CN109362113A - A kind of water sound sensor network cooperation exploration intensified learning method for routing - Google Patents
A kind of water sound sensor network cooperation exploration intensified learning method for routing Download PDFInfo
- Publication number
- CN109362113A CN109362113A CN201811310120.6A CN201811310120A CN109362113A CN 109362113 A CN109362113 A CN 109362113A CN 201811310120 A CN201811310120 A CN 201811310120A CN 109362113 A CN109362113 A CN 109362113A
- Authority
- CN
- China
- Prior art keywords
- node
- value
- data packet
- packet
- routing
- 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
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W40/00—Communication routing or communication path finding
- H04W40/02—Communication route or path selection, e.g. power-based or shortest path routing
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W40/00—Communication routing or communication path finding
- H04W40/02—Communication route or path selection, e.g. power-based or shortest path routing
- H04W40/22—Communication route or path selection, e.g. power-based or shortest path routing using selective relaying for reaching a BTS [Base Transceiver Station] or an access point
-
- 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
- H04W52/02—Power saving arrangements
- H04W52/0203—Power saving arrangements in the radio access network or backbone network of wireless communication networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W84/00—Network topologies
- H04W84/18—Self-organising networks, e.g. ad-hoc networks or sensor networks
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The present invention relates to water sound sensor network, underwater sound routing protocol technology field, in particular to intensified learning method for routing is explored in a kind of water sound sensor network cooperation.The present invention is the following steps are included: (1) initializes each node Q value and V value；(2) judgeIt is whether true；(3) relay node receives data packet/control packet, updates neighbor list, and judge whether to continue to forward；(4) sink receives data packet, terminates this transmission.Global optimum can be reached approximately when selecting path based on the Routing Protocol of intensified learning, and can merge the factor of multinomial influence performance.In the present invention, when algorithm is not converged, source node sends several control packets while sending data packet, with the convergence of accelerating algorithm, otherwise, only sends data packet.After algorithmic statement, approximate global optimum path is realized by the highest next-hop node of selection V value, so that equilibrium network energy consumption, extends network life, solve the problems, such as that intensified learning convergence rate is slow.
Description
Technical field
The present invention relates to water sound sensor network, underwater sound routing protocol technology field, in particular to a kind of underwater sound sensors
Network cooperation explores intensified learning method for routing.
Background technique
Water sound sensor network, Underwater Acoustic Sensor Networks, i.e. UASNs, by deployment underwater
Sensor node and for receiving data aggregation node sink composition.These nodes provide many applications such as environment and supervise
Survey, tactical surveillance, resource exploration, assisting navigation and Disaster Defensive etc..It is underwater logical due to the limitation of radio wave high-transmission loss
Letter is frequently with sound wave.Meanwhile UASNs is faced with that limited battery capacity, the bit error rate are high, end-to-end time delay is high, available bandwidth is limited
Etc. unique challenge.
Due to inherent characteristics such as the high latency of UASNs, high energy consumption and low bandwidth, network topology structure is usually to be distributed
Formula network.The main problem that its Routing Protocol faces is to find efficient and energy-efficient path.It interacts with environment trial and error to seek
The nitrification enhancement for looking for greatest hope to reward has been applied to UASNs, the Routing Protocol based on intensified learning, each node
Global optimum can be reached approximately by needing not know about full mesh topology information when selecting path.Nitrification enhancement can make node
The dynamic environment locating for it is practised and adapted to, and the factor of multinomial influence routing performance can be merged, considers routing decision
More fully.In the present invention, with the convergence rate of the convergence rate characterization intensified learning of source node V value.
In UASNs, with the expansion of network size, the convergence rate of intensified learning slows down, and network energy consumption is big, and
In network topological change, its variation cannot be tracked well, influences network performance.
Summary of the invention
The purpose of the present invention is in view of the above shortcomings of the prior art, propose that it is strong that a kind of water sound sensor network cooperation is explored
Chemistry practises method for routing.When algorithm is not converged, source node sends several control packets and carries out to path while sending data packet
Cooperation is explored, and to accelerate the convergence of its V value, solves the problems, such as that intensified learning convergence rate is slow, while reducing network energy consumption,
Extend network life.
The present invention can realize by the following technical solutions:
A kind of water sound sensor network cooperation exploration intensified learning method for routing, method includes the following steps:
(1) each node Q value and V value are initialized；
(2) according to the Q value of each node and V value, judgementIt is whether true:
(2.1) if it is determined that setting up, source node only sends data packet；
(2.2) if it is determined that invalid, source node sends control packet while sending data packet；
(3) data packet or control sent according to source node is wrapped, and relay node receives data and reads packet header；
(4) routing table is updated according to the received data of relay node, and judges whether it continues to be sent to this node, if judgement
Data are destined for this node, then calculate Q value, update V value to packet header, and continue to transmit data packet；
(5) judge whether aggregation node sink receives data packet:
(5.1) if sink receives data packet, terminate this transmission；
(5.2) if sink does not receive data packet, repeatedly step (3) arrives step (5), until sink receives data packet.
The step (1) the following steps are included:
(1.1) reward function is determined；
(1.2) according to reward function, the Q value iteration function of each node is determined；
Step (1.1) the reward function RnmAfter the completion of transmitting data packet/control packet to second node m for first node n
Instant reward obtained, reward function are settled accounts as the following formula:
Rnm=-g- α1c+α2d
Wherein, g is fixed loss of the node when transmitting data, and c is residue energy of node cost function, and d is node energy
Measure distribution situation, α1For the specific gravity parameter of residue energy of node cost function c, α2Join for the specific gravity of node energy distribution situation d
Number；
The iteration function of step (1.2) the Q value is calculated as follows:
Wherein,Indicating Q value of the first node n at the t+1 moment, α indicates the renewal rate of Q value, and γ is discount factor,For second node m t moment Q value.
Step (2) described Rule of judgmentIn, Vt sIndicate source node t moment V value,When indicating t+1
The V value of source node is carved, ε indicates a minimum greater than 0；
If step (2.1) judgement is set up, source node terminates the transmission of control packet, passes through Q value iteration in conjunction with routing table
Formula calculates optimal path and transmits data packet upwards, until sink；
If step (2.2) judgement is invalid, i.e.,When, source node V value calculates function are as follows:
Wherein, α is identical as the α numerical value in the iteration function of step (1.2) the Q value, indicates learning rate herein, meaning
For the renewal rate of V value；ω is the normalized parameter for controlling packet detective path, Vt jIndicate each data packet or control detective rope path
Obtained experience.
If the packet as described in step (4) is sent to this node, root calculates Q value according to Q value iteration function, select Q value be its most
Big value QmaxWhen node be next-hop node, and V value is updated to Qmax, and rewrite nodal information and continue to transmit to packet header.
Compared with prior art, the present invention the beneficial effects of the present invention are:
(1) the present invention provides a kind of water sound sensor network cooperations to explore intensified learning routing algorithm, does not receive in algorithm
When holding back, source node sends data packet and control packet simultaneously, accelerates the convergence rate of source node V value.
(2) present invention realizes approximate global optimum road by the highest next-hop node of selection V value after algorithmic statement
Diameter, so that balanced network energy consumption, extends network life.
Detailed description of the invention
Fig. 1 is water sound sensor network structure chart.
Fig. 2 is the schematic diagram that intensified learning method for routing is explored in cooperation.
Fig. 3 is that source node realizes that the flow chart of nitrification enhancement is explored in cooperation.
Fig. 4 is routing forwarding flow chart.
Specific embodiment
The present invention is further elaborated with reference to the accompanying drawing.
Obviously, the described embodiment is only a part of the embodiment of the present invention, rather than whole embodiments.Therefore, below
The range of claimed invention is not intended to limit to the detailed description of the embodiment of the present invention provided in the accompanying drawings, and
It is to be merely representative of selected embodiment of the invention.Embodiment based on invention, those skilled in the art do not make creative labor
Every other embodiment obtained under the premise of dynamic, shall fall within the protection scope of the present invention.
The present invention provides a kind of water sound sensor network cooperation exploration intensified learning method for routing.Road based on intensified learning
Global optimum can be reached approximately when selecting path by agreement, and can merge the factor of multinomial influence performance.The present invention
In, when algorithm is not converged, source node sends several control packets for containing only header packet information to path while sending data packet
It cooperates exploration, to accelerate the convergence of source node V value, otherwise, only sends data packet.The present invention solves intensified learning convergence
Slow-footed problem, while network energy consumption is reduced, extend network life.The present invention comprising the following steps:
(1) each node Q value and V value are initialized.
(2) judgeIt is whether true, wherein Vt sSource node is indicated in the V value of t moment, ε indicates one big
In 0 minimum.If set up, source node only sends data packet；Otherwise, source node sends control while sending data packet
Packet.
(3) relay node receives data packet/control packet, updates neighbor list, and judge whether to continue to forward.
(4) sink receives data packet, terminates this transmission.
In step (2),When not setting up, the V value iteration function of source node are as follows:
Wherein, α indicates learning rate, means the renewal rate of V value, it is controlled between previous V value and new V value
How many is taken into account difference.γ is discount factor, means influence of the experience to current V value.ω is that road is surveyed in control detective
The normalized parameter of diameter, Vt jIndicate each data packet/obtained experience in control detective rope path.In step (3),When, source node only sends data packet；?When, source node is sent while sending data packet
Control packet.
Attached drawing 1 is water sound sensor network structure chart provided in an embodiment of the present invention, and attached drawing 2 provides for the embodiment of the present invention
Cooperation explore intensified learning method for routing schematic diagram.In conjunction with above structure figure and schematic diagram, present embodiment discloses one kind
The implementation method of intensified learning Routing Protocol is explored in water sound sensor network cooperation, specific as follows as shown in attached drawing 3 and attached drawing 4:
(1) each node Q value V value is initialized.
(2) reward value function is determined.
In the present embodiment, value function R is rewardednmIt is obtained after the completion of transmitting data packet/control packet to node m by node n
Instant reward.
Rnm=-g- α1c+α2d
G is fixed loss of the node when transmitting data, and c is residue energy of node cost function, and d is node energy distribution
Situation, α1And α2The specific gravity parameter of respectively c and d.
(3) the Q value iteration function of each node is determined.
Indicating Q value of the node n at the t+1 moment, α indicates the renewal rate of Q value, and γ is discount factor,For node m
In the Q value of t moment.
(4) determine that source node V value calculates function.
When source node V value calculate function:
Indicate the V value of subsequent time source node, ω is the normalized parameter for controlling packet detective path, Vt jIndicate each number
According to packet/obtained experience in control detective rope path.
(5) source node is cooperated exploration.
Water sound sensor network structure chart of the invention is as shown in Fig. 1, for the sake of simplicity, the network structure of the present embodiment is
Single mono- sink in source-, source node be responsible for collect data, and by the data being collected by underwater acoustic network along relay node gradually to
Upper transmission, until sink.Sink by nautical receiving set receive under sea relay node data, and with radio wave to
Base station sends data, and base station carries out subsequent analysis and processing after receiving the data of sink.
It is illustrated in conjunction with attached drawing 2, whenWhen, source node sends data packet and control packet simultaneously, in this reality
It applies in example, for convenience of description, control packet is set to two.
Source node calculates Q value according to Q value iteration function and updates V value, selects a node to send number according to calculated result
According to packet, two nodes send control packet, and in the present embodiment, source node selects its neighbor node 3 to transmit as data packet
The next-hop node of next-hop node, simultaneous selection node 1 and node 5 as control packet transmission.
Node 1,3,5 reads packet header after listening to data packet/control packet, by the information update of upper hop node to oneself
In neighbor list, if the packet is sent to this node, Q value is calculated according to Q value iteration function, selecting Q value is QmaxNode be it is next
Hop node, and V value is updated to Qmax, and rewrite nodal information and continue to transmit to packet header.
The neighbor node of node 1,3,5 repeats above-mentioned movement until data packet/control packet reaches sink.
(6) whenWhen, source node stops sending control packet.
Source node judgementIt sets up, at this point, source node terminates the transmission of control packet, passes through Q in conjunction with routing table
Value iterative formula calculates optimal path and transmits data packet upwards, until sink.
Claims (4)
1. intensified learning method for routing is explored in a kind of water sound sensor network cooperation, which is characterized in that this method includes following step
It is rapid:
(1) each node Q value and V value are initialized；
(2) according to the Q value of each node and V value, judgementIt is whether true:
(2.1) if it is determined that setting up, source node only sends data packet；
(2.2) if it is determined that invalid, source node sends control packet while sending data packet；
(3) data packet or control sent according to source node is wrapped, and relay node receives data and reads packet header；
(4) routing table is updated according to the received data of relay node, and judges whether it continues to be sent to this node, if judging data
It is destined for this node, then calculates Q value, update V value to packet header, and continues to transmit data packet；
(5) judge whether aggregation node sink receives data packet:
(5.1) if sink receives data packet, terminate this transmission；
(5.2) if sink does not receive data packet, repeatedly step (3) arrives step (5), until sink receives data packet.
2. intensified learning method for routing is explored in a kind of water sound sensor network cooperation according to claim 1, feature exists
In, the step (1) the following steps are included:
(1.1) reward function is determined；
(1.2) according to reward function, the Q value iteration function of each node is determined；
Step (1.1) the reward function RnmIt is obtained after the completion of transmitting data packet/control packet to second node m by first node n
The instant reward obtained, reward function are settled accounts as the following formula:
Rnm=-g- α1c+α2d
Wherein, g is fixed loss of the node when transmitting data, and c is residue energy of node cost function, and d is node energy point
Cloth situation, α1For the specific gravity parameter of residue energy of node cost function c, α2For the specific gravity parameter of node energy distribution situation d；
The iteration function of step (1.2) the Q value is calculated as follows:
Wherein,Indicating Q value of the first node n at the t+1 moment, α indicates the renewal rate of Q value, and γ is discount factor,For
Q value of the second node m in t moment.
3. intensified learning method for routing is explored in a kind of water sound sensor network cooperation according to claim 2, feature exists
In: step (2) described Rule of judgmentIn, Vt sIndicate source node t moment V value,Indicate t+1 time source
The V value of node, ε indicate a minimum greater than 0；
If step (2.1) judgement is set up, source node terminates the transmission of control packet, passes through Q value iterative formula in conjunction with routing table
It calculates optimal path and transmits data packet upwards, until sink；
If step (2.2) judgement is invalid, i.e.,When, source node V value calculates function are as follows:
Wherein, α is identical as the α numerical value in the iteration function of step (1.2) the Q value, indicates learning rate herein, means V
The renewal rate of value；ω is the normalized parameter for controlling packet detective path, Vt jIndicate each data packet or control detective rope path institute
Obtained experience.
4. intensified learning method for routing is explored in a kind of water sound sensor network cooperation according to claim 3, feature exists
In: if the packet as described in step (4) is sent to this node, root calculates Q value according to Q value iteration function, and selecting Q value is its maximum value
QmaxWhen node be next-hop node, and V value is updated to Qmax, and rewrite nodal information and continue to transmit to packet header.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811310120.6A CN109362113B (en) | 2018-11-06 | 2018-11-06 | Underwater acoustic sensor network cooperation exploration reinforcement learning routing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811310120.6A CN109362113B (en) | 2018-11-06 | 2018-11-06 | Underwater acoustic sensor network cooperation exploration reinforcement learning routing method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109362113A true CN109362113A (en) | 2019-02-19 |
| CN109362113B CN109362113B (en) | 2022-03-18 |
Family
ID=65344072
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811310120.6A Active CN109362113B (en) | 2018-11-06 | 2018-11-06 | Underwater acoustic sensor network cooperation exploration reinforcement learning routing method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109362113B (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110719617A (en) * | 2019-09-30 | 2020-01-21 | 西安邮电大学 | Q routing method based on arc tangent learning rate factor |
| CN110868727A (en) * | 2019-10-28 | 2020-03-06 | 辽宁大学 | Data transmission delay optimization method in wireless sensor network |
| CN111629440A (en) * | 2020-05-19 | 2020-09-04 | 哈尔滨工程大学 | Method for judging convergence of MAC protocol by adopting Q learning |
| CN112351400A (en) * | 2020-10-15 | 2021-02-09 | 天津大学 | Underwater multi-modal network routing strategy generation method based on improved reinforcement learning |
| CN112469103A (en) * | 2020-11-26 | 2021-03-09 | 厦门大学 | Underwater sound cooperative communication routing method based on reinforcement learning Sarsa algorithm |
| CN112867089A (en) * | 2020-12-31 | 2021-05-28 | 厦门大学 | Underwater sound network routing method based on information importance and Q learning algorithm |
| CN112954769A (en) * | 2021-01-25 | 2021-06-11 | 哈尔滨工程大学 | Underwater wireless sensor network routing method based on reinforcement learning |
| CN113141592A (en) * | 2021-04-11 | 2021-07-20 | 西北工业大学 | Long-life-cycle underwater acoustic sensor network self-adaptive multi-path routing mechanism |
| CN113783782A (en) * | 2021-09-09 | 2021-12-10 | 哈尔滨工程大学 | Opportunistic routing candidate set node ordering method for deep reinforcement learning |
| CN114786236A (en) * | 2022-04-27 | 2022-07-22 | 曲阜师范大学 | Method and device for heuristic learning of routing protocol of wireless sensor network |
| CN114828141A (en) * | 2022-04-25 | 2022-07-29 | 广西财经学院 | UWSNs multi-hop routing method based on AUV networking |
| CN115175268A (en) * | 2022-07-01 | 2022-10-11 | 重庆邮电大学 | Heterogeneous network energy-saving routing method based on deep reinforcement learning |
| CN115843083A (en) * | 2023-02-24 | 2023-03-24 | 青岛科技大学 | Underwater wireless sensor network routing method based on multi-agent reinforcement learning |
| CN115987886A (en) * | 2022-12-22 | 2023-04-18 | 厦门大学 | Underwater acoustic network Q learning routing method based on meta-learning parameter optimization |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106358308A (en) * | 2015-07-14 | 2017-01-25 | 北京化工大学 | Resource allocation method for reinforcement learning in ultra-dense network |
| CN107809781A (en) * | 2017-11-02 | 2018-03-16 | 中国科学院声学研究所 | A kind of loop free route selection method of load balancing |
| US20180302172A1 (en) * | 2015-10-16 | 2018-10-18 | Universita' Degli Studi Di Roma "La Sapienza" | Method for managing in an adaptive and joint way the routing policy and the retransmission policy of a node in an underwater network, and means for its implementation |
-
2018
- 2018-11-06 CN CN201811310120.6A patent/CN109362113B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106358308A (en) * | 2015-07-14 | 2017-01-25 | 北京化工大学 | Resource allocation method for reinforcement learning in ultra-dense network |
| US20180302172A1 (en) * | 2015-10-16 | 2018-10-18 | Universita' Degli Studi Di Roma "La Sapienza" | Method for managing in an adaptive and joint way the routing policy and the retransmission policy of a node in an underwater network, and means for its implementation |
| CN107809781A (en) * | 2017-11-02 | 2018-03-16 | 中国科学院声学研究所 | A kind of loop free route selection method of load balancing |
Non-Patent Citations (5)
| Title |
|---|
| 冯晓宁: ""AUV-Aided Communication Method for Underwater Mobile Sensor Network"", 《IEEE》 * |
| 冯晓宁: ""基于L-π演算的WSN路由协议形式化方法"", 《吉林大学学报(工学版)》 * |
| 卜任菲: ""基于反馈的合作强化学习水下路由算法"", 《通信技术》 * |
| 王卓: ""多普勒辅助水下传感器网络时间同步机制研究"", 《通信学报》 * |
| 金志刚: ""基于指向性换能器水声传感器网络功率控制算法"", 《华中科技大学学报(自然科学版) 2017-07-14 》 * |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110719617A (en) * | 2019-09-30 | 2020-01-21 | 西安邮电大学 | Q routing method based on arc tangent learning rate factor |
| CN110719617B (en) * | 2019-09-30 | 2023-02-03 | 西安邮电大学 | Q routing method based on arc tangent learning rate factor |
| CN110868727A (en) * | 2019-10-28 | 2020-03-06 | 辽宁大学 | Data transmission delay optimization method in wireless sensor network |
| CN111629440A (en) * | 2020-05-19 | 2020-09-04 | 哈尔滨工程大学 | Method for judging convergence of MAC protocol by adopting Q learning |
| CN112351400B (en) * | 2020-10-15 | 2022-03-11 | 天津大学 | Underwater multi-modal network routing strategy generation method based on improved reinforcement learning |
| CN112351400A (en) * | 2020-10-15 | 2021-02-09 | 天津大学 | Underwater multi-modal network routing strategy generation method based on improved reinforcement learning |
| CN112469103B (en) * | 2020-11-26 | 2022-03-08 | 厦门大学 | Underwater sound cooperative communication routing method based on reinforcement learning Sarsa algorithm |
| CN112469103A (en) * | 2020-11-26 | 2021-03-09 | 厦门大学 | Underwater sound cooperative communication routing method based on reinforcement learning Sarsa algorithm |
| CN112867089A (en) * | 2020-12-31 | 2021-05-28 | 厦门大学 | Underwater sound network routing method based on information importance and Q learning algorithm |
| CN112954769A (en) * | 2021-01-25 | 2021-06-11 | 哈尔滨工程大学 | Underwater wireless sensor network routing method based on reinforcement learning |
| CN112954769B (en) * | 2021-01-25 | 2022-06-21 | 哈尔滨工程大学 | Underwater wireless sensor network routing method based on reinforcement learning |
| CN113141592A (en) * | 2021-04-11 | 2021-07-20 | 西北工业大学 | Long-life-cycle underwater acoustic sensor network self-adaptive multi-path routing mechanism |
| CN113783782A (en) * | 2021-09-09 | 2021-12-10 | 哈尔滨工程大学 | Opportunistic routing candidate set node ordering method for deep reinforcement learning |
| CN114828141A (en) * | 2022-04-25 | 2022-07-29 | 广西财经学院 | UWSNs multi-hop routing method based on AUV networking |
| CN114828141B (en) * | 2022-04-25 | 2024-04-19 | 广西财经学院 | UWSNs multi-hop routing method based on AUV networking |
| CN114786236A (en) * | 2022-04-27 | 2022-07-22 | 曲阜师范大学 | Method and device for heuristic learning of routing protocol of wireless sensor network |
| CN114786236B (en) * | 2022-04-27 | 2024-05-31 | 曲阜师范大学 | Method and device for heuristic learning of routing protocol by wireless sensor network |
| CN115175268A (en) * | 2022-07-01 | 2022-10-11 | 重庆邮电大学 | Heterogeneous network energy-saving routing method based on deep reinforcement learning |
| CN115987886A (en) * | 2022-12-22 | 2023-04-18 | 厦门大学 | Underwater acoustic network Q learning routing method based on meta-learning parameter optimization |
| CN115987886B (en) * | 2022-12-22 | 2024-06-04 | 厦门大学 | Underwater acoustic network Q learning routing method based on meta learning parameter optimization |
| CN115843083A (en) * | 2023-02-24 | 2023-03-24 | 青岛科技大学 | Underwater wireless sensor network routing method based on multi-agent reinforcement learning |
| CN115843083B (en) * | 2023-02-24 | 2023-05-12 | 青岛科技大学 | Underwater wireless sensor network routing method based on multi-agent reinforcement learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109362113B (en) | 2022-03-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109362113A (en) | A kind of water sound sensor network cooperation exploration intensified learning method for routing | |
| Zheng et al. | A mobility and load aware OLSR routing protocol for UAV mobile ad-hoc networks | |
| CN109547351B (en) | Routing method based on Q learning and trust model in Ad Hoc network | |
| KR100689305B1 (en) | Mobile Ad Hoc Network and Method for Detecting Variable Beacon Signals in Mobile Ad Hoc Network | |
| CN109104366B (en) | Link duration calculation method, MPR node selection method and routing protocol | |
| CN114025330B (en) | Air-ground cooperative self-organizing network data transmission method | |
| KR20050035295A (en) | Intelligent communication node object beacon framework in a mobile ad hoc network | |
| US20120030150A1 (en) | Hybrid Learning Component for Link State Routing Protocols | |
| US9426716B2 (en) | Optimizing communication for mesh routing protocols using directional beam forming | |
| CN109246786A (en) | Balancing energy Dynamic Geographic method for routing in underwater sensor network based on distance | |
| CN112188583B (en) | Ocean underwater wireless sensing network opportunistic routing method based on reinforcement learning | |
| CN108632940B (en) | Reliable multipath routing algorithm suitable for photoelectric sensor wireless MESH network | |
| Ashraf et al. | Sagacious communication link selection mechanism for underwater wireless sensors network | |
| Ahmadi et al. | A hybrid algorithm for preserving energy and delay routing in mobile ad-hoc networks | |
| Ji et al. | Keep forwarding path freshest in VANET via applying reinforcement learning | |
| CN110267321B (en) | Greedy multicast routing protocol design method in three-dimensional scene | |
| CN104053208B (en) | Method for routing based on channel distribution, device in wireless self-networking | |
| CN106879042B (en) | A kind of underwater wireless sensor network shortest-path rout ing algorithms | |
| WO2016135711A1 (en) | Method and system for operating a vehicular data network based on a layer-2 periodic frame broadcast, in particular a routing protocol | |
| CN117528696A (en) | Distributed time delay optimization routing method for location-directed DQN multi-agent satellite network | |
| Rahman et al. | An Optimal Delay Tolerant and Improved Data Collection Schema Using AUVs for Underwater Wireless Sensor Networks | |
| CN110493843A (en) | 3D-GPSR method for routing based on circular ring shape omnidirectional antenna model | |
| Ashraf et al. | Succulent link selection strategy for underwater sensor network | |
| CN110971524B (en) | Centralized routing method for wireless sensor network | |
| Khan et al. | Energy-aware multipath routing scheme based on particle swarm optimization (EMPSO) |
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 |