CN116980941B - Terminal parameter configuration method, device and equipment for low-orbit satellite Internet of things - Google Patents

Terminal parameter configuration method, device and equipment for low-orbit satellite Internet of things Download PDF

Info

Publication number
CN116980941B
CN116980941B CN202311230556.5A CN202311230556A CN116980941B CN 116980941 B CN116980941 B CN 116980941B CN 202311230556 A CN202311230556 A CN 202311230556A CN 116980941 B CN116980941 B CN 116980941B
Authority
CN
China
Prior art keywords
terminal
predicted value
satellite
state information
channel state
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
CN202311230556.5A
Other languages
Chinese (zh)
Other versions
CN116980941A (en
Inventor
洪涛
周文东
钱铭
张更新
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.)
Nanjing Royal Communication Information Technology Co ltd
Nanjing University of Posts and Telecommunications
Original Assignee
Nanjing Royal Communication Information Technology Co ltd
Nanjing University of Posts and Telecommunications
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 Nanjing Royal Communication Information Technology Co ltd, Nanjing University of Posts and Telecommunications filed Critical Nanjing Royal Communication Information Technology Co ltd
Priority to CN202311230556.5A priority Critical patent/CN116980941B/en
Publication of CN116980941A publication Critical patent/CN116980941A/en
Application granted granted Critical
Publication of CN116980941B publication Critical patent/CN116980941B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • H04W28/00—Network traffic management; Network resource management
    • H04W28/02—Traffic management, e.g. flow control or congestion control
    • H04W28/0215—Traffic management, e.g. flow control or congestion control based on user or device properties, e.g. MTC-capable devices
    • H04W28/0221—Traffic management, e.g. flow control or congestion control based on user or device properties, e.g. MTC-capable devices power availability or consumption
    • 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
    • H04W28/0925—Management thereof using policies
    • H04W28/0942—Management thereof using policies based on measured or predicted load of entities- or links
    • 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
    • H04W28/0925—Management thereof using policies
    • H04W28/095—Management thereof using policies based on usage history, e.g. usage history of devices
    • 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
    • H04W28/0958—Management thereof based on metrics or performance parameters
    • H04W28/0967—Quality of Service [QoS] parameters
    • H04W28/0983—Quality of Service [QoS] parameters for optimizing bandwidth or throughput
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W74/00—Wireless channel access, e.g. scheduled or random access
    • H04W74/08—Non-scheduled or contention based access, e.g. random access, ALOHA, CSMA [Carrier Sense Multiple Access]
    • H04W74/0833—Non-scheduled or contention based access, e.g. random access, ALOHA, CSMA [Carrier Sense Multiple Access] using a random access procedure
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W84/00—Network topologies
    • H04W84/02—Hierarchically pre-organised networks, e.g. paging networks, cellular networks, WLAN [Wireless Local Area Network] or WLL [Wireless Local Loop]
    • H04W84/04—Large scale networks; Deep hierarchical networks
    • H04W84/06—Airborne or Satellite Networks
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00—Reducing energy consumption in communication networks
    • Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks

Abstract

The invention discloses a method, a device and equipment for configuring terminal parameters of a low-orbit satellite Internet of things, wherein the method comprises the following steps: acquiring a predicted value of a satellite end access load in a preset time period in the low-orbit satellite Internet of things and a predicted value of terminal channel state information; based on the predicted value of the satellite end access load and the predicted value of the terminal channel state information, training a reinforcement learning model for the terminal parameters to obtain the terminal parameters when the throughput of the system is maximized; and configuring the terminal based on the terminal parameters. The method enables the random access of the satellite to the terminal to be in a controllable state, avoids network blocking, and improves network throughput and fairness thereof.

Description

Terminal parameter configuration method, device and equipment for low-orbit satellite Internet of things
Technical Field
The invention relates to the technical field of satellite communication, in particular to a method, a device and equipment for configuring terminal parameters of a low-orbit satellite internet of things.
Background
With the development of the age, the internet of things (Internet of Things, ioT) has penetrated into various fields, and the biggest characteristic of the internet of things (IoT) is that the internet of things can be realized by adopting a Low-Power Wide-Area Network (LPWAN) technology. The ground LoRa (Long Range Radio) is used as the ground internet of things of the LPWAN technology, has the characteristics of low power consumption, long distance, large connection and the like, and is widely applied. But over 80% of the land and over 95% of the ocean worldwide, none of the traditional mobile communication technologies can cover. The satellite Internet of things is effectively supplemented to the ground Internet of things due to the characteristics of wide coverage, no influence of weather and geographic conditions, easiness in providing network connection support for a large-range motion platform and the like. At present, the technology of the internet of things is increasingly mature, the combination of satellites and the internet of things is a necessary development trend, and for this reason, whether the existing LoRa technology of the ground internet of things can be applied to the scene of the low-orbit satellite internet of things is searched, how to combine the LoRa technology with the scene of the low-orbit satellite internet of things is researched, and the method has profound significance for the communication mechanism of the terminal and the satellites under the low-orbit satellite internet of things. To develop the Internet of things of the LoRa low-orbit satellite, the adaptability of the LoRa system low-orbit satellite Internet of things must be studied.
In the LoRa system satellite Internet of things, on one hand, because communication resources are limited, massive connection of terminals inevitably causes serious network congestion, and the performance of a communication system is greatly reduced; on the other hand, due to the high dynamic characteristic of the low-orbit satellite, the network state of the satellite can change drastically along with the time and space difference; on the other hand, most terminals of the Internet of things have weak capability and cannot perform a large amount of calculation.
Disclosure of Invention
The invention provides a method, a device and equipment for configuring terminal parameters of a low-orbit satellite Internet of things, which are used for solving the defect that the LoRa low-orbit satellite Internet of things is easy to jam in the prior art and realizing the maximization of throughput of the low-orbit satellite Internet of things.
In a first aspect, the present invention provides a method for configuring terminal parameters of a low-orbit satellite internet of things, including:
acquiring a predicted value of a satellite end access load in a preset time period in the low-orbit satellite Internet of things and a predicted value of terminal channel state information;
based on the predicted value of the satellite end access load and the predicted value of the terminal channel state information, training a reinforcement learning model for the terminal parameters to obtain the terminal parameters when the throughput of the system is maximized;
and configuring the terminal based on the terminal parameters.
Optionally, the terminal parameters include one or more of the following:
terminal transmitting power; a spreading factor; a sub-channel.
Optionally, obtaining the predicted value of the satellite end access load further includes:
acquiring a plurality of historical satellite access loads;
and inputting the plurality of historical satellite-end access loads into a first LSTM neural network for prediction to obtain a predicted value of the satellite-end access load.
Optionally, obtaining the predicted value of the terminal channel state information further includes:
acquiring channel state information of a plurality of historical terminals;
and inputting the plurality of historical terminal channel state information into a second LSTM neural network for prediction to obtain a predicted value of the terminal channel state information.
Optionally, based on the predicted value of the satellite end access load and the predicted value of the terminal channel state information, performing reinforcement learning model training on the terminal parameter to obtain the terminal parameter when the throughput of the system is maximized, and further including:
taking the terminal parameters, the predicted value of the satellite end access load and the predicted value of the terminal channel state information as the input of a reinforcement learning model;
taking the system throughput as the output of the reinforcement learning model;
establishing a target optimization problem:
；
；
；
subchannel->Subchannel set->；
Where G is the system throughput;the transmitting power of the terminal i is represented, and W represents the power unit in watts; />Represents a set of spreading factors, j represents a set of spreading factors; v represents a subchannel set, V represents the V-th subchannel,>；is indicated at->The v-th sub-channel selected by the lower terminal i;
and solving a target optimization problem to obtain terminal parameters when the throughput of the system is maximized, wherein the terminal parameters comprise transmitting power, SF and sub-channels.
Optionally, the method of acquiring the historical satellite access load further comprises:
acquiring a preamble sequence of a LoRa frame structure;
and based on the preamble sequence, carrying out asynchronous collision detection on satellite receiving end data by adopting a maximum likelihood method to obtain the collision probability of asynchronous access, and obtaining the historical satellite access load according to the collision probability.
Optionally, the method for acquiring the historical terminal channel state information further comprises:
acquiring a preamble sequence in a LoRa frame structure;
and based on the preamble sequence, estimating the channel state information of the LoRa terminal by adopting a compressed sensing algorithm to obtain the channel state information of the historical terminal.
In a second aspect, the present invention further provides a low-orbit satellite internet of things terminal parameter configuration device, including:
the acquisition module is used for acquiring a predicted value of a satellite end access load and a predicted value of terminal channel state information in a preset time period in the low-orbit satellite Internet of things;
the training module is used for carrying out reinforcement learning model training on the terminal parameters based on the predicted value of the satellite end access load and the predicted value of the terminal channel state information to obtain the terminal parameters when the throughput of the system is maximized;
and the configuration module is used for configuring the terminal based on the terminal parameters.
In a third aspect, the present invention further provides an electronic device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the processor implements the method for configuring terminal parameters of the low-orbit satellite internet of things according to the first aspect when executing the program.
In a fourth aspect, the present invention further provides a computer readable storage medium, on which a computer program is stored, the computer program implementing the method for configuring terminal parameters of the low-orbit satellite internet of things according to the first aspect when being executed by a processor.
Compared with the prior art, the invention has the beneficial effects that:
(1) According to the predicted access load and channel state information, the method and the device obtain the transmission parameters of terminal transmission power, SF selection and subchannel selection through reinforcement learning model training, perform joint configuration on the terminal, optimize random access process control and improve system throughput;
(2) The terminal of the invention adopts asynchronous unauthorized random access to the LoRa low orbit satellite Internet of things, avoids complex synchronization and handshake processes, can send signals on a satellite channel in a completely asynchronous and random mode, and the calculation burden is transferred to a receiving end.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of a low orbit satellite internet of things terminal parameter configuration method according to an embodiment of the invention;
fig. 2 is a schematic diagram of a configuration method of terminal parameters of a low-orbit satellite internet of things according to an embodiment of the invention;
FIG. 3 is a graph of simulated data Bao Pu peak detection under a double collision according to an embodiment of the invention;
FIG. 4 is a graph of simulated data Bao Pu peak detection at a triple collision according to an embodiment of the present invention;
FIG. 5 is a graph of simulated data Bao Pu peak detection at a quadruple collision according to an embodiment of the invention;
FIG. 6 is a graph of a comparison of LSTM neural network load prediction versus actual value simulation in accordance with an embodiment of the present invention;
FIG. 7 is a simulated performance analysis of a channel estimation algorithm at MSE according to an embodiment of the present invention;
FIG. 8 is a simulated performance analysis of a channel estimation algorithm over BER according to an embodiment of the present invention;
FIG. 9 is a graph of a simulation comparison of predicted values and actual values of channel state information for an LSTM neural network in accordance with an embodiment of the present invention;
fig. 10 is a simulation diagram of a system scene for initial setting of transmission parameters of a LoRa internet of things terminal under a LoRa wan according to an embodiment of the present application;
fig. 11 is a system scenario simulation diagram after a method for jointly optimizing terminal parameters of a LoRa internet of things terminal according to an embodiment of the present application;
fig. 12 is a comparison diagram of a terminal parameter joint optimization method and a lorewan in terms of fairness according to an embodiment of the present application;
fig. 13 is a diagram comparing a terminal parameter joint optimization method with a lorewan in terms of throughput according to an embodiment of the present application;
fig. 14 is a schematic structural diagram of a terminal parameter configuration device of the low-orbit satellite internet of things provided by the invention;
fig. 15 is a schematic structural diagram of an electronic device provided by the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The biggest characteristic of LoRa is that the distance of the LoRa is farther than the distance of the LoRa transmitted by other wireless modes under the same power consumption condition, and the unification of low power consumption and long distance is realized. The physical layer of LoRa adopts chirp Spread Spectrum (Chirp Spread Spectrum, CSS) modulation technology to realize long-distance transmission, each Spread Spectrum (SF) has different performances, the transmission distance of small SF is short but the transmission rate is high, the transmission distance of large SF is long but the transmission rate is low, and different SF are mutually orthogonal, so that simultaneous transmission and mutual noninterference can be realized. The medium access control (Media Access Control, MAC) layer of the LoRa adopts the LoRa wide area network (Long Range Wide Area Network, loRa wan) protocol similar to ALOHA, and the terminal can initiate an uplink message at any time under the condition of meeting the Duty Cycle mechanism without synchronization and carrier sensing.
The following describes a method, a device, equipment and a medium for configuring terminal parameters of the internet of things of a low orbit satellite with reference to fig. 1 to 15.
Example 1
As shown in fig. 1, the invention provides a method for configuring terminal parameters of a low-orbit satellite internet of things, which comprises the following steps:
and 100, acquiring a predicted value of a satellite end access load and a predicted value of terminal channel state information in a preset time period in the low-orbit satellite Internet of things.
And step 101, training a reinforcement learning model for the terminal parameters based on the predicted value of the satellite end access load and the predicted value of the terminal channel state information to obtain the terminal parameters when the system throughput is maximized.
And 102, configuring the terminal based on the terminal parameters.
In particular, in the low-orbit satellite internet of things, because of limited communication resources, massive access of the terminal is easy to cause network congestion, and the random access process of the internet of things is controlled according to the network state (access load and terminal channel state), so that the network congestion can be effectively relieved. However, the network state of the low-orbit satellite can change drastically with time and space, so that it is necessary to predict the access load and channel state information of the internet of things of the low-orbit satellite, so as to obtain the terminal parameter when the network throughput is maximum according to the predicted network state, and let the terminal configure itself according to the parameter, and after configuration, perform random access of the internet of things according to the configuration parameter, thereby improving the network throughput of the internet of things and the fairness of throughput.
In the low orbit satellite Internet of things scene, most of the terminals of the Internet of things have weaker capability, so that an asynchronous unlicensed random access protocol scheme is adopted, the complex synchronization and handshake processes are avoided, the terminals can send signals on satellite channels in a completely asynchronous and random mode, and the calculation burden is transferred to a receiving end.
The terminal parameter may be terminal transmitting power, spreading factor, sub-channel, or any combination of these parameters.
The predicted value of the satellite-side access load in the preset time period can be obtained by inputting a certain number of historical satellite-side access loads into a prediction model, such as a differential equation model, a time sequence model, a long-short-term memory (Long Short Term Memory, LSTM) neural network model and the like, so as to obtain the predicted value of the satellite-side access load in the preset time period. The preset time period may be a period of time after obtaining the predicted value after obtaining the historical satellite access load, and the time period may be set according to the used prediction model, for example, the LSTM neural network model may predict the satellite access load value of one month in the future according to the historical satellite access load data of the previous year.
Similarly, the predicted value of the terminal channel state information in the preset time period can be obtained by inputting a certain amount of historical terminal channel state information into a prediction model.
After the predicted value of the satellite end access load and the predicted value of the terminal channel state information are obtained, the predicted value and the terminal parameters are used as the input of the reinforcement learning model, and the terminal parameters when the reinforcement learning model output system maximizes the throughput are the target terminal parameters.
The satellite transmits the target terminal parameters to the terminal, and the terminal configures itself according to the target terminal parameters.
According to the technical scheme, the predicted value of the satellite-side access load and the predicted value of the terminal channel state information in the preset time period are input into the reinforcement learning model, so that the terminal parameter when the throughput of the system is maximized is obtained, and the terminal configures itself by utilizing the parameter, so that the random access of the satellite to the terminal is in a controllable state, network blocking is avoided, and the network throughput and fairness thereof are improved.
Example 2
As shown in fig. 2, when performing satellite access load prediction, asynchronous load estimation is required.
Under the asynchronous access scene, the satellite access load estimation and prediction method comprises the following steps:
spreading factor for binary information by LoRa terminalDividing eachSFThe binary bits are divided into a block of information, if the LoRa signalThe bandwidth isBThe duration of each symbolFor symbol->Signal initial frequency +.>. LoRa passband bandwidth value is. The working band of LoRa is +.>To->Will beBEqually divide into->Part by weight, orderThe transmission symbol can be obtained by the following equationsCorresponding initial frequency->：
；
In one period of the LoRa signal, the frequency is changed toLinearly rise to +.>Then->Jump to->Finally by->Linearly rise to +.>. Frequency hopping time->The method comprises the following steps:
；
LoRa signalFrequency function over time>The expression of (2) is:
；
wherein,μfor the LoRa tone frequency, i.e. the rate of change of frequency,is constant.
From the following componentsCan get +.>Is represented by the expression:
；
when using the Nyquist frequencyAt sampling, the discrete-time signal of the symbol is composed of +.>Sample composition, loRa symbolsExpressed as a discrete time equivalent model of:
；
wherein,is->Is>。
The LoRa Internet of things terminal transmits data packets on a satellite channel in an unauthorized mode, and the satellite channel model is considered to be a rice channel model. At the satellite receiving end, the received signal can be expressed as:
；
wherein the method comprises the steps ofhAs the channel state information, a channel state information,is noise with a noise power of +>。
For LoRa data packets, the preamble sequence includes severalsThe method for detecting the preamble sequence of the LoRa data packet by using the maximum likelihood detection method when the receiving end detects the LoRa preamble belongs to priori knowledge, and comprises the following steps:
step 1: for single-terminal, the maximum likelihood detection method of the LoRa symbol can use discrete fourier transform at nyquist frequencyAnd the method is effectively realized.
Step 1.1: sampling signalsFirst multiply by +.>Is->：
；
Wherein PWR is the receiving power of the receiving end,for the phase +.>Is->And->Multiplication result->Representing transmission symbols for a standard down-chirp signal sequencesConjugation of the expression of the LoRa signal at =0, which is locally generated at the signal receiver, frequency modulation slope and +.>Frequency modulation slope +.>Are of opposite numbers, sequence length and +.>Equal to the initial frequency ofThe method comprises the following steps:
；
step 1.2: for a pair ofAnd (3) performing DFT to obtain:
；
wherein,is noise item->DFT results of->。
Step 1.3: the receiver performs incoherent ML detection by selecting the DFT bin with the largest amplitude. The result after DFT is subjected to spectral peak search to extract the symbol valueThe method comprises the following steps:
；
step 2: at the satellite receiving end, asynchronous multi-data packet collision occurs, namely, data packets sent by a plurality of LoRa (Internet of things) terminal terminals collide at the receiving end in the same SF and the same sub-channel. Therefore, to realize the detection of the LoRa multiple collision data packet, the detection can be realized based on a multi-terminal combined maximum likelihood detection method.
Step 2.1: in the first placekIn each detection window, a terminal is arrangediThe transmitted symbol isTaking terminal 1 as an example, assuming that the data packet sent by terminal 1 arrives first at the low-orbit satellite, then the low-orbit satellite receiver and terminal 1 are in time andand synchronizing in frequency. Based on the data packet of the desired terminal 1, < > and->Is the normalized delay difference between collision symbols. In the first placekIn the detection window, terminal->Expression of first collision symbol and second collision symbol with terminal 1:
；
；
wherein,is a sequence of unit steps.
Step 2.2: is provided withFor terminalsiRelative carrier frequency offset with terminal 1, +.>For terminalsiThe carrier frequency offset is opposite between the receiving end and the transmitting end; />The carrier frequency offset is relative between a receiving end and a transmitting end of the terminal 1; will->And->Defined as terminal 1 and terminaliIn the first placekThe initial phase of the symbol under the detection window. Thus, at sampling frequency +.>Sampling, the firstkThe discrete time baseband equivalent model expression of the received signals of the detection windows is as follows:
；
wherein,the received power for terminal 1 to reach the low-orbit satellite; />) The received power for terminal i to reach the low-orbit satellite; />For the opposite terminaliThe actual carrier frequency offset affects.
Step 2.3: with the above baseband signalAs input to a maximum likelihood detector and at the Nyquist frequency +.>Sampling is performed. Terminal 1 and terminaliThe collision part of the data packet is in the sampling sampleNA kind of electronic deviceMDetected in successive windows. Will->The de-chirped sequence sampled at each detection window with the standard down-chirp signal>Multiplication to obtain->：/>；
Step 2.4: de-chirped frequencySymbol set of->The method comprises the following steps:
；
step 2.5: the probability that a collision can be detected is obtained as P:
；
wherein,is shown at the multi-terminal at the firstkThe de-chirping of the windows is expressed as:
；
wherein,，/>，/>representing an upward rounding function,/->Representing a downward rounding function.
Step 3: after collision detection of the received data packet, the formula of load access in the satellite receiving window time can be obtained as follows:
；
；
wherein,for the number of satellite subchannels divided, +.>For sub-channelsvThe number of data packets without collision in the data packet,for the number of collision packets which are asynchronously superimposed, +.>For the number of collision weights thereof,Ncindicating the total number of packets in the sub-channel.
Step 4: for load prediction, it willThe number obtained as load is +.>Is a data set of (2)FFirst, for a data setFNormalization is carried out:
；
wherein:representing normalized load value, +.>For the original load value, +.>，Expressed as:
；
expressed as:
；
will normalizeAnd (5) sending the model parameters into a neural network for training, and storing the optimal model parameters. And predicting the access load through the stored model parameters.
Setting a backtracking windowAnd predicting the access load value of the satellite-side receiving window in a future preset time period by using 40 historical data values, and the like. Meanwhile, the error of the predicted value and the true value of the point is calculated by a satellite end receiving window in a preset time period in the future, the average absolute percentage error MAPE of 100 time points is counted, and if the MAPE is more than or equal to 15%, the predicted error of the model is larger and retraining is needed.
As shown in fig. 3, 4 and 5, based on the simulation of the present invention, the present invention provides a data Bao Pu peak detection diagram under double, triple and quadruple collision.
The relevant simulation parameter settings are shown in table 1 and table 2:
table 1 channel and service simulation parameter table
TABLE 2 LSTM neural network prediction model parameter Table
As shown in FIG. 6, based on the simulation of the present invention, a comparison graph of the predicted value and the actual value of the LSTM neural network load is provided.
Example 3
The terminal channel estimation and prediction method comprises the following steps:
at the low-orbit satellite side, the received signal is expressed as:
according to the compressed sensing principle, the multipath channel of LoRa is a sparse channel and the channel state matrixHThrough orthogonal exchange baseDConversion to sparse matrixh(i.e., channel state information), sparse matrixhSparsity of degree ofLThe expression can therefore be rewritten as:
；
wherein,Xin order to transmit the signal,Afor the measurement matrix.
In the LoRa leader sequencesNumber of LoRa symbols=0 isThe transmitted signal preamble matrix is expressed as:the received signal preamble matrix is expressed as: />The matrix between the transmitted and received signals is then expressed as:
；
wherein,is a discrete fourier matrix.
Step 1: the channel estimation method based on the compressed sensing algorithm comprises the following steps:
the subcarrier of the LoRa signal isMeasurement matrixAResidual threshold->Additional threshold->Initial step size set，VFor a set of sub-channels, a measurement matrix is storedAAnd residual errorrThe set of inner product values->。
Step 1.1: initialization of，/>，/>Index set->Candidate set->Residual->Size of final support set +.>Step is the algorithm step size, final support set +.>Iterative index->；
Step 1.2: signal channelThrough the first stepAfter secondary reconstitution, if->Directly ending to obtain channel parametershIf not, continuing to execute the following steps;
step 1.3: the value of the product of the measurement matrix and the residual is calculated,；
step 1.4: at the position ofSPBefore selecting in (a)Maximum values are associated with the measurement matrixASequence number indexing set->；
Step 1.5: merging the index set and the final support set obtained in the step 1.4 into a candidate support set to obtain；
Step 1.6: calculatingAnd selecting the value of +.>Index of the largest element, get final support set +.>；
Step 1.7: estimating channel parameters to obtainCalculating a current residual:；
step 1.8: comparing current residual errorsAnd residual threshold->If->，/>Stopping iteration and entering step 1.9; if->And->Updating the final support set of parametersResidual->Iteration number->If->Returning to the step 1.2 to continue iteration, otherwise, entering the step 1.9 to stop iteration;
step 1.9: reconstructing to obtain channel parametershEstimate of (2)；
Step 2: mean square error for selecting good or bad performance of channel estimation algorithmMSEBit error rateBERThe mean square error and bit error rate expressions are measured as follows:
；
；
step 3: for channel state information prediction, it willhThe obtained quantity as channel state information isIs a data set of (2)FFirst, for a data setFNormalization is carried out:
；
wherein:representing normalized channel state information values, +.>As the value of the original channel state information,，/>expressed as:
；
expressed as:
；
will normalizeAnd (5) sending the model parameters into a neural network for training, and storing the optimal model parameters. Predicting channel state information through saved model parametersAnd (5) extinguishing the value.
The relevant simulation parameter settings are shown in table 3:
table 3 channel estimation Performance simulation parameter Table
Based on the simulation of the present invention, the performance analysis of the channel estimation algorithm used in the present invention at MSE is shown in fig. 7.
Based on the simulation of the present invention, the performance analysis of the channel estimation algorithm used in the present invention in BER is shown in fig. 8.
Based on the simulation of the invention, a comparison graph of the predicted value and the actual value of the LSTM neural network channel state information is shown in fig. 9.
Example 4
Step 1: in the Internet of things of low-orbit satellites in LoRa system, settingIs the firstiThe transmit power of the individual user terminals, wherein>The step size can be adjusted to 0.1W. Considering large-scale and small-scale fading, 0.5W is the lowest power for ensuring that the terminal of the Internet of things can be connected with a low-orbit satellite, and the initial transmitting power of the terminal of the Internet of things is set to be 1W; />For the spread spectrum factor set, < >>Setting initial setting of Internet of things terminal according to ring division areaSF；VFor subchannel set, ++>Is at->Lower firstiThe first terminal selectionvSubchannel, & gt>And setting the terminal of the Internet of things to randomly select an initial sub-channel. Based on the initial setting, load estimation and prediction and channel estimation and prediction are performed, and according to the load and channel state information prediction values, a parameter configuration method of joint optimization of terminal transmission parameter transmission power, SF selection and sub-channel selection is adopted, and a low orbit satellite performs information interaction with a terminal through an MAC command, so that the terminal configures own transmission parameters: transmitting power, SF and sub-channels, thereby achieving the purpose of improving the throughput of the whole system.
Step 2: terminal transmitting power, SF selection and sub-channel selection transmitting parameter joint configuration method based on reinforcement learning to transmit powerSpreading factor->Subchannel->As input, with throughputGAs an output, a throughput-targeted function is established such that the target is maximized. Set->Is the firstiThe signal-to-interference-and-noise ratio of the received signal at the satellite that the individual terminal arrives at, and (2)>The received signal-to-interference-noise ratio threshold is demodulated for a serial interference cancellation technique (Successive Interference Cancellation, SIC) technique. The multiple input objective optimization problem can be expressed as:
；
；
；
sub-channel set->；
The method for jointly configuring the emission parameters based on reinforcement learning comprises the following steps:
input: initializing model parametersIteration number->Transmit power->Demodulation of the received signal-to-interference-and-noise threshold +.>. Spreading factor->Subchannel->Scheduling flagflagAdjustment rate->Training round +.>Training length->Prize value->LSTM predicted channel state informationhTotal number of sub-channels>Subchannel load->；
And (3) outputting: the throughput of the system is maximized;
step 2.1: initialization ofPower->Spreading factor->Sub-channelsTotal->Prize value vector->Zero.
Step 2.2:according to the transmit power->Spreading factor->Subchannel->Total->Calculate the +.>Terminal->；
Step 2.3: calculation ofWherein->The method is a Q-Learning reinforcement Learning algorithm, and parameters input to the reinforcement Learning algorithm are arranged in brackets; if the result of calculation，/>Otherwise->，/>Obtainingindex；
Step 2.4: according toindexSelecting a corresponding sub-channel，/>，；
Step 2.5: if it isBy->、/>、/>Calculating the signal-to-interference-plus-noise value under the current sub-channel>；
Step 2.6: if the signal-to-interference-and-noise ratio calculation result under the current sub-channelAnd->Setting the current sub-channel prize value +.>Otherwise->；
Step 2.7: if it isThen choose random +.>，/>，/>，/>，/>And->Training for monitoring loss->；
Step 2.8: no order of noSo that->Starting iteration from the step 2.2 again;
step 2.9: when (when)Stopping iteration and outputting a target;
the relevant simulation parameter settings are shown in table 4:
table 4 terminal emission parameter table
Based on the simulation of the invention, a system scene diagram of initial setting of the emission parameters of the LoRa Internet of things terminal under the LoRaWAN is shown in FIG. 10.
Based on the simulation of the invention, a system scene diagram of the LoRa Internet of things terminal after the terminal parameter joint optimization method is used by the invention is shown in FIG. 11.
Based on the simulation of the invention, a comparison diagram of the terminal parameter joint optimization method used by the invention and the LoRaWAN in fairness aspect is shown in fig. 12. The results show that the method has more advantages in the aspect of fairness.
Based on the simulation of the invention, a comparison diagram of the terminal parameter joint optimization method used by the invention and the LoRaWAN in terms of throughput is shown in FIG. 13. The results show that the method is more advantageous in terms of throughput.
The low-orbit satellite internet of things terminal parameter configuration device provided by the invention is described below, and the low-orbit satellite internet of things terminal parameter configuration device described below and the low-orbit satellite internet of things terminal parameter configuration method described above can be correspondingly referred to each other.
As shown in fig. 14, the present invention provides a low-orbit satellite internet of things terminal parameter configuration device, which includes:
the acquiring module 1400 is configured to acquire a predicted value of a satellite end access load and a predicted value of terminal channel state information in a preset time period in the low-orbit satellite internet of things;
the training module 1410 is configured to perform reinforcement learning model training on the terminal parameters based on the predicted value of the satellite access load and the predicted value of the terminal channel state information, so as to obtain the terminal parameters when the throughput of the system is maximized;
the configuration module 1420 configures the terminal based on the terminal parameters.
Fig. 15 illustrates a physical structure diagram of an electronic device, as shown in fig. 15, which may include: a processor 1510, a communication interface (Communications Interface) 1520, a memory 1530, and a communication bus 1540, wherein the processor 1510, the communication interface 1520, and the memory 1530 communicate with each other via the communication bus 1540. Processor 1510 may invoke logic instructions in memory 1530 to perform a low-orbit satellite internet of things terminal parameter configuration method comprising:
acquiring a predicted value of a satellite end access load in a preset time period in the low-orbit satellite Internet of things and a predicted value of terminal channel state information;
based on the predicted value of the satellite end access load and the predicted value of the terminal channel state information, training a reinforcement learning model for the terminal parameters to obtain the terminal parameters when the throughput of the system is maximized;
and configuring the terminal based on the terminal parameters.
Further, the logic instructions in the memory 1530 described above may be implemented in the form of software functional units and may be stored on a computer readable storage medium when sold or used as a stand alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In still another aspect, the present invention further provides a computer readable storage medium having stored thereon a computer program, which when executed by a processor, is implemented to perform the method for configuring terminal parameters of a low-orbit satellite internet of things provided by the above methods, the method comprising: acquiring a predicted value of a satellite end access load in a preset time period in the low-orbit satellite Internet of things and a predicted value of terminal channel state information;
based on the predicted value of the satellite end access load and the predicted value of the terminal channel state information, training a reinforcement learning model for the terminal parameters to obtain the terminal parameters when the throughput of the system is maximized;
and configuring the terminal based on the terminal parameters.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims (7)

1. The method for configuring the terminal parameters of the low-orbit satellite Internet of things is characterized by comprising the following steps of:
acquiring a predicted value of a satellite end access load in a preset time period in the low-orbit satellite Internet of things and a predicted value of terminal channel state information;
based on the predicted value of the satellite end access load and the predicted value of the terminal channel state information, training a reinforcement learning model for the terminal parameters to obtain the terminal parameters when the throughput of the system is maximized;
configuring a terminal based on the terminal parameters;
the method for obtaining the predicted value of the satellite-side access load further comprises the following steps: acquiring a plurality of historical satellite access loads; inputting the plurality of historical satellite-end access loads into a first LSTM neural network for prediction to obtain a predicted value of the satellite-end access load;
acquiring the predicted value of the terminal channel state information, and further comprises: acquiring channel state information of a plurality of historical terminals; inputting the plurality of historical terminal channel state information into a second LSTM neural network for prediction to obtain a predicted value of the terminal channel state information;
based on the predicted value of the satellite end access load and the predicted value of the terminal channel state information, training a reinforcement learning model for the terminal parameters to obtain the terminal parameters when the throughput of the system is maximized, and further comprising:
taking the terminal parameters, the predicted value of the satellite end access load and the predicted value of the terminal channel state information as the input of a reinforcement learning model;
taking the system throughput as the output of the reinforcement learning model;
establishing a target optimization problem:
s.t.PWR i ∈[0.5W,1W]；
subchannel V e subchannel set V e {1,2,3,., 96};
where G is the system throughput; PWR (PWR) i The transmitting power of the terminal i is represented, and W represents the power unit in watts; SF (sulfur hexafluoride) j Represents a set of spreading factors, j represents a set of spreading factors; v represents a sub-channel set, V represents a V-th sub-channel, V e V;indicated at SF j The v-th sub-channel selected by the lower terminal i;
and solving a target optimization problem to obtain terminal parameters when the throughput of the system is maximized, wherein the terminal parameters comprise transmitting power, SF and sub-channels.
2. The method for configuring terminal parameters of the low-orbit satellite internet of things according to claim 1, wherein the terminal parameters comprise one or more of the following:
terminal transmitting power; a spreading factor; a sub-channel.
3. The method for configuring terminal parameters of the internet of things of low orbit satellite according to claim 1, wherein the method for acquiring the historical satellite end access load further comprises:
acquiring a preamble sequence of a LoRa frame structure;
and based on the preamble sequence, carrying out asynchronous collision detection on satellite receiving end data by adopting a maximum likelihood method to obtain the collision probability of asynchronous access, and obtaining the historical satellite access load according to the collision probability.
4. The method for configuring terminal parameters of the internet of things of low orbit satellite according to claim 1, wherein the method for acquiring the historical terminal channel state information further comprises:
acquiring a preamble sequence in a LoRa frame structure;
and based on the preamble sequence, estimating the channel state information of the LoRa terminal by adopting a compressed sensing algorithm to obtain the channel state information of the historical terminal.
5. The utility model provides a low orbit satellite thing networking terminal parameter configuration device which characterized in that includes:
the acquisition module is used for acquiring a predicted value of a satellite end access load and a predicted value of terminal channel state information in a preset time period in the low-orbit satellite Internet of things;
the training module is used for carrying out reinforcement learning model training on the terminal parameters based on the predicted value of the satellite end access load and the predicted value of the terminal channel state information to obtain the terminal parameters when the throughput of the system is maximized;
the configuration module is used for configuring the terminal based on the terminal parameters;
the method for obtaining the predicted value of the satellite-side access load further comprises the following steps: acquiring a plurality of historical satellite access loads; inputting the plurality of historical satellite-end access loads into a first LSTM neural network for prediction to obtain a predicted value of the satellite-end access load;
acquiring the predicted value of the terminal channel state information, and further comprises: acquiring channel state information of a plurality of historical terminals; inputting the plurality of historical terminal channel state information into a second LSTM neural network for prediction to obtain a predicted value of the terminal channel state information;
based on the predicted value of the satellite end access load and the predicted value of the terminal channel state information, training a reinforcement learning model for the terminal parameters to obtain the terminal parameters when the throughput of the system is maximized, and further comprising:
taking the terminal parameters, the predicted value of the satellite end access load and the predicted value of the terminal channel state information as the input of a reinforcement learning model;
taking the system throughput as the output of the reinforcement learning model;
establishing a target optimization problem:
S.t.PWR i ∈[0.5W,1W]；
subchannel V e subchannel set V e {1,2,3,., 96};
where G is the system throughput; PWR (PWR) i The transmitting power of the terminal i is represented, and W represents the power unit in watts; SF (sulfur hexafluoride) j Represents a set of spreading factors, j represents a set of spreading factors; v represents a sub-channel set, V represents a V-th sub-channel, V e V;indicated at SF j The v-th sub-channel selected by the lower terminal i;
and solving a target optimization problem to obtain terminal parameters when the throughput of the system is maximized, wherein the terminal parameters comprise transmitting power, SF and sub-channels.
6. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method for configuring terminal parameters of the low-orbit satellite internet of things as claimed in any one of claims 1 to 4 when executing the program.
7. A computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the low orbit satellite internet of things terminal parameter configuration method according to any one of claims 1 to 4.
CN202311230556.5A 2023-09-22 2023-09-22 Terminal parameter configuration method, device and equipment for low-orbit satellite Internet of things Active CN116980941B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311230556.5A CN116980941B (en) 2023-09-22 2023-09-22 Terminal parameter configuration method, device and equipment for low-orbit satellite Internet of things

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311230556.5A CN116980941B (en) 2023-09-22 2023-09-22 Terminal parameter configuration method, device and equipment for low-orbit satellite Internet of things

Publications (2)

Publication Number Publication Date
CN116980941A CN116980941A (en) 2023-10-31
CN116980941B true CN116980941B (en) 2023-12-22

Family

ID=88473377

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311230556.5A Active CN116980941B (en) 2023-09-22 2023-09-22 Terminal parameter configuration method, device and equipment for low-orbit satellite Internet of things

Country Status (1)

Country Link
CN (1) CN116980941B (en)

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CA2395048A1 (en) * 2001-08-03 2003-02-03 M/A-Com Private Radio Systems, Inc. Method and processor for determining loading of a telecommunications system and applications of the system-loading determinaton
WO2017156089A1 (en) * 2016-03-08 2017-09-14 Qualcomm Incorporated Load-based techniques for selecting a wireless operating channel in an unlicensed spectrum
CN107432000A (en) * 2014-06-25 2017-12-01 英特尔公司 For strengthening the technology of Wireless Personal Network performance under disturbance regime
CN107431598A (en) * 2015-03-17 2017-12-01 高通股份有限公司 Load knows channel status reference signal transmission
CN114040447A (en) * 2021-10-19 2022-02-11 中国电子科技集团公司第五十四研究所 Intelligent flow load balancing method for high-speed satellite-ground link communication service
CN114157337A (en) * 2021-11-02 2022-03-08 西安电子科技大学 Low-orbit satellite inter-satellite switching prediction method based on time-varying graph
CN114867128A (en) * 2022-05-05 2022-08-05 南京邮电大学 Random access self-adaption method, device and storage medium for satellite Internet of things
CN116170066A (en) * 2023-04-21 2023-05-26 南京邮电大学 Load prediction method for low-orbit satellite Internet of things
CN116302515A (en) * 2023-03-02 2023-06-23 四川大学 Cloud service load prediction method and system based on double channels

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CA2395048A1 (en) * 2001-08-03 2003-02-03 M/A-Com Private Radio Systems, Inc. Method and processor for determining loading of a telecommunications system and applications of the system-loading determinaton
CN107432000A (en) * 2014-06-25 2017-12-01 英特尔公司 For strengthening the technology of Wireless Personal Network performance under disturbance regime
CN107431598A (en) * 2015-03-17 2017-12-01 高通股份有限公司 Load knows channel status reference signal transmission
WO2017156089A1 (en) * 2016-03-08 2017-09-14 Qualcomm Incorporated Load-based techniques for selecting a wireless operating channel in an unlicensed spectrum
CN114040447A (en) * 2021-10-19 2022-02-11 中国电子科技集团公司第五十四研究所 Intelligent flow load balancing method for high-speed satellite-ground link communication service
CN114157337A (en) * 2021-11-02 2022-03-08 西安电子科技大学 Low-orbit satellite inter-satellite switching prediction method based on time-varying graph
CN114867128A (en) * 2022-05-05 2022-08-05 南京邮电大学 Random access self-adaption method, device and storage medium for satellite Internet of things
CN116302515A (en) * 2023-03-02 2023-06-23 四川大学 Cloud service load prediction method and system based on double channels
CN116170066A (en) * 2023-04-21 2023-05-26 南京邮电大学 Load prediction method for low-orbit satellite Internet of things

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
Mario Neugebauer.《ScienceDirect》.2003,全文. *
QoS区分的自适应p-Persistent MAC算法对信道利用率的动态优化;白翔;《软件学报》;全文 *
基于波束成形的低轨卫星物联网接入技术;洪涛;《天地一体化信息网络》;全文 *

Also Published As

Publication number Publication date
CN116980941A (en) 2023-10-31

Similar Documents

Publication Publication Date Title
Atapattu et al. Energy detection for spectrum sensing in cognitive radio
US11096069B2 (en) Apparatus and method for hybrid multiple access wireless communication system
CN112533251B (en) Cell interference assessment method and device
Yadav et al. A comprehensive study of spectrum sensing techniques in cognitive radio
Kakalou et al. A survey on spectrum sensing algorithms for cognitive radio networks
Guimaraes Spectrum sensing: A tutorial
Jin et al. Compressive spectrum sensing for mimo-ofdm based cognitive radio networks
Li et al. System‐level performance simulation analysis of non‐orthogonal multiple access technology in 5G mobile communication network
CN113099423B (en) Deployment method of narrowband cellular Internet of things based on Poisson cluster process
CN116980941B (en) Terminal parameter configuration method, device and equipment for low-orbit satellite Internet of things
Garcia Marti et al. A mixture density channel model for deep learning-based wireless physical layer design
CN114337876B (en) AMP detection method based on NSGA2 algorithm training and system for implementing same
Verma et al. Analysis of combined data-decision fusion scheme for cognitive radio networks
Ma et al. User sensing based on MIMO cognitive radio sensor networks
Caetano et al. A recurrent neural network mac protocol towards to opportunistic communication in wireless networks
CN114430590A (en) Wireless transmission method for realizing uplink large-scale URLLC
CN110312280B (en) Method and device for calculating downlink throughput
CN106656376B (en) Cooperative spectrum sensing method based on characteristic value consistency estimation
Darghouthi et al. Link performance analysis for GFDM wireless systems
Banjade et al. Spectrum sensing performance of p-norm detector in random network interference
Lücken Communication and localization in UWB sensor networks: A synergetic approach
Kuzminskiy et al. Maximum likelihood optimization of adaptive asynchronous interference mitigation beamformer
Gouissem et al. Sparsity-aware narrowband interference mitigation and subcarriers selection in OFDM-based cognitive radio networks
Chowdappa et al. A low complexity distributed cluster based algorithm for spatial prediction
CN114978254B (en) Machine learning auxiliary low-complexity robust precoding algorithm based on OFDM system

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