CN-116390145-B - System state prediction method and device for mobile communication system

CN116390145BCN 116390145 BCN116390145 BCN 116390145BCN-116390145-B

Abstract

The application relates to a system state prediction method for a mobile communication system, which comprises the steps of obtaining system parameters of all subsystems in the communication system, respectively constructing sub-vectors corresponding to all the subsystems according to the system parameters of all the subsystems, constructing system state vectors of the communication system according to all the sub-vectors, respectively determining clustering distances between the system state vectors and a plurality of system state clustering results, determining target system state clustering results corresponding to the system state vectors according to the clustering distances, and taking a system prediction state corresponding to the target system state clustering results as a target system prediction state. The method can reduce the calculated amount of system state prediction and simultaneously maintain the precision of system state prediction.

Inventors

LIU WEIWEI
WANG XIN
LIU WEI
ZHAO XIAOBO
HOU CONG
Chang Enbiao
LI ZIJING
ZHAO LINGLING
HUA KE
ZHANG XIBO
YIN YING
TANG YUJIAN
SUN JIANTAO
BAI HUAYING
HUANG YUBIN
TANG YI
DONG HAN
SHI LIYA
YANG TI
ZHOU LEI
Dou Songyu
MA LIMENG

Assignees

中国人民解放军61623部队

Dates

Publication Date: 20260508
Application Date: 20230406

Claims (10)

1. A system state prediction method for a mobile communication system, the method comprising: acquiring each historical system state vector and a system prediction state corresponding to each historical system state vector; aiming at any system prediction state, each historical system state vector is respectively used as a temporary system state clustering result, and clustering vectors corresponding to each temporary system state clustering result are respectively determined; Determining the vector distance between every two clustering vectors in the clustering vectors, and taking the minimum vector distance in the vector distances as a target vector distance; When the target vector distance is greater than a vector distance threshold, taking each temporary system state clustering result as each system state clustering result, or when the target vector distance is less than or equal to the vector distance threshold, merging the temporary system state clustering results corresponding to two clustering vectors corresponding to the target vector distance into one temporary system state clustering result, and jumping to a step of respectively determining the clustering vectors corresponding to each temporary system state clustering result; Acquiring system parameters of all subsystems in a communication system, respectively constructing sub-vectors corresponding to all the subsystems according to the system parameters of all the subsystems, and constructing a system state vector of the communication system according to all the sub-vectors, wherein the system parameters comprise operation parameters and/or detected environment parameters; determining each sub-vector of the clustering vector and the sub-vector distance between each sub-vector of the system state vector respectively aiming at the clustering vector corresponding to any system state clustering result; according to the sub-vector distances, determining a vector distance between the clustering vector and the system state vector, taking the vector distance as a clustering distance between the system state vector and the system state clustering result, and determining a target system state clustering result corresponding to the system state vector according to the clustering distance, wherein the system state clustering result comprises at least one historical system state vector which is a system state vector constructed in historical system state prediction; and taking the system prediction state corresponding to the target system state clustering result as a target system prediction state.
2. The method of claim 1, wherein prior to the obtaining system parameters for each subsystem in the communication system, the method further comprises: Under the condition that a target subsystem exists in the communication system and/or a target sub-vector exists in each historical system state vector, each historical system state vector is adjusted so that each sub-vector of each adjusted historical system state vector corresponds to each sub-system in the communication system one by one, wherein the target sub-system is a sub-system which does not have a corresponding relation with any sub-vector, and the target sub-vector is a sub-vector which does not have a corresponding relation with any sub-system; And carrying out clustering treatment on each historical system state vector again to obtain a plurality of system state clustering results.
3. The method of claim 2, wherein adjusting each of the historical system state vectors in the presence of a target subsystem in the communication system and/or in the presence of a target sub-vector in each of the historical system state vectors comprises: If a target subsystem exists, adding a sub-vector corresponding to the target subsystem in each historical system state vector; and deleting the target sub-vector from each historical system state vector when the target sub-vector exists.
4. The method according to claim 1, wherein the method further comprises: under the condition that a state adjustment instruction is received, the system prediction state corresponding to the system state vector is adjusted to be the system prediction state indicated by the state adjustment instruction; and taking the system state vector with the system prediction state adjusted as the historical system state vector.
5. A system state predicting apparatus for a mobile communication system, the apparatus comprising: the acquisition module is used for acquiring each historical system state vector and a system prediction state corresponding to each historical system state vector; The first clustering module is used for regarding any system prediction state, taking each historical system state vector as a temporary system state clustering result respectively, and determining a clustering vector corresponding to each temporary system state clustering result respectively; the method comprises the steps of determining a vector distance between every two clustering vectors in the clustering vectors, taking the smallest vector distance in the vector distances as a target vector distance, taking each temporary system state clustering result as each system state clustering result when the target vector distance is larger than a vector distance threshold, or combining the temporary system state clustering results corresponding to the two clustering vectors corresponding to the target vector distance into one temporary system state clustering result when the target vector distance is smaller than or equal to the vector distance threshold, and jumping to a step of respectively determining the clustering vectors corresponding to each temporary system state clustering result; The system comprises a construction module, a detection module and a control module, wherein the construction module is used for acquiring system parameters of all subsystems in a communication system, respectively constructing sub-vectors corresponding to all the subsystems according to the system parameters of all the subsystems, and constructing a system state vector of the communication system according to all the sub-vectors, wherein the system parameters comprise operation parameters and/or detected environment parameters; The system state clustering module is used for determining the sub-vector distance between each sub-vector of the clustering vector and each sub-vector of the system state vector according to the sub-vector distance, determining the vector distance between the clustering vector and the system state vector, taking the vector distance as the clustering distance between the system state vector and the system state clustering result, and determining the target system state clustering result corresponding to the system state vector according to each clustering distance, wherein the system state clustering result comprises at least one historical system state vector which is a system state vector constructed in the historical system state prediction; And the first processing module is used for taking the system prediction state corresponding to the target system state clustering result as a target system prediction state.
6. The apparatus of claim 5, wherein the apparatus further comprises: The first adjusting module is configured to adjust each historical system state vector so that each sub-vector of each adjusted historical system state vector corresponds to each sub-system in the communication system one by one when a target sub-system exists in the communication system and/or when a target sub-vector exists in each historical system state vector, wherein the target sub-system is a sub-system which does not have a corresponding relation with any sub-vector, and the target sub-vector is a sub-vector which does not have a corresponding relation with any sub-system; and the second clustering module is used for carrying out clustering processing on each historical system state vector again to obtain a plurality of system state clustering results.
7. The apparatus of claim 6, wherein the first adjustment module is further configured to: If a target subsystem exists, adding a sub-vector corresponding to the target subsystem in each historical system state vector; and deleting the target sub-vector from each historical system state vector when the target sub-vector exists.
8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 4 when the computer program is executed.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 4.
10. A computer program product comprising a computer program, characterized in that the computer program, when executed by a processor, implements the steps of the method of any of claims 1 to 4.

Description

System state prediction method and device for mobile communication system Technical Field The present application relates to the field of mobile communications technologies, and in particular, to a system state prediction method and apparatus for a mobile communications system. Background The mobile communication system is an important component of the communication system, utilizes the comprehensive service digital network and the Internet to integrate the mobile communication network with the motion communication network, makes the best of the invention, and can expand the communication coverage through the lift-off platform communication system and the mobile satellite communication system, thereby forming an integrated communication system. Compared with civil information communication systems, mobile communication systems exhibit characteristics of multiple device types, multiple terminal types, and complex and variable operating environments. At present, most of operation and maintenance state prediction technologies for communication systems are concentrated on civil communication systems, the civil communication systems are generally arranged in a machine room, the environment inside the machine room is stable, the equipment intervals are far, and the influence among the equipment intervals is negligible. However, the operating environment of the mobile communication system is much more complex than that of the civil communication system, and the distance between devices in the mobile communication system is relatively short, so that the devices are easy to influence other nearby devices when operating. If the operation and maintenance state prediction method for the civil communication system in the prior art is adopted, the influence factors to be considered are very many, so that modeling is complex, the prediction calculation amount is high, and the mobile communication system may not bear the calculation amount required by the system state prediction. Disclosure of Invention In view of the foregoing, it is desirable to provide a system state prediction method and apparatus for a mobile communication system. In a first aspect, the present application provides a system state prediction method for a mobile communication system. The method comprises the following steps: Acquiring system parameters of all subsystems in a communication system, respectively constructing sub-vectors corresponding to all the subsystems according to the system parameters of all the subsystems, and constructing a system state vector of the communication system according to all the sub-vectors, wherein the system parameters comprise operation parameters and/or detected environment parameters; Determining clustering distances between the system state vector and a plurality of system state clustering results respectively, and determining a target system state clustering result corresponding to the system state vector according to each clustering distance, wherein the system state clustering result comprises at least one historical system state vector which is a system state vector constructed in historical system state prediction; and taking the system prediction state corresponding to the target system state clustering result as a target system prediction state. In one embodiment, before the acquiring the system parameters of each subsystem in the communication system, the method further includes: Acquiring each historical system state vector and the system prediction state corresponding to each historical system state vector; and carrying out hierarchical clustering processing on each historical system state vector corresponding to any system prediction state to obtain a plurality of system state clustering results corresponding to the system prediction state. In one embodiment, the hierarchical clustering processing is performed on each historical system state vector corresponding to the system prediction state to obtain a plurality of system state clustering results corresponding to the system prediction state, where the hierarchical clustering processing includes: Respectively taking each historical system state vector as a temporary system state clustering result, and respectively determining a clustering vector corresponding to each temporary system state clustering result; Determining the vector distance between every two clustering vectors in the clustering vectors, and taking the minimum vector distance in the vector distances as a target vector distance; under the condition that the target vector distance is larger than a vector distance threshold value, taking each temporary system state clustering result as each system state clustering result, or alternatively; and merging the temporary system state clustering results corresponding to the two clustering vectors corresponding to the target vector distance into one temporary system state clustering result and jumping to the step of respectively determining the clu