[go: up one dir, main page]

CN111884740B - Method and system for optimal allocation of UAV channel based on spectrum cognition - Google Patents

Method and system for optimal allocation of UAV channel based on spectrum cognition Download PDF

Info

Publication number
CN111884740B
CN111884740B CN202010510635.1A CN202010510635A CN111884740B CN 111884740 B CN111884740 B CN 111884740B CN 202010510635 A CN202010510635 A CN 202010510635A CN 111884740 B CN111884740 B CN 111884740B
Authority
CN
China
Prior art keywords
channel
spectrum
information
uav
module
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
CN202010510635.1A
Other languages
Chinese (zh)
Other versions
CN111884740A (en
Inventor
翟学锋
潘志新
王永强
王红星
黄郑
高超
韩卫
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Multi Wing Electrical Intelligence Technology Co ltd
State Grid Jiangsu Electric Power Co Ltd
Jiangsu Fangtian Power Technology Co Ltd
Original Assignee
Shenzhen Multi Wing Electrical Intelligence Technology Co ltd
State Grid Jiangsu Electric Power Co Ltd
Jiangsu Fangtian Power Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenzhen Multi Wing Electrical Intelligence Technology Co ltd, State Grid Jiangsu Electric Power Co Ltd, Jiangsu Fangtian Power Technology Co Ltd filed Critical Shenzhen Multi Wing Electrical Intelligence Technology Co ltd
Priority to CN202010510635.1A priority Critical patent/CN111884740B/en
Publication of CN111884740A publication Critical patent/CN111884740A/en
Application granted granted Critical
Publication of CN111884740B publication Critical patent/CN111884740B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B17/00—Monitoring; Testing
    • H04B17/30—Monitoring; Testing of propagation channels
    • H04B17/382—Monitoring; Testing of propagation channels for resource allocation, admission control or handover
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B17/00—Monitoring; Testing
    • H04B17/30—Monitoring; Testing of propagation channels
    • H04B17/373—Predicting channel quality or other radio frequency [RF] parameters
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W72/00—Local resource management
    • H04W72/50—Allocation or scheduling criteria for wireless resources
    • H04W72/54—Allocation or scheduling criteria for wireless resources based on quality criteria
    • H04W72/542—Allocation or scheduling criteria for wireless resources based on quality criteria using measured or perceived quality
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Quality & Reliability (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Physics & Mathematics (AREA)
  • Electromagnetism (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

本发明公开了一种基于频谱认知的无人机信道优化分配方法和系统，将正在飞行的无人机自身作为频谱感知监测节点，对无人机使用的频段进行频谱扫描和监测，得到频域功率谱数据，将其量化得到信道状态信息，采用数传电台将频谱感知数据和遥测信息回传至地面控制与数据处理中心，地面控制与数据处理中心将全部节点的回传数据进行汇总，计算时间和信道间的相关度，结合信道优化分配模型，根据频谱感知数据与时间和信道间的相关度对空闲频谱和信道进行预测，为无人机分配空闲概率最大的信道，并将信道分配信息回传至无人机，无人机自动切换至优化分配的信道上，保持连续通信。本发明能够极大减少图传信道受到干扰的概率，提高图传信道的可靠性。

Figure 202010510635

The invention discloses a method and system for optimizing the channel allocation of unmanned aerial vehicles based on spectrum cognition. The flying unmanned aerial vehicle itself is used as a spectrum sensing monitoring node, and the frequency band used by the unmanned aerial vehicle is scanned and monitored to obtain the frequency spectrum. domain power spectrum data, quantify it to obtain channel state information, and use digital radio to transmit spectrum sensing data and telemetry information back to the ground control and data processing center. Calculate the correlation between time and channel, combine the channel optimization allocation model, predict the idle spectrum and channel according to the correlation between spectrum sensing data and time and channel, allocate the channel with the highest idle probability to the UAV, and assign the channel to the channel. The information is sent back to the drone, and the drone automatically switches to the optimally allocated channel to maintain continuous communication. The invention can greatly reduce the probability of the image transmission channel being interfered, and improve the reliability of the image transmission channel.

Figure 202010510635

Description

Unmanned aerial vehicle channel optimal allocation method and system based on frequency spectrum cognition
Technical Field
The invention relates to the technical field of wireless communication, in particular to an unmanned aerial vehicle channel optimal allocation method based on frequency spectrum cognition.
Background
In recent years, civil unmanned aerial vehicles have been developed rapidly, and remote control, telemetry and image transmission devices mainly use two wifi (wireless fidelity) frequency bands of 2.4GHz and 5GHz, which are also Industrial, Scientific and Medical (ISM) frequency bands. The connection modes such as Bluetooth and ZigBee also use the 2.4GHz frequency band. Because the two frequency bands are free open frequency bands, the number of used devices is increased day by day, and the interference to users is more and more serious. The communication channels of the civil unmanned aerial vehicles are all fixedly distributed in advance, so that once the communication channels are interfered, the error rate is rapidly increased, even the communication is interrupted, the remote control and remote measurement function is not good, video mosaics are increased, or no images exist.
In order to solve the problem of channel interference, the invention of patent No. CN108513734A discloses a channel switching method, a device, and a communication device, which employs a channel switching method, wherein an interference power obtaining module obtains interference powers of a plurality of channels in a communication frequency band, and if the interference power of a current channel exceeds a preset threshold, a target channel selecting module selects a suitable target channel according to the interference powers of the plurality of channels, and switches the target channel to the target channel through the channel switching module to continue communication. The method simply judges whether the channel is available according to the interference power currently suffered by the channel, whether the interference at the future moment exists is not predicted, and when the current channel is seriously interfered and the communication between the ground station and the unmanned aerial vehicle is interrupted, the channel switching information can not be interacted, and the channel switching is difficult to succeed.
The invention patent No. CN1084966384A discloses a method and device for controlling communication mode, which determines whether two communication parties use TDD or FDD duplex mode for communication by observing the measurement parameters of the communication channel. The method is essentially to dynamically adjust communication parameters according to channel conditions, but the number of parameters to be measured is small, and the parameters to be adjusted are limited.
The invention patent CN106877947A discloses a radio frequency channel parallel detection device and method for an unmanned aerial vehicle, which divides a 2.4GHz communication frequency band commonly used by the unmanned aerial vehicle into 42 parallel channels, measures the signal intensity and background noise of each channel, and detects the image transmission signal and the remote control and remote measurement signal of the unmanned aerial vehicle by using the signal bandwidth characteristic. Although the method improves the accuracy of channel measurement, the complexity is greatly increased, and the method is mainly used for unmanned aerial vehicle signal detection.
To sum up, at present, a mechanism and a method for sensing, analyzing and optimizing the full-band frequency spectrum used by the unmanned aerial vehicle and rapidly allocating and switching the channel when the communication channel of the unmanned aerial vehicle is interfered are lacked, so that the reliability and effectiveness of the communication of the unmanned aerial vehicle are improved.
Disclosure of Invention
The invention aims to provide an unmanned aerial vehicle channel optimal allocation method based on frequency spectrum cognition, which is characterized in that idle frequency spectrums or channels are predicted by utilizing frequency spectrum sensing data and time channel correlation degree information and adopting a machine learning-based algorithm, and an appropriate channel with the maximum idle probability is selected according to a prediction result, so that the probability of interference on a picture transmission channel is greatly reduced, and the reliability of the picture transmission channel is improved; in addition, the high-reliability and anti-interference digital radio station is used for transmitting remote control information, frequency spectrum sensing information and channel control information to ensure the reliable transmission of control signals, and the high-capacity and high-speed WiFi module is used for transmitting image and video information and can be quickly switched to an idle channel when being interfered to ensure the continuous and uninterrupted image transmission.
In order to achieve the above object, with reference to fig. 1, the present invention provides an unmanned aerial vehicle channel optimal allocation method based on spectrum cognition, where the optimal allocation method includes:
s1: and taking each unmanned aerial vehicle in the flight state as a spectrum sensing monitoring node, and carrying out spectrum scanning and monitoring sensing on each working frequency band used by each unmanned aerial vehicle in the flight state to obtain corresponding frequency domain power spectrum data.
S2: and each frequency spectrum sensing monitoring node quantizes the respective frequency domain power spectrum data to obtain the channel state information of each unmanned aerial vehicle in the flight state.
S3: and each frequency spectrum sensing monitoring node transmits respective frequency domain power spectrum data back to the ground control and data processing center by adopting a data transmission radio station.
S4: and the ground control and data processing center collects frequency domain power spectrum data returned by all the spectrum sensing monitoring nodes and calculates the correlation between time and channels.
S5: the method comprises the steps of importing frequency domain power spectrum data acquired in real time and correlation information between time and channels obtained through calculation into a pre-trained channel optimization allocation model, predicting idle frequency spectrums or channels, selecting a certain number of channels with the maximum idle probability according to a prediction result, allocating corresponding optimal channels for all unmanned aerial vehicles in a flight state according to a preset allocation principle, and transmitting channel allocation information back to all unmanned aerial vehicles in the flight state through a data transmission radio station.
S6: and each unmanned aerial vehicle in the flight state receives the channel allocation information and automatically switches the respective transmission channel to the optimally allocated channel.
As a preferred example, each unmanned aerial vehicle in a flight state is simultaneously provided with a data transmission radio station and a Wifi module, and the unmanned aerial vehicle transmits remote control and remote measurement information by using the data transmission radio station and transmits image/video information by using the Wifi module.
As a preferable example, the frequency band occupied by the transmission of the remote control and telemetry information includes a frequency band dedicated to the unmanned aerial vehicle of 840.5-845MHz, and the frequency band occupied by the transmission of the image/video information includes two frequency bands of 2.4GHz and 5 GHz.
As a preferable example, in step S2, the process of obtaining the channel state information of each drone in flight state includes the following steps:
setting the channel state information of each unmanned aerial vehicle in the flight state as CSI (t, c):
Figure BDA0002528272360000031
wherein, 0 represents that the channel is in an idle state, 1 represents that the channel is in an occupied state, R (T, C) is the power value of the channel C at the sampling time T, the unit dBm, T is the total duration, and C is the total number of the channels.
As a preferred example, in step S4, the process of calculating the correlation between time and channel includes the following steps:
s41, setting Xk、YkTwo channel state information sequences are provided, and each channel state information sequence is a 0-1 sequence.
S42, calculating to obtain X according to the following formulak、YkCorrelation degree ρ:
Figure BDA0002528272360000032
wherein, i (a) is a judgment function, if a is true, i (a) is 1, if a is not true, i (a) is 0, ΣkCalculated for the accumulated sum.
As a preferred example, the preset allocation principle includes matching the channel idle probability with the mission emergency degree of the drone and the distance between the drone and the control center, that is, the channel with the highest idle probability is allocated to the drone with the most emergency or farthest mission, and the channel with the second idle probability is allocated to the drone with the second most important mission or farthest mission.
As a preferred example, the channel optimization allocation model is constructed based on a back propagation neural network algorithm, and includes a first layer neural network and a second layer neural network connected to each other.
The first layer of neural network is used for performing parallel training on input vectors of a time domain and a frequency domain to obtain a time domain training result and a frequency domain training result, the second layer of neural network is used for integrating the time domain training result and the frequency domain training result of the first layer of neural network by combining the correlation of the time domain and the frequency domain of a channel, an idle frequency spectrum or the channel is predicted, and the prediction result is the idle probability of each channel.
As a preferred example, the optimal allocation method further includes:
the unmanned aerial vehicle collects telemetering information in real time/periodically, the telemetering information is added into a frequency spectrum sensing data frame and is transmitted back to a ground control and data processing center, and the telemetering information comprises: the geographical position, speed, acceleration, self state information and the collection timestamp of unmanned aerial vehicle.
And the ground control and data processing center processes the remote information, calculates to obtain corresponding remote control information, and transmits the calculated remote control information and channel allocation information back to each unmanned aerial vehicle in a flight state through the data transmission radio station.
With reference to fig. 2, the present invention further provides an unmanned aerial vehicle channel optimal allocation system based on spectrum cognition, where the unmanned aerial vehicle channel optimal allocation system includes a ground control and data processing center and at least one unmanned aerial vehicle in a flight state.
Unmanned aerial vehicle includes the unmanned aerial vehicle body to and carry on first spectrum sensing module, first data processing module, first GPS module, remote control telemetering measurement module, first Wifi module and the first digital radio station on the unmanned aerial vehicle body.
The first data processing module is connected with the first spectrum sensing module, the first GPS module, the first remote control and telemetry module, the first Wifi module and the first data transmission radio module respectively.
The first frequency spectrum sensing module is used for monitoring and sensing the frequency spectrum of the current used frequency band of the unmanned aerial vehicle to obtain corresponding frequency domain power spectrum data; the first data processing module is used for processing the received frequency domain power spectrum data, obtaining channel state information of the unmanned aerial vehicle after quantization, and sending the quantization result back to the ground control and data processing center through the first data transmission radio module.
The first GPS module is used for collecting position and speed information of the unmanned aerial vehicle in real time/periodically, the remote control and telemetry module is used for collecting state information of the unmanned aerial vehicle in real time/periodically, and the first data processing module integrates the collection results of the first GPS module and the first remote control and telemetry module into telemetry information, adds the telemetry information into a frequency spectrum sensing data frame and transmits the telemetry information back to the ground control and data processing center.
The ground control and data processing center comprises a second data processing module, and a second spectrum sensing module, a second GPS module, a second Wifi module, a second data transmission station and a channel optimization distribution module which are connected with the second data processing module.
A data transmission channel is established between the second data transmission radio station and the first data transmission radio station of each unmanned aerial vehicle, spectrum sensing data frames sent by all the first data transmission radio stations are received, and the received spectrum sensing data frames are sent to the second data processing module.
The second frequency spectrum sensing module is used for monitoring and sensing the frequency spectrum of the current used frequency band of the ground unmanned aerial vehicle to obtain corresponding frequency domain power spectrum data.
The second data processing module receives frequency domain power spectrum data of the ground unmanned aerial vehicle fed back by frequency spectrum sensing data frames sent by all unmanned aerial vehicles and the second frequency spectrum sensing module, analyzes the frequency domain power spectrum data to obtain channel state information and telemetering information of each unmanned aerial vehicle, continuously processes the telemetering information to obtain corresponding remote control information, and simultaneously sends the channel state information of each unmanned aerial vehicle to the channel optimization distribution module, the channel optimization distribution module adopts the unmanned aerial vehicle channel optimization distribution calculation based on frequency spectrum cognition to obtain an optimal channel corresponding to each unmanned aerial vehicle, and the calculation result is fed back to the second data processing module.
The second data processing module transmits the channel distribution information and the remote control information back to each unmanned aerial vehicle through the second data transmission radio station, so that the unmanned aerial vehicle automatically switches channels of the first Wifi module and the first data transmission radio station according to the received channel distribution information, and drives the remote control and remote measurement module to execute flight control on the unmanned aerial vehicle according to the received remote control information.
A data transmission channel is established between the second Wifi module and the first Wifi module of each unmanned aerial vehicle, and image/video information sent by all the unmanned aerial vehicles through the first Wifi modules is received.
And the second GPS module is used for acquiring the position and speed information of the ground control and data processing center in real time/periodically and transmitting the acquisition result and the channel allocation information to the unmanned aerial vehicle.
As a preferred example, the channel optimization allocation module includes a spectrum analysis unit, a spectrum prediction and channel allocation unit.
The frequency spectrum analysis unit is used for processing frequency domain power spectrum data acquired in real time and calculating correlation degree information between time and channels.
The frequency spectrum prediction and channel allocation unit is used for predicting the idle frequency spectrum or the channel by combining frequency domain power spectrum data and correlation degree information between time and the channel, selecting a certain amount of channels with the maximum idle probability according to a prediction result, and allocating corresponding optimal channels to each unmanned aerial vehicle in a flight state according to a preset allocation principle.
In summary, the invention uses the unmanned aerial vehicle as a spectrum sensing monitoring node, performs spectrum scanning and monitoring on a frequency band used by the unmanned aerial vehicle to obtain frequency domain power spectrum data, quantizes the frequency domain power spectrum data to obtain channel state information CSI, and then uses a data transmission radio station to transmit the spectrum sensing data and telemetry information back to the ground, the ground collects the returned data of all nodes, calculates the correlation between time and channels, predicts the idle spectrum and channels according to the correlation between the spectrum sensing data and the time and the channels by combining with a channel optimization distribution model, distributes channels with the maximum idle probability to the unmanned aerial vehicle, and transmits channel distribution information back to the unmanned aerial vehicle, and the unmanned aerial vehicle automatically switches to the optimally distributed channels to maintain continuous communication. In addition, the data transmission radio station is used for transmitting remote control and remote measurement information, the Wifi module transmits image/video information, for example, the remote control and remote measurement information uses 840.5-845MHz frequency band, the image/video information transmission dynamically selects 2.4GHz and 5GHz frequency bands, and reliable transmission of control signals and continuous and uninterrupted image transmission are ensured.
Compared with the prior art, the technical scheme of the invention has the following remarkable beneficial effects:
(1) the invention uses the high-reliability data transmission station with anti-interference capability for remote control and remote measurement information, frequency spectrum sensing information and channel control information transmission, thereby ensuring the reliable transmission of control signals.
(2) The invention uses the WiFi module with large capacity and high speed rate for image and video information transmission, and can quickly switch to an idle channel when being interfered, thereby ensuring continuous and uninterrupted image transmission.
(3) The method and the device utilize the frequency spectrum sensing data and the time channel correlation degree information, adopt an algorithm based on machine learning to predict the idle frequency spectrum or the channel, and select the proper channel with the maximum idle probability according to the prediction result, thereby greatly reducing the probability of the interference on the image transmission channel and improving the reliability of the image transmission channel.
It should be understood that all combinations of the foregoing concepts and additional concepts described in greater detail below can be considered as part of the inventive subject matter of this disclosure unless such concepts are mutually inconsistent. In addition, all combinations of claimed subject matter are considered a part of the presently disclosed subject matter.
The foregoing and other aspects, embodiments and features of the present teachings can be more fully understood from the following description taken in conjunction with the accompanying drawings. Additional aspects of the present invention, such as features and/or advantages of exemplary embodiments, will be apparent from the description which follows, or may be learned by practice of specific embodiments in accordance with the teachings of the present invention.
Drawings
The drawings are not intended to be drawn to scale. In the drawings, each identical or nearly identical component that is illustrated in various figures may be represented by a like numeral. For purposes of clarity, not every component may be labeled in every drawing. Embodiments of various aspects of the present invention will now be described, by way of example, with reference to the accompanying drawings, in which:
fig. 1 is a flowchart of an unmanned aerial vehicle channel optimal allocation method based on spectrum cognition in the invention.
Fig. 2 is a schematic diagram of an unmanned aerial vehicle channel optimization allocation system based on spectrum cognition.
Fig. 3 is a schematic diagram of the unmanned aerial vehicle channel optimization distribution method based on spectrum cognition.
Detailed Description
In order to better understand the technical content of the present invention, specific embodiments are described below with reference to the accompanying drawings.
In this disclosure, aspects of the present invention are described with reference to the accompanying drawings, in which a number of illustrative embodiments are shown. Embodiments of the present disclosure are not necessarily defined to include all aspects of the invention. It should be appreciated that the various concepts and embodiments described above, as well as those described in greater detail below, may be implemented in any of numerous ways, as the disclosed concepts and embodiments are not limited to any one implementation. In addition, some aspects of the present disclosure may be used alone, or in any suitable combination with other aspects of the present disclosure.
In practical application, the information quantity required to be transmitted by remote control and telemetry is small, and the reliability requirement is high, so that a frequency hopping data transmission radio station with high reliability and strong anti-interference capability can be selected to transmit the remote control and telemetry information. The image/video transmission information quantity is large, the information association degree is high, and a certain error rate can be tolerated, so that a Wifi module can be selected for image/video information transmission.
In order to further improve the reliability of information transmission of the unmanned aerial vehicle, a special frequency band of the unmanned aerial vehicle of 840.5-845MHz is selected as a remote control and telemetry information transmission channel, the frequency band has less interference and high reliability, two frequency bands of 2.4GHz and 5GHz are dynamically selected as image/video information transmission channels, and automatic switching can be performed according to the interference degree.
Therefore, in the invention, the unmanned aerial vehicle is simultaneously provided with the data transmission radio station and the Wifi module, the data transmission radio station is adopted to transmit remote control and remote measurement information, the Wifi module transmits image/video information, and the frequency band occupied by the remote control and remote measurement information and the image/video information is different. In fact, the channel optimal allocation method mentioned in the present invention needs to perform optimal allocation on the channels occupied by two transmission modules. Considering that the frequency bands occupied by the Wifi module are only two, the computing resources are more prone to frequency band optimization of the data transmission radio station.
With reference to fig. 1 and fig. 3, the present invention provides a spectrum cognition-based channel optimization allocation method for an unmanned aerial vehicle, including:
s1: and taking each unmanned aerial vehicle in the flight state as a spectrum sensing monitoring node, and carrying out spectrum scanning and monitoring sensing on each working frequency band used by each unmanned aerial vehicle in the flight state to obtain corresponding frequency domain power spectrum data.
All unmanned aerial vehicles in the flight working state are used as spectrum sensing monitoring nodes, frequency bands used by all unmanned aerial vehicles, such as frequency bands of 840M, 2.4G and 5G, are scanned comprehensively and rapidly, the service conditions of the frequency bands are monitored in a sensing mode, and frequency domain power spectrum data are obtained.
S2: and each frequency spectrum sensing monitoring node quantizes the respective frequency domain power spectrum data to obtain the channel state information of each unmanned aerial vehicle in the flight state.
Setting the channel state information of each unmanned aerial vehicle in the flight state as CSI (t, c):
Figure BDA0002528272360000071
wherein, 0 represents that the channel is in an idle state, 1 represents that the channel is in an occupied state, R (T, C) is the power value of the channel C at the sampling time T, the unit dBm, T is the total duration, and C is the total number of the channels.
CSI (t, c) is information about whether channel c is occupied at the time of t sampling, specifically: (1) when the value of CSI (t, c) is 0, the channel is not occupied and is in an idle state; (2) when the value of CSI (t, c) is 1, it indicates that the channel is occupied and in a busy state.
S3: and each frequency spectrum sensing monitoring node transmits respective frequency domain power spectrum data back to the ground control and data processing center by adopting a data transmission radio station.
And each unmanned aerial vehicle frequency spectrum sensing monitoring node transmits the acquired telemetering information and the processed frequency spectrum sensing data back to the ground control and data processing center through the data transmission radio station for data processing.
Preferably, each unmanned aerial vehicle frequency spectrum perception monitoring node still will acquire through first GPS module and remote control telemeasuring module unmanned aerial vehicle's positional information and state information, for example geographical position, speed, acceleration and time stamp etc. add to frequency spectrum perception data frame as telemeasuring information, pass back ground control and data processing center in the lump through the data transfer radio station and handle the analysis, improve the whole transmission efficiency of data.
S4: and the ground control and data processing center collects frequency domain power spectrum data returned by all the spectrum sensing monitoring nodes and calculates the correlation between time and channels.
Let Xk、YkFor two channel state information sequences, each of which is a 0-1 sequence, then Xk、YkThe correlation ρ of (d) is:
Figure BDA0002528272360000072
wherein, i (a) is a judgment function, if a is true, i (a) is 1, if a is not true, i (a) is 0, ΣkCalculated for the accumulated sum.
And a spectrum analysis module located in the ground control and data processing center collects and analyzes spectrum sensing data returned by all the spectrum sensing monitoring nodes of the unmanned aerial vehicle, calculates correlation numerical values rho of channel state information between each time interval and each channel, and provides a data analysis basis for subsequent channel prediction and optimized distribution.
When there is the ground unmanned aerial vehicle who does not take off who occupies the channel on ground, can gather ground unmanned aerial vehicle's spectrum perception data by ground control and data processing center, the spectrum perception data that the unmanned aerial vehicle that reintegrates the flight that receives sent, as complete unmanned aerial vehicle's channel relevant information.
S5: the method comprises the steps of importing frequency domain power spectrum data acquired in real time and correlation information between time and channels obtained through calculation into a pre-trained channel optimization allocation model, predicting idle frequency spectrums or channels, selecting a certain number of channels with the maximum idle probability according to a prediction result, allocating corresponding optimal channels for all unmanned aerial vehicles in a flight state according to a preset allocation principle, and transmitting channel allocation information back to all unmanned aerial vehicles in the flight state through a data transmission radio station.
The preset allocation principle comprises the steps of matching the idle probability of the channel with the task urgency of the unmanned aerial vehicle and the distance between the unmanned aerial vehicle and the control center, namely allocating the channel with the maximum idle probability to the unmanned aerial vehicle with the most urgent or farthest task, allocating the channel with the second idle probability to the unmanned aerial vehicle with the second important or second distant task, and so on until the channel allocation is finished.
The channel optimization distribution model is constructed based on a machine learning algorithm, and can be trained by using received historical spectrum sensing data, and the adopted machine learning algorithm comprises a reverse transmission neural network algorithm.
And substituting the frequency spectrum sensing data acquired in real time and the correlation information between the time and the channel obtained by analysis into the trained channel optimization distribution model, performing prediction analysis on the idle frequency spectrum and the channel, distributing the information with the maximum idle probability to all the unmanned aerial vehicles according to the prediction result, and sending the obtained channel distribution information to each unmanned aerial vehicle through a data transmission radio station.
For example, the channel optimization allocation model is constructed based on a back propagation neural network algorithm, and comprises a first layer neural network and a second layer neural network which are connected with each other.
The first layer of neural network is used for performing parallel training on input vectors of a time domain and a frequency domain to obtain a time domain training result and a frequency domain training result, the second layer of neural network is used for integrating the time domain training result and the frequency domain training result of the first layer of neural network by combining the correlation of the time domain and the frequency domain of a channel, an idle frequency spectrum or the channel is predicted, and the prediction result is the idle probability of each channel.
S6: and each unmanned aerial vehicle in the flight state receives the channel allocation information and automatically switches the respective transmission channel to the optimally allocated channel.
The unmanned aerial vehicle receives the channel allocation information and the remote control information (as feedback to the telemetering information) returned by the ground control and data processing center, and automatically switches to the idle channel for optimized allocation, so that the interference channel is avoided, and the continuous and uninterrupted transmission of the image transmission information is ensured.
With reference to fig. 2, the invention provides an unmanned aerial vehicle channel optimization allocation system based on spectrum cognition, which includes an unmanned aerial vehicle and a ground control and data processing center.
Unmanned aerial vehicle includes the unmanned aerial vehicle body to and carry on first spectrum sensing module, first data processing module, first GPS module, remote control telemetering measurement module, first Wifi module and the first digital radio station on the unmanned aerial vehicle body.
The first data processing module is connected with the first spectrum sensing module, the first GPS module, the first remote control and telemetry module, the first Wifi module and the first data transmission radio module respectively.
The first frequency spectrum sensing module is used for monitoring and sensing the frequency spectrum of the current used frequency band of the unmanned aerial vehicle to obtain corresponding frequency domain power spectrum data; the first data processing module is used for processing the received frequency domain power spectrum data, obtaining channel state information of the unmanned aerial vehicle after quantization, and sending the quantization result back to the ground control and data processing center through the first data transmission radio module.
The first GPS module is used for collecting position and speed information of the unmanned aerial vehicle in real time/periodically, the remote control and telemetry module is used for collecting state information of the unmanned aerial vehicle in real time/periodically, and the first data processing module integrates the collection results of the first GPS module and the first remote control and telemetry module into telemetry information, adds the telemetry information into a frequency spectrum sensing data frame and transmits the telemetry information back to the ground control and data processing center.
The ground control and data processing center comprises a second data processing module, and a second spectrum sensing module, a second GPS module, a second Wifi module, a second data transmission station and a channel optimization distribution module which are connected with the second data processing module.
A data transmission channel is established between the second data transmission radio station and the first data transmission radio station of each unmanned aerial vehicle, spectrum sensing data frames sent by all the first data transmission radio stations are received, and the received spectrum sensing data frames are sent to the second data processing module.
The second frequency spectrum sensing module is used for monitoring and sensing the frequency spectrum of the current used frequency band of the ground unmanned aerial vehicle to obtain corresponding frequency domain power spectrum data.
The second data processing module receives frequency domain power spectrum data of the ground unmanned aerial vehicle fed back by frequency spectrum sensing data frames sent by all unmanned aerial vehicles and the second frequency spectrum sensing module, analyzes the frequency domain power spectrum data to obtain channel state information and telemetering information of each unmanned aerial vehicle, continuously processes the telemetering information to obtain corresponding remote control information, and simultaneously sends the channel state information of each unmanned aerial vehicle to the channel optimization distribution module, the channel optimization distribution module adopts the unmanned aerial vehicle channel optimization distribution calculation based on frequency spectrum cognition to obtain an optimal channel corresponding to each unmanned aerial vehicle, and the calculation result is fed back to the second data processing module.
The second data processing module transmits the channel distribution information and the remote control information back to each unmanned aerial vehicle through the second data transmission radio station, so that the unmanned aerial vehicle automatically switches channels of the first Wifi module and the first data transmission radio station according to the received channel distribution information, and drives the remote control and remote measurement module to execute flight control on the unmanned aerial vehicle according to the received remote control information.
A data transmission channel is established between the second Wifi module and the first Wifi module of each unmanned aerial vehicle, and image/video information sent by all the unmanned aerial vehicles through the first Wifi modules is received.
And the second GPS module is used for acquiring the position and speed information of the ground control and data processing center in real time/periodically and transmitting the acquisition result and the channel allocation information to the unmanned aerial vehicle.
Preferably, the channel optimization allocation module includes a spectrum analysis unit and a spectrum prediction and channel allocation unit.
The frequency spectrum analysis unit is used for processing frequency domain power spectrum data acquired in real time and calculating correlation degree information between time and channels. The frequency spectrum prediction and channel allocation unit is used for predicting the idle frequency spectrum or the channel by combining frequency domain power spectrum data and correlation degree information between time and the channel, selecting a certain amount of channels with the maximum idle probability according to a prediction result, and allocating corresponding optimal channels to each unmanned aerial vehicle in a flight state according to a preset allocation principle.
Although the present invention has been described with reference to the preferred embodiments, it is not intended to be limited thereto. Those skilled in the art can make various changes and modifications without departing from the spirit and scope of the invention. Therefore, the protection scope of the present invention should be determined by the appended claims.

Claims (8)

1.一种基于频谱认知的无人机信道优化分配方法，其特征在于，所述优化分配方法包括：1. a UAV channel optimization allocation method based on spectrum cognition, is characterized in that, described optimal allocation method comprises: S1：将每个处于飞行状态的无人机作为一个频谱感知监测节点，针对所述每个处于飞行状态的无人机使用的每个工作频段进行频谱扫描和监测感知，得到对应的频域功率谱数据；S1: Take each UAV in flight as a spectrum sensing monitoring node, perform spectrum scanning and monitoring and sensing for each working frequency band used by each UAV in flight, and obtain the corresponding frequency domain power spectral data; S2：每个频谱感知监测节点将各自的频域功率谱数据进行量化，得到每个处于飞行状态的无人机的信道状态信息；S2: Each spectrum sensing monitoring node quantifies its own frequency domain power spectrum data to obtain the channel state information of each UAV in flight state; 其中，所述得到每个处于飞行状态的无人机的信道状态信息的过程包括以下步骤：Wherein, the process of obtaining the channel state information of each UAV in the flying state includes the following steps: 设所述每个处于飞行状态的无人机的信道状态信息为CSI(t,c)：Let the channel state information of each UAV in flight state be CSI(t,c):
Figure FDA0003551827470000011
Figure FDA0003551827470000011
 其中，“0”表示信道处于空闲状态，“1”表示信道处于被占用状态，R(t,c)为t采样时刻、信道c的功率值，单位dBm，T为时长总数，C为信道总数；Among them, "0" indicates that the channel is in an idle state, "1" indicates that the channel is in an occupied state, R(t,c) is the power value of the channel c at the t sampling time, in dBm, T is the total number of durations, and C is the total number of channels ; S3：每个频谱感知监测节点采用数传电台将各自的频域功率谱数据回传至地面控制与数据处理中心；S3: Each spectrum sensing monitoring node transmits its own frequency domain power spectrum data back to the ground control and data processing center using a digital radio; S4：地面控制与数据处理中心汇总全部频谱感知监测节点回传的频域功率谱数据，并计算时间和信道间的相关度；S4: The ground control and data processing center summarizes the frequency domain power spectrum data returned by all spectrum sensing monitoring nodes, and calculates the correlation between time and channels; 所述计算时间和信道间的相关度的过程包括以下步骤：The process of calculating the correlation between time and channels includes the following steps: S41，设Xk、Yk为两个信道状态信息序列，且每个信道状态信息序列均为0-1序列；S41, set X k and Y k to be two channel state information sequences, and each channel state information sequence is a 0-1 sequence; S42，根据下述公式计算得到Xk、Yk的相关度ρ：S42, calculate the correlation ρ of X k and Y k according to the following formula:
Figure FDA0003551827470000012
Figure FDA0003551827470000012
 其中，I(A)为判断函数，若A为真，I(A)＝1，若A不为真，I(A)＝0，∑k为累加求和计算；Among them, I(A) is the judgment function, if A is true, I(A)=1, if A is not true, I(A)=0, ∑ k is the cumulative sum calculation; S5：将实时获取的频域功率谱数据以及计算得到的时间和信道间的相关度信息导入预先训练好的信道优化分配模型，对空闲频谱或信道进行预测，并根据预测结果选择一定量空闲概率最大的信道，按照预设的分配原则为每个处于飞行状态的无人机分配对应的最优信道，将信道分配信息通过数传电台回传至每个处于飞行状态的无人机；S5: Import the frequency domain power spectrum data obtained in real time and the calculated correlation information between time and channels into the pre-trained channel optimization allocation model, predict the idle spectrum or channel, and select a certain amount of idle probability according to the prediction result The largest channel, according to the preset allocation principle, allocates the corresponding optimal channel for each UAV in flight state, and transmits the channel allocation information back to each UAV in flight state through the data transmission radio; S6：每个处于飞行状态的无人机接收信道分配信息，自动将各自的传输信道切换至优化分配的信道。S6: Each UAV in the flying state receives the channel allocation information, and automatically switches its respective transmission channel to the optimally allocated channel. 2.根据权利要求1所述的基于频谱认知的无人机信道优化分配方法，其特征在于，所述每个处于飞行状态的无人机上同时搭载有数传电台和Wifi模块，所述无人机采用数传电台传输遥控遥测信息，采用Wifi模块传输图像/视频信息。2. The spectrum cognition-based UAV channel optimization allocation method according to claim 1, wherein each UAV in a flying state is equipped with a digital radio station and a Wifi module simultaneously, and the unmanned aerial vehicle is The machine uses digital radio to transmit remote control telemetry information, and uses Wifi module to transmit image/video information. 3.根据权利要求2所述的基于频谱认知的无人机信道优化分配方法，其特征在于，所述遥控遥测信息传输所占用的频段包括840.5-845MHz无人机专用频段，所述图像/视频信息传输所占用的频段包括2.4GHz和5GHz两个频段。3. The spectrum cognition-based UAV channel optimization allocation method according to claim 2, wherein the frequency band occupied by the remote control and telemetry information transmission comprises an 840.5-845MHz UAV dedicated frequency band, and the image/ The frequency bands occupied by video information transmission include two frequency bands, 2.4GHz and 5GHz. 4.根据权利要求1所述的基于频谱认知的无人机信道优化分配方法，其特征在于，步骤S5中，所述预设的分配原则包括按照信道空闲概率的大小与无人机任务紧急程度，以及无人机离开控制中心的距离远近进行匹配，即空闲概率最大的信道分配给任务最紧急或最远的无人机，空闲概率次之的信道分配给任务次重要或距离次远的无人机。4. The UAV channel optimization allocation method based on spectrum cognition according to claim 1, is characterized in that, in step S5, described preset distribution principle comprises according to the size of channel idle probability and UAV task urgency The degree and the distance of the UAV from the control center are matched, that is, the channel with the highest idle probability is assigned to the UAV with the most urgent or farthest mission, and the channel with the next most important idle probability is assigned to the mission with the second most important or farthest distance. drone. 5.根据权利要求1所述的基于频谱认知的无人机信道优化分配方法，其特征在于，所述信道优化分配模型基于反向传播神经网络算法构建，包括相互连接的第一层神经网络和第二层神经网络；5. The UAV channel optimization allocation method based on spectrum cognition according to claim 1, is characterized in that, described channel optimization allocation model is constructed based on back-propagation neural network algorithm, comprises the first layer neural network connected with each other and the second layer of neural network; 所述第一层神经网络用于对时域及频域的输入向量进行并行训练，得到时域训练结果和频域训练结果，所述第二层神经网络用于结合信道时域和频域的相关性整合第一层神经网络的时域训练结果和频域训练结果，对空闲频谱或信道进行预测，预测结果为每个信道的空闲概率。The first layer of neural network is used to perform parallel training on the input vectors in the time domain and frequency domain to obtain the time domain training results and frequency domain training results, and the second layer neural network is used to combine the channel time domain and frequency domain training results. The correlation integrates the time domain training results and the frequency domain training results of the first layer of neural network, and predicts the idle spectrum or channel, and the prediction result is the idle probability of each channel. 6.根据权利要求1所述的基于频谱认知的无人机信道优化分配方法，其特征在于，所述优化分配方法还包括：6. The UAV channel optimal allocation method based on spectrum cognition according to claim 1, is characterized in that, described optimal allocation method also comprises: 无人机实时/周期性采集遥测信息，将遥测信息加入至频谱感知数据帧，回传至地面控制与数据处理中心，所述遥测信息包括：无人机的地理位置、速度、加速度、自身状态信息和采集时间戳；The UAV collects telemetry information in real time/periodically, adds the telemetry information to the spectrum sensing data frame, and transmits it back to the ground control and data processing center. The telemetry information includes: the UAV’s geographic location, speed, acceleration, and its own state Information and collection timestamps; 地面控制与数据处理中心对遥测信息进行处理，计算得到对应的遥控信息，将计算得到的遥控信息与信道分配信息一起通过数传电台回传至每个处于飞行状态的无人机。The ground control and data processing center processes the telemetry information, calculates the corresponding remote control information, and transmits the calculated remote control information together with the channel allocation information to each UAV in flight through the digital radio. 7.一种基于频谱认知的无人机信道优化分配系统，其特征在于，所述无人机信道优化分配系统包括地面控制与数据处理中心和至少一个处于飞行状态的无人机；7. A UAV channel optimization distribution system based on spectrum cognition, is characterized in that, described UAV channel optimization distribution system comprises ground control and data processing center and at least one UAV in flight state; 所述无人机包括无人机本体，以及搭载在无人机本体上的第一频谱感知模块、第一数据处理模块、第一GPS模块、遥控遥测模块、第一Wifi模块和第一数传电台；The drone includes a drone body, and a first spectrum sensing module, a first data processing module, a first GPS module, a remote control telemetry module, a first Wifi module, and a first data transmission module mounted on the drone body. radio; 所述第一数据处理模块与第一频谱感知模块、第一GPS模块、第一遥控遥测模块、第一Wifi模块和第一数传电台模块分别连接；The first data processing module is respectively connected with the first spectrum sensing module, the first GPS module, the first remote control telemetry module, the first Wifi module and the first digital radio module; 所述第一频谱感知模块用于对所属无人机当前使用频段频谱进行监测和感知，得到对应的频域功率谱数据；所述第一数据处理模块用于处理接收到的频域功率谱数据，量化后得到所属无人机的信道状态信息，将量化结果通过第一数传电台模块发送回地面控制与数据处理中心；The first spectrum sensing module is used for monitoring and sensing the frequency band spectrum currently used by the affiliated UAV to obtain corresponding frequency-domain power spectrum data; the first data processing module is used for processing the received frequency-domain power spectrum data , obtain the channel status information of the UAV after quantization, and send the quantization result back to the ground control and data processing center through the first digital radio module; 所述第一GPS模块用于实时/周期性采集所属无人机的位置和速度信息，所述遥控遥测模块用于实时/周期性采集所属无人机的状态信息，所述第一数据处理模块将第一GPS模块和第一遥控遥测模块的采集结果整合成遥测信息，加入至频谱感知数据帧，回传至地面控制与数据处理中心；The first GPS module is used for real-time/periodic collection of the position and speed information of the UAV, the remote control telemetry module is used for real-time/periodic collection of the state information of the UAV, the first data processing module Integrate the collection results of the first GPS module and the first remote control telemetry module into telemetry information, add it to the spectrum sensing data frame, and send it back to the ground control and data processing center; 所述地面控制与数据处理中心包括第二数据处理模块，以及与第二数据处理模块连接的第二频谱感知模块、第二GPS模块、第二Wifi模块、第二数传电台和信道优化分配模块；The ground control and data processing center includes a second data processing module, and a second spectrum sensing module, a second GPS module, a second Wifi module, a second data transmission station, and a channel optimization allocation module connected to the second data processing module ; 所述第二数传电台与每个无人机的第一数传电台之间建立有数据传输通道，接收所有第一数传电台发送的频谱感知数据帧，将接收到的频谱感知数据帧发送至第二数据处理模块；A data transmission channel is established between the second data transmission station and the first data transmission station of each drone, and the spectrum sensing data frames sent by all the first data transmission stations are received, and the received spectrum sensing data frames are sent. to the second data processing module; 所述第二频谱感知模块用于对地面无人机当前使用频段频谱进行监测和感知，得到对应的频域功率谱数据；The second spectrum sensing module is used for monitoring and sensing the frequency spectrum currently used by the ground UAV to obtain corresponding frequency domain power spectrum data; 所述第二数据处理模块接收所有无人机发送的频谱感知数据帧和第二频谱感知模块反馈的地面无人机的频域功率谱数据，解析得到每个无人机的信道状态信息和遥测信息，对遥测信息继续处理得到对应的遥控信息，同时将每个无人机的信道状态信息发送至信道优化分配模块，所述信道优化分配模块采用如权利要求1-6任意一项中所述的基于频谱认知的无人机信道优化分配方法 计算得到每个无人机对应的最优信道，将计算结果反馈至第二数据处理模块；The second data processing module receives the spectrum sensing data frames sent by all the drones and the frequency domain power spectrum data of the ground drones fed back by the second spectrum sensing module, and analyzes to obtain the channel state information and telemetry of each drone. information, continue to process the telemetry information to obtain the corresponding remote control information, and at the same time send the channel state information of each UAV to the channel optimization allocation module, the channel optimization allocation module adopts the method described in any one of claims 1-6. The spectrum cognition-based UAV channel optimization allocation method calculates the optimal channel corresponding to each UAV, and feeds back the calculation result to the second data processing module; 所述第二数据处理模块将信道分配信息和遥控信息通过第二数传电台回传至每个无人机，使无人机根据接收到的信道分配信息自动切换第一Wifi模块和第一数传电台的信道，以及驱使遥控遥测模块根据接收到的遥控信息对无人机执行飞行控制；The second data processing module transmits the channel allocation information and the remote control information back to each drone through the second data transmission radio, so that the drone automatically switches the first Wifi module and the first data module according to the received channel allocation information. transmit the channel of the radio station, and drive the remote control telemetry module to perform flight control on the UAV according to the received remote control information; 所述第二Wifi模块与每个无人机的第一Wifi模块之间建立有数据传输通道，接收所有无人机通过第一Wifi模块发送的图像/视频信息；A data transmission channel is established between the second Wifi module and the first Wifi module of each drone to receive image/video information sent by all drones through the first Wifi module; 所述第二GPS模块用于实时/周期性采集地面控制与数据处理中心的位置和速度信息，将采集结果与信道分配信息一起发送至无人机。The second GPS module is used for real-time/periodic collection of the position and speed information of the ground control and data processing center, and sends the collection result together with the channel allocation information to the UAV. 8.根据权利要求7所述的基于频谱认知的无人机信道优化分配系统，其特征在于，所述信道优化分配模块包括频谱分析单元、频谱预测与信道分配单元；8. The UAV channel optimization distribution system based on spectrum cognition according to claim 7, wherein the channel optimization distribution module comprises a spectrum analysis unit, a spectrum prediction and a channel distribution unit; 所述频谱分析单元用于对实时获取的频域功率谱数据进行处理，计算得到的时间和信道间的相关度信息；The spectrum analysis unit is used to process the frequency domain power spectrum data acquired in real time, and calculate the correlation information between time and channels; 所述频谱预测与信道分配单元用于结合频域功率谱数据和时间和信道间的相关度信息，对空闲频谱或信道进行预测，并根据预测结果选择一定量空闲概率最大的信道，按照预设的分配原则为每个处于飞行状态的无人机分配对应的最优信道。The spectrum prediction and channel allocation unit is used for combining frequency domain power spectrum data and correlation information between time and channels to predict idle frequency spectrum or channel, and select a certain number of channels with the largest idle probability according to the prediction result, according to the preset The allocation principle is to allocate the corresponding optimal channel for each UAV in flight state.
CN202010510635.1A 2020-06-08 2020-06-08 Method and system for optimal allocation of UAV channel based on spectrum cognition Active CN111884740B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010510635.1A CN111884740B (en) 2020-06-08 2020-06-08 Method and system for optimal allocation of UAV channel based on spectrum cognition

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010510635.1A CN111884740B (en) 2020-06-08 2020-06-08 Method and system for optimal allocation of UAV channel based on spectrum cognition

Publications (2)

Publication Number Publication Date
CN111884740A CN111884740A (en) 2020-11-03
CN111884740B true CN111884740B (en) 2022-04-29

Family

ID=73154368

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010510635.1A Active CN111884740B (en) 2020-06-08 2020-06-08 Method and system for optimal allocation of UAV channel based on spectrum cognition

Country Status (1)

Country Link
CN (1) CN111884740B (en)

Families Citing this family (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112423304B (en) * 2020-11-06 2021-11-16 北京隆普智能科技有限公司 Multi-unmanned aerial vehicle scheduling communication frequency band allocation method and system
CN114189903B (en) * 2020-12-23 2025-06-06 技象科技(南京)有限公司 Channel allocation method, device, system and storage medium based on channel status
CN113301654B (en) * 2021-04-12 2022-06-14 吉林大学 Unmanned aerial vehicle communication frequency band distribution system and method based on semi-supervised learning algorithm
CN113347638B (en) * 2021-05-14 2024-04-30 东北大学 A dynamic collaborative spectrum prediction and perception method for cognitive industrial Internet of Things
CN114143890B (en) * 2022-02-07 2022-04-15 南京信息工程大学 Method and system for optimizing transmission power in unmanned aerial vehicle communication based on overlapping channels
CN114867029B (en) * 2022-05-07 2024-05-17 中国人民解放军国防科技大学 Unmanned aerial vehicle group dynamic spectrum allocation method and system for malicious interference
CN115297549B (en) * 2022-06-22 2024-06-14 广西大学 UAV network spectrum management method and system based on blockchain
CN116633368B (en) * 2023-06-12 2026-01-02 深圳市边界智控科技有限公司 Redundant radio communication control device and flight system
CN116938567B (en) * 2023-07-25 2024-03-08 云擎智能科技有限公司 Computer network data safety transmission method, device, equipment and medium
CN120129008B (en) * 2025-05-15 2025-07-22 南京拓恒无人系统研究院有限公司 Image transmission separation intelligent channel switching evaluation system and method based on interference analysis
CN120915951A (en) * 2025-10-10 2025-11-07 齐芯频顺半导体(杭州)有限公司 Video optimization method and system based on wireless transmission

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108712747A (en) * 2018-03-29 2018-10-26 中国人民解放军陆军工程大学 Quick link establishment method based on spectrum prediction

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9641239B2 (en) * 2012-06-22 2017-05-02 Fitbit, Inc. Adaptive data transfer using bluetooth
CN107204107B (en) * 2017-04-21 2020-05-08 杭州昊舜视讯科技有限公司 Method and system for transmitting frequency spectrum in real time through unmanned aerial vehicle
CN108134967B (en) * 2017-11-27 2022-06-07 全球能源互联网研究院有限公司 Power optical network routing frequency spectrum distribution method and system
CN107992029A (en) * 2017-12-15 2018-05-04 中国电子产品可靠性与环境试验研究所 Unmanned plane device for detecting performance based on status monitoring
CN108135002B (en) * 2017-12-22 2021-12-21 南京航空航天大学 Unmanned aerial vehicle frequency spectrum resource allocation method based on block coordinate reduction
CN108333584A (en) * 2017-12-28 2018-07-27 陕西弘毅军民融合智能科技有限公司 A kind of remote unmanned plane detection system of low altitude small target and detection method
US20190235047A1 (en) * 2018-01-26 2019-08-01 Easymap Digital Technology Inc. Unmanned aerial vehicle detection system and detection method
CN109039502A (en) * 2018-09-04 2018-12-18 中国人民解放军陆军工程大学 Channel selection method based on spectrum prediction and perception fusion
CN109245840B (en) * 2018-10-15 2021-02-02 哈尔滨工业大学 Spectrum prediction method based on convolutional neural network in cognitive radio system
CN109614930A (en) * 2018-12-11 2019-04-12 湖南华诺星空电子技术有限公司 A UAV spectrum detection method based on deep learning
CN109743210B (en) * 2019-01-25 2020-04-17 电子科技大学 Unmanned aerial vehicle network multi-user access control method based on deep reinforcement learning

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108712747A (en) * 2018-03-29 2018-10-26 中国人民解放军陆军工程大学 Quick link establishment method based on spectrum prediction

Also Published As

Publication number Publication date
CN111884740A (en) 2020-11-03

Similar Documents

Publication Publication Date Title
CN111884740B (en) Method and system for optimal allocation of UAV channel based on spectrum cognition
Xiao et al. UAV anti-jamming video transmissions with QoE guarantee: A reinforcement learning-based approach
CN110839184B (en) Method and device for bandwidth adjustment of mobile fronthaul optical network based on traffic prediction
US11108993B2 (en) Predictive network management for real-time video with varying video and network conditions
KR20230131923A (en) Sensing and Joint Adaptive Frame Selection for Sensing and Communication Applications
EP3491793B1 (en) System and method for resource-aware and time-critical iot frameworks
CN113271221A (en) Network capacity opening method and system and electronic equipment
Sansoy et al. Spectrum sensing algorithms in Cognitive Radio: A survey
CN113922899A (en) Spectrum sensing access method based on neural network and Welch transformation
KR20220111111A (en) System and method for processing super-resolution images based on deep learning and computer program for the same
CN113301654B (en) Unmanned aerial vehicle communication frequency band distribution system and method based on semi-supervised learning algorithm
Gupta et al. Resource orchestration in network slicing using GAN-based distributional deep Q-network for industrial applications: RK Gupta et al.
Shinkuma et al. Data assessment and prioritization in mobile networks for real-time prediction of spatial information with machine learning
CN116567843A (en) Wireless resource allocation optimization device and method
Cho et al. Scalable multi-modal learning for cross-link channel prediction in massive IoT networks
Baidya et al. Content-aware cognitive interference control for urban IoT systems
Colonnese et al. QoE-aware UAV flight path design for mobile video streaming in HetNet
US20250056372A1 (en) Method, apparatus and system for managing network resources
CN120391039A (en) Method and apparatus for wireless communication
Xu Gradient-free scheduling of fog computation for marine data feedback
Martini et al. Challenges and perspectives in neuromorphic-based visual IoT systems and networks
CN117607636A (en) Multi-spectral fusion integrated sensing, storage and computing high-voltage discharge detection method
CN119172768A (en) Automatic monitoring method, network management device and storage medium of radio frequency board
CN109450534B (en) Visible light wireless local area network based on image sensor
RU2855297C1 (en) Method for adaptation of radio system of aviation robotic device to cognitively formed request of operator

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