CN108235423A - Wireless communication anti-eavesdrop jamming power control algolithm based on Q study - Google Patents
Wireless communication anti-eavesdrop jamming power control algolithm based on Q study Download PDFInfo
- Publication number
- CN108235423A CN108235423A CN201711475264.2A CN201711475264A CN108235423A CN 108235423 A CN108235423 A CN 108235423A CN 201711475264 A CN201711475264 A CN 201711475264A CN 108235423 A CN108235423 A CN 108235423A
- Authority
- CN
- China
- Prior art keywords
- jamming power
- time slot
- jammer
- friendly
- power
- 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.)
- Granted
Links
- 230000006854 communication Effects 0.000 title claims abstract description 17
- 238000004891 communication Methods 0.000 title claims abstract description 16
- 230000005540 biological transmission Effects 0.000 claims abstract description 34
- 238000011156 evaluation Methods 0.000 claims abstract description 17
- 230000000694 effects Effects 0.000 claims abstract description 13
- 238000012549 training Methods 0.000 claims abstract description 8
- 230000009471 action Effects 0.000 claims description 9
- 230000006399 behavior Effects 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 5
- 238000005516 engineering process Methods 0.000 claims description 4
- 238000005562 fading Methods 0.000 claims description 3
- 230000036039 immunity Effects 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 238000012546 transfer Methods 0.000 claims description 3
- 230000000875 corresponding effect Effects 0.000 abstract description 6
- 238000000034 method Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W52/00—Power management, e.g. TPC [Transmission Power Control], power saving or power classes
- H04W52/04—TPC
- H04W52/18—TPC being performed according to specific parameters
- H04W52/24—TPC being performed according to specific parameters using SIR [Signal to Interference Ratio] or other wireless path parameters
- H04W52/243—TPC being performed according to specific parameters using SIR [Signal to Interference Ratio] or other wireless path parameters taking into account interferences
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04K—SECRET COMMUNICATION; JAMMING OF COMMUNICATION
- H04K3/00—Jamming of communication; Counter-measures
- H04K3/40—Jamming having variable characteristics
- H04K3/43—Jamming having variable characteristics characterized by the control of the jamming power, signal-to-noise ratio or geographic coverage area
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04K—SECRET COMMUNICATION; JAMMING OF COMMUNICATION
- H04K3/00—Jamming of communication; Counter-measures
- H04K3/80—Jamming or countermeasure characterized by its function
- H04K3/82—Jamming or countermeasure characterized by its function related to preventing surveillance, interception or detection
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The present invention relates to a kind of wireless communication anti-eavesdrop jamming power control algolithms based on Q study, include the following steps：S1. initialization transmission power Ps, security evaluation coefficient ρ, jamming power xiWith the grade t of working times, by the working time t of Edge ServersK part is averagely divided into, is denoted as a time slotS2. k-th of time slot is calculatedThe correlative of working condition；S3. friendly jammer is learnt using Q learning algorithms, in each time slotAccording to system mode S(k)It makes a policy, selects corresponding action xi (k)；S4. after Edge Server completes Q learning trainings, friendly jammer is according to current state S in Q value tables(k)It is correspondingEquation scheduling actionsSend friendly interference signal.The present invention trains jammer by Q learning algorithms, it can be continuously attempted to according to the information transmission power of legitimate sender, emit jamming power, it is finally reached best jamming power, so as to obtain the minimum of the maximization of information security and network energy loss, the ideal effect of network energy utilization rate is improved.
Description
Technical field
The present invention relates to machine learning and safety of physical layer field, more particularly, to a kind of channel radio based on Q study
Believe anti-eavesdrop jamming power control algolithm.
Background technology
Friendly jammer is interfered with certain power emission, it is intended to be interfered listener-in, be made it that can not intercept legal transmission
The information that machine is sent, so as to ensure its confidentiality.The adjusting of friendly jammer interference power has secrecy effect most important
Influence.Jamming power is excessive, and jammer interference listener-in while can also interfere with the information transmission on main channel, and it is legal to cause
Recipient can not restore the information that sender is transmitted, and more consume a large amount of energy, increase the energy consumption of network；If interference
Power is too small, and listener-in remains able to eavesdropping most information, and secrecy effect is not achieved.Jammer is needed by perceiving legal hair
The information transmission power for the person of sending is so as to the jamming power of itself, make and rationally be provided and selected.
The paper of 2013《Physical Layer Securityfor Two-Way UntrustedRelaying
With FriendlyJammers》It is middle to propose optimal jamming power algorithm, it is to establish mould by measuring computable quantity of state
Type is interfered with constant optimal power, so as to fulfill the confidentiality of communication channel.Paper《Ally Friendly
Jamming:How to Jam Your Enemy and Maintain Your Own Wireless Connectivity at
the Same Time》It proposes to use key suitable control close friend's interference signal, it is unpredictable for unwarranted equipment to make it
Interference, and legitimate receiver can be restored according to key, but key is once stolen hearer obtains, it will be difficult in the short time
It was found that and effective protection secret information.Paper《Secure Communication through Wireless-Powered
Friendly Jamming:Jointly Online Optimization over Geography,Energy and Time、
Competing mobile network game:Embracing antijamming andjammingstrategies with
reinforcement learning》It is to carry out intensified learning for factors such as channel check and correction, interference unit geographical location arrangements, it is false
Determine premise and be in alignment with channel to interfere successfully.But the information transmission power of sender is typically due to the geographical position of legal recipient
It puts, receive the factors such as power, decoding capability and change fluctuation.
Invention content
It is an object of the invention to overcome the deficiencies of the prior art and provide a kind of wireless communication anti-eavesdrops based on Q study
Jamming power control algolithm trains jammer by Q learning algorithms, can be according to the information transmission power of legitimate sender
It continuously attempts to, emits jamming power, be finally reached best jamming power
To solve the above problems, technical solution provided by the invention is：A kind of wireless communication anti-eavesdrop based on Q study is done
Power control algorithm is disturbed, is included the following steps：
S1. initialization transmission power Ps, security evaluation coefficient ρ, jamming power xiWith the grade t of working times, by edge
The working time t of serversK part is averagely divided into, is denoted as a time slot
S2. k-th of time slot is calculatedThe correlative of working condition；
S3. friendly jammer is learnt using Q learning algorithms, in each time slotAccording to system mode S(k)It makes a policy,
The corresponding action x of selectioni (k)；
S4. after Edge Server completes Q learning trainings, friendly jammer is according to current state S in Q value tables(k)It is correspondingEquation scheduling actionsSend friendly interference signal.
Further, the S1 steps include：
S101. by transmission power PsN grades are averagely divided into, note transmission power integrates as L, enables L=[P1,P2,···,Pn]；
S102. determine that legitimate sender cooperates with security evaluation coefficient ρ, the ρ ∈ [0,1] made with recipient；
S103. by legitimate sender transmission power Ps, security evaluation coefficient ρ merge to obtain state set, be denoted as S, S=
[Ps, ρ]；
S104. the jamming power of friendly jammer is averagely divided into n grades, remembers the jamming power behavior aggregate of friendly jammer
For A, A=[x are enabled1,x2,···,xn]；
S105. by the working time t of Edge ServersK part is averagely divided into, is denoted as a time slot ts(k)。
Further, the S2 steps include：
S201. it is λ to determine channel fading coefficient, λ ∈ [0,1], measures legitimate sender to the distance d of recipientsr, it is legal
Sender is to the distance d of listener-inse, friendly jammer to listener-in distance be dje；
It calculates listener-in and eavesdrops information obtained by channel：
S202. information obtained by legitimate receiver is calculated：Wherein θ ∈ [0,1] is are encrypting
Under technology helps, legal recipient is to the immunity programm of interference；
S203. metrical information secrecy capacity C (P are calculateds (k),xi (k))：
C(Ps (k),xi (k))=log (γr(Ps (k),xi (k)))-log(γe(Ps (k),xi (k)))
S204. computational security information content I (S(k),xi (k))：
I(S(k),xi (k))=ρ(k)C(Ps (k),xi (k))
S205. measuring system energy loss E is calculateds(xi (k))：
Es(xi (k))=xi (k)Ei+xi (k)Ev+ηEn
Wherein, EiTo measure friendly jammer rate of Energy Loss, EvEnergy loss, E are calculated for Edge ServernIt is normal
Advise information transmission energy loss, note η be regular coefficients, η ∈ [0,1]；
S206. the secrecy capacity and energy loss, calculating obtained according to above-mentioned measurement wirelessly communicates anti-eavesdrop jamming power
The immediate effect function of control algolithm：
U(S(k), xi (k))=I (S(k), xi (k))-Es(xi (k))。
Further, the S3 steps specifically include：
S301. the state set and jammer interference power behavior aggregate formed according to the transmission power of legitimate sender initializes
Q matrixes；Order matrix V=mn, m >=0, n >=0, and list Q value tables；The learning rate of default Q study and the attenuation of following attention degree
Coefficient be respectively α ∈ (0,1], δ ∈ (0,1], adjust α, δ to suitable value；
S302. the transmission power P of k-th of time slot legitimate sender is measureds (k), security evaluation coefficient ρ(k), obtain state value
S(k)；Inquire S in Q value tables(k)Corresponding optimal jamming power xi *, optimal scheduling probability is remembered for (1- ε), ε ∈ (0,1]；Pass through plan
Transfer at this time is slightly selected to act, adjusts ε to appropriate value；
S303. work as k=1, at the beginning gapDue to can not measuring state S1One jamming power action of random selection
When k >=2, it is S to measure measuring state in k time slots(k), friendly jammer interference power isEdge Server passes through at this time
The formula of S206 steps calculates the immediate effect U (S that this training obtains(k),xi (k))；
S304. at the end of time slot k, the transmitting work(of (k+1) a time slot sender is measured according to step S101 to S104
Rate Ps (k+1)With security evaluation coefficient ρ(k+1), so that it is determined that the state value S of next time slot(k+1)；
S305. friendly jammer is updated in state S(k)Under takeThe Q equations of action and pass through optimal actionIt obtains
V equations；Edge Server is according to formula：
S306. step S302 to step S305 is repeated, until obtaining a convergent ideal Q value table.
In the present invention, it is calculated using the Q learning algorithms design wireless communication anti-eavesdrop jamming power control in intensified learning
Method.Since all it is difficult to predict Q study is calculated for the anti-interference degree of communication channel, energy loss, transmission power fluctuation in communication process
Method training jammer can cooperate with what is decided through consultation according to information transmission power, the legitimate sender of legitimate sender with recipient
Security evaluation coefficient is continuously attempted to, and is emitted jamming power, best jamming power is finally reached, so as to obtain information security
Property maximization and network energy loss minimum, improve network energy utilization rate ideal effect.
The Core Superiority of Q learning algorithms is that it is a kind of deep learning algorithm of model-free.It without to quantity of state into
Row is precisely specific to be measured, and only relevant operating conditions need to be observed in the course of work of equipment and be passed through Markov and determined
Plan process will feed back maximizing the benefits, and then Q functions, which are updated, can continue to optimize decision.The present invention is in unknown signaling mould
In the case of type, the peace decided through consultation is cooperateed with recipient based on transmission power continually changing by environmental fluctuating, legitimate sender
Full metewand generation state space, the retrievable information content such as energy loss is considered and is included in benefit function, is solved due to closing
The problem of key physical quantity can not measure and be difficult to optimize friendly jamming power.Further, it is best to be finally reached balance for optimization
The state of balance between jamming power and energy loss, so as to obtain the maximization of information security and network energy loss
It minimizes, improves the ideal effect of network energy utilization rate.
Compared with prior art, advantageous effect is：A kind of wireless communication anti-eavesdrop based on Q study provided by the invention is done
Power control algorithm is disturbed, considers the interference performance of interference unit and the energy loss problem of Edge Server, learns to calculate using Q
Method does not need to measure specific energy loss, information content, only attempts to can obtain by iteration optimal；It is instructed by Q learning algorithms
Practice jammer, can be continuously attempted to according to the information transmission power of legitimate sender, emit jamming power, be finally reached most
Good jamming power so as to obtain the minimum of the maximization of information security and network energy loss, improves network energy profit
With the ideal effect of rate.
Description of the drawings
Fig. 1 is the method for the present invention flow chart.
Fig. 2 is functional structure chart of the present invention.
Specific embodiment
As shown in Figure 1, a kind of wireless communication anti-eavesdrop jamming power control algolithm based on Q study, includes the following steps：
Step 1：Initialize transmission power Ps, security evaluation coefficient ρ, jamming power xiWith the grade t of working times。
S101. by transmission power PsN grades are averagely divided into, note transmission power integrates as L, enables L=[P1,P2,···,Pn]；
S102. determine that legitimate sender cooperates with security evaluation coefficient ρ, the ρ ∈ [0,1] made with recipient；
S103. by legitimate sender transmission power Ps, security evaluation coefficient ρ merge to obtain state set, be denoted as S, S=
[Ps, ρ]；
S104. the jamming power of friendly jammer is averagely divided into n grades, remembers the jamming power behavior aggregate of friendly jammer
For A, A=[x are enabled1,x2,···,xn]；
S105. by the working time t of Edge ServersK part is averagely divided into, is denoted as a time slot
Step 2：Calculate k-th of time slotThe correlative of working condition.
S201. it is λ to determine channel fading coefficient, λ ∈ [0,1], measures legitimate sender to the distance d of recipientsr, it is legal
Sender is to the distance d of listener-inse, friendly jammer to listener-in distance be dje；
It calculates listener-in and eavesdrops information obtained by channel：
S202. information obtained by legitimate receiver is calculated：Wherein θ ∈ [0,1] is are encrypting
Under technology helps, legal recipient is to the immunity programm of interference；
S203. metrical information secrecy capacity C (P are calculateds (k),xi (k))：
C(Ps (k),xi (k))=log (γr(Ps (k),xi (k)))-log(γe(Ps (k),xi (k)))
S204. computational security information content I (S(k),xi (k))：
I(S(k),xi (k))=ρ(k)C(Ps (k),xi (k))
S205. measuring system energy loss E is calculateds(xi (k))：
Es(xi (k))=xi (k)Ei+xi (k)Ev+ηEn
Wherein, EiTo measure friendly jammer rate of Energy Loss, EvEnergy loss, E are calculated for Edge ServernIt is normal
Advise information transmission energy loss, note η be regular coefficients, η ∈ [0,1]；
S206. the secrecy capacity and energy loss, calculating obtained according to above-mentioned measurement wirelessly communicates anti-eavesdrop jamming power
The immediate effect function of control algolithm：
U(S(k), xi (k))=I (S(k), xi (k))-Es(xi (k))。
Step 3：Friendly jammer is learnt using Q learning algorithms, in each time slotAccording to system mode S(k)It makes certainly
Plan selects corresponding action xi (k)。
S301. the state set and jammer interference power behavior aggregate formed according to the transmission power of legitimate sender initializes
Q matrixes；Order matrix V=mn, m >=0, n >=0, and list Q value tables；The learning rate of default Q study and the attenuation of following attention degree
Coefficient be respectively α ∈ (0,1], δ ∈ (0,1], adjust α, δ to suitable value；
S302. the transmission power P of k-th of time slot legitimate sender is measureds (k), security evaluation coefficient ρ(k), obtain state value
S(k)；Inquire S in Q value tables(k)Corresponding optimal jamming powerOptimal scheduling probability is remembered for (1- ε), ε ∈ (0,1]；Pass through plan
Transfer at this time is slightly selected to act, such as：It is acted, is denoted as with the probability selection optimal scheduling of (1- ε)With the probability of ε with
Machine selects remaining scheduling actions in addition to optimal, is denoted as x-i, ε is adjusted to appropriate value；
S303. work as k=1, at the beginning gapDue to can not measuring state S1One jamming power action of random selection
When k >=2, it is S to measure measuring state in k time slots(k), friendly jammer interference power isEdge Server passes through at this time
The formula of S206 steps calculates the immediate effect U (S that this training obtains(k),xi (k))；
S304. at the end of time slot k, the transmitting work(of (k+1) a time slot sender is measured according to step S101 to S104
Rate Ps (k+1)With security evaluation coefficient ρ(k+1), so that it is determined that the state value S of next time slot(k+1)；
S305. friendly jammer is updated in state S(k)Under takeThe Q equations of action and pass through optimal actionIt obtains
V equations；Edge Server is according to formula：
S306. step S302 to step S305 is repeated, until obtaining a convergent ideal Q value table.
Step 4：After Edge Server completes Q learning trainings, friendly jammer is according to current state S in Q value tables(k)It is corresponding
'sEquation scheduling actionsSend friendly interference signal.
Obviously, the above embodiment of the present invention be only to clearly illustrate example of the present invention, and not be pair
The restriction of embodiments of the present invention.For those of ordinary skill in the art, may be used also on the basis of the above description
To make other variations or changes in different ways.There is no necessity and possibility to exhaust all the enbodiments.It is all this
All any modification, equivalent and improvement made within the spirit and principle of invention etc., should be included in the claims in the present invention
Protection domain within.
Claims (4)
1. a kind of wireless communication anti-eavesdrop jamming power control algolithm based on Q study, which is characterized in that include the following steps：
S1. initialization transmission power Ps, security evaluation coefficient ρ, jamming power xiWith the grade t of working times, by edge service
The working time t of devicesK part is averagely divided into, is denoted as a time slot
S2. k-th of time slot is calculatedThe correlative of working condition；
S3. friendly jammer is learnt using Q learning algorithms, in each time slotAccording to system mode S(k)It makes a policy, selects phase
The action x answeredi (k)；
S4. after Edge Server completes Q learning trainings, friendly jammer is according to current state S in Q value tables(k)Corresponding equation tune
Degree actsSend friendly interference signal.
2. the wireless communication anti-eavesdrop jamming power control algolithm according to claim 1 based on Q study, feature exist
In the S1 steps include：
S101. by transmission power PsN grades are averagely divided into, note transmission power integrates as L, enables L=[P1,P2,…,Pn]；
S102. determine that legitimate sender cooperates with security evaluation coefficient ρ, the ρ ∈ [0,1] made with recipient；
S103. by legitimate sender transmission power Ps, security evaluation coefficient ρ merge to obtain state set, be denoted as S, S=[Ps, ρ]；
S104. the jamming power of friendly jammer being averagely divided into n grades, the jamming power behavior aggregate for remembering friendly jammer is A,
Enable A=[x1,x2,…,xn]；
S105. by the working time t of Edge ServersK part is averagely divided into, is denoted as a time slot
3. the wireless communication anti-eavesdrop jamming power control algolithm according to claim 2 based on Q study, feature exist
In the S2 steps include：
S201. it is λ to determine channel fading coefficient, λ ∈ [0,1], measures legitimate sender to the distance d of recipientsr, legal transmission
Person is to the distance d of listener-inse, friendly jammer to listener-in distance be dje；
It calculates listener-in and eavesdrops information obtained by channel：
S202. information obtained by legitimate receiver is calculated：Wherein θ ∈ [0,1] are in encryption technology
Under help, legal recipient is to the immunity programm of interference；
S203. metrical information secrecy capacity is calculated
C(Ps (k),xi (k))=log (γr(Ps (k),xi (k)))-log(γe(Ps (k),xi (k)))
S204. computational security information content I (S(k),xi (k))：
I(S(k),xi (k))=ρ(k)C(Ps (k),xi (k))
S205. measuring system energy loss E is calculateds(xi (k))：
Es(xi (k))=xi (k)Ei+xi (k)Ev+ηEn
Wherein, EiTo measure friendly jammer rate of Energy Loss, EvEnergy loss, E are calculated for Edge ServernFor conventional letter
Breath transmission energy loss, note η be regular coefficients, η ∈ [0,1]；
S206. the secrecy capacity and energy loss, calculating wireless communication anti-eavesdrop jamming power obtained according to above-mentioned measurement controls
The immediate effect function of algorithm：
U(S(k), xi (k))=I (S(k), xi (k))-Es(xi (k))。
4. the wireless communication anti-eavesdrop jamming power control algolithm according to claim 3 based on Q study, feature exist
In the S3 steps specifically include：
S301. the state set and jammer interference power behavior aggregate formed according to the transmission power of legitimate sender initializes Q squares
Battle array；Order matrix V=mn, m >=0, n >=0, and list Q value tables；The learning rate of default Q study and the attenuation system of following attention degree
Number be respectively α ∈ (0,1], δ ∈ (0,1], adjust α, δ to suitable value；
S302. the transmission power P of k-th of time slot legitimate sender is measureds (k), security evaluation coefficient ρ(k), obtain state value S(k)；
Inquire S in Q value tables(k)Corresponding optimal jamming powerOptimal scheduling probability is remembered for (1- ε), ε ∈ (0,1]；It is selected by strategy
Transfer action at this time is selected, adjusts ε to appropriate value；
S303. work as k=1, at the beginning gapDue to can not measuring state S1One jamming power action of random selectionWhen k >=
2, it is S to measure measuring state in k time slots(k), friendly jammer interference power isEdge Server passes through S206 steps at this time
Formula calculate this training obtain immediate effect U (S(k),xi (k))；
S304. at the end of time slot k, the transmission power P of (k+1) a time slot sender is measured according to step S101 to S104s (k +1)With security evaluation coefficient ρ(k+1), so that it is determined that the state value S of next time slot(k+1)；
S305. friendly jammer is updated in state S(k)Under takeThe Q equations of action and pass through optimal actionObtained V side
Journey；Edge Server is according to formula：
S306. step S302 to step S305 is repeated, until obtaining a convergent ideal Q value table.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711475264.2A CN108235423B (en) | 2017-12-29 | 2017-12-29 | Wireless communication anti-eavesdrop interference power control method based on Q learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711475264.2A CN108235423B (en) | 2017-12-29 | 2017-12-29 | Wireless communication anti-eavesdrop interference power control method based on Q learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108235423A true CN108235423A (en) | 2018-06-29 |
| CN108235423B CN108235423B (en) | 2021-01-22 |
Family
ID=62646124
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711475264.2A Expired - Fee Related CN108235423B (en) | 2017-12-29 | 2017-12-29 | Wireless communication anti-eavesdrop interference power control method based on Q learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108235423B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108923828A (en) * | 2018-07-06 | 2018-11-30 | 西北工业大学 | A kind of emitting antenna selecting method of the MIMO tapping channel based on deeply study |
| CN109274456A (en) * | 2018-09-10 | 2019-01-25 | 电子科技大学 | A kind of imperfect information intelligence anti-interference method based on intensified learning |
| CN110662238A (en) * | 2019-10-24 | 2020-01-07 | 南京大学 | Reinforced learning scheduling method and device for burst request under edge network |
| CN112087749A (en) * | 2020-08-27 | 2020-12-15 | 华北电力大学（保定） | Cooperative active eavesdropping method for realizing multiple listeners based on reinforcement learning |
| CN112260796A (en) * | 2020-10-21 | 2021-01-22 | 三维通信股份有限公司 | Method and device for controlling interference signal emission |
| CN113038567A (en) * | 2021-01-20 | 2021-06-25 | 中国人民解放军陆军工程大学 | Anti-interference model and anti-interference method in multi-relay communication |
| CN113452470A (en) * | 2021-05-06 | 2021-09-28 | 浙江工业大学 | Signal power optimization method of wireless energy supply communication network |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104994569A (en) * | 2015-06-25 | 2015-10-21 | 厦门大学 | Multi-user reinforcement learning-based cognitive wireless network anti-hostile interference method |
| US9322907B1 (en) * | 2012-08-07 | 2016-04-26 | Rockwell Collins, Inc. | Behavior based friend foe neutral determination method |
-
2017
- 2017-12-29 CN CN201711475264.2A patent/CN108235423B/en not_active Expired - Fee Related
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9322907B1 (en) * | 2012-08-07 | 2016-04-26 | Rockwell Collins, Inc. | Behavior based friend foe neutral determination method |
| CN104994569A (en) * | 2015-06-25 | 2015-10-21 | 厦门大学 | Multi-user reinforcement learning-based cognitive wireless network anti-hostile interference method |
Non-Patent Citations (3)
| Title |
|---|
| DANIEL S. BERGER等: "Friendly Jamming on Access Points: Analysis and Real-World Measurements", 《IEEE》 * |
| LI WANG等: "Joint Optimization for Energy Consumption and Secrecy Capacity in Wireless Cooperative Networks", 《IEEE》 * |
| YING WANG等: "Distributed coalitional game for friendly jammer selection in ultra-dense networks", 《EURASIP JOURNAL ON WIRELESS COMMUNICATIONS AND NETWORKING》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108923828A (en) * | 2018-07-06 | 2018-11-30 | 西北工业大学 | A kind of emitting antenna selecting method of the MIMO tapping channel based on deeply study |
| CN108923828B (en) * | 2018-07-06 | 2019-06-07 | 西北工业大学 | A kind of emitting antenna selecting method of the MIMO tapping channel based on deeply study |
| CN109274456A (en) * | 2018-09-10 | 2019-01-25 | 电子科技大学 | A kind of imperfect information intelligence anti-interference method based on intensified learning |
| CN110662238A (en) * | 2019-10-24 | 2020-01-07 | 南京大学 | Reinforced learning scheduling method and device for burst request under edge network |
| CN110662238B (en) * | 2019-10-24 | 2020-08-25 | 南京大学 | Reinforced learning scheduling method and device for burst request under edge network |
| CN112087749A (en) * | 2020-08-27 | 2020-12-15 | 华北电力大学（保定） | Cooperative active eavesdropping method for realizing multiple listeners based on reinforcement learning |
| CN112087749B (en) * | 2020-08-27 | 2023-06-02 | 华北电力大学（保定） | Cooperative active eavesdropping method for realizing multiple listeners based on reinforcement learning |
| CN112260796A (en) * | 2020-10-21 | 2021-01-22 | 三维通信股份有限公司 | Method and device for controlling interference signal emission |
| CN113038567A (en) * | 2021-01-20 | 2021-06-25 | 中国人民解放军陆军工程大学 | Anti-interference model and anti-interference method in multi-relay communication |
| CN113452470A (en) * | 2021-05-06 | 2021-09-28 | 浙江工业大学 | Signal power optimization method of wireless energy supply communication network |
| CN113452470B (en) * | 2021-05-06 | 2022-06-17 | 浙江工业大学 | Signal power optimization method of wireless energy supply communication network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108235423B (en) | 2021-01-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108235423A (en) | Wireless communication anti-eavesdrop jamming power control algolithm based on Q study | |
| Li et al. | Cognitive AmBC-NOMA IoV-MTS networks with IQI: Reliability and security analysis | |
| He et al. | Secure social networks in 5G systems with mobile edge computing, caching, and device-to-device communications | |
| Xiao et al. | User-centric view of jamming games in cognitive radio networks | |
| Xiao et al. | Game theoretic study on channel-based authentication in MIMO systems | |
| Xiao et al. | PHY-layer spoofing detection with reinforcement learning in wireless networks | |
| Sagduyu et al. | MAC games for distributed wireless network security with incomplete information of selfish and malicious user types | |
| Koda et al. | Differentially private aircomp federated learning with power adaptation harnessing receiver noise | |
| Tang et al. | Distributed consensus-based security mechanisms in cognitive radio mobile ad hoc networks | |
| Tang et al. | Securing wireless transmission against reactive jamming: A Stackelberg game framework | |
| Chorppath et al. | Bayesian mechanisms and detection methods for wireless network with malicious users | |
| Lee et al. | Distributed network secrecy | |
| Li et al. | Game theoretic study of protecting MIMO transmissions against smart attacks | |
| Xu et al. | Towards a secure medium access control protocol for cluster-based underwater wireless sensor networks | |
| Li et al. | Believe yourself: A user-centric misbehavior detection scheme for secure collaborative spectrum sensing | |
| Lin et al. | A secure collaborative spectrum sensing strategy in cyber-physical systems | |
| Xie et al. | Physical-layer authentication in wirelessly powered communication networks | |
| Kalogerias et al. | Mobile jammers for secrecy rate maximization in cooperative networks | |
| Li et al. | Reinforcement learning-based intelligent reflecting surface assisted communications against smart attackers | |
| Xiao et al. | Channel-based authentication game in MIMO systems | |
| Lin et al. | Physical layer security enhancement in energy harvesting-based cognitive internet of things: A GAN-powered deep reinforcement learning approach | |
| Sheng et al. | Online primary user emulation attacks in cognitive radio networks using Thompson sampling | |
| Huo et al. | A learning-aided intermittent cooperative jamming scheme for nonslotted wireless transmission in an IoT system | |
| Yu et al. | The security of physical layer in cognitive radio networks | |
| YANG et al. | Detection method of physical-layer impersonation attack based on deep Q-network in edge computing |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210122 Termination date: 20211229 |