CN116074991A - Intelligent cluster clustering method based on K-means++ clustering algorithm - Google Patents
Intelligent cluster clustering method based on K-means++ clustering algorithm Download PDFInfo
- Publication number
- CN116074991A CN116074991A CN202310035576.0A CN202310035576A CN116074991A CN 116074991 A CN116074991 A CN 116074991A CN 202310035576 A CN202310035576 A CN 202310035576A CN 116074991 A CN116074991 A CN 116074991A
- Authority
- CN
- China
- Prior art keywords
- cluster
- node
- clustering
- nodes
- selecting
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 20
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 13
- 241000854291 Dianthus carthusianorum Species 0.000 claims abstract description 18
- 238000004891 communication Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 3
- 238000004088 simulation Methods 0.000 description 3
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006855 networking Effects 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000009827 uniform distribution Methods 0.000 description 1
Images
Classifications
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W16/00—Network planning, e.g. coverage or traffic planning tools; Network deployment, e.g. resource partitioning or cells structures
- H04W16/18—Network planning tools
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W16/00—Network planning, e.g. coverage or traffic planning tools; Network deployment, e.g. resource partitioning or cells structures
- H04W16/22—Traffic simulation tools or models
-
- 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
- H04W40/32—Connectivity information management, e.g. connectivity discovery or connectivity update for defining a routing cluster membership
-
- 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)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to an intelligent cluster clustering method based on a K-means++ clustering algorithm, which can prevent clusters with independent nodes or fewer nodes from being present in uniform clusters, thereby optimizing a clustering structure. The cluster number is smaller than the initial optimal value k * As the number of nodes increases, this may put more load on the Cluster Head (CH). However, it can be observed from the IWLC scheme that the increasing trend of the number of clusters is more stable, which can better cope with the increase of the number of nodes and improve the expandability of the clustered network.
Description
Technical Field
The invention relates to the technical field of clustering methods, in particular to an intelligent cluster clustering method based on a K-means++ clustering algorithm.
Background
Under the background of the battlefield Internet of things, the development of ammunition is proceeding towards informatization, intellectualization and networking, wherein the most representative is the self-networking of patrol missiles, and the patrol missiles are used as a new concept ammunition capable of performing patrol flight and standby above a target area to perform various combat tasks. The intelligent ammunition is a product of combining an advanced unmanned plane technology and a missile technology, can quickly reach a target area, can perform tasks such as reconnaissance monitoring, target positioning, air blocking, accurate striking, damage effect evaluation and the like, and is characterized by being clear and capable of meeting future informatization combat demands. The patrol projectile can form an ammunition cluster through networking, the ammunition cluster is called as a networked ammunition, the networked ammunition can emerge a multiplication effect in the actual combat process, and meanwhile, the system has stronger system damage resistance and autonomy control, so that the system has extremely superior combat capability.
Clustering is a network structure dividing method driven by tasks, communication, calculation and resource multiparty, and aims to balance the calculation pressure of each node, reasonably allocate network resources, and the nodes with better resources serve as more calculation tasks, so that the stability of the network is improved. In ammunition ad hoc networks, clustering is critical to efficiently managing network topology.
Disclosure of Invention
The invention provides an intelligent cluster clustering method based on a K-means++ clustering algorithm for effectively solving the clustering problem of intelligent platform nodes.
In order to solve the technical problems, the invention adopts the following technical scheme:
an intelligent cluster clustering method based on a K-means++ clustering algorithm comprises the following steps of;
step 1, determining the initial clustering number k * ，
Wherein B is 1 And B 2 Bandwidth of intra-cluster and inter-cluster communication, respectively, N being the number of unmanned aerial vehicles;
step 3, dividing each node into clusters corresponding to the cluster centers closest to the nodes;
and step 5, obtaining a final clustering result and selecting a cluster head.
Further, the method for selecting the cluster head in the step 5 includes the following steps:
step 5.1, calculating the W value of each node in each final cluster, wherein the node i corresponds to
Wherein->
For the number of nodes around node i, (x) i ,y i ,z i ) Is the three-dimensional coordinates of node i, (x j ,y j ,z j ) Is the coordinates of the neighbor node j of node i;
and 5.2, selecting the node with the largest W value in each cluster as a cluster head.
After the technical scheme is adopted, compared with the prior art, the invention has the following advantages:
the uniform clustering of the invention can prevent the clustering with independent nodes or less nodes, thereby optimizing the clustering structure. The cluster number is smaller than the initial optimal value k * As the number of nodes increases, this may put more load on the CH. However, it can be observed from the IWLC scheme that the increasing trend of the number of clusters is more stable, which can better cope with the increase of the number of nodes and improve the expandability of the clustered network.
The invention will now be described in detail with reference to the drawings and examples.
Drawings
FIG. 1 is a diagram of a network topology in a point-to-point mode;
FIG. 2 is a diagram of a network topology in a clustered mode;
fig. 3 is a graph showing a comparison of the number of clusters according to the change of the number of nodes.
Detailed Description
The principles and features of the present invention are described below with reference to the drawings, the examples are illustrated for the purpose of illustrating the invention and are not to be construed as limiting the scope of the invention.
IWLC algorithm
1. Formation of clusters
The initial number of clusters is determined as follows: in the clustering process, in order to reduce the clustering overhead and effectively utilize the bandwidth, the main number of clusters needs to be optimally determined in the initial cluster center selection. The throughput of each common node (CM) is
In addition, the throughput of each Cluster Head (CH) is
Where N is the number of drones and k is the number of clusters. Θ () is an asymptotic tight constraint. B (B) 1 And B 2 Bandwidth for intra-cluster and inter-cluster communications, respectively, assumingNetwork traffic is evenly distributed. T of one CH due to throughput balancing of inter-cluster and intra-cluster communication CH The ratio of traffic to other groups is (k-1)/k, which should be less than or equal to T of the CH CH 。
When (when)
Maximum throughput is reached, i.e. the predominant number of clusters k when inequality (3) holds * The method comprises the following steps:
if N is large enough, the number of clusters is approximately:
based on the initial value k * The K-means++ clustering algorithm is further developed, and N intelligent platforms are divided into clusters. The K-means++ clustering algorithm can reduce errors and computational complexity of clustering results. The intelligent platform node is modeled as a set of points s= { S 1 ,s 2 ,...s i ...,s N }. The algorithm is as follows:
the initial cluster center is selected as follows: randomly selecting an initial cluster center c from the set S according to a uniform distribution 1 . Minimum distance, i.e. point s i The minimum value of Euclidean distance between the cluster center selected at present and the cluster center is expressed as D (s i ). Then we calculate the point S in S by using the following equation i Probability of being selected as the next cluster center:
the point with the highest probability is selected as the next center c 1 . Repeating the above process until k is selected * A hub, which may be represented as a collection
This k * The individual centers will be used as the original cluster centers for the K-means++ clusters.
The cluster formation process is as follows. With the original cluster center, the set S can be divided into k by searching the closest cluster center * And (5) clustering. A point S in S i The minimum distance to the cluster center can be expressed as
If it is
Then the point s i Should be clustered into an nth cluster. The cluster center is then updated with the following formula.
Wherein C represents a set of cluster centers, N n Is the number of points in the nth cluster.
Equations (7) and (8) will be repeated multiple times until C converges. In this process, the actual number k of clusters may be less than the initial number k of clusters * . The reason is that the adaptive clustering method incorporates clusters that are close to each other to reduce isolated or small-node-number clusters.
2. Cluster head selection
The invention develops a cluster head selection algorithm based on the average distance between nodes. To calculate the average distance, the node appends GPS location information to the communication message and sends it to the neighbor node. The average distance between i and its neighbors can be calculated as
Wherein (x) i ,y i ,z i ) Is the three-dimensional coordinates of i, (x j ,y j ,z j ) Is the location of its neighbor node j,
the number of nodes near node i;
the normalized average distance is:
order the
Calculating W of each node in each cluster i Wherein maximum W is taken i The node of the cluster is the cluster head of the cluster.
2. Simulation of
Comparing the IWLC of the present invention with the baseline methods (i.e., WSCA and ACO), the simulation parameters are as follows
The results of the network and cluster-based mode simulation operating in the point-to-point mode are shown in fig. 1 and 2, respectively. The clustered network is orderly connected compared to the network before clustering, and by utilizing a clustering-based architecture, network overhead and latency can be reduced.
Fig. 3 shows a comparison of the number of clusters as a function of the number of nodes. As the number of nodes in a network increases, the number of clusters for the three schemes is also increasing. Obviously, the IWLC of the present invention forms fewer clusters than the other two schemes. This is because uniform clustering can prevent the presence of clustering in which nodes are independent or the number of nodes is small, thereby optimizing the clustering structure. The number of clusters is smaller than the initial optimal value k, which may put more load on CH as the number of nodes increases. However, it can be observed from the IWLC scheme that the increasing trend of the number of clusters is more stable, which can better cope with the increase of the number of nodes and improve the expandability of the clustered network.
The foregoing is illustrative of the best mode of carrying out the invention, and is not presented in any detail as is known to those of ordinary skill in the art. The protection scope of the invention is defined by the claims, and any equivalent transformation based on the technical teaching of the invention is also within the protection scope of the invention.
Claims (2)
1. An intelligent cluster clustering method based on a K-means++ clustering algorithm is characterized by comprising the following steps of;
step 1, determining the initial clustering number k * ，
Wherein B is 1 And B 2 Bandwidth of intra-cluster and inter-cluster communication, respectively, N being the number of unmanned aerial vehicles;
step 2, the intelligent platform node is modeled as a point set s= { S 1 ,s 2 ,...s i ...,s N Randomly selecting k from a set of points * Initial cluster centers;
step 3, dividing each node into clusters corresponding to the cluster centers closest to the nodes;
step 4, calculating the cluster center probability of the cluster after the node in each cluster is selected as the next iteration, and selecting the node with the highest probability in each cluster as the cluster center of the next iteration, wherein the node s i Probability of being selected as cluster center for next iteration
D(s i ) For node s i Euclidean distance from the center of the current cluster; judging whether the cluster center position is not changed any more, if so, turning to the next step, otherwise, returning to the step 3;
and step 5, obtaining a final clustering result and selecting a cluster head.
2. The intelligent cluster clustering method based on the K-means++ clustering algorithm as set forth in claim 1, wherein the method for selecting cluster heads in step 5 comprises the steps of:
step 5.1, calculating the W value of each node in each final cluster, wherein the node i corresponds to
Wherein->
For the number of nodes around node i, (x) i ,y i ,z i ) Is the three-dimensional coordinates of node i, (x j ,y j ,z j ) Is the coordinates of the neighbor node j of node i;
and 5.2, selecting the node with the largest W value in each cluster as a cluster head.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310035576.0A CN116074991A (en) | 2023-01-10 | 2023-01-10 | Intelligent cluster clustering method based on K-means++ clustering algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310035576.0A CN116074991A (en) | 2023-01-10 | 2023-01-10 | Intelligent cluster clustering method based on K-means++ clustering algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116074991A true CN116074991A (en) | 2023-05-05 |
Family
ID=86183240
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310035576.0A Pending CN116074991A (en) | 2023-01-10 | 2023-01-10 | Intelligent cluster clustering method based on K-means++ clustering algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116074991A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105744566A (en) * | 2016-01-28 | 2016-07-06 | 北京邮电大学 | Self-adaptive on-demand weighted clustering method based on perceptron |
| CN108770029A (en) * | 2018-05-02 | 2018-11-06 | 天津大学 | Cluster-Based Routing Protocols for Wireless Sensor based on cluster and fuzzy system |
| CN108990129A (en) * | 2018-08-14 | 2018-12-11 | 长春理工大学 | A kind of wireless sensor network cluster-dividing method and system |
| CN113891426A (en) * | 2021-09-29 | 2022-01-04 | 光大科技有限公司 | Distributed multi-node networking method and device |
| CN115297497A (en) * | 2022-10-08 | 2022-11-04 | 中国人民解放军海军工程大学 | High-efficiency energy-saving clustering method based on biological heuristic algorithm |
-
2023
- 2023-01-10 CN CN202310035576.0A patent/CN116074991A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105744566A (en) * | 2016-01-28 | 2016-07-06 | 北京邮电大学 | Self-adaptive on-demand weighted clustering method based on perceptron |
| CN108770029A (en) * | 2018-05-02 | 2018-11-06 | 天津大学 | Cluster-Based Routing Protocols for Wireless Sensor based on cluster and fuzzy system |
| CN108990129A (en) * | 2018-08-14 | 2018-12-11 | 长春理工大学 | A kind of wireless sensor network cluster-dividing method and system |
| CN113891426A (en) * | 2021-09-29 | 2022-01-04 | 光大科技有限公司 | Distributed multi-node networking method and device |
| CN115297497A (en) * | 2022-10-08 | 2022-11-04 | 中国人民解放军海军工程大学 | High-efficiency energy-saving clustering method based on biological heuristic algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110362380B (en) | Network shooting range-oriented multi-objective optimization virtual machine deployment method | |
| CN112737837A (en) | Method for allocating bandwidth resources of unmanned aerial vehicle cluster under high dynamic network topology | |
| Yu et al. | Bio-Inspired Mobility Prediction Clustering Algorithm for Ad Hoc UAV Networks. | |
| CN106789320B (en) | Multi-population coevolution method for optimizing wireless sensor network topology | |
| CN113872661B (en) | Unmanned aerial vehicle network three-dimensional deployment method and system for accessing user classification service | |
| CN113031650B (en) | Unmanned aerial vehicle cluster cooperative target distribution design method under uncertain environment | |
| CN113573271A (en) | DV-hop positioning method based on Levy flight strategy and three-dimensional wolf algorithm optimization | |
| CN114885379B (en) | Large-scale unmanned aerial vehicle cluster self-adaptive clustering networking method | |
| CN110687926B (en) | Rapid formation method for unmanned aerial vehicle group | |
| CN117042083A (en) | Distributed reliable transmission guarantee method for unmanned cluster networking | |
| CN110177011B (en) | Network controller deployment method suitable for dynamic network structure | |
| CN111093216A (en) | Wireless sensor network node scheduling method based on improved binary particle swarm optimization | |
| CN115118728A (en) | Ant colony algorithm-based edge load balancing task scheduling method | |
| CN114828146A (en) | Routing method for geographical position of unmanned cluster based on neural network and iterative learning | |
| CN110248386B (en) | Hierarchical load balancing method for large-scale dense wireless network | |
| CN110933728B (en) | Mapping method, device and storage medium of virtualized wireless sensor network | |
| CN116074991A (en) | Intelligent cluster clustering method based on K-means++ clustering algorithm | |
| CN110673651B (en) | Robust formation method for unmanned aerial vehicle cluster under limited communication condition | |
| Wang et al. | Clustering strategy of UAV network based on deep Q-learning | |
| CN117156450A (en) | Mobile edge computing task unloading method based on improved artificial buzzing algorithm | |
| CN114783215B (en) | Unmanned aerial vehicle clustering method and device and electronic equipment | |
| Yu et al. | Comprehensive mobility prediction based clustering algorithm for Ad hoc UAV networks | |
| Vasilev et al. | Optimization of wireless node discovery in an IoT network | |
| CN108282742B (en) | Wireless optical communication network dynamic topology control method based on clustering | |
| CN114125759B (en) | Wireless sensor network clustering method based on improved particle swarm |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230505 |
|
| RJ01 | Rejection of invention patent application after publication |