CN114760174B - Modulation recognition method and device, electronic equipment and storage medium - Google Patents

Modulation recognition method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN114760174B
CN114760174B CN202210666241.4A CN202210666241A CN114760174B CN 114760174 B CN114760174 B CN 114760174B CN 202210666241 A CN202210666241 A CN 202210666241A CN 114760174 B CN114760174 B CN 114760174B
Authority
CN
China
Prior art keywords
otfs
sample
determining
signal
samples
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
CN202210666241.4A
Other languages
Chinese (zh)
Other versions
CN114760174A (en
Inventor
刘杨
汪斯佳
彭木根
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.)
Beijing University of Posts and Telecommunications
Original Assignee
Beijing 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 Beijing University of Posts and Telecommunications filed Critical Beijing University of Posts and Telecommunications
Priority to CN202210666241.4A priority Critical patent/CN114760174B/en
Publication of CN114760174A publication Critical patent/CN114760174A/en
Application granted granted Critical
Publication of CN114760174B publication Critical patent/CN114760174B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L27/00—Modulated-carrier systems
    • H04L27/0012—Modulated-carrier systems arrangements for identifying the type of modulation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
    • G06F2218/08—Feature extraction
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
    • G06F2218/12—Classification; Matching

Abstract

The invention provides a modulation identification method, a modulation identification device, electronic equipment and a storage medium, and relates to the technical field of wireless network frequency spectrum, wherein the method comprises the following steps: receiving and demodulating an OTFS (optical transport plane) communication integrated signal sent by a vRAN (virtual radio access network) base station, wherein the OTFS communication integrated signal is transmitted in a time delay-Doppler domain; determining an IQ sample based on the demodulated OTFS common sense integrated signal, wherein the high-order cumulant of the IQ sample is determined based on the air calculation; determining the global characteristics of the IQ sample based on the high-order cumulant of the IQ sample; determining local features of the IQ samples; and carrying out modulation identification on the global features and the local features of the series-connected IQ samples to obtain a modulation identification result. The invention can improve the modulation recognition efficiency and precision, reduce the communication time delay and error, realize the integration of communication, perception and calculation and improve the communication reliability.

Description

Modulation recognition method and device, electronic equipment and storage medium
Technical Field
The present application relates to the field of wireless network spectrum technologies, and in particular, to a modulation identification method, an apparatus, an electronic device, and a storage medium.
Background
With the development and deployment of 5G and 6G, reliable communication in a high-speed mobile scene becomes one of the research focuses in the future wireless communication field. Modulation identification is an important step between signal detection and signal demodulation, and aims to judge the modulation mode of a signal and estimate corresponding modulation parameters by processing a received signal without other prior knowledge. Modulation identification generally involves two steps: data acquisition (i.e., spectrum sensing) and data analysis (i.e., identification). And the future communication network needs to support high-reliability low-delay communication among nodes of mass equipment, and modulation identification is used as an important functional component in the future wireless network, so that great challenges are faced.
In the prior art, the existing modulation identification method has low efficiency and identification precision when facing massive nodes, and has high communication delay, which further causes the reduction of communication reliability.
Disclosure of Invention
The invention provides a modulation identification method, a modulation identification device, electronic equipment and a storage medium, which are used for solving the technical problems of higher communication time delay, lower efficiency and identification precision of the existing modulation identification technology, realizing integration of communication, perception and calculation and improving the communication reliability.
The invention provides a modulation identification method, which comprises the following steps:
receiving and demodulating an OTFS (optical transport plane) universal sense integrated signal sent by a vRAN (virtual radio access network) base station, wherein the OTFS universal sense integrated signal is transmitted in a time delay-Doppler domain;
determining IQ samples based on the demodulated OTFS common sense integration signal, wherein the high-order cumulant of the IQ samples is determined based on over-the-air calculation;
determining global features of the IQ samples based on the high-order cumulant of the IQ samples;
determining local features of the IQ samples;
and carrying out modulation identification on the global features and the local features of the IQ samples connected in series to obtain a modulation identification result.
According to the modulation identification method provided by the invention, the acquiring the global characteristics of the IQ samples based on the high-order cumulant of the IQ samples comprises the following steps:
determining a sum function of the higher order cumulants determined based on the moment estimates related to the IQ sample observations;
and acquiring an objective function of the IQ sample according to the sum function of the high-order cumulant, wherein the objective function is used for representing the global characteristics of the IQ sample.
According to the modulation identification method provided by the invention, the determining the local characteristics of the IQ samples comprises the following steps:
determining an ordered subsequence of the IQ sample based on a limited condition by utilizing a kernel framework based on limited characteristic information of the IQ sample, wherein the limited characteristic information comprises phase information and amplitude information of the IQ sample;
determining a Gaussian Mixture Model (GMM) according to the ordered subsequence, wherein the GMM is used for representing and generating distribution;
and determining the local characteristics of the IQ sample according to the Gaussian mixture model GMM.
According to the modulation identification method provided by the invention, the modulation identification is carried out on the global characteristics and the local characteristics of the IQ samples connected in series to obtain a modulation identification result, and the modulation identification method comprises the following steps:
carrying out feature series connection on the global features and the local features of the IQ samples to determine a feature group;
and inputting the characteristic group into a pre-constructed modulation classifier to obtain a modulation identification result.
The invention also provides a modulation identification method, which comprises the following steps:
determining an OTFS initial signal, and mapping the OTFS initial signal to a time delay-Doppler domain;
converting the OTFS initial signal in the time delay-Doppler domain into an OTFS initial signal in the time domain-frequency domain by utilizing inverse finite-cosine Fourier transform;
and modulating the OTFS initial signal in the time domain-frequency domain to obtain an OTFS universal induction integrated signal, and sending the OTFS universal induction integrated signal to a receiving terminal.
The present invention also provides a modulation identification apparatus, comprising:
the receiving module is used for receiving and demodulating an OTFS (optical transport plane) communication integrated signal sent by a vRAN (virtual radio access network) base station, wherein the OTFS communication integrated signal is transmitted in a time delay-Doppler domain;
a first determining module, configured to determine an IQ sample based on the demodulated OTFS common-sense integrated signal, where a high-order cumulant of the IQ sample is determined based on an over-the-air calculation;
a second determining module, configured to determine a global feature of the IQ sample based on the high-order cumulant of the IQ sample;
a third determining module, configured to determine a local feature of the IQ sample;
and the acquisition module is used for carrying out modulation identification on the global features and the local features of the IQ samples which are connected in series to acquire a modulation identification result.
The present invention also provides a signal control apparatus, comprising:
a fourth determining module, configured to determine an OTFS initial signal, and map the OTFS initial signal to a delay-doppler domain;
the conversion module is used for converting the OTFS initial signal in the time delay-Doppler domain into an OTFS initial signal in the time domain-frequency domain by utilizing inverse finite octyl Fourier transform;
and the sending module is used for modulating the OTFS initial signal in the time domain-frequency domain, acquiring an OTFS integrated signal and sending the OTFS integrated signal to a receiving terminal.
The invention also provides an electronic device comprising a processor and a memory storing a computer program, wherein the processor implements any one of the modulation identification methods when executing the computer program.
The present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements any of the modulation identification methods described above.
The present invention also provides a computer program product comprising a computer program which, when executed by a processor, implements any of the modulation identification methods described above.
The invention provides a modulation identification method, a device, electronic equipment and a storage medium, which are based on OTFS (optical transmission system) through-sensing integrated signals transmitted in a time delay-Doppler domain and sent by a vRAN (virtual radio access network) base station, acquire IQ (in-phase quadrature phase) samples, complete calculation through air calculation and acquire modulation identification results, realize deep fusion of communication, sensing and calculation, effectively improve modulation identification efficiency, reduce communication time delay, effectively solve the problem of communication limitation caused by massive nodes, effectively solve Doppler effect and multipath effect under a high-speed mobile environment and realize efficient and reliable large-scale spectrum analysis, wherein the local characteristics of the IQ samples are extracted to adapt to global change in potential signals, namely the local characteristics still keep inherent characteristics under the influence of receiving constellation symbol misrepresentation, higher noise level or partial transmitter overlapping by the global characteristics, the modulation identification performance is improved; meanwhile, the OTFS (over the air technology) communication integrated signal is sent by the vRAN base station, and computing and caching resources are distributed for air computing by the aid of the virtualized resource pool and the cloud resource pool, so that flexible deployment of network modules as required is achieved, burst data can be flushed, and communication requirements of mass nodes of a future network are met.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed for the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of a modulation identification method provided in the present invention;
FIG. 2 is an aerial computing architecture diagram of the modulation identification method provided by the present invention;
FIG. 3 is a second schematic flow chart of a modulation identification method according to the present invention;
FIG. 4 is a third schematic flow chart of a modulation identification method provided by the present invention;
FIG. 5 is a schematic structural diagram of a modulation recognition apparatus provided in the present invention;
FIG. 6 is a schematic structural diagram of a signal control device provided in the present invention;
fig. 7 is a schematic structural diagram of an electronic device provided by the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. 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.
The modulation identification method of the present invention is described below in conjunction with fig. 1-4.
The invention provides a modulation identification method for realizing the integration of general sensing calculation, and fig. 1 is one of the flow diagrams of the modulation identification method provided by the invention, as shown in fig. 1, the method comprises the following steps:
step 110, receiving and demodulating an OTFS (over the air frequency domain) common sense integrated signal sent by a vRAN (virtualized wireless access network) base station, where the OTFS (orthogonal time frequency space) common sense integrated signal is transmitted in a delay-doppler domain.
Optionally, the method for demodulating an OTFS (Orthogonal Time Frequency Space) integrated signal includes:
the time-varying channel is converted into a time delay-Doppler domain sparse channel, the variability of the channel is low, and the channel is sparse, so that all received data signals experience the almost same and slowly-varying sparse channel and are influenced by the same channel frequency selection and time diversity;
before the over-the-air calculation, the OTFS integrated signal is subjected to multi-carrier demodulation, the demodulated OTFS integrated signal is subjected to finite-order-of-components Fourier transform (SFFT), and the OTFS integrated signal is converted into a time delay-Doppler domain.
Optionally, the time delay-doppler domain sparse channel comprises a time-frequency dual selective fading channel.
Optionally, fig. 2 is an over-the-air computing architecture diagram of the modulation identification method provided in the present invention, and as shown in fig. 2, the vRAN base station includes, but is not limited to: the vRAN multiplex base stations, the number of the vRAN base stations is not limited, and the vRAN base stations comprise a multi-carrier system used for carrying out multi-carrier modulation on OTFS common sensing integrated signals.
Step 120, determining IQ (quadrature signal) samples based on the demodulated OTFS common sense integrated signal, wherein high order cumulants of the IQ samples are determined based on over the air calculation.
Alternatively, IQ samples refer to Quadrature signals, a pair of periodic signals are referred to as "Quadrature" signals, "In-phase" or reference signals as "I" (In-phase) when the phases are 90 degrees apart, and a signal shifted by 90 degrees (Quadrature signal) is referred to as "Q" (Quadrature), the acquisition device of the IQ samples including, but not limited to, a sensor.
Optionally, in the conventional mode, communication and calculation are separated, and all nodes need to be calculated after being recovered one by one at a receiving end, so that higher communication delay domain spectrum resource waste is caused.
Optionally, the vRAN base station implements flexible deployment of Network elements as needed by using a Virtualized Radio Access Network (vRAN) technology, and allocates computing and cache resources for air computing by using a Virtualized resource pool and a cloud resource pool without additionally deploying hardware facilities. Wherein, part of the cloud resources have the function of any network element to complete the data processing of the sensing and communication information.
And step 130, determining the global features of the IQ samples based on the high-order cumulant of the IQ samples.
Optionally, the method for extracting global features of the IQ samples includes:
determining a sum function of higher-order cumulants, wherein the higher-order cumulants are determined based on moment estimates related to IQ sample observation;
and acquiring an objective function of the IQ sample according to the sum function of the high-order cumulant, wherein the objective function is used for representing the global characteristics of the IQ sample.
Optionally, the higher order cumulants are calculated by mixing moments. The high-order cumulant calculation method comprises the following steps:
defining a complex random process X (t) with zero mean value, wherein the mixing moment of the order p is shown as formula (1):
Figure 453081DEST_PATH_IMAGE001
wherein
Figure 576895DEST_PATH_IMAGE002
Denotes conjugation, p and q both denote orders, and q is any non-negative integer less than p.
The higher order cumulant is expressed as follows:
Figure 907251DEST_PATH_IMAGE003
Figure 116515DEST_PATH_IMAGE004
Figure 941252DEST_PATH_IMAGE005
Figure 670305DEST_PATH_IMAGE006
where cum () represents the joint cumulant function,
Figure 656715DEST_PATH_IMAGE007
、
Figure 87697DEST_PATH_IMAGE008
the second-order cumulative amount is represented,
Figure 702742DEST_PATH_IMAGE009
、
Figure 801148DEST_PATH_IMAGE010
、
Figure 958460DEST_PATH_IMAGE011
all represent fourth order cumulative amounts.
Alternatively, discrete random processes are considered
Figure 893049DEST_PATH_IMAGE012
If the arithmetic mean can be used to replace the statistical mean in the calculation of the mixing moments, the p-order mixing moments are expressed by the following equation (2):
Figure 59588DEST_PATH_IMAGE013
where K represents the number of signal nodes.
Step 140, determining local characteristics of the IQ samples.
Optionally, the method for determining the local feature of the IQ sample includes:
determining an ordered subsequence of the IQ sample based on a limited condition by using an inner core frame based on the limited characteristic information of the IQ sample, wherein the limited characteristic information comprises phase information and amplitude information of the IQ sample;
determining a Gaussian Mixture Model (GMM) according to the ordered subsequence, wherein the GMM is used for representing and generating distribution;
and determining the local characteristics of the IQ sample according to the Gaussian mixture model GMM.
Optionally, the local feature extraction method specifically includes:
the Kernel framework, including but not limited to a Fisher Kernel generation framework, models the phase and amplitude information of the IQ samples, generates ordered subsequences for characterizing the sequence of IQ samples, wherein,
Figure 481342DEST_PATH_IMAGE014
a real-valued sequence representing the observed amplitude and phase information in the ordered subsequence.
Using Fisher Kernel (FK) notation, the similarity between tile-in-model products of fisher vectors (Fv) is defined as shown in equation (3):
Figure 324402DEST_PATH_IMAGE015
wherein, the first and the second end of the pipe are connected with each other,
Figure 995555DEST_PATH_IMAGE016
denotes an ordered subsequence of length l starting from position i, an ordered subsequence of length n having a total of (n-l + 1) ordered subsequences of this type,
Figure 450938DEST_PATH_IMAGE017
is the square root of the inverse of the Fisher Information Matrix (FIM),
Figure 258357DEST_PATH_IMAGE018
is a Gaussian Mixture Model (GMM),
Figure 23051DEST_PATH_IMAGE019
is formed by Gaussian mixture model
Figure 156399DEST_PATH_IMAGE020
Generated observed ordered subsequence
Figure 664741DEST_PATH_IMAGE021
A gradient of the log likelihood of;
k component GMM is composed of
Figure 326666DEST_PATH_IMAGE022
Determination of wherein
Figure 12994DEST_PATH_IMAGE023
Is a non-negative mixing weight of the k-th component and
Figure 393159DEST_PATH_IMAGE024
，
Figure 174034DEST_PATH_IMAGE025
is a vector of the mean value thereof,
Figure 205312DEST_PATH_IMAGE026
learning and generating a Gaussian mixture model GMM for a diagonal covariance matrix based on a training example of an IQ sample, wherein the training example of the IQ sample comprises examples of all modulation classes to be predicted, and the GMM is shown as formula (4):
Figure 311809DEST_PATH_IMAGE027
by GMM model
Figure 930003DEST_PATH_IMAGE028
Obtaining a local feature representation of the entire IQ sample
Figure 780147DEST_PATH_IMAGE029
Local feature representation of IQ samples as an average Fisher vector of all observed shingles within the IQ sample
Figure 151086DEST_PATH_IMAGE030
As shown in formula (5):
Figure 680681DEST_PATH_IMAGE031
and 150, carrying out modulation identification on the global features and the local features of the series-connected IQ samples to obtain a modulation identification result.
Optionally, the method for determining the modulation identification result includes:
carrying out feature series connection on the global features and the local features of the IQ samples to determine a feature group;
and inputting the feature group into a pre-constructed modulation classifier to obtain a modulation identification result.
Optionally, the modulation classifier is constructed, trained and optimized on a vRAN center cloud, the vRAN center cloud is obtained by performing virtualization and clouding deployment construction on the centralized processing unit, and the vRAN center cloud is used for processing data, executing global information perception, training and optimizing a global model and obtaining a modulation recognition result.
Optionally, during modulation identification, on a vRAN central cloud, for a received OTFS common-mode signal, time delay and doppler shift are mapped into two physical quantities, namely distance and speed, and accordingly, a target is monitored and positioned or an environmental condition is sensed.
The invention provides a modulation identification method, which is based on an OTFS (optical transmission system) through-sensing integrated signal which is sent by a vRAN (virtual radio access network) base station and transmitted in a time delay-Doppler domain, acquires an IQ (in-phase quadrature phase) sample, completes calculation through aerial calculation, and acquires a modulation identification result, thereby realizing deep fusion of communication, sensing and calculation, effectively improving modulation identification efficiency, reducing communication time delay, effectively solving the problem of communication limitation caused by massive nodes, effectively solving the Doppler effect and multipath effect in a high-speed mobile environment, realizing efficient and reliable large-scale spectrum analysis, wherein the local characteristics of the IQ sample are extracted to adapt to global change in a potential signal, namely, the local characteristics still retain inherent characteristics under the influence of the fact that the global characteristics receive the error representation of constellation symbols, higher noise level or partial transmitter overlapping, and improving modulation identification performance.
Fig. 3 is a second schematic flow chart of the modulation identification method provided by the present invention, and as shown in fig. 3, the method includes:
step 210, determining an OTFS initial signal, and mapping the OTFS initial signal to a delay-Doppler domain;
step 210, converting the OTFS initial signal in the delay-doppler domain into an OTFS initial signal in the time domain-frequency domain by using inverse finite-octave fourier transform;
and step 230, modulating the OTFS initial signal in the time domain and the frequency domain to obtain an OTFS integrated signal, and sending the OTFS integrated signal to a receiving terminal.
Optionally, fig. 4 is a third schematic flow chart of the modulation identification method provided by the present invention, as shown in fig. 4, the OTFS initial signal includes, but is not limited to, MPSK or MQAM information symbols, and is mapped to values of equally spaced grid points in a delay-Doppler (DD) domain, and information in each DD domain is subjected to inverse finite-length-symplectic fourier transform (ISFFT), that is, the OTFS initial signal in the delay-Doppler domain is converted into a time domain-frequency domain, and is modulated and transmitted through a multi-carrier system.
According to the modulation identification method provided by the invention, the OTFS (optical transmission system) communication-sensing integrated signal transmitted in the delay-Doppler domain is sent through the vRAN base station, the Doppler effect and the multipath effect under the high-speed mobile environment are effectively responded, the efficient and reliable large-scale spectrum analysis is realized, the calculation and cache resources are distributed for air calculation by utilizing the virtualized resource pool and the clouded resource pool, the flexible deployment of network modules as required is realized, the burst type data burst can be responded, and the communication requirement of mass nodes of the future network is met.
Fig. 5 is a schematic structural diagram of the modulation recognition apparatus provided in the present invention, and as shown in fig. 5, the modulation recognition apparatus 300 includes: a receiving module 301, a first determining module 302, a second determining module 303, a third determining module 304, and an obtaining module 305, wherein:
the receiving module 301 is configured to receive and demodulate an OTFS common sense integrated signal sent by a vRAN base station, where the OTFS common sense integrated signal is transmitted in a delay-doppler domain;
a first determining module 302, configured to determine an IQ sample based on the demodulated OTFS common-mode signal, where a high-order cumulant of the IQ sample is determined based on an over-the-air calculation;
a second determining module 303, configured to determine a global feature of the IQ sample based on a high-order cumulant of the IQ sample;
a third determining module 304, configured to determine a local feature of the IQ sample;
an obtaining module 305, configured to perform modulation identification on the global features and the local features of the IQ samples connected in series, so as to obtain a modulation identification result.
The invention provides a modulation recognition device, which is based on an OTFS (optical transmission system) general sensing integrated signal which is sent by a vRAN (virtual radio access network) base station and transmitted in a time delay-Doppler domain, acquires an IQ (in-phase quadrature) sample, completes calculation through aerial calculation, and acquires a modulation recognition result, thereby realizing deep fusion of communication, perception and calculation, effectively improving modulation recognition efficiency, reducing communication time delay, and effectively solving the problem of communication limitation caused by massive nodes, wherein the local characteristics of the IQ sample are extracted to adapt to global changes in potential signals, namely the local characteristics still retain inherent characteristics under the influence of error representation of constellation symbols, higher noise level or partial transmitter overlapping received by the global characteristics, and improving modulation recognition performance; meanwhile, the OTFS (over the air technology) communication integrated signal is sent by the vRAN base station, and computing and caching resources are distributed for air computing by the aid of the virtualized resource pool and the cloud resource pool, so that flexible deployment of network modules as required is achieved, burst data can be flushed, and communication requirements of mass nodes of a future network are met.
Optionally, the second determining module 303 is specifically configured to:
determining a sum function of higher-order cumulants, wherein the higher-order cumulants are determined based on moment estimates related to IQ sample observation;
and acquiring an objective function of the IQ sample according to the sum function of the high-order cumulant, wherein the objective function is used for representing the global characteristics of the IQ sample.
Optionally, the third determining module 304 is specifically configured to:
determining an ordered subsequence of the IQ sample based on a limited condition by using an inner core frame based on the limited characteristic information of the IQ sample, wherein the limited characteristic information comprises phase information and amplitude information of the IQ sample;
determining a Gaussian Mixture Model (GMM) according to the ordered subsequence, wherein the GMM is used for representing and generating distribution;
and determining the local characteristics of the IQ sample according to the Gaussian mixture model GMM.
Optionally, the obtaining module 305 is specifically configured to:
carrying out feature series connection on the global features and the local features of the IQ samples to determine a feature group;
and inputting the feature group into a pre-constructed modulation classifier to obtain a modulation identification result.
Fig. 6 is a schematic structural diagram of the signal control apparatus provided in the present invention, and as shown in fig. 6, the signal control apparatus 400 includes: a fourth determining module 401, a converting module 402 and a sending module 403, wherein:
a fourth determining module 401, configured to determine an OTFS initial signal, and map the OTFS initial signal to a delay-doppler domain;
a converting module 402, configured to convert the OTFS initial signal in the delay-doppler domain into an OTFS initial signal in the time domain-frequency domain by using inverse finite-octant fourier transform;
the sending module 403 is configured to modulate the OTFS initial signal in the time domain-frequency domain, acquire an OTFS sense-integrated signal, and send the OTFS sense-integrated signal to the receiving terminal.
The signal control device provided by the invention maps the OTFS (optical transmission line) general-purpose sensing integrated signal generated by the vRAN base station into a time delay-Doppler domain, performs inverse finite-cosine Fourier transform, expands the signal into the time domain-frequency domain, and sends the signal to the receiving terminal, thereby effectively coping with the Doppler effect and the multipath effect in the high-speed mobile environment and reducing the error caused by interference.
Fig. 7 illustrates a physical structure diagram of an electronic device, and as shown in fig. 7, the electronic device 500 may include: a processor (processor)510, a communication Interface (Communications Interface)520, a memory (memory)530 and a communication bus 540, wherein the processor 510, the communication Interface 520 and the memory 530 communicate with each other via the communication bus 540. Processor 510 may invoke logic instructions in memory 530 to perform a modulation identification method comprising:
receiving and demodulating an OTFS (optical transport plane) communication integrated signal sent by a vRAN (virtual radio access network) base station, wherein the OTFS communication integrated signal is transmitted in a time delay-Doppler domain;
determining an IQ sample based on the demodulated OTFS common sense integrated signal, wherein the high-order cumulant of the IQ sample is determined based on the air calculation;
determining the global characteristics of the IQ sample based on the high-order cumulant of the IQ sample;
determining local features of the IQ samples;
carrying out modulation identification on the global features and the local features of the IQ samples connected in series to obtain a modulation identification result;
alternatively, the first and second electrodes may be,
determining an OTFS initial signal, and mapping the OTFS initial signal to a delay-Doppler domain;
converting an OTFS initial signal in a time delay-Doppler domain into an OTFS initial signal in a time domain-frequency domain by utilizing inverse finite-octave Fourier transform;
and modulating the OTFS initial signal in the time domain-frequency domain to obtain an OTFS universal induction integrated signal, and sending the OTFS universal induction integrated signal to a receiving terminal.
Furthermore, the logic instructions in the memory 530 may be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute 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), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product, the computer program product including a computer program, the computer program being storable on a non-transitory computer readable storage medium, when the computer program is executed by a processor, the computer being capable of executing the modulation identification method provided by the above methods, the method including:
receiving and demodulating an OTFS (optical transport plane) communication integrated signal sent by a vRAN (virtual radio access network) base station, wherein the OTFS communication integrated signal is transmitted in a time delay-Doppler domain;
determining IQ samples based on the demodulated OTFS common sense integrated signal, wherein high-order cumulant of the IQ samples is determined based on air calculation;
determining the global characteristics of the IQ sample based on the high-order cumulant of the IQ sample;
determining local features of the IQ samples;
carrying out modulation identification on the global features and the local features of the IQ samples connected in series to obtain a modulation identification result;
alternatively, the first and second electrodes may be,
determining an OTFS initial signal, and mapping the OTFS initial signal to a delay-Doppler domain;
converting an OTFS initial signal in a time delay-Doppler domain into an OTFS initial signal in a time domain-frequency domain by utilizing inverse finite-octave Fourier transform;
and modulating the OTFS initial signal in the time domain-frequency domain to obtain an OTFS universal induction integrated signal, and sending the OTFS universal induction integrated signal to a receiving terminal.
In yet another aspect, the present invention also provides a non-transitory computer-readable storage medium having stored thereon a computer program which, when executed by a processor, is implemented to perform the modulation recognition method provided by the above methods, the method comprising:
receiving and demodulating an OTFS (optical transport plane) communication integrated signal sent by a vRAN (virtual radio access network) base station, wherein the OTFS communication integrated signal is transmitted in a time delay-Doppler domain;
determining an IQ sample based on the demodulated OTFS common sense integrated signal, wherein the high-order cumulant of the IQ sample is determined based on the air calculation;
determining the global characteristics of the IQ sample based on the high-order cumulant of the IQ sample;
determining local features of the IQ samples;
carrying out modulation identification on the global features and the local features of the IQ samples connected in series to obtain a modulation identification result;
alternatively, the first and second electrodes may be,
determining an OTFS initial signal, and mapping the OTFS initial signal to a delay-Doppler domain;
converting an OTFS initial signal in a time delay-Doppler domain into an OTFS initial signal in a time domain-frequency domain by utilizing inverse finite-octave Fourier transform;
and modulating the OTFS initial signal in the time domain-frequency domain to obtain an OTFS universal induction integrated signal, and sending the OTFS universal induction integrated signal to a receiving terminal.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods of the various embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, and not to limit it; although the present 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 solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims (9)

1. A modulation identification method, comprising:
receiving and demodulating an orthogonal time-frequency space OTFS (optical transport plane) general sensing integrated signal sent by a virtual radio access network vRAN (virtual radio access network) base station, wherein the OTFS general sensing integrated signal is transmitted in a time delay-Doppler domain;
determining an IQ sample of an orthogonal signal based on the demodulated OTFS common sense integration signal, wherein the high-order cumulant of the IQ sample is determined based on over-the-air calculation;
determining global features of the IQ samples based on the high-order cumulant of the IQ samples;
determining local features of the IQ samples;
and carrying out modulation identification on the global features and the local features of the IQ samples connected in series to obtain a modulation identification result.
2. The modulation identification method according to claim 1, wherein the obtaining global features of the IQ samples based on the high-order cumulant of the IQ samples comprises:
determining a sum function of the higher order cumulants determined based on the moment estimates related to the IQ sample observations;
and acquiring an objective function of the IQ sample according to the sum function of the high-order cumulant, wherein the objective function is used for representing the global characteristics of the IQ sample.
3. The modulation identification method according to claim 1, wherein the determining the local characteristics of the IQ samples comprises:
determining an ordered subsequence of the IQ sample based on a limited condition by utilizing a kernel framework based on limited characteristic information of the IQ sample, wherein the limited characteristic information comprises phase information and amplitude information of the IQ sample;
determining a Gaussian Mixture Model (GMM) according to the ordered subsequence, wherein the GMM is used for representing and generating distribution;
and determining the local characteristics of the IQ sample according to the Gaussian mixture model GMM.
4. The modulation identification method according to claim 1, wherein the performing modulation identification on the global features and the local features of the IQ samples connected in series to obtain a modulation identification result comprises:
carrying out feature series connection on the global features and the local features of the IQ samples to determine a feature group;
and inputting the characteristic group into a pre-constructed modulation classifier to obtain a modulation identification result.
5. A modulation identification method, comprising:
determining an OTFS initial signal in an orthogonal time-frequency space mode, and mapping the OTFS initial signal to a time delay-Doppler domain;
converting the OTFS initial signal in the time delay-Doppler domain into an OTFS initial signal in the time domain-frequency domain by utilizing inverse finite-length Fourier transform;
modulating the OTFS initial signal in the time domain and the frequency domain to obtain an OTFS integrated signal, sending the OTFS integrated signal to a receiving terminal, and performing air calculation on the OTFS integrated signal so that the receiving terminal receives and demodulates the OTFS integrated signal sent by a virtual radio access network vRAN base station, wherein the OTFS integrated signal is transmitted in a time delay-Doppler domain; determining an IQ sample of an orthogonal signal based on the demodulated OTFS common sense integration signal, wherein the high-order cumulant of the IQ sample is determined based on over-the-air calculation; determining global features of the IQ sample based on the high-order cumulant of the IQ sample; determining local features of the IQ samples; and carrying out modulation identification on the global features and the local features of the IQ samples connected in series to obtain a modulation identification result.
6. A modulation identification apparatus, comprising:
the receiving module is used for receiving and demodulating an orthogonal time-frequency-space OTFS (optical transmission system) universal sensing integrated signal sent by a virtual radio access network vRAN (virtual radio access network) base station, wherein the OTFS universal sensing integrated signal is transmitted in a time delay-Doppler domain;
a first determining module, configured to determine an IQ sample of an orthogonal signal based on the demodulated OTFS common sense integration signal, wherein a high-order cumulant of the IQ sample is determined based on an over-the-air calculation;
a second determining module, configured to determine a global feature of the IQ sample based on the high-order cumulant of the IQ sample;
a third determining module, configured to determine a local feature of the IQ sample;
and the acquisition module is used for carrying out modulation identification on the global features and the local features of the IQ samples which are connected in series to acquire a modulation identification result.
7. A signal control apparatus, comprising:
a fourth determining module, configured to determine an orthogonal time-frequency-space OTFS initial signal, and map the OTFS initial signal to a delay-doppler domain;
the conversion module is used for converting the OTFS initial signal in the time delay-Doppler domain into an OTFS initial signal in the time domain-frequency domain by utilizing inverse finite octyl Fourier transform;
the sending module is used for modulating the OTFS initial signal in the time domain-frequency domain, acquiring an OTFS integrated signal, sending the OTFS integrated signal to a receiving terminal, and performing over-the-air calculation on the OTFS integrated signal so that the receiving terminal receives and demodulates the OTFS integrated signal sent by a virtualized wireless access network vRAN base station, wherein the OTFS integrated signal is transmitted in a time delay-Doppler domain; determining an IQ sample of an orthogonal signal based on the demodulated OTFS common sense integration signal, wherein the high-order cumulant of the IQ sample is determined based on over-the-air calculation; determining global features of the IQ sample based on the high-order cumulant of the IQ sample; determining local features of the IQ samples; and carrying out modulation identification on the global features and the local features of the IQ samples connected in series to obtain a modulation identification result.
8. An electronic device comprising a processor and a memory storing a computer program, wherein the processor implements the modulation recognition method of any one of claims 1 to 4 or the modulation recognition method of claim 5 when executing the computer program.
9. A non-transitory computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the modulation recognition method according to any one of claims 1 to 4 or the modulation recognition method according to claim 5.
CN202210666241.4A 2022-06-14 2022-06-14 Modulation recognition method and device, electronic equipment and storage medium Active CN114760174B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210666241.4A CN114760174B (en) 2022-06-14 2022-06-14 Modulation recognition method and device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210666241.4A CN114760174B (en) 2022-06-14 2022-06-14 Modulation recognition method and device, electronic equipment and storage medium

Publications (2)

Publication Number Publication Date
CN114760174A CN114760174A (en) 2022-07-15
CN114760174B true CN114760174B (en) 2022-09-13

Family

ID=82336412

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210666241.4A Active CN114760174B (en) 2022-06-14 2022-06-14 Modulation recognition method and device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN114760174B (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112804172A (en) * 2020-12-24 2021-05-14 天津光电通信技术有限公司 Method for realizing signal modulation mode identification based on high-order cumulant
CN113904902A (en) * 2021-09-18 2022-01-07 北京理工大学 Method and device for identifying signal modulation type
CN114374447A (en) * 2022-01-06 2022-04-19 中国人民解放军国防科技大学 Channel detection method, device and medium

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10090973B2 (en) * 2015-05-11 2018-10-02 Cohere Technologies, Inc. Multiple access in an orthogonal time frequency space communication system

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112804172A (en) * 2020-12-24 2021-05-14 天津光电通信技术有限公司 Method for realizing signal modulation mode identification based on high-order cumulant
CN113904902A (en) * 2021-09-18 2022-01-07 北京理工大学 Method and device for identifying signal modulation type
CN114374447A (en) * 2022-01-06 2022-04-19 中国人民解放军国防科技大学 Channel detection method, device and medium

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
"Low-Complexity Symbol Detection and Interference";Huiyang Qu等;《IEEE TRANSACTIONS ON COMMUN》;20210331;全文 *
"基于高阶累积量特征学习的调制识别方法";袁莉芬等;《系统工程与电子技术》;20190930;全文 *

Also Published As

Publication number Publication date
CN114760174A (en) 2022-07-15

Similar Documents

Publication Publication Date Title
CN101064571B (en) Apparatus for enhancing channel evaluation in OFDM receiver and its method
CN110113288A (en) A kind of design and demodulation method of the ofdm demodulator based on machine learning
CN106302298A (en) A kind of method eliminating OFDM underwater sound communication system clipped noise
CN113395225B (en) Universal intelligent processing method and device for directly receiving communication signal waveform to bit
CN113971430A (en) Signal detection and model training method, device, equipment and storage medium
Chen et al. Emd and vmd empowered deep learning for radio modulation recognition
Zhang et al. Modulation classification of active attacks in internet of things: Lightweight mcbldn with spatial transformer network
CN114925720A (en) Small sample modulation signal identification method based on space-time mixed feature extraction network
CN114760174B (en) Modulation recognition method and device, electronic equipment and storage medium
CN104601512A (en) Method and system for detecting carrier frequency offset of phase-modulated signals
CN113890799A (en) Underwater acoustic communication channel estimation and signal detection method based on domain countermeasure network
CN105812299A (en) Channel estimation algorithm and system of wireless sensor network based on joint block sparse reconstruction
CN105162533A (en) Transmitter amplitude imbalance and phase imbalance measuring method
CN102487364B (en) Channel estimation method and apparatus thereof
CN113726711B (en) OFDM receiving method and device, and channel estimation model training method and device
CN113726710B (en) OFDM signal transmitting method, OFDM signal receiving method, OFDM signal transmitting device, OFDM signal receiving device, storage medium and electronic device
CN112671419B (en) Wireless signal reconstruction method, device, system, equipment and storage medium
CN114172771A (en) Method and system for rapid frequency offset estimation and compensation based on burst communication
CN104468426A (en) Method and system for estimating LTE uplink channel
Zhang et al. Deep learning‐based digital signal modulation identification under different multipath channels
CN104735003A (en) Euclidean distance calculation method, module and multi-input-multi-output decoding device
Li et al. A robust signal recognition method for communication system under time-varying SNR environment
Feng et al. FCGCN: Feature Correlation Graph Convolution Network for Few-Shot Individual Identification
Sembiring et al. Performance analysis of discrete hartley transform based ofdm modulator and demodulator
CN106302279A (en) FBMC system equalization method based on interference variance statistics

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