be stored in the memory of the computer device and executed by at least one processor to implement the network access type decision function of the indoor user terminal.
Referring to fig. 4, in this embodiment, the network access type decision device 200 may be divided into a plurality of functional modules according to the functions performed by the network access type decision device, where each functional module is configured to perform each step in the corresponding embodiment of fig. 2, so as to implement the function of making a decision on the network access type of the indoor user terminal. In this embodiment, the functional modules of the network access type decision device 200 may include a visible light communication channel blocking parameter monitoring module 201, a data transmission rate obtaining module 202, a network access type decision module 203, and a model training module 204. The functions of the respective functional blocks will be described in detail in the following embodiments.
The Visible Light Communication channel blockage parameter monitoring module 201 is configured to continuously monitor VLC (Visible Light Communication) channel blockage parameters of the user terminal at each time interval T at fixed time intervals T, where each time interval T is defined as a state, and the VLC channel blockage parameters include a channel blockage occurrence rate λ and an occupancy rate η.
In this embodiment, the time interval T may be set to an appropriate time length value as needed. For example, the network switching control device continuously monitors the VLC channel blocking parameter of the user terminal at a time interval T of 60 seconds, the first 60 seconds is defined as the first state, the second 60 seconds is defined as the second state, and so on, the nth 60 seconds is defined as the nth state. The natural number n indicates the sequence number of each state.
The occurrence rate λ corresponding to a state (i.e. a time interval T) refers to the number of VLC channel blocking occurring in the time interval T, and the occupancy rate η is the proportion of the time during which the user terminal encounters channel blocking to the time interval T. Since the occupancy η of congestion is an arbitrary number between 0 and 1, η is discretized with an accuracy of 0.1 for ease of analysis.
In the monitoring process, due to the movement of the user end and the obstacle, the VLC channel blocking parameter between two adjacent states changes correspondingly, and the VLC channel blocking parameter changes into a new value in the next state. In an actual application scenario, a user cannot know VLC channel blocking parameters in a current n-state time period, and the information known by the user is n-1 state blocking occurrence rate lambdan-1And occupancy rate ηn-1。
The data transmission rate obtaining module 202 obtains the LiFi data transmission rate when the visible light communication channel is not blocked in the current n state of the user terminal.
The network access type decision module 203 is configured to determine, according to a VLC channel blocking parameter in a previous state and a LiFi data transmission rate in a current state, an access type with a maximum equivalent data rate as an access type of a user end in the current state according to a pre-trained nonlinear SVM (Support Vector Machine) model. The network access type decision module 203 is further configured to send the determined access type of the user terminal in the current state to the user terminal, and control the user terminal to access the network according to the determined access type.
In each state, the network switching control device decides the network access type for all the user terminals in the wireless communication system. In a VLC-WiFi hybrid network of a hybrid indoor wireless communication system, VLC channel blockage parameters change to new values in the next state due to the movement of a user terminal and an obstacle, the time interval between two adjacent states is T, and a network switching control device updates the network access type of each user terminal at the time interval T as a period.
The model training module 204 is configured to train the non-linear SVM model.
Specifically, the method for training the non-linear SVM model by the model training module 204 includes the following steps:
step (I): establishing an initial data set of user terminal access type decision, wherein the initial data set comprises VLC channel blockage occurrence rate lambda of the user terminal in an n-1 staten-1And occupancy rate ηn-1And the transmission rate of unshielded LiFi in the current n state
Figure BDA0001923482280000161
I.e. the initial data set
Figure BDA0001923482280000162
Wherein n is a natural number.
In this embodiment, the VLC channel blocking occurrence rate and occupancy rate are obtained by collecting statistical information of the user terminal over a long period of time. In an actual scene, a user cannot know VLC channel blocking parameters in a current n-state time period, and the known information of the user side is the n-1 state occurrence rate lambdan-1And occupancy rate ηn-1And the current n-state unshielded LiFi transmission rate
Figure BDA0001923482280000163
Thus is provided withThe last three parameters constitute the initial data set of the sample input
Figure BDA0001923482280000164
The VLC channel blocking parameters (incidence and occupancy rate) of the user terminal in each state are kept unchanged, when the state changes, the VLC channel blocking parameters of the user terminal also change, and the incidence rate lambda of the current state changesnAnd occupancy rate ηnOnly with respect to the last state. In the embodiment, the SVM model is trained to make a decision by utilizing the correlation between the LiFi channel blocking parameters of the states before and after the actual indoor scene.
And (ii) training a nonlinear SVM model by using a Radial Basis Function (RBF) kernel function on the initial data set, wherein a training sample data set is the initial data set x, and tags are three user network access types y, wherein a first tag type y is 1 for only connecting WiFi, a second tag type y is 2 for only connecting LiFi, and a third tag type y is 3 for LiFi/WiFi, that is, when a visible light channel is blocked, a user terminal switches from LiFi to WiFi to ensure data transmission, and switches back to LiFi when the LiFi connection is restored.
In this embodiment, the current actual channel blocking occurrence rate λ measured within the preset time length is usednAnd occupancy rate ηnAnd calculating the equivalent rate of the current state user side and selecting the network access type with the maximum equivalent rate as the training sample data set label y.
Specifically, for a ue, the effective transmission time in one state is the time ratio of the time interval T minus the channel blocking time and the time occupied by the network handover.
Let kappa denote the access type, T, of the user sideHThe vertical switching time representing network switching of the user side accounts for the time interval proportion, and the data transmission efficiency of the user side using WiFi in the current state is as follows:
Figure BDA0001923482280000171
the access type of the user side represented by κ ═ WiFi is only WiFi connected, the access type of the user side represented by κ ═ LiFi is only LiFi connected, the access type of the user side represented by κ ═ LiFi/WiFi is that the user side switches from LiFi to WiFi when a visible light channel is blocked to ensure data transmission, and switches back to LiFi when the LiFi connection is restored;
the data transmission efficiency of the user side using the LiFi is as follows:
Figure BDA0001923482280000172
the access type of the user side represented by κ ═ WiFi is only WiFi connected, the access type of the user side represented by κ ═ LiFi is only LiFi connected, the access type of the user side represented by κ ═ LiFi/WiFi is that the user side switches from LiFi to WiFi when a visible light channel is blocked to ensure data transmission, and switches back to LiFi when the LiFi connection is restored;
rLiFiis the actual received current state LiFi transmission rate, r of the user terminalWiFiFor a WiFi constant transmission rate, the ue equivalent rate r is:
Figure BDA0001923482280000173
and calculating equivalent rates of different access types by using actual parameter values of the current state, and selecting the access type with the maximum equivalent rate as the training sample data set label y.
The user terminal with the tag type y being 1 is always connected to the WiFi, and the switching between APs is not performed; the ue with tag type y 2 is always connected to LiFi, and no switching between APs is performed. When the LiFi channel blocking occurs, the client with tag type y 3 switches from LiFi to WiFi and switches back to the original AP when the LiFi connection is restored. The classification is as follows, not every LiFi user terminal experiencing VLC channel blockage should switch to WiFi, considering the handover overhead. When the user equipment has a high channel blocking occurrence rate, switching it to WiFi may result in frequent switching. In this case, if the congestion occupancy is high, the ue is preferably always connected to WiFi, otherwise the ue should remain in the LiFi network. For a user terminal with low occurrence rate but high occupancy rate, the user terminal should be switched to WiFi when channel blocking occurs, in this case, the user terminal is switched infrequently between APs, and robust transmission of data during the blocked occupancy period is also ensured.
In this embodiment, the trained nonlinear SVM model is denoted as y ═ f (x), where the x vector includes the n-1 state occurrence rate λn-1And occupancy rate ηn-1And the current n-state unshielded LiFi transmission rate
Figure BDA0001923482280000181
y is the network access type.
And (III) acquiring a test sample data set, and testing the decision effect of the trained nonlinear SVM model, wherein the test sample data set comprises VLC channel blockage occurrence rate and occupancy rate of a user terminal in a previous state (n-1 state) and the unoccluded LiFi transmission rate in a current state (n state).
In this embodiment, the method for obtaining the test sample data set is the same as the method for obtaining the initial data set, that is, the test sample data set is obtained by collecting statistical information of the user terminal for a long time.
Fig. 5 is a functional block diagram of a network switching control device according to an embodiment of the present invention. The network handover control device 10 comprises at least a communication unit 11, a memory 12, a processor 13 and a computer program 14, such as a network access type decision program, stored in the memory 12 and executable on the processor 13. The processor 13, when executing the computer program 14, implements the steps in the above-described network access type decision method embodiments. Alternatively, the processor 13 implements the functions of the modules/units in the above device embodiments when executing the computer program 14, such as the module 201 and 204 in fig. 4.
Illustratively, the computer program 14 may be partitioned into one or more modules/units that are stored in the memory 12 and executed by the processor 13 to implement the present invention. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution of the computer program 14 in the handover control apparatus 1. For example, the computer program 14 may be partitioned into modules 201 and 204 in FIG. 3.
It will be understood by those skilled in the art that the schematic diagram 5 is merely an example of the network switching control apparatus 10, and does not constitute a limitation to the network switching control apparatus 10, and the network switching control apparatus 10 may include more or less components than those shown, or combine some components, or different components, for example, the network switching control apparatus 10 may further include an input/output device, etc.
The Processor 13 may be a Central Processing Unit (CPU), and may include other general purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, and the like. The general purpose processor may be a microprocessor or the processor may be any conventional processor, etc., and the processor 13 is a control center of the network switching control apparatus 10, and various interfaces and lines are used to connect various parts of the entire network switching control apparatus 10.
The memory 12 may be used to store the computer program 14 and/or the modules/units, and the processor 13 implements various functions of the network switching control device 10 by running or executing the computer program and/or the modules/units stored in the memory 12 and calling data stored in the memory 12. The storage 12 may include an external storage medium, and may also include a memory. Further, the memory 12 may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
The modules/units integrated with the network switching control device 10 may be stored in a computer-readable storage medium if they are implemented as software functional units and sold or used as independent products. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned. Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. The units or computer means recited in the computer means claims may also be implemented by the same unit or computer means, either in software or in hardware. The terms first, second, etc. are used to denote names, but not any particular order.
Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims (10)

1. A network access type decision method is applied to a hybrid indoor wireless communication system composed of visible light communication and traditional radio frequency communication, the indoor wireless communication system comprises at least one network switching control device, at least one visible light communication device, at least one wireless radio frequency communication device and at least one user terminal, and the method is characterized by comprising the following steps:
continuously monitoring visible light communication channel blocking parameters of a user terminal in each time interval at fixed time intervals, wherein each time interval is defined as a state, the channel blocking parameters comprise channel blocking occurrence rate and occupancy rate, the occurrence rate corresponds to the channel blocking times occurring in the time interval, and the occupancy rate is the proportion of the time of the user terminal encountering channel blocking to the time interval;
and acquiring the data transmission rate of the user side when the visible light communication channel is not shielded in the current state, and determining the access type with the maximum equivalent data rate as the access type of the user side in the current state according to the known channel blocking parameter in the previous state and the data transmission rate of the user side when the visible light communication channel is not shielded in the current state and a pre-trained nonlinear support vector machine model.
2. The method for network access type decision making according to claim 1, wherein the method for training the pre-trained non-linear support vector machine model comprises:
establishing an initial data set of a user side access type decision, wherein the initial data set comprises the channel blocking occurrence rate and the occupancy rate of a user side in a previous state and the data transmission rate when a visible light communication channel is not blocked in a current state;
training the nonlinear support vector machine model by adopting a radial basis kernel function on the initial data set, wherein a training sample data set is the initial data set, and tags are three user network access types, wherein a first tag type y is 1 for only connecting WiFi, a second tag type y is 2 for only connecting LiFi, and a third tag type y is 3 for LiFi/WiFi, namely, when a visible light channel is blocked, a user end switches from LiFi to WiFi to ensure data transmission, and when LiFi connection is recovered, the user end switches back to LiFi;
and obtaining a test sample data set, and testing the decision effect of the trained nonlinear support vector machine model, wherein the test sample data set comprises the channel blockage occurrence rate and the occupancy rate of the user terminal in the previous state and the data transmission rate when the visible light communication channel is not blocked in the current state.
3. The network access type decision method of claim 2, wherein the label calculation method comprises:
and calculating the equivalent rate of the user terminal in the current state by using the measured current actual channel blocking parameters within the preset time length, and selecting the network access type with the maximum equivalent rate as a training sample data set label.
4. The method for deciding network access type according to claim 3, wherein the calculating the equivalent rate of the user terminal in the current state and selecting the network access type with the largest equivalent rate as the training sample data set label comprises:
1) calculating the equivalent rate of the current state user side:
let k denote the access type, T, of the subscriber sideHThe vertical switching time representing network switching of the user side accounts for the time interval proportion, and the data transmission efficiency of the user side using WiFi in the current state is as follows:
Figure FDA0002856312630000021
wherein λ isnAnd ηnRespectively representing the occurrence rate and the occupancy rate of the current n state; the access type of the user side represented by k ═ WiFi is only WiFi connection, the access type of the user side represented by k ═ LiFi is only LiFi connection, and the access type of the user side represented by k ═ LiFi/WiFi is that the user side is switched from LiFi to WiFi to ensure data transmission when a visible light channel is blocked, and the LiFi connection is switched back to LiFi when the LiFi connection is recovered;
the data transmission efficiency of the user side using the LiFi is as follows:
Figure FDA0002856312630000022
the access type of the user side represented by κ ═ WiFi is only WiFi connected, the access type of the user side represented by κ ═ LiFi is only LiFi connected, the access type of the user side represented by κ ═ LiFi/WiFi is that the user side switches from LiFi to WiFi when a visible light channel is blocked to ensure data transmission, and switches back to LiFi when the LiFi connection is restored;
rLiFiis the actual received current state LiFi transmission rate, r of the user terminalWiFiFor a WiFi constant transmission rate, the ue equivalent rate r is:
Figure FDA0002856312630000031
2) and selecting the network access type with the maximum equivalent rate from the equivalent rates of the user side as a training sample data set label.
5. The method of claim 2, wherein the initial data set is composed of the channel blocking parameter and the visible light data transmission rate collected by the ue within a predetermined time period.
6. An apparatus for network access type decision, the apparatus comprising:
a visible light communication channel blocking parameter monitoring module, configured to continuously monitor, at fixed time intervals, a visible light communication channel blocking parameter of a user terminal at each time interval, where each time interval is defined as a state, the channel blocking parameter includes a channel blocking occurrence rate and an occupancy rate, the occurrence rate corresponds to the number of channel blocking occurring in the time interval, and the occupancy rate is a proportion of time during which the user terminal encounters channel blocking to the time interval;
the data transmission rate acquisition module is used for acquiring the data transmission rate when the visible light communication channel is not shielded in the current state of the user side; and
and the network access type decision module is used for determining the access type with the maximum equivalent data rate as the access type of the user terminal in the current state according to the known channel blocking parameter in the previous state and the data transmission rate when the visible light communication channel in the current state is not blocked and a pre-trained nonlinear support vector machine model.
7. The apparatus for network access type decision making of claim 6, the apparatus further comprising a model training module for training the non-linear support vector machine model, the model training module training the non-linear support vector machine model comprising:
establishing an initial data set of a user side access type decision, wherein the initial data set comprises the channel blocking occurrence rate and the occupancy rate of a user side in a previous state and the data transmission rate when a visible light communication channel is not blocked in a current state;
training the nonlinear support vector machine model by adopting a radial basis kernel function on the initial data set, wherein a training sample data set is the initial data set, and tags are three user network access types, wherein a first tag type y is 1 for only connecting WiFi, a second tag type y is 2 for only connecting LiFi, and a third tag type y is 3 for LiFi/WiFi, namely, when a visible light channel is blocked, a user end switches from LiFi to WiFi to ensure data transmission, and when LiFi connection is recovered, the user end switches back to LiFi;
and obtaining a test sample data set, and testing the decision effect of the trained nonlinear support vector machine model, wherein the test sample data set comprises the channel blockage occurrence rate and the occupancy rate of the user terminal in the previous state and the data transmission rate when the visible light communication channel is not blocked in the current state.
8. The network access type decision device of claim 7, wherein the label calculation method comprises:
calculating the equivalent rate of a user terminal in the current state by using the measured current actual channel blocking parameter within a preset time length, and selecting the network access type with the maximum equivalent rate as a training sample data set label;
wherein, the calculating the equivalent rate of the current state user terminal and selecting the network access type with the maximum equivalent rate as the training sample data set label includes:
1) calculating the equivalent rate of the current state user side:
let kappa denote the access type, T, of the user sideHThe vertical switching time representing network switching of the user side accounts for the time interval proportion, and the data transmission efficiency of the user side using WiFi in the current state is as follows:
Figure FDA0002856312630000041
wherein λ isnAnd ηnRespectively representing the occurrence rate and the occupancy rate of the current n state; the access type of the representative user side of k ═ WiFi is only WiFi connection, the access type of the representative user side of k ═ LiFi is only LiFi connection, the access type of the representative user side of k ═ LiFi is that the user side is switched from LiFi to WiFi to ensure data transmission when a visible light channel is blocked, and the LiFi connection is switched back to LiFi when the LiFi connection is recovered;
the data transmission efficiency of the user side using the LiFi is as follows:
Figure FDA0002856312630000042
the access type of the user terminal represented by k ═ WiFi is only WiFi connected, the access type of the user terminal represented by k ═ LiFi is only LiFi connected, the access type of the user terminal represented by k ═ LiFi/WiFi is that the user terminal is switched from LiFi to WiFi when a visible light channel is blocked to ensure data transmission, and the user terminal is switched back to LiFi when the LiFi connection is restored;
rLiFiis the actual received current state LiFi transmission rate, r of the user terminalWiFiFor a WiFi constant transmission rate, the ue equivalent rate r is:
Figure FDA0002856312630000051
2) and selecting the network access type with the maximum equivalent rate from the equivalent rates of the user side as a training sample data set label.
9. A handover control apparatus, comprising a processor configured to implement the network access type decision method of any one of claims 1-5 when executing a computer program stored in a memory.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out a network access type decision method according to any one of claims 1 to 5.
CN201811605468.8A 2018-12-26 2018-12-26 Network access type decision method, device, switching control device and storage medium Active CN109511144B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811605468.8A CN109511144B (en) 2018-12-26 2018-12-26 Network access type decision method, device, switching control device and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811605468.8A CN109511144B (en) 2018-12-26 2018-12-26 Network access type decision method, device, switching control device and storage medium

Publications (2)

Publication Number Publication Date
CN109511144A CN109511144A (en) 2019-03-22
CN109511144B true CN109511144B (en) 2021-03-02

Family

ID=65755383

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811605468.8A Active CN109511144B (en) 2018-12-26 2018-12-26 Network access type decision method, device, switching control device and storage medium

Country Status (1)

Country Link
CN (1) CN109511144B (en)

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110336608A (en) * 2019-06-28 2019-10-15 清华大学 Photoelectricity mixing monochromatic network broadcast method and system
CN110493837B (en) * 2019-07-04 2021-08-06 西安理工大学 Method for realizing efficient switching in VLC/RF heterogeneous network
CN110572208B (en) * 2019-09-16 2021-07-16 Oppo广东移动通信有限公司 Network switching method and related equipment
CN112994797B (en) * 2019-12-13 2022-09-09 Oppo广东移动通信有限公司 Communication control method for electronic device, and storage medium
CN112202686B (en) * 2020-09-07 2022-09-13 鹏城实验室 Adaptive access identification method for differential flow control and terminal equipment
CN112153713B (en) * 2020-10-23 2021-08-20 珠海格力电器股份有限公司 Obstacle determination method and apparatus, storage medium, and electronic apparatus
CN112312501B (en) * 2020-11-06 2022-08-26 中国联合网络通信集团有限公司 Method for determining access network equipment and terminal
CN115225205A (en) * 2022-07-07 2022-10-21 中国科学院空间应用工程与技术中心 VLC-RF hybrid communication method, system, medium, and device

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103796292A (en) * 2012-10-26 2014-05-14 国际商业机器公司 Base station power control in a mobile network
CN105959988A (en) * 2016-04-15 2016-09-21 北京航空航天大学 Cognitive radio ad hoc network node stability determining method based on support vector machine
CN107846714A (en) * 2017-10-31 2018-03-27 中国农业大学 The switching method and equipment of a kind of visible light communication and WiFi heterogeneous systems
CN207753719U (en) * 2017-11-22 2018-08-21 广州市浩洋电子股份有限公司 A kind of communication system based on WiFi Yu LiFi mixed types

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103796292A (en) * 2012-10-26 2014-05-14 国际商业机器公司 Base station power control in a mobile network
CN105959988A (en) * 2016-04-15 2016-09-21 北京航空航天大学 Cognitive radio ad hoc network node stability determining method based on support vector machine
CN107846714A (en) * 2017-10-31 2018-03-27 中国农业大学 The switching method and equipment of a kind of visible light communication and WiFi heterogeneous systems
CN207753719U (en) * 2017-11-22 2018-08-21 广州市浩洋电子股份有限公司 A kind of communication system based on WiFi Yu LiFi mixed types

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
基于可见光通信的异构网络切换机制研究与实现;吴柯;《中国优秀硕士学位论文全文数据库·信息科技辑》;20180331;全文 *

Also Published As

Publication number Publication date
CN109511144A (en) 2019-03-22

Similar Documents

Publication Publication Date Title
CN109511144B (en) Network access type decision method, device, switching control device and storage medium
Abuella et al. Hybrid RF/VLC systems: A comprehensive survey on network topologies, performance analyses, applications, and future directions
KR102296164B1 (en) Apparatus and method for optimizing antenna parameter in wireless communication system
CN101536351A (en) Sub-band dependent uplink load management
US11395160B2 (en) Energy consumption optimization method and system for radio access spectrum-flexible optical network
KR20120112678A (en) Virtual antenna array for wireless devices
Saud et al. Implementation of a hybrid optical-RF wireless network with fast network handover
CN109952806A (en) The determination method, apparatus and storage medium of SR configuration
Yücel et al. Optical communication infrastructure in new generation mobile networks
CN113840298B (en) Networking architecture of base station, communication control method and equipment
CN102045808B (en) Method for guiding terminal to reside and access network equipment
Nguyen et al. A cross-layer analysis of TCP/link adaptation technologies over free-space optical links with Markov error model
Ji et al. SVM-based network access type decision in hybrid LiFi and WiFi networks
Murugaveni et al. Optimal frequency reuse scheme based on cuckoo search algorithm in Li‐Fi fifth‐generation bidirectional communication
Kapetanovic et al. Glaze: Overlaying occupied spectrum with downlink iot transmissions
US20190115978A1 (en) Access method, apparatus, device, and system for visible light communication
Ngene et al. Perfect and imperfect successive interference cancellation for channel decoding in downlink visible light non-orthogonal multiple access network
Reus-Muns et al. Senseoran: O-RAN based radar detection in the cbrs band
Qian et al. Optimization design of RIS-assisted high-capacity visible light communications based on HDMA
Agarwal et al. Intelligence and Internet of Things with 5G Technology: Application and Development
Mai et al. Performance analysis of TCP over visible light communication networks with ARQ‐SR protocol
CN111095974B (en) Apparatus and method for analyzing service availability in wireless communication system
CN112114526A (en) Intelligent household control system
CN112153094A (en) Data transmission control method and device between electronic devices
CN109889417B (en) Communication component switch control system and method

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