A clustering method and system of 6g network coordination sensing device

Abstract

The present application relates to the technical field of mobile communication, and particularly relates to a clustering method and system of 6G integrated sensing network cooperative sensing device. The clustering method of the 6G integrated sensing network cooperative sensing device, the edge server collects and analyzes environmental information in real time, and adjusts the resource allocation strategy according to the environmental change; the future position of the sensing target is predicted by using historical data and machine learning algorithm; the dynamic clustering problem is modeled, and solved by a dynamic clustering algorithm based on sensing cost optimization, aiming at the characteristics of the sensing target movement and environmental dynamic change, taking minimizing the sensing cost as the clustering target, and realizing intelligent integrated sensing network cooperative sensing device clustering. The clustering method and system of the 6G integrated sensing network cooperative sensing device are flexible and reliable, realize intelligent integrated sensing network cooperative sensing device clustering, and lay a foundation for real-time collaborative sensing resource allocation.

Description

Technical Field

[0001] This invention relates to the field of mobile communication technology, and in particular to a clustering method and system for 6G integrated sensing network collaborative sensing devices. Background Technology

[0002] To meet the requirements of smart factories for flexible scheduling of Automated Guided Vehicles (AGVs), the factory itself deploys a large number of wireless communication nodes to ensure seamless wireless network coverage in the workshop and even the entire factory area. With the development of integrated sensing technology, it has become possible to simultaneously meet the communication and positioning needs of AGVs by utilizing the large number of 5G / B5G base stations deployed in the environment.

[0003] On the one hand, wireless resources can be used to enhance sensing capabilities, and sensing capabilities can share the same hardware and spectrum resources with communication capabilities to complete different types of sensing tasks. On the other hand, with the assistance of sensing capabilities, the efficiency of communication link establishment, management and networking processes will be further improved, and the quality of communication services will be improved, achieving mutual benefit between sensing and communication capabilities.

[0004] Furthermore, in complex environments, sensing tasks require collaborative processing by multiple base stations. Different stations can flexibly sense different targets and collect sensing information, while utilizing the available resources of different stations. However, Automated Guided Vehicles (AGVs) in factories are densely packed and mobile. How to cluster collaborative sensing devices and rationally utilize the capabilities of each node is a key research focus.

[0005] To address the challenges of sensing target movement and dynamic environmental changes, this invention proposes a clustering method and system for collaborative sensing devices in a 6G integrated sensing network. Summary of the Invention

[0006] To overcome the shortcomings of the prior art, this invention provides a simple and efficient clustering method and system for collaborative sensing devices in a 6G integrated sensing network.

[0007] This invention is achieved through the following technical solution:

[0008] A clustering method for collaborative sensing devices in a 6G integrated sensing network includes the following steps:

[0009] Step S1: Real-time collection and analysis of environmental information

[0010] The computing power of edge servers is used to collect and analyze environmental information in real time, including obstacle locations and AGV density, and resource allocation strategies are customized and adjusted according to environmental changes; historical data and machine learning algorithms are used to predict the future location of perceived targets.

[0011] In step S1, the Kalman filter algorithm and recurrent neural network are used to predict the future position of the perceived target.

[0012] Step S2: Construct a dynamic clustering model based on perceived cost optimization.

[0013] The dynamic clustering problem is modeled and solved using a dynamic clustering algorithm based on perception cost optimization. Considering the characteristics of target movement and dynamic environmental changes, the clustering objective is to minimize perception cost, thereby achieving intelligent clustering of collaborative sensing devices in a network of integrated sensing and communication.

[0014] In step S2, the coverage area of ​​the IPPO base station is analyzed and each IPPO base station is marked as an independent cluster. If the perception cost of merging two clusters decreases by more than a preset threshold, the corresponding two clusters are merged in pairs until there are no clusters that can be merged.

[0015] In step S2, a dynamic clustering algorithm is used to optimize base station cooperation. Intra-cluster sensing redundancy and inter-cluster interference are denoted as sensing costs. Minimizing sensing costs is the clustering objective, and the clustering optimization problem is expressed as:

[0016]

[0017] Among them, S ij (t) represents the similarity measure at time t, I ik (t) represents the interference intensity at time t, C(t) is the set of base stations within the cluster, c∈C(t), and k is the sensing target.

[0018] The similarity metric S ij (t) represents the coverage overlap between base station i and base station j at time t. ij (t) and channel correlation ρ ij The weighted sum of (t) is expressed as:

[0019] S ij (t)=w1·O ij (t)+w2·ρ ij (t)

[0020] Where w1 and w2 are the coverage overlap O of base station i and base station j at time t, respectively. ij (t) and channel correlation ρ ij The weights of (t);

[0021] The coverage overlap O ij (t) represents the percentage of the overlapping area of ​​the coverage areas of base station i and base station j at time t;

[0022]

[0023] Among them, A i (t) represents the coverage area of ​​base station i at time t (determined by beamwidth and transmit power), A j (t) represents the coverage area of ​​base station j at time t.

[0024] Channel correlation ρ ij (t) is the correlation coefficient based on Channel State Information (CSI) at time t, expressed as:

[0025]

[0026] Among them, H i (t) and H j (t) represents the channel state information matrix between base station i and base station j and the sensing target at time t. It is matrix H j The conjugate transpose of (t).

[0027] In the inter-cluster interference term, the interference intensity I at time t ik (t), represented as:

[0028]

[0029] in, H is the transmit power of base station i. ik (t) represents the complex channel gain between base station i and sensing target k, and d ik (t) represents the distance between base station i and sensing target k, and α is the path loss factor.

[0030] A clustering system for a 6G integrated sensing network collaborative sensing device, used to implement the above method, includes a data acquisition and processing module and a dynamic clustering module;

[0031] The data acquisition and processing module is responsible for using the computing power of the edge server to collect and analyze environmental information in real time, including obstacle locations and AGV density, and customizing resource allocation strategies according to environmental changes; it also uses historical data and machine learning algorithms to predict the future location of perceived targets.

[0032] The dynamic clustering module is responsible for modeling the dynamic clustering problem and solving it using a dynamic clustering algorithm based on perception cost optimization. Taking into account the characteristics of target movement and dynamic environmental changes, it aims to minimize perception cost and achieve intelligent clustering of collaborative sensing devices in a network of integrated sensing and communication.

[0033] A clustering computing device for a 6G integrated sensing network collaborative sensing device includes:

[0034] One or more processors, one or more memories, and one or more programs, wherein the one or more programs are stored in the one or more memories and configured to be executed by the one or more processors, and the one or more programs include instructions for performing any of the methods described above.

[0035] A computer-readable storage medium storing one or more programs, the one or more programs including instructions that, when executed by a cluster computing device of a 6G integrated sensing network cooperative sensing device, cause the cluster computing device of the 6G integrated sensing network cooperative sensing device to perform any of the methods described above.

[0036] The beneficial effects of this invention are: the clustering method and system of the 6G integrated sensing network collaborative sensing device are flexible and reliable, and can sense different targets and collect sensing information based on different sites. At the same time, it solves the problems of target movement and dynamic changes in the environment, realizes intelligent clustering of integrated sensing network collaborative sensing devices, and lays the foundation for the allocation of real-time collaborative sensing resources. Attached Figure Description

[0037] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0038] Appendix Figure 1 This is a schematic diagram of the clustering system architecture of the 6G integrated sensing network collaborative sensing device of the present invention. Detailed Implementation

[0039] To enable those skilled in the art to better understand the technical solutions of this invention, the technical solutions in the embodiments of this invention will be clearly and completely described below in conjunction with the embodiments of this invention. Obviously, the described embodiments are merely some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this invention.

[0040] The clustering method for collaborative sensing devices in the 6G integrated sensing network includes the following steps:

[0041] Step S1: Real-time collection and analysis of environmental information

[0042] The computing power of edge servers is used to collect and analyze environmental information in real time, including obstacle locations and AGV density, and resource allocation strategies are customized and adjusted according to environmental changes; historical data and machine learning algorithms are used to predict the future location of perceived targets.

[0043] In step S1, the Kalman filter algorithm and recurrent neural network are used to predict the future position of the perceived target.

[0044] Step S2: Construct a dynamic clustering model based on perceived cost optimization.

[0045] The dynamic clustering problem is modeled and solved using a dynamic clustering algorithm based on perception cost optimization. Considering the characteristics of target movement and dynamic environmental changes, the clustering objective is to minimize perception cost, thereby achieving intelligent clustering of collaborative sensing devices in a network of integrated sensing and communication.

[0046] In step S2, the coverage area of ​​the IPPO base station is analyzed and each IPPO base station is marked as an independent cluster. If the perception cost of merging two clusters decreases by more than a preset threshold, the corresponding two clusters are merged in pairs until there are no clusters that can be merged.

[0047] In step S2, a dynamic clustering algorithm is used to optimize base station cooperation. Intra-cluster sensing redundancy and inter-cluster interference are denoted as sensing costs. Minimizing sensing costs is the clustering objective, and the clustering optimization problem is expressed as:

[0048]

[0049] Among them, S ij (t) represents the similarity measure at time t, I ik (t) represents the interference intensity at time t, C(t) is the set of base stations within the cluster, c∈C(t), and k is the sensing target.

[0050] The similarity metric S ij (t) represents the coverage overlap between base station i and base station j at time t. ij (t) and channel correlation ρ ij The weighted sum of (t) is expressed as:

[0051] S ij (t)=w1·O ij (t)+w2·ρ ij (t)

[0052] Where w1 and w2 are the coverage overlap O of base station i and base station j at time t, respectively. ij (t) and channel correlation ρ ij The weights of (t);

[0053] The coverage overlap O ij (t) represents the percentage of the overlapping area of ​​the coverage areas of base station i and base station j at time t;

[0054]

[0055] Among them, A i (t) represents the coverage area of ​​base station i at time t (determined by beamwidth and transmit power), A j (t) represents the coverage area of ​​base station j at time t.

[0056] Channel correlation ρ ij (t) is the correlation coefficient based on Channel State Information (CSI) at time t, expressed as:

[0057]

[0058] Among them, H i (t) and H j (t) represents the channel state information matrix between base station i and base station j and the sensing target at time t. It is matrix H j The conjugate transpose of (t).

[0059] In the inter-cluster interference term, the interference intensity I at time t ik (t), represented as:

[0060]

[0061] Among them, P i s (t) represents the transmit power of base station i, H ik (t) represents the complex channel gain between base station i and sensing target k, and d ik (t) represents the distance between base station i and sensing target k, and α is the path loss factor.

[0062] In step S2, the pseudocode for the dynamic clustering algorithm is as follows:

[0063] Algorithm 1: Dynamic clustering algorithm based on perceptual cost optimization:

[0064] Input: Coverage area of ​​the IPPO base station;

[0065] Initialization: Each base station is an independent cluster;

[0066] Do{

[0067] The perceived cost reduction after merging clusters c1 and c2 exceeds the threshold Δ th If so, then merge;

[0068] Until the cost decrease of all possible clusters to be merged is less than Δ th .

[0069] Output: Collaboration relationship diagram of IPPO base stations.

[0070] The clustering system of the 6G integrated sensing network collaborative sensing device is used to implement the above method, including a data acquisition and processing module and a dynamic clustering module;

[0071] The data acquisition and processing module is responsible for using the computing power of the edge server to collect and analyze environmental information in real time, including obstacle locations and AGV density, and customizing resource allocation strategies according to environmental changes; it also uses historical data and machine learning algorithms to predict the future location of perceived targets.

[0072] The dynamic clustering module is responsible for modeling the dynamic clustering problem and solving it using a dynamic clustering algorithm based on perception cost optimization. Taking into account the characteristics of target movement and dynamic environmental changes, it aims to minimize perception cost and achieve intelligent clustering of collaborative sensing devices in a network of integrated sensing and communication.

[0073] The cluster computing device of this 6G integrated sensing network collaborative sensing device includes:

[0074] One or more processors, one or more memories, and one or more programs, wherein the one or more programs are stored in the one or more memories and configured to be executed by the one or more processors, and the one or more programs include instructions for performing any of the methods described above.

[0075] The computer-readable storage medium stores one or more programs, the one or more programs including instructions that, when executed by the cluster computing device of the 6G integrated sensing network cooperative sensing device, cause the cluster computing device of the 6G integrated sensing network cooperative sensing device to perform any of the methods described above.

[0076] This clustering method and system for collaborative sensing devices in a 6G integrated sensing network is designed for 6G integrated sensing networks. Based on different sites, it can flexibly sense different targets and collect sensing information. It can simultaneously utilize the characteristics of available resources at different sites to solve the problems of target movement and dynamic environmental changes. With minimizing sensing costs as the clustering objective, it realizes intelligent clustering of collaborative sensing devices in an integrated sensing network, laying the foundation for real-time collaborative sensing resource allocation.

[0077] The embodiments described above are merely one specific implementation of the present invention. Ordinary changes and substitutions made by those skilled in the art within the scope of the technical solution of the present invention should be included within the protection scope of the present invention.

Claims

1. A clustering method for collaborative sensing devices in a 6G integrated sensing network, characterized in that: Includes the following steps: Step S1: Real-time collection and analysis of environmental information The computing power of edge servers is used to collect and analyze environmental information in real time, including obstacle locations and AGV density, and resource allocation strategies are customized and adjusted according to environmental changes; historical data and machine learning algorithms are used to predict the future location of perceived targets. Step S2: Construct a dynamic clustering model based on perceived cost optimization. The dynamic clustering problem is modeled and solved using a dynamic clustering algorithm based on perception cost optimization. Considering the characteristics of target movement and dynamic environmental changes, the clustering objective is to minimize perception cost, thereby achieving intelligent clustering of collaborative sensing devices in a network of integrated sensing and communication. In step S2, a dynamic clustering algorithm is used to optimize base station cooperation. Intra-cluster sensing redundancy and inter-cluster interference are denoted as sensing costs. Minimizing sensing costs is the clustering objective, and the clustering optimization problem is expressed as: in, This represents the similarity measure at time t. This represents the intensity of the interference at time t. For the set of base stations within the cluster, , where k is the target being perceived.

2. The clustering method for 6G integrated sensing network cooperative sensing devices according to claim 1, characterized in that: In step S1, the Kalman filter algorithm and recurrent neural network are used to predict the future position of the perceived target.

3. The clustering method for 6G integrated sensing network cooperative sensing devices according to claim 1, characterized in that: In step S2, the coverage area of ​​the IPPO base station is analyzed and each IPPO base station is marked as an independent cluster. If the perception cost of merging two clusters decreases by more than a preset threshold, the corresponding two clusters are merged in pairs until there are no clusters that can be merged.

4. The clustering method for 6G integrated sensing network collaborative sensing devices according to claim 1, characterized in that: The similarity measure The coverage overlap between base station i and base station j at time t Channel correlation The weighted sum is expressed as: in, and The coverage overlap between base station i and base station j at time t are respectively. Channel correlation The weights; The coverage overlap Let be the percentage of the overlapping area of ​​the coverage areas of base station i and base station j at time t; in, Let be the coverage area of ​​base station i at time t. Let be the coverage area of ​​base station j at time t; Channel correlation Let be the correlation coefficient based on Channel State Information (CSI) at time t, expressed as: in, and These are the channel state information matrices between base station i and base station j and the sensing target at time t. It is a matrix The conjugate transpose of .

5. The clustering method for 6G integrated sensing network cooperative sensing devices according to claim 1, characterized in that: In the inter-cluster interference term, the interference intensity at time t , is represented as: in, Let i be the transmit power of base station i. Let be the complex channel gain between base station i and sensing target k. Let α be the distance between base station i and sensing target k, and α be the path loss factor.

6. A clustering system for 6G integrated sensing network collaborative sensing devices, characterized in that: The method for implementing any one of claims 1 to 5 includes a data acquisition and processing module and a dynamic clustering module; The data acquisition and processing module is responsible for using the computing power of the edge server to collect and analyze environmental information in real time, including obstacle locations and AGV density, and customizing resource allocation strategies according to environmental changes; it also uses historical data and machine learning algorithms to predict the future location of perceived targets. The dynamic clustering module is responsible for modeling the dynamic clustering problem and solving it using a dynamic clustering algorithm based on perception cost optimization. Taking into account the characteristics of target movement and dynamic environmental changes, it aims to minimize perception cost and achieve intelligent clustering of collaborative sensing devices in a network of integrated sensing and communication.

7. A clustering computing device for a 6G integrated sensing network collaborative sensing device, characterized in that: include: One or more processors, one or more memories, and one or more programs, wherein the one or more programs are stored in the one or more memories and configured to be executed by the one or more processors, the one or more programs including instructions for performing the method according to any one of claims 1 to 5.

8. A computer-readable storage medium for storing one or more programs, characterized in that: The one or more programs include instructions that, when executed by the cluster computing device of the 6G integrated sensing network collaborative sensing device, cause the cluster computing device of the 6G integrated sensing network collaborative sensing device to perform the method according to any one of claims 1 to 5.

Images