CN115665759A - Auxiliary wireless safety communication transmission method based on UAV-RIS - Google Patents
Auxiliary wireless safety communication transmission method based on UAV-RIS Download PDFInfo
- Publication number
- CN115665759A CN115665759A CN202211305933.2A CN202211305933A CN115665759A CN 115665759 A CN115665759 A CN 115665759A CN 202211305933 A CN202211305933 A CN 202211305933A CN 115665759 A CN115665759 A CN 115665759A
- Authority
- CN
- China
- Prior art keywords
- ris
- aerial vehicle
- unmanned aerial
- uav
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000004891 communication Methods 0.000 title claims abstract description 33
- 230000005540 biological transmission Effects 0.000 title claims abstract description 21
- 238000012549 training Methods 0.000 claims abstract description 17
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 14
- 238000005457 optimization Methods 0.000 claims abstract description 10
- 230000009471 action Effects 0.000 claims abstract description 8
- 230000008569 process Effects 0.000 claims abstract description 6
- 230000010363 phase shift Effects 0.000 claims description 21
- 238000004364 calculation method Methods 0.000 claims description 10
- 230000006870 function Effects 0.000 claims description 10
- 239000011159 matrix material Substances 0.000 claims description 9
- 230000007704 transition Effects 0.000 claims description 6
- 238000004088 simulation Methods 0.000 claims description 5
- 239000003795 chemical substances by application Substances 0.000 claims description 4
- 230000007423 decrease Effects 0.000 claims description 3
- 230000001419 dependent effect Effects 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 238000012546 transfer Methods 0.000 claims 2
- 238000013507 mapping Methods 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000005265 energy consumption Methods 0.000 description 2
- 230000002708 enhancing effect Effects 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002401 inhibitory effect Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Mobile Radio Communication Systems (AREA)
Abstract
The invention relates to an auxiliary wireless security communication transmission method based on UAV-RIS, which mainly comprises a modeling process and a training iteration process, wherein the modeling process mainly converts a track optimization problem in a double-unmanned aerial vehicle mobile system model consisting of a ground Base Station (BS), single-antenna User Equipment (UE), a single-antenna eavesdropper (Eve) and the RIS on an unmanned aerial vehicle into a Markov decision problem model, the training iteration process mainly adopts a DQN algorithm as a solving model, an achievable rate as an expectation, a state space and an action space as characteristics and a reward and punishment function as a convergence direction for training, so that in the practical application of unmanned aerial vehicle track planning, auxiliary communication and privacy protection are really realized, and the security performance obtained by a wireless system in the practical application is effectively improved.
Description
Technical Field
The invention relates to an auxiliary wireless safety communication transmission method based on a UAV-RIS, belonging to the field of information physical system and physical layer safety.
Background
Today, commercialization of fifth generation (5G) communication networks is becoming increasingly popular. In order to obtain more reliable and faster data transmission, a potential key technology of the sixth generation mobile communication (6G) has received much attention. Among them, reconfigurable Intelligent Surface (RIS) is a 6G wireless communication technology with great potential. The 5G communication technology can generally adapt to changes in the wireless environment, but the nature of the signal is random and largely uncontrollable. The RIS controls the amplitude and the phase of the reflected signal through the controller, so that fine-grained three-dimensional beam forming is cooperatively realized and used for enhancing and offsetting directional signals.
One of the typical applications of RIS is in physical layer assisted secure communication, where legitimate user signals are enhanced by adjusting the phase of the reflected signal, counteracting eavesdropping, and thereby reducing information leakage. In the prior art, the RIS is used for enhancing the required signals, inhibiting the unnecessary signals, and designing the emission beam forming of a multi-antenna access point and the reflection beam forming of the RIS in a combined way, thereby improving the secrecy rate of legal users. Yu Xianghao et al jointly optimize the beamforming and phase shift of the transmitter, and further find that large-scale RIS is more effective in improving confidentiality and energy efficiency than enlarging the antenna array size of the transmitter. In the presence of a plurality of single-antenna eavesdroppers and imperfect Channel State Information (CSI) between the RIS and the user, the transmission power is minimized by jointly optimizing the transmitter beam forming, the artificial noise covariance matrix transformation and the RIS phase shift.
On the other hand, the drone assisted communication technology has many applications in the aspect of physical layer security, such as using a friendly interference drone to improve the security performance of a wireless system. Bang xiaoweei et al propose a multi-drone wireless communication system. One drone is used as a relay and the other emits noise to co-interfere with eavesdroppers. The probability of closed secrecy interruption between the unmanned aerial vehicle and the ground node is obtained. Similarly, in the multi-unmanned-aerial-vehicle auxiliary communication system, a plurality of people optimize multi-user communication scheduling and track and power control of the combined unmanned aerial vehicle, so that the minimum throughput is maximized, and the fairness performance among users is realized.
Unmanned aerial vehicle and RIS collaborative promotion wireless communication security have also received extensive attention. Many scholars introduce the RIS constructively into the unmanned aerial vehicle communication network, and the application of the RIS changes the characteristics of the propagation environment, and improves the performance of the wireless communication network. In complex urban scenarios, the high mobility of drones and the adjustability of RIS are used to combat potential eavesdroppers. Notably, most attention is focused on deploying the RIS on the ground. Zhang Qianqiian et al have installed the reconfigurable intelligent surface on unmanned aerial vehicle, optimized the position and the reflection coefficient of UAV-RIS, obtained the biggest downlink transmission ability.
Especially considering the concealment of eavesdroppers, ng Derric et al assume that the CSI of a channel is imperfect and use a deterministic model to describe the uncertainty of the CSI. Xuvian et al chose the maximum eavesdropping probability at the potential eavesdropper location as the worst case to avoid using complex equations to estimate CSI.
To our knowledge, there is currently a lack of research to reduce the probability of eavesdropping using mobile RIS. We piggyback the RIS with drones to solve the challenge of eavesdroppers in complex environments of unknown location. Based on the characteristics of easy integration, low energy consumption and easy deployment of the unmanned aerial vehicle, the unmanned aerial vehicle is used for carrying the RIS, and the safety and the quality of wireless communication are improved. The security of the user is improved by adding the reflected signal to the accuracy of the legitimate user and the destructiveness of the eavesdropper. Therefore, the average downlink reachability can be maximized by jointly optimizing the trajectories of the drones and the phase shift matrix of the RIS.
Disclosure of Invention
The invention aims to reduce the problem of the probability of interception of a legal user by using a mobile RIS. The RIS is piggybacked with a drone to address the challenge of eavesdroppers in complex environments of unknown location. Based on the characteristics of easy integration, low energy consumption and easy deployment of the unmanned aerial vehicle, the unmanned aerial vehicle is used for carrying the RIS, and the safety and the quality of wireless communication are improved. By adding the reflected signal to the forward direction of the legitimate user and the reverse direction of the eavesdropper, the security of the user is improved. Therefore, the average downlink reachability can be maximized by jointly optimizing the trajectories of the drones and the phase shift matrix of the RIS.
The invention adopts the following technical scheme for solving the technical problems: the invention designs an auxiliary wireless security communication transmission method based on UAV-RIS, which comprises the following steps i to vii, obtaining a Markov decision problem model; performing iterative optimization on the DQN algorithm according to the following steps A to E so as to determine the optimal flight planning path of the unmanned aerial vehicle;
simulating a reflection function theta of the RIS unit, wherein the RIS on the unmanned aerial vehicle comprises N reflection units, and theta n And beta n Respectively representing the phase shift reflection coefficient and the amplitude reflection coefficient of the nth unit, wherein j is an optional parameter;
Θ=diag[Θ 1 ,Θ 2 ,…,Θ N ]
simulating path loss for B-R-U (base station-UAV-user) and B-R-E (base station-UAV-eavesdropper)Andwherein,representing the three-dimensional position of the drone at the t-slot,is an abscissa, a variable ρ is a path loss at a reference distance d =1m, α is a loss index, and U, I, E, B represents a user, an unmanned aerial vehicle, an eavesdropper, and a base station, respectively;
step iii. For direct links, a distance dependent path loss model L is simulated BU K is a path loss index;
simulating the received signal-to-noise ratio γ and the rate R of U, E using steps i-iii, where p is the transmit power of B, σ 2 Is the variance of the noise, H BI And h IU Channels, h, representing BS-RIS link and RIS-UE link, respectively BU 、h BE And h IE Respectively representing channels of BS-UE, BS-Eve and RIS-Eve links;
step v, aiming at worst track situation, simulating average descending reachable rateWherein N is t Representing the total number of time slots of the time period T, (Deltax) E ,Δy E ) Representing an estimation error;
step vi, constructing a phase shift matrix and an unmanned aerial vehicle track optimization model;
max qU,Θ R down
0≤θ n <2π
0≤β n ≤1.
step vii, converting the phase shift matrix and the unmanned aerial vehicle track optimization model in the step vi into a Markov decision model;
step A, randomly initializing Q network parameters;
step B, the new state s is obtained by the interactive calculation of DQN and state space (phase shift of RIS and position of RIS) t+1 ,
The state space is mainly measured by the phase shift of each reflection unit at time slot tAnd the two-dimensional position of UAV-RIS at t-slotForming;
and C, carrying out iterative training on the network parameters mentioned in the step A by an empirical playback training method to obtain an optimal model QT, and assuming that the playback memory is D, the size of the small batch is n and the learning rate is alpha, the main flow of the empirical playback training method in the step C is as follows:
step C-1: initializing replay memory D, Q-network weight omega, target network weight omega * ,Q(s,a);
Step C-2: selecting an action a with a probability epsilon t ;
Step C-3: calculating the prize r by the prize function t ;
Step C-4: jump to new state s t+1 ;
Step C-5: storage transition(s) t ,a t ,r t ,s t+1 ) And randomly sampling transitions(s) from D i ,a i ,r i ,s′ i ) i∈n ;
step C-8: and repeating the steps C-2 to C-7 until the cycle is ended.
The reward function in the experience playback training method is determined by the downlink average privacy ratio, and the calculation formula is as follows:
wherein when the algorithm performs an action to increase the average privacy rate, it gives the agent a positive reward; if the average privacy rate decreases, the reward is negative.
Step D, obtaining a maximum Q value by using QT prediction;
step E, calculating the optimal motion space by using the Q value mapping and updating the phase shift of the RIS and the position of the RIS in the step B, wherein the motion space is mainly composed of variable quantities of the phase shift value of the reflecting unitAnd slot motion vector distanceThe calculation formula is as follows:
where t represents the several time slots.
And F, repeating the steps A-E to determine the optimal planning path for the unmanned aerial vehicle to fly.
The invention has the beneficial effects that:
compared with the prior art, the auxiliary wireless safety communication transmission method based on the UAV-RIS has the following technical effects by adopting the technical scheme:
the invention designs an auxiliary wireless security communication transmission method based on a UAV-RIS, which is characterized in that a Markov decision problem model is formed based on a ground Base Station (BS), a single-antenna User Equipment (UE), a single-antenna eavesdropper (Eve) and the RIS on an unmanned aerial vehicle, and the Markov decision problem is solved by carrying out DQN model training with the reachable rate as an expectation, a state space and an action space as characteristics and a reward and punishment function as a convergence direction to obtain an optimal decision path. Thus, the RIS which is deployed in the past in a building is arranged on the unmanned aerial vehicle, and the position and the phase shift of the unmanned aerial vehicle can be adjusted more flexibly and effectively by utilizing the quick mobility of the unmanned aerial vehicle. Compared with the prior method for assisting the legal user by using the RIS, the invention designs an auxiliary wireless secure communication transmission method based on the UAV-RIS, which utilizes the RIS to add the reflected signal with the forward direction of the legal user and add the reverse direction of the eavesdropper, thereby maximizing the downlink reachable rate.
Drawings
FIG. 1 is a schematic diagram of a system model in the transmission method of the invention for auxiliary wireless security communication based on UAV-RIS;
FIG. 2 is a flow chart of DQN algorithm in the transmission method of auxiliary wireless security communication based on UAV-RIS designed by the present invention;
FIG. 3 is a simulation diagram of the convergence of DQN algorithm in the transmission method of the invention based on UAV-RIS for assisting wireless secure communication;
FIG. 4 is a diagram of a UAV simulation trajectory in the UAV-RIS based assisted wireless secure communication transmission method of the present invention;
FIG. 5 is an experimental diagram of simulation reachable rate in the transmission method of assisted wireless secure communication based on UAV-RIS according to the present invention;
Detailed Description
The following description will explain embodiments of the present invention in further detail with reference to the accompanying drawings.
The invention designs an auxiliary wireless security communication transmission method based on UAV-RIS, in practical application, aiming at a system model shown in figure 1, the following steps i to vii are executed to obtain a Markov decision problem model;
simulating a reflection function theta of the RIS unit, wherein the RIS on the unmanned aerial vehicle comprises N reflection units, and theta n And beta n Respectively representing the phase shift reflection coefficient and the amplitude reflection coefficient of the nth unit, wherein j is an optional parameter;
Θ=diag[Θ 1 ,Θ 2 ,…,Θ N ]
simulating path loss for B-R-U (base station-UAV-user) and B-R-E (base station-UAV-eavesdropper)Andwherein,representing the three-dimensional position of the drone at the t-slot,is an abscissa, a variable ρ is a path loss at a reference distance d =1m, α is a loss index, and U, I, E, B represents a user, an unmanned aerial vehicle, an eavesdropper, and a base station, respectively;
step iii. For direct links, a distance dependent path loss model L is simulated BU K is a path loss index;
simulating the received signal-to-noise ratio γ and the rate R of U, E using steps i-iii, where p is the transmit power of B, σ 2 Is the variance of the noise, H BI And h IU Channels, h, representing BS-RIS link and RIS-UE link respectively BU 、h BE And h IE Respectively representing channels of BS-UE, BS-Eve and RIS-Eve links;
step v, aiming at worst track situation, simulating average descending reachable rateWherein N is t Representing the total number of time slots of the time period T, (Deltax) E ,Δy E ) Representing an estimation error;
step vi, constructing a phase shift matrix and an unmanned aerial vehicle track optimization model;
max qU,Θ R down
0≤θ n <2π
0≤β n ≤1.
and step vii, converting the phase shift matrix and the unmanned aerial vehicle track optimization model in the step vi into a Markov decision model.
After the Markov decision model is obtained, in practical application, as shown in a DQN algorithm flow chart of FIG. 2, carrying out iterative optimization on the DQN algorithm according to the following steps A to E so as to determine an optimal planning path for unmanned aerial vehicle flight;
step A, randomly initializing Q network parameters;
step B, the new state s is obtained by the interactive calculation of DQN and state space (phase shift of RIS and position of RIS) t+1 ,
The state space is mainly measured by the phase shift of each reflection unit at time slot tAnd the two-dimensional position of UAV-RIS at t-slotForming;
and C, carrying out iterative training on the network parameters mentioned in the step A by an empirical playback training method to obtain an optimal model QT, and assuming that the playback memory is D, the size of the small batch is n and the learning rate is alpha, the main flow of the empirical playback training method in the step C is as follows:
step C-1: initializing replay memory D, Q-network weight omega, target network weight omega * ,Q(s,a);
Step C-2 selecting action a with probability epsilon t ;
Step C-3: calculating the reward r through the reward function t ;
Step C-4: jump to new state s t+1 ;
Step C-5: storage transition(s) t ,a t ,r t ,s t+1 ) And randomly sampling transitions(s) from D i ,a i ,r i ,s′ i ) i∈n ;
step C-8: and repeating the steps C-2 to C-7 until the cycle is ended.
The reward function in the experience playback training method is determined by the downlink average privacy ratio, and the calculation formula is as follows:
wherein when the algorithm performs an action to increase the average privacy rate, it gives the agent a positive reward; if the average privacy rate decreases, the reward is negative.
Step D, obtaining a maximum Q value by using QT prediction;
step E, calculating the optimal motion space by using the Q value mapping and updating the phase shift of the RIS and the position of the RIS in the step B, wherein the motion space is mainly composed of variable quantities of the phase shift value of the reflecting unitAnd slot motion vector distanceThe calculation formula is as follows:
where t represents the several time slots.
And F, repeating the steps A-E to determine the optimal planning path for the unmanned aerial vehicle to fly.
Fig. 3 shows the convergence speed of DQN algorithm in UAV-RIS assisted wireless networks. As is evident from the figure, in this envelope the state and motion space is not large enough, which means that the DQN algorithm is more suitable for higher dimensions. Further, when γ =0.9,0.95 and 0.99, there is a large difference in convergence speed. The larger the value of γ, the slower the convergence speed. This is because the higher the γ, the more the agent is interested in the future, which is more difficult than the current time, and therefore the slower the training process.
Fig. 4 shows the trajectory simulation results of the drones, and the trajectories of the drones with RIS assistance and with non-RIS assistance. First, without RIS assistance, the UAV flight length is shorter than with RIS assistance. This means that the introduction of a RIS can significantly reduce the flight length of the drone. Therefore, the RIS can greatly shorten the flight length of the unmanned aerial vehicle, save energy and improve the running time of an unmanned aerial vehicle system.
Fig. 5 shows the variation of the average downlink reachability for both algorithms. It can be seen that the difference in the algorithms affects the convergence speed. The change in average reachability indicates that the RIS equipped drones are able to reach the peak and destination faster.
The digital description of the above results is expressed in real implementation cases as: the RIS which is deployed in the past on the building is arranged on the unmanned aerial vehicle, and the position and the phase shift of the unmanned aerial vehicle can be adjusted more flexibly and effectively by utilizing the rapid mobility of the unmanned aerial vehicle. Compared with the prior method for assisting the legal user by using the RIS, the method uses the RIS to add the reflected signal with the forward direction of the legal user and the reverse direction of the eavesdropper, thereby maximizing the downlink reachable rate.
The embodiments of the present invention have been described in detail with reference to the drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge of those skilled in the art without departing from the gist of the present invention.
Claims (5)
1. An auxiliary wireless security communication transmission method based on UAV-RIS is characterized in that: comprises the following steps i to vii, obtaining a Markov decision problem model; performing iterative optimization on the DQN algorithm according to the following steps A to E so as to solve a Markov decision problem model;
step i. Simulation of the reflection function Θ of the RIS unit,
Θ=diag[Θ 1 ,Θ 2 ,…,Θ N ]
wherein, the RIS on the unmanned aerial vehicle contains N reflection unit, theta n And beta n Respectively representing the phase shift reflection coefficient and the amplitude reflection coefficient of the nth unit, wherein j is an optional parameter;
wherein,representing the three-dimensional position of the drone at the t-slot,is an abscissa, a variable ρ is a path loss at a reference distance d =1m, α is a loss index, and U, I, E, B represents a user, an unmanned aerial vehicle, an eavesdropper, and a base station, respectively;
step iii. For direct links, a distance dependent path loss model L is simulated BU K is a path loss index;
simulating U, E received signal to noise ratio γ and rate R using steps i-iii,
where p is the transmission power of B, σ 2 Is the variance of the noise, H BI And h IU Channels, h, representing BS-RIS link and RIS-UE link respectively BU 、h BE And h IE Respectively representing channels of BS-UE, BS-Eve and RIS-Eve links;
Wherein N is t Representing the total number of time slots of the time period T, (Deltax) E ,Δy E ) Representing an estimation error;
step vi, constructing a phase shift matrix and an unmanned aerial vehicle track optimization model;
max qU,Θ R down
0≤θ n <2π
0≤β n ≤1.
step vii, converting the phase shift matrix and the unmanned aerial vehicle track optimization model in the step vi into a Markov decision model;
step A, randomly initializing Q network parameters;
step B, obtaining a new state s through the mutual calculation of the DQN and the state space t+1 ;
Step C, carrying out iterative training on the network parameters mentioned in the step A by an empirical playback training method to obtain an optimal model QT;
step D, obtaining a maximum Q value by using QT prediction;
step E, calculating the optimal motion space by using the Q value mapping and updating the phase shift of the RIS and the position of the RIS in the step B;
and F, repeating the steps A-E to determine the optimal planning path for the unmanned aerial vehicle to fly.
3. The UAV-RIS based assisted wireless secure communication transfer method of claim 1, wherein: assuming that the replay memory is D, the size of the small batch is n, and the learning rate is α, the main process of the experimental replay training method in step C is as follows:
step C-1: initializing replay memory D, Q-network weight omega, target network weight omega * ,Q(s,a);
Step C-2: selecting an action a with a probability epsilon t ;
Step C-3: calculating the reward r through the reward function t ;
Step C-4: jump to new state s t+1 ;
Step C-5: storage transition(s) t ,a t ,r t ,s t+1 ) And randomly sampling transitions(s) from D i ,a i ,r i ,s′ i ) i∈n ;
Step C-7: random gradient descent calculation was performed:
step C-8: and repeating the steps C-2 to C-7 until the cycle is ended.
4. An auxiliary wireless security communication transmission method based on UAV-RIS as claimed in claim 1, wherein: in the step E, the motion space is phase-shifted by a variable amount of the reflection unitAnd slot motion vector distanceThe calculation formula is as follows:
where t represents the several time slots.
5. The UAV-RIS based assisted wireless secure communication transfer method of claim 1, wherein: the reward function in the experience playback training method is determined by the downlink average privacy ratio, and the calculation formula is as follows:
wherein when the algorithm performs an action to increase the average privacy rate, it gives the agent a positive reward; if the average privacy rate decreases, the positive reward is negative.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211305933.2A CN115665759A (en) | 2022-10-24 | 2022-10-24 | Auxiliary wireless safety communication transmission method based on UAV-RIS |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211305933.2A CN115665759A (en) | 2022-10-24 | 2022-10-24 | Auxiliary wireless safety communication transmission method based on UAV-RIS |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115665759A true CN115665759A (en) | 2023-01-31 |
Family
ID=84992372
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211305933.2A Withdrawn CN115665759A (en) | 2022-10-24 | 2022-10-24 | Auxiliary wireless safety communication transmission method based on UAV-RIS |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115665759A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116449836A (en) * | 2023-04-07 | 2023-07-18 | 北京天坦智能科技有限责任公司 | Reconfigurable intelligent surface-assisted multi-robot system track planning method |
-
2022
- 2022-10-24 CN CN202211305933.2A patent/CN115665759A/en not_active Withdrawn
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116449836A (en) * | 2023-04-07 | 2023-07-18 | 北京天坦智能科技有限责任公司 | Reconfigurable intelligent surface-assisted multi-robot system track planning method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Guo et al. | Learning-based robust and secure transmission for reconfigurable intelligent surface aided millimeter wave UAV communications | |
CN113162679B (en) | DDPG algorithm-based IRS (intelligent resilient software) assisted unmanned aerial vehicle communication joint optimization method | |
CN113489521B (en) | Reflective surface assisted cell-free large-scale MIMO network combined beam forming method | |
CN113472419B (en) | Safe transmission method and system based on space-based reconfigurable intelligent surface | |
Sun et al. | Secure and energy-efficient UAV relay communications exploiting collaborative beamforming | |
CN112968743A (en) | Time-varying de-cellular large-scale MIMO channel modeling method based on visible region division | |
Wang et al. | Joint power and QoE optimization scheme for multi-UAV assisted offloading in mobile computing | |
Zhu et al. | Multi-UAV aided millimeter-wave networks: Positioning, clustering, and beamforming | |
CN113890588B (en) | Unmanned aerial vehicle relay communication method based on virtual array antenna cooperative beam forming | |
CN115665759A (en) | Auxiliary wireless safety communication transmission method based on UAV-RIS | |
Lima et al. | User pairing and power allocation for UAV-NOMA systems based on multi-armed bandit framework | |
Zhao et al. | MADRL-based 3D deployment and user association of cooperative mmWave aerial base stations for capacity enhancement | |
Sun et al. | Leveraging uav-ris reflects to improve the security performance of wireless network systems | |
Mahmood et al. | Deep learning meets swarm intelligence for UAV-assisted IoT coverage in massive MIMO | |
Lan et al. | Blockchain-secured data collection for uav-assisted iot: A ddpg approach | |
Gao et al. | Dynamic role switching scheme with joint trajectory and power control for multi-UAV cooperative secure communication | |
Hua et al. | On sum-rate maximization in downlink UAV-aided RSMA systems | |
Xu et al. | Soft Actor–Critic Based 3-D Deployment and Power Allocation in Cell-Free Unmanned Aerial Vehicle Networks | |
Wang et al. | Uplink data transmission based on collaborative beamforming in UAV-assisted MWSNs | |
Yang et al. | 3D beamforming based on deep learning for secure communication in 5G and beyond wireless networks | |
CN116667890A (en) | Anti-eavesdropping transmission method for honeycomb-removed large-scale MIMO downlink | |
You et al. | Distributed deep learning for RIS aided UAV-D2D communications in space-air-ground networks | |
Lu et al. | Machine learning for predictive deployment of UAVs with multiple access | |
CN115052285A (en) | Unmanned aerial vehicle intelligent reflecting surface safe transmission method based on deep reinforcement learning | |
CN114157392A (en) | Optimization method for safety transmission of distributed IRS auxiliary communication system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20230131 |
|
WW01 | Invention patent application withdrawn after publication |