CN111586790B - Wireless converged network best effort communication method - Google Patents
Wireless converged network best effort communication method Download PDFInfo
- Publication number
- CN111586790B CN111586790B CN202010240461.1A CN202010240461A CN111586790B CN 111586790 B CN111586790 B CN 111586790B CN 202010240461 A CN202010240461 A CN 202010240461A CN 111586790 B CN111586790 B CN 111586790B
- Authority
- CN
- China
- Prior art keywords
- network
- communication
- cost
- flow
- network diagram
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
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
- 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
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/12—Discovery or management of network topologies
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/142—Network analysis or design using statistical or mathematical methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W40/00—Communication routing or communication path finding
- H04W40/24—Connectivity information management, e.g. connectivity discovery or connectivity update
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B7/00—Radio transmission systems, i.e. using radiation field
- H04B7/14—Relay systems
- H04B7/15—Active relay systems
- H04B7/185—Space-based or airborne stations; Stations for satellite systems
- H04B7/18502—Airborne stations
- H04B7/18506—Communications with or from aircraft, i.e. aeronautical mobile service
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W84/00—Network topologies
- H04W84/02—Hierarchically pre-organised networks, e.g. paging networks, cellular networks, WLAN [Wireless Local Area Network] or WLL [Wireless Local Loop]
- H04W84/04—Large scale networks; Deep hierarchical networks
- H04W84/06—Airborne or Satellite Networks
-
- 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
Abstract
The invention relates to a self-adaptive intelligent cluster communication and non-layout architecture technology, in particular to a wireless converged network best effort communication method, which comprises the following steps: step one, establishing a relay communication topology model between adjacent groups and designing AICA; step two, establishing a corresponding network flow model by applying graph theory knowledge to the established relay communication topology model; thirdly, adding an algorithm of maximum cost and maximum flow to solve the network flow model; the scheme enables stable communication links to be established among clusters, further reduces the link energy consumption of communication and prolongs the overall life cycle of the network.
Description
Technical Field
The invention relates to a self-adaptive intelligent cluster communication and non-layout architecture technology, in particular to a best effort communication method of a wireless fusion network.
Background
Wireless communication networks are often affected by terrain, weather, etc., and the link state is not stable enough. According to different scene demands, wireless networks with different characteristics, such as Wireless sensor networks (Wireless SensorNetwork, WSN), ad Hoc networks (Ad Hoc), car networking and the like, are derived. In certain specific scenarios, such as battlefield networks, satellite communication networks, emergency rescue networks, wild animal tracking networks, the end-to-end connection is often unstable or intermittent, which results in the absence of a stable end-to-end communication link between the communicating parties. We will refer to this particular network as a wireless converged network.
In a wireless fusion network, a small-scale communication group can be formed, any two communication points in the group can communicate through delivery forwarding, but when the two communication points belong to different communication groups, the communication path between the groups is poor, and normal communication requirements cannot be completed. Because of the time-varying topology, when two communication points need to communicate with each other, if the middle spans a plurality of communication groups, a stable communication link from the source end to the destination end cannot be found.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides a best effort communication method of a wireless converged network. The technical problems to be solved by the invention are realized by the following technical scheme:
a wireless converged network best effort communication method comprises the following steps: step one, establishing a relay communication topology model between adjacent groups and designing AICA; step two, establishing a corresponding network flow model by applying graph theory knowledge to the established relay communication topology model; and thirdly, adding an algorithm of maximum cost and maximum flow to solve the network flow model.
Furthermore, the AICA internally comprises a relay center and a virtual node, wherein the relay center is responsible for sensing and generating the virtual node, and the virtual node is responsible for pairing the edge communication nodes among groups.
Further, the network flow model specific establishing method is to construct a relay communication topology model into a capacity network diagram and a cost network diagram, and combine the capacity network diagram and the cost network diagram to establish a network flow model.
Further, the capacity network graph is a connected weighting directed graph D 1 = (V, E, C, F), where V is the vertex set of the graph, E is the directed edge set, C is the capacity on the arc, F is the flow through the arc (C Σf), the vertex set includes a start point and an end point, the flow on the network graphI.e. a viable stream flowing from a start point to an end point.
Further, the fee network diagram is a weighting directed diagram D of communication 2 = (V, E, B), where V is the vertex set of the graph, E is the edge set, B is the weight of the edge, representing the cost value generated by the edge.
Further, the method for combining the capacity network map and the cost network map is to create a starting point V of a cost capacity network map d= (V, E, C, F, B) s With edge communication node X i Edge communication node X i And AICA link obtained cost value w, as cost network map cost B, AICA built-in virtual node is converged into relay center node, namely end point V t ，V t Representing the endpoints of two populations, V s Starting point V representing two populations xs And V is equal to ys 。
Further, the algorithm of the maximum cost and maximum flow is specifically that a network flow model is split into V xs To V t 、V ys To V t Two parts and constructing respective expense network diagram W b (V, E, B) and Capacity network map W c (V, E, C, F), for V xs To V t 、V ys To V t Two parts of each cost network graph W are traversed deeply b All paths L from start point to end point in (V, E, B) k Sorting according to the cost from big to small; in respective capacity network diagrams W c Find the corresponding path L in (V, E, C, F) k Judging whether the path is feasible or not, if not, directly marking the next path; if feasible, the next path is marked after updating the total cost until all feasible paths are marked or W c Has been saturated.
The invention has the beneficial effects that:
the scheme is suitable for the communication field in which the network structure can dynamically change and the communication link state is unstable. By designing the AICA, any two terminals which cannot find a route for communication can establish a communication link through the optimal bit filling of the AICA to form a robust network structure, so that information delivery is completed;
the present invention will be described in further detail with reference to the accompanying drawings and examples.
Drawings
Fig. 1 is a schematic diagram of a relay communication topology model.
Fig. 2 is a schematic diagram of a network flow model.
FIG. 3 is a flow chart of an algorithm execution for maximum cost maximum flow.
Fig. 4 is a diagram of a cost flow network.
FIG. 5 is a network flow model D x 。
FIG. 6 is a capacity network diagram W xc 。
FIG. 7 is a cost network diagram W xb 。
Fig. 8 is an algorithm execution effect diagram.
Detailed Description
The following detailed description, structural features and functions of the present invention are provided with reference to the accompanying drawings and examples in order to further illustrate the technical means and effects of the present invention to achieve the predetermined objects.
Example 1:
a wireless converged network best effort communication method comprises the following steps: step one, establishing a relay communication topology model between adjacent groups and designing AICA; step two, establishing a corresponding network flow model by applying graph theory knowledge to the established relay communication topology model; and thirdly, adding an algorithm of maximum cost and maximum flow to solve the network flow model.
Each communication group G is made up of several communication points v. And obtaining a cost value w required to be consumed for establishing a communication link between surrounding individuals and the communication point by sensing the position information of the adjacent individuals. If the cost value w between each communication individual ij Greater than w min It is considered that a reliable communication link cannot be established between the two individuals, and thus data forwarding and delivery cannot be performed. By judging w, a plurality of communication groups can be partitioned, and communication can be performed through a storage-delivery-forwarding mechanism inside the groups. Between groups, however, due to communication links between edge communication nodes of adjacent groupsThe route is unstable, and data forwarding and delivery cannot be performed.
The relay communication topology model shown in fig. 1 is built, AICA is designed, the AICA internally comprises a relay center and virtual nodes, the relay center is responsible for sensing and generating the virtual nodes, and the virtual nodes are responsible for pairing edge communication nodes among groups. After AICA works, it can sense the number of edge communication nodes of two communication groups, adaptively generate multiple virtual nodes to match with the edge communication nodes, intelligently select multiple links to establish links with the communication groups, ensure the stability of communication links, and ensure the optimal communication link quality while selecting the most communication links, so that the life cycle of the whole network is prolonged, the agent will G 1 And the data sent by the group are transferred to a relay center, and the relay center stores the transferred data. At the same time, sense G 2 And the edge communication nodes of the group adaptively generate virtual contact nodes matched with the edge communication nodes. And intelligently generating a matching strategy, and selecting an optimal link to deliver and forward data. Thus G 1 The data sent by the community completes the process of communicating across the community.
The specific network flow model building method is that a relay communication topology model is built into a capacity network diagram and a cost network diagram, and the capacity network diagram and the cost network diagram are combined to build the network flow model.
The capacity network diagram is a connected weighted directed diagram D 1 = (V, E, C, F), where V is the vertex set of the graph, E is the directed edge set, C is the volume on the arc, F is the flow through on the arc (C Σf), the vertex set includes a start point and an end point, the flow on the network graph is a feasible flow from the start point to the end point, which is limited by the volume on the one hand, and on the other hand, except the start point and the end point, it is required to keep the inflow and outflow balanced at all intermediate points.
The fee network diagram is a weighting directed diagram D of communication 2 = (V, E, B), where V is the vertex set of the graph, E is the edge set, B is the weight of the edge, representing the cost value generated by the edge.
The capacity network diagram and the cost network diagram combining method are that a cost capacity network is createdDiagram d= (V, E, C, F, B) origin V s With edge communication node X i In order to connect only one definite path (except the starting point and the end point) for each node in the graph, the edge capacity of the direct connection of the starting point and the end point is 1, and the cost is 0. And the edge communication node and the AICA determine the link state (if there is a link, there is a directed edge between them, otherwise, there is no, and the cost value w obtained by the link is used as the cost B of the cost network diagram) according to the perception of the communication link. The virtual nodes built in AICA are converged into a relay center node, namely a terminal point V t ，V t Representing the endpoints of two populations, V s Starting point V representing two populations xs And V is equal to ys The endpoints of the two groups are coincident, so the communication scenario as applied herein actually corresponds to two symmetrical cost capacity network graphs, ultimately creating a network flow model as shown in fig. 2.
As shown in fig. 3, the algorithm of the maximum cost and maximum flow is specifically to construct a capacity network diagram W according to a relay communication topology model c (V, E, C, F), cost network map W b (V, E, B), due to V s To V t Path and V s' To V t There is no direct dependency between paths, so a single, relatively high cost maximum flow algorithm is split into two parallel algorithms, and the network flow model is split into V xs To V t 、V ys To V t Two parts, pair V xs To V t 、V ys To V t Two-part respectively depth traversal cost network diagram W b All paths L from start point to end point in (V, E, B) k Sorting according to the cost from big to small; in a capacity network diagram W c Find the corresponding path L in (V, E, C, F) k Judging whether the path is feasible or not, if not, directly marking the next path; if feasible, the next path is marked after updating the total cost until all feasible paths are marked or W c Already saturated, the result is the maximum flow at a high cost, since the model is a unidirectional weighted directed graph, no remaining network of negative loops exists, i.e. no further optimization is possible, so the resulting high cost is the maximumCost is increased.
Example 2:
the communication scheme designed above is taken as an example of unmanned aerial vehicle cluster, and example analysis is performed. When the unmanned aerial vehicle cluster executes the task, a relay communication topology model is adopted at a certain moment, a network flow model of the model is a cost flow network diagram D of FIG. 4, and the diagram D is split into V in order to improve the operation efficiency of an algorithm xs To V t Subgraph D of (2) x And V ys To V t Subgraph D of (2) y . The following algorithm process is sub-graph D x Is instance procedure of subgraph D y The same method is used.
According to the idea of the new algorithm, the specific implementation steps are as follows:
(1) Network flow model D according to FIG. 5 x Construction of the Capacity network map W of FIG. 6 xc Cost network diagram W of FIG. 7 xb . Depth traversal W xb From V xs To V t According to the cost (B) k ) Sequentially arranged from large to small.
L1:V s -X 1 -A 2 -V t
L2:V s -X 1 -A 1 -V t
L3:V s -X 3 -A 1 -V t
L4:V s -X 3 -A 2 -V t
L5:V s -X 2 -A 2 -V t
L6:V s -X 5 -A 3 -V t
L7:V s -X 2 -A 1 -V t
L8:V s -X 4 -A 2 -V t
L9:V s -X 4 -A 3 -V t
L10:V s -X 5 -A 2 -V t
L11:V s -X 2 -A 3 -V t
(2) In a capacity network diagram W xc Each feasible path is sequentially iterated, whether the feasible path is an available path is judged according to the limit of capacity, if so, path cost is obtained, total cost is updated, and the newly added path is marked at the same time, as shown in a path iterating table of the table.
(3) When all nodes of the A queue are marked as viable paths, the algorithm ends, resulting in subgraph D x Maximum flow (value) of maximum cost in (a) a (b). Likewise, subgraph D y Another maximum cost maximum flow scheme is obtained by the algorithm. The two sub-graph schemes are fused to obtain the algorithm execution effect graph of fig. 8, and the result is the final communication link linking scheme.
The working flow is as follows:
(1) Each communication point senses adjacent individuals to form an initial communication population.
(2) And judging whether the weak connection can ensure the basic link communication among groups. If not, AICA is introduced into the method to construct a relay communication topology model.
(3) The AICA self-adaptively establishes a virtual node, establishes a link between two communication group edge nodes, and evaluates the quality of the link.
(4) And (3) introducing the larger-cost maximum flow algorithm proposed herein into the established network flow model, and calculating the optimal communication link scheme with the minimum cost.
(5) After the communication groups complete the communication among the groups, the virtual links are released, and the whole communication process is completed.
The best effort communication scheme of the wireless fusion network designed by the invention can realize cross-platform deployment, and can be embedded into different hardware platforms so as to adapt to changeable task demands in a real battlefield. In practical application, the theory is converted into practical application by writing an algorithm and transplanting a program to different embedded platforms, so that the combat life cycle of a real battlefield can be truly improved.
The invention can be applied to different scene requirements. The method can be suitable for communication of the air-to-air unmanned aerial vehicle clusters, the tank clusters of the ground and the like and also suitable for interaction among the air-to-ground heterogeneous clusters. And the designed self-adaptive relay agent is used as a liaison for cluster combat, so that information interaction, task deployment and the like under the isomorphic clusters and the heterogeneous clusters are realized.
The foregoing is a further detailed description of the invention in connection with the preferred embodiments, and it is not intended that the invention be limited to the specific embodiments described. It will be apparent to those skilled in the art that several simple deductions or substitutions may be made without departing from the spirit of the invention, and these should be considered to be within the scope of the invention.
Claims (1)
1. A wireless converged network best effort communication method is characterized in that: the method comprises the following steps: step one, establishing a relay communication topology model between adjacent groups and designing intelligent communication bodies; step two, establishing a corresponding network flow model by applying graph theory knowledge to the established relay communication topology model; thirdly, adding an algorithm of maximum cost and maximum flow to solve the network flow model;
the intelligent communication body internally comprises a relay center and virtual nodes, wherein the relay center is responsible for sensing and generating the virtual nodes, and the virtual nodes are responsible for pairing edge communication nodes among groups;
the network flow model specific establishing method is that a relay communication topology model is established as a capacity network diagram and a cost network diagram, and the network flow model is established by combining the capacity network diagram and the cost network diagram;
the capacity network diagram is a connected weighting directed diagram D 1 = (V, E, C, F), where V is the vertex set of the graph, E is the directed edge set, C is the volume on the arc, F is the flow through on the arc (C Σf), the vertex set includes a start point and an end point, and the flow on the network graph is the feasible flow from the start point to the end point;
the expense network diagram is the communication assignmentDirected graph D of weights 2 = (V, E, B), where V is the vertex set of the graph, E is the directed edge set, B is the weight on an edge, representing the cost value generated by that edge;
the method for combining the capacity network diagram and the cost network diagram is that a starting point V of a cost capacity network diagram D= (V, E, C, F, B) is created s With edge communication node X i Edge communication node X i And the cost value w obtained by the link between the intelligent communication bodies is used as the cost B of the cost network diagram, and the virtual nodes built in the intelligent communication bodies are converged into a relay center node, namely a terminal point V t ，V t Representing the endpoints of two populations, V s Starting point V representing two populations xs And V is equal to ys ；
The algorithm of the maximum cost and maximum flow is specifically that a network flow model is split into V xs To V t 、V ys To V t Two parts and constructing respective construction cost network diagram W b (V, E, B) and Capacity network map W c (V, E, C, F), for V xs To V t 、V ys To V t Two parts of each cost network graph W are traversed deeply b All paths L from start point to end point in (V, E, B) k Sorting according to the cost from big to small; in respective capacity network diagrams W c Find the corresponding path L in (V, E, C, F) k Judging whether the path is feasible or not, if not, directly marking the next path; if feasible, the next path is marked after updating the total cost until all feasible paths are marked or W c Has been saturated.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010240461.1A CN111586790B (en) | 2020-03-31 | 2020-03-31 | Wireless converged network best effort communication method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010240461.1A CN111586790B (en) | 2020-03-31 | 2020-03-31 | Wireless converged network best effort communication method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111586790A CN111586790A (en) | 2020-08-25 |
| CN111586790B true CN111586790B (en) | 2023-07-04 |
Family
ID=72114880
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010240461.1A Active CN111586790B (en) | 2020-03-31 | 2020-03-31 | Wireless converged network best effort communication method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111586790B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101610580A (en) * | 2008-06-16 | 2009-12-23 | 华为技术有限公司 | The resource allocation methods of junction network and base station |
| CN105812254A (en) * | 2016-03-21 | 2016-07-27 | 湖南城市学院 | Data transmission method of opportunistic network |
| CN107318146A (en) * | 2017-07-03 | 2017-11-03 | 西安工业大学 | The topology control method of mobile cluster MANET |
| CN107529196A (en) * | 2017-08-24 | 2017-12-29 | 深圳市盛路物联通讯技术有限公司 | A kind of method and system of the data transmission of internet of things based on dummy node |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR2954028B1 (en) * | 2009-12-11 | 2012-01-20 | Univ Paris Sud 11 | METHOD FOR QUALITATIVE ROUTING IN A MULTI-HOP COMMUNICATION NETWORK, NETWORK NODE MANAGEMENT EQUIPMENT |
| JP6904127B2 (en) * | 2017-07-19 | 2021-07-14 | 富士通株式会社 | Relay node determination program, relay node determination method and parallel processing device |
-
2020
- 2020-03-31 CN CN202010240461.1A patent/CN111586790B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101610580A (en) * | 2008-06-16 | 2009-12-23 | 华为技术有限公司 | The resource allocation methods of junction network and base station |
| CN105812254A (en) * | 2016-03-21 | 2016-07-27 | 湖南城市学院 | Data transmission method of opportunistic network |
| CN107318146A (en) * | 2017-07-03 | 2017-11-03 | 西安工业大学 | The topology control method of mobile cluster MANET |
| CN107529196A (en) * | 2017-08-24 | 2017-12-29 | 深圳市盛路物联通讯技术有限公司 | A kind of method and system of the data transmission of internet of things based on dummy node |
Non-Patent Citations (3)
| Title |
|---|
| WSNs中基于能量代价的最小权和支配集拓扑控制算法;孙超等;《电子与信息学报》;20100415(第04期);全文 * |
| Xinfang Yan ; Jiangtao Xi，etc..An Energy-Aware Multilevel Clustering algorithm for wireless sensor networks.《2008 International Conference on Intelligent Sensors, Sensor Networks and Information Processing》.2009, * |
| 网络优化算法及其应用;程凤敏;《CNKI-硕士论文》;20131215;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111586790A (en) | 2020-08-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhao et al. | Novel online sequential learning-based adaptive routing for edge software-defined vehicular networks | |
| CN108112049B (en) | A kind of wireless sensor network efficiency optimization cluster-dividing method based on whale group algorithm | |
| CN109039942B (en) | Network load balancing system and balancing method based on deep reinforcement learning | |
| Wang et al. | Wireless sensor network deployment optimization based on two flower pollination algorithms | |
| CN110336751B (en) | Low-orbit satellite network routing strategy based on membership function | |
| CN108307435A (en) | A kind of multitask route selection method based on SDSIN | |
| CN106550422B (en) | A kind of wireless sensor network clustering routing based on harmonic search algorithm | |
| Javadi et al. | Learning automaton based topology control protocol for extending wireless sensor networks lifetime | |
| CN103906164A (en) | Maritime search and rescue wireless sensor network topology structure and topology control method thereof | |
| CN110161861B (en) | Aircraft ad hoc network routing decision method and device based on fuzzy neural network | |
| CN103220747A (en) | Route designing method of cognitive radio mesh network | |
| CN112486665B (en) | Edge artificial intelligence computing task scheduling method based on peer-to-peer network | |
| CN114143264A (en) | Traffic scheduling method based on reinforcement learning in SRv6 network | |
| CN107969008B (en) | Centralized routing calculation method for software defined sensor network | |
| CN114827931B (en) | WSN energy efficiency optimization routing method based on multi-agent reinforcement learning | |
| Umashankar et al. | Design of high speed reconfigurable distributed life time efficient routing algorithm in wireless sensor network | |
| CN113411766B (en) | Intelligent Internet of things comprehensive sensing system and method | |
| Zhou et al. | Long link wireless sensor routing optimization based on improved adaptive ant colony algorithm | |
| CN111586790B (en) | Wireless converged network best effort communication method | |
| Sangeetha et al. | Genetic optimization of hybrid clustering algorithm in mobile wireless sensor networks | |
| CN104093182A (en) | Method for acquiring a plurality of reliable communication paths based on field intensity in multi-layer wireless network | |
| Singh et al. | A GA-QMR: Genetic algorithm oriented MANET QoS multicast routing | |
| Wang et al. | A machine learning based connectivity restoration strategy for industrial IoTs | |
| Bharany et al. | Energy Efficient Clustering Protocol for FANETS Using Moth Flame Optimization. Sustainability 2022, 14, 6159 | |
| CN116939761A (en) | Air-ground cooperative routing method based on reinforcement learning |
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 |