CN-122002307-A - RU information acquisition method, container scheduling method and device based on RU information

CN122002307ACN 122002307 ACN122002307 ACN 122002307ACN-122002307-A

Abstract

The invention provides an RU information acquisition method, a container scheduling method and a device based on RU information, wherein the RU information acquisition method comprises the steps that first equipment acquires information of RU equipment managed by a schedulable node in a network cluster; the first device sends the information of the RU device to the second device for determining a target scheduling node among the schedulable nodes. Therefore, the capability of the existing second equipment is enhanced, the acquisition of RU information is supplemented, node selection is carried out on containers to be scheduled based on the acquired RU information of schedulable nodes, and therefore the situations that the containers to be scheduled, particularly the containers to be scheduled of high-real-time tasks, are scheduled to nodes which do not meet the RU requirements of the containers are avoided.

Inventors

ZHANG XIAOHUA
HUANG YIXUAN
NI WEICHEN
LI TING

Assignees

中国移动通信有限公司研究院
中国移动通信集团有限公司

Dates

Publication Date: 20260508
Application Date: 20241107

Claims (13)

1. A method for obtaining RU information in a radio frequency unit, comprising: The method comprises the steps that first equipment obtains information of RU equipment managed by a schedulable node in a network cluster; The first device sends the information of the RU device to the second device for determining a target scheduling node among the schedulable nodes.
2. The method of claim 1, wherein the first device obtaining information for RU devices managed by a schedulable node in the network cluster comprises at least one of: the first equipment receives information broadcast by RU equipment managed by a schedulable node in the network cluster; and the first equipment sends a first request to the network cluster and receives information of the RU equipment fed back by the RU equipment based on the first request, wherein the first request is used for requesting to acquire the information of the RU equipment managed by the schedulable node in the network cluster.
3. The method of claim 1, wherein the information of the RU device includes one of: First information; First information and second information; The first information is basic configuration information of the RU equipment, wherein the basic configuration information comprises at least one of equipment address, equipment capability, port address of equipment, port description of the equipment and virtual local area network identifier VLAN ID of the equipment port; The second information includes at least one of a device name, a device model number, a device manufacturer, a frequency band supported by the device, a multiple input multiple output MIMO configuration of the device.
4. A method according to claim 3, wherein, in case the information comprises first information and second information, the first device obtaining information of RU devices managed by a schedulable node in the network cluster comprises: The first equipment receives the first information and the second information sent by the RU equipment; Or alternatively The first equipment receives first information sent by the RU equipment; The first device sends a second request to a network management unit in the network cluster, wherein the second request is used for requesting to acquire the second information of the RU device, and the network management unit receives and stores the second information of the RU device when the RU device is registered; the first device receives second information of the RU device fed back by the network management unit based on the second request.
5. The method of claim 1, wherein the first device transmitting information of the RU device to the second device for use in determining a target scheduling node among schedulable nodes comprises: The first device invokes an interface of the second device to create resource description information containing information of the RU device, and sends the resource description information to the second device for determining a target scheduling node in the schedulable nodes.
6. The method of claim 5, wherein, in the case where the RU device is a direct connection device of the first device, the resource description information includes at least one of a device model, a device manufacturer, a frequency band supported by the device, a MIMO configuration of the device, a device capability; In the case that the RU equipment is a direct connection equipment of the first equipment in the network cluster, the resource description information comprises at least one of equipment address, equipment capability, port address of equipment, port description of equipment, VLAN ID of equipment port and custom performance index, wherein the custom performance index at least comprises time delay information between the custom performance index and the server node.
7. A method for scheduling containers based on RU information, comprising: The second equipment receives a container scheduling request of a user, wherein the container scheduling request carries RU demand information of a container to be scheduled; the second equipment receives information of RU equipment managed by the schedulable node and sent by the first equipment; The second equipment determines a target scheduling node from the schedulable nodes based on the information of the RU equipment and the RU demand information; and the second equipment dispatches the container to be dispatched to the target dispatching node.
8. The method of claim 7, wherein the second device determining a target scheduling node from the schedulable nodes based on the information of the RU device and the RU demand information comprises: the second equipment traverses all the schedulable nodes and executes an alternative node determining step on each schedulable node until an alternative node list is determined; The method comprises the steps of determining the candidate node, wherein the step of determining the candidate node comprises the steps of randomly selecting one schedulable node from all schedulable nodes by a second device, determining whether RU information managed by the randomly selected schedulable node meets each requirement in the RU requirement information or not, classifying the randomly selected schedulable node into a candidate node list if the RU information managed by the randomly selected schedulable node meets each requirement in the RU requirement information, and rejecting the randomly selected schedulable node if the RU information managed by the randomly selected schedulable node meets each requirement in the RU requirement information; The second equipment scores each alternative node in the alternative node list to obtain a score corresponding to each alternative node; the scoring method comprises the steps of scoring each index in information of RU equipment managed by the alternative node by the second equipment to obtain a score corresponding to each index, and carrying out weighted summation calculation on the score corresponding to each index to obtain the score corresponding to the alternative node.
9. An RU information acquisition apparatus, comprising: the acquisition module is used for acquiring information of the RU equipment managed by the schedulable node in the network cluster of the first equipment; and the first execution module is used for sending the information of the RU equipment to the second equipment so as to determine a target scheduling node in each schedulable node.
10. A RU information based container scheduling apparatus, comprising: the receiving module is used for receiving a container scheduling request of a user, wherein the container scheduling request carries RU demand information of a container to be scheduled; receiving information of RU equipment managed by a schedulable node sent by first equipment; a second execution module, configured to determine a target scheduling node from the schedulable nodes based on the information of the RU device and the RU demand information; and dispatching the container to be dispatched to the target dispatching node.
11. A network device, comprising a processor, a memory, and a program stored on the memory and executable on the processor, the program implementing the steps of the RU information acquisition method as recited in any one of claims 1-6 when executed by the processor, or the program implementing the steps of the RU information based container scheduling method as recited in any one of claims 7-8 when executed by the processor.
12. A computer readable storage medium, wherein a computer program is stored on the computer readable storage medium, the computer program implementing the steps of the RU information acquisition method according to any one of claims 1-6 when executed by a processor, or the steps of the RU information based container scheduling method according to any one of claims 7-8 when executed by the processor.
13. A computer program product comprising computer instructions which, when executed by a processor, implement the steps of the RU information acquisition method of any one of claims 1-6, or which, when executed by the processor, implement the steps of the RU information based container scheduling method of any one of claims 7-8.

Description

RU information acquisition method, container scheduling method and device based on RU information Technical Field The embodiment of the invention relates to the technical field of communication, in particular to an RU information acquisition method, an RU information-based container scheduling method and an RU information-based container scheduling device. Background In the prior art, the container schedule management tool is responsible for distributing containers to the appropriate nodes in the cluster. The scheduler's working process includes two phases, node filtering and node scoring. In the node filtering stage, the scheduler can filter out nodes which do not meet the conditions according to the scheduling requirements of the Pod and the characteristics of the nodes so as to reduce the candidate node set. Node filtering is typically based on the availability of resources such as CPUs (Central Processing Unit, central processing units), memory, etc., by checking the use of resources on the node to ensure that the node has enough resources to accommodate the new Pod. Node labels and tags the labels and tags of the nodes are checked to ensure that the nodes meet the scheduling requirements of Pod, such as specific hardware, operating system, etc. Affinity and anti-affinity-according to the affinity and anti-affinity rules of Pod, the nodes that are not satisfactory are filtered out. In the node scoring stage, the scheduler calculates a score for each node meeting the filtering condition, and selects the most suitable node to schedule Pod according to the score ranking. Node scoring is typically based on a criterion of resource utilization by evaluating the utilization of resources on the node, tending to select a node with a lower resource utilization. And (3) node load, namely evaluating the load condition of the nodes, and tending to select the node with lower load. And (3) evaluating the health status of the nodes, wherein the nodes with good health status tend to be selected. And (3) position sensing, namely selecting the node with the optimal position by considering the position information of the node, such as the area where the node is located, the rack and the like. Whereas in existing O-RAN (Open Radio Access Network ) architecture, at the O-Cloud (Cloud Infrastructure layer of open Radio access network) level, SMO (SERVICE MANAGEMENT AND Orchestration, service management and orchestration layer) may schedule RU (Radio Unit) dependent VNF (Virtual Network Function )/CNF (Cloud-native Network Function, cloud primary network function) on the appropriate O-Cloud cluster according to relevant resource information managed by IMS (Infrastructure MANAGEMENT SERVICES, infrastructure management service). However, on the one hand, the RU information needs to be manually queried, configured and reported, on the other hand, the Kubernetes scheduler in the cluster performs scheduling according to node resources (such as CPU and memory), and does not consider network topology and RU physical locations, when a subsequent RU establishes a connection with a corresponding VNF/CNF, an IP (Internet Protocol ) address of an O-RU (Open Radio Unit) controller, i.e., an O-DU (Open Distributed Unit ) is acquired through DHCP (Dynamic Host Configuration Protocol ), and NETCONF (Network Configuration Protocol, network configuration protocol) capability discovery and configuration management is performed, and in this process, the O-DU may be scheduled to a node far away from the O-RU, which causes a connection delay to increase or even fails to establish a connection, thereby damaging reliability and quality of service in the container. In the prior art, the container scheduling does not include the perception of RU information in a cluster, and a mechanism for scheduling containers according to RU information does not exist, so that there is a case that the containers are scheduled to nodes which do not meet the RU requirement of internal service, and further reliability and service quality of the service in the containers are damaged, particularly in a wireless cloud network service scene, many base station services in the containers have RU function requirements, and certain requirements on RU performance and parameters, and once the containers are scheduled to the nodes which do not meet the certain RU requirement, the availability of the base station service is affected immediately. Disclosure of Invention The embodiment of the invention provides an RU information acquisition method, an RU information-based container scheduling method and an RU information-based container scheduling device, which are used for solving the technical problems that in the prior art, container scheduling does not comprise sensing of RU information in a cluster, and a mechanism for scheduling containers according to the RU information does not exist, so that the containers are scheduled to nodes which do not meet the RU requirements of inte