Network recommendation method and device, electronic equipment, chip and medium

Abstract

The invention provides a network recommendation method and device, electronic equipment, a chip and a medium, and relates to the technical field of cloud computing. The network recommendation method comprises the steps of collecting network feature factors of a bare metal server in multiple dimensions, wherein the multiple dimensions comprise at least two of data traffic, network networking, network configuration, overlay and tenant service; and based on the network feature factors, recommending a target position of the access network to the bare metal server through a network recommendation model. Through the technical scheme provided by the invention, the problem that the tenant cannot obtain the optimal network in the bare metal server is solved, and the user experience of the tenant using the bare metal server is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of cloud computing, and in particular to a network recommendation method, device, electronic device, chip and medium. Background Art

[0002] The computing resource pool selects the computing instance to a physical server node and schedules the optimal computing node based on the server's computing attributes such as the CPU, memory, hard disk, affinity, etc. However, the network or network card of the computing instance can only be pre-planned based on the physical connection. Users can only select the port of the network device connected to the server, and cannot get the optimal network in the bare metal server. Summary of the invention

[0003] The present disclosure aims to solve one of the technical problems in the related art at least to some extent.

[0004] The present disclosure provides a network recommendation method, device, electronic device, chip and medium to solve the problem that tenants in bare metal servers cannot obtain the optimal network. Through correlation analysis of forwarding traffic, networking, configuration, overlay network, tenant business and other dimensions, the optimal network dynamic intelligent recommendation and scheduling capabilities centered on user business are automatically recommended to customers, which can improve the utilization rate of resources and energy and provide users with a better user experience.

[0005] A first aspect of the present disclosure provides a network recommendation method, the method comprising:

[0006] Collect network feature factors of bare metal servers in multiple dimensions, including at least two of data traffic, network networking, network configuration, overlay network, and tenant services;

[0007] Based on network characteristic factors, the network recommendation model recommends the target location for accessing the network to the bare metal server.

[0008] In one embodiment of the present disclosure, based on the network characteristic factors, a target location for accessing the network is recommended to the bare metal server through a network recommendation model, including:

[0009] Based on the network characteristic factors, the network similarity is determined one by one with each case feature in the case library of the network recommendation model through a similarity algorithm. The case library includes the characteristic factors of the existing network links of the network where the bare metal server is located;

[0010] The maximum value in the set of network similarities is taken as the target similarity, and the network position corresponding to the target similarity is taken as the target position;

[0011] Connect the bare metal server to the target location.

[0012] In one embodiment of the present disclosure, before determining the network similarity one by one with each case feature in the case library of the network recommendation model through a similarity algorithm based on the network feature factor, it also includes:

[0013] Record the different network links in the network where the bare metal server is located;

[0014] Convert network links into network characteristic factors of multiple dimensions;

[0015] Based on the network characteristic factors of multiple dimensions, different network links are classified by clustering algorithm to obtain classification results;

[0016] Add the classification results to the case library.

[0017] In one embodiment of the present disclosure, network characteristic factors of bare metal servers in multiple dimensions are collected, including:

[0018] Collect the traffic parameters of the bare metal server's network card and the switch connected to the bare metal server as network characteristic factors in the data traffic dimension. The traffic parameters include the real-time traffic of the network card and the switch, the bandwidth of the target port of the network card to access the switch, and the MAC address table of the switch.

[0019] Based on the MAC address table, determine the number of tenants and network access points for all ports of the switch;

[0020] Get the tenant priorities of all tenants of the bare metal server;

[0021] In the tenant business dimension, obtain the business priority and online status of each tenant of all tenants;

[0022] In the overlay dimension, collect the network bandwidth and latency of tenants;

[0023] In the network networking dimension, collect the status of all ports of the switch;

[0024] In the network configuration dimension, collect the status of the network card;

[0025] Traffic parameters, bandwidth of target ports, number of tenants on all ports, network access points, tenant priority, service priority, online status, network bandwidth, latency, status of all ports, and status of network cards are taken as network characteristic factors of bare metal servers.

[0026] In one embodiment of the present disclosure, collecting the network bandwidth and latency of a tenant includes:

[0027] Use ping and trace to dynamically measure tenants' network bandwidth and latency in the overlay dimension.

[0028] In one embodiment of the present disclosure, based on the network characteristic factors, a target location for accessing the network is recommended to the bare metal server through a network recommendation model, further comprising:

[0029] Based on the service priority and the status of the network card, determine the list of selectable target networks in the virtual LAN or virtual subnet of the bare metal server;

[0030] Determine the access point location of the target network in the selectable target network list according to the bandwidth of the target port, the real-time traffic of the switch, and the number of tenants of all ports;

[0031] The access point location is used as the target location.

[0032] A second aspect of the present disclosure provides a network recommendation device, the device comprising:

[0033] The collection module is used to collect network characteristic factors of bare metal servers in multiple dimensions, including data traffic, network networking, network configuration, overlay network, and tenant services;

[0034] The recommendation module is used to recommend a target location for accessing the network to the bare metal server through a network recommendation model based on network characteristic factors.

[0035] The third aspect embodiment of the present disclosure proposes an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute any one of the methods in the first aspect embodiment of the present disclosure.

[0036] The fourth aspect embodiment of the present disclosure proposes a non-transitory computer-readable storage medium storing computer instructions, characterized in that the computer instructions are used to enable a computer to execute the method in the first aspect embodiment of the present disclosure.

[0037] The fifth aspect embodiment of the present disclosure proposes a computer program product, characterized in that it includes a computer program, and when the computer program is executed by a processor, it implements any method in the first aspect embodiment of the present disclosure.

[0038] In summary, according to the network recommendation method proposed in the present invention, network characteristic factors of bare metal servers in multiple dimensions are collected, and the multiple dimensions include at least two of data traffic, network networking, network configuration, overlay network and tenant services, which provides data preparation for network recommendation for tenants of bare metal servers; based on the network characteristic factors, the target location for accessing the network is recommended to the bare metal server through the network recommendation model, which provides the optimal network location or path for tenants in the bare metal server, and improves the tenants' network usage experience.

[0039] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the description are used to explain the principles of the present disclosure, and do not constitute improper limitations on the present disclosure.

[0041] Figure 1 A schematic diagram of the server docking architecture and service process in the relevant technical cloud scenario;

[0042] Figure 2 A schematic diagram of a server managed TOR switch in the related art;

[0043] Figure 3 A flowchart of a network recommendation method according to an embodiment of the present disclosure;

[0044] Figure 4 It is a flowchart of a method for recommending a target location for accessing a network to a bare metal server through a network recommendation model based on network characteristic factors according to an embodiment of the present disclosure;

[0045] Figure 5 A flowchart of a case library for building a network recommendation model according to an embodiment of the present disclosure;

[0046] Figure 6 It is a flow chart of a method for collecting network characteristic factors of bare metal servers in multiple dimensions according to an embodiment of the present disclosure;

[0047] Figure 7 This is a flow chart of a method for collecting network bandwidth and latency of tenants according to an embodiment of the present disclosure;

[0048] Figure 8 A flowchart of an embodiment of the present disclosure for recommending a target location for accessing a network to a bare metal server through a network recommendation model based on network characteristic factors;

[0049] Fig. 9 A schematic diagram of network recommendation for tenants in a bare metal server according to an embodiment of the present disclosure;

[0050] Fig.10 A flowchart of a network recommendation method according to an embodiment of the present disclosure;

[0051] Fig.11 A schematic diagram of a decision tree model according to an embodiment of the present disclosure;

[0052] Fig.12A schematic diagram of implementing network traffic load balancing in a bare metal server according to an embodiment of the present disclosure;

[0053] Fig.13 The intention of realizing load balancing of the number of tenants in a bare metal server of an embodiment of the present disclosure is;

[0054] Fig.14 A schematic diagram of the structure of a network recommendation device according to an embodiment of the present disclosure;

[0055] Fig.15 It is a block diagram of an electronic device for implementing the network recommendation method disclosed in the present invention according to an exemplary embodiment. DETAILED DESCRIPTION

[0056] Embodiments of the present disclosure are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout identify the same or similar originals or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present disclosure, and should not be construed as limiting the present disclosure.

[0057] First, a brief introduction to the relevant terms in this disclosure is given:

[0058] Bare Metal (BM) Server: In this disclosure, it refers to a computing service that combines the elasticity of cloud services with the performance of physical machines. Bare Metal Servers combine the advantages of traditional physical servers and modern cloud computing to provide a high-performance, secure and flexible computing resource. It supports running code directly on the hardware, avoiding the performance loss caused by virtualization and ensuring the exclusivity and isolation of resources.

[0059] Software Defined Network (SDN): In this disclosure, it refers to an emerging network architecture and a way to implement network virtualization. Its core technology, OpenFlow, separates the control plane from the data plane of network devices, thereby achieving flexible control of network traffic, making the network more intelligent and providing a good platform for innovation of core networks and applications.

[0060] Top of Rack (TOR): In this disclosure, it refers to a network device that implements data exchange in a computer network, usually located at the top of a data center or computer room.

[0061] Figure 1This is a schematic diagram of the server docking architecture and service process in the relevant technical cloud scenario. In this cloud scenario, SDN is connected to the bare metal server, and the SDN controller is used to manage the TOR switch to enable the switching of the bare metal access deployment network and the tenant network on demand. Among them, the docking structure includes the following points:

[0062] 1. The console is connected to the Tianchi SDN network, and the console is connected to Nova and Ironic to deploy bare metal. Nova is a module in the openstack software used to manage virtual machines; Ironic is a module in the openstack software used to manage bare metal servers; openstack is an open source cloud computing management platform.

[0063] 2. Ironic is responsible for the lifecycle management and deployment of bare metal servers. SDN uniformly manages vSwitch and TOR switches, providing Ironic with the deployment network of bare metal servers and the connection and switching of tenant networks.

[0064] 3. Tenants apply for bare metal servers according to specifications to achieve interconnection between virtual machines, bare metal machines and container networks under the same virtual private cloud (VPC).

[0065] The business process includes the following steps:

[0066] 1. In SDN, the administrator discovers the device ports through network topology and monitors the port bandwidth and traffic of network devices.

[0067] 2. The administrator registers a bare metal server and collects the connection relationship between the server network card and the switch through self-checking.

[0068] 3. Tenant 1 applies for a VPC network and creates a virtual network (network1) and a virtual subnet (subnet1).

[0069] 4. The tenant applies for bare metal according to the specifications and selects the network card subnet or VLAN of the bare metal server.

[0070] 5. In Nova or Ironic, randomly select a network card to create a port for the bare metal server and update the port.

[0071] 6. On SDN, the deployment network and tenant network connected to the bare metal server are automatically opened. After the bare metal server is automatically installed and deployed successfully, it switches to the tenant network. Through TOR or VXLAN Tunnel Endpoint (VTEP), the virtual local area network (VLAN) is converted to a virtual extended local area network (VXLAN), thereby opening up the bare metal server network. Tenant applications can use the bare metal server and virtual machine network under the same VPC to communicate with each other.

[0072] In the related art, by applying for a bare metal server and selecting a network card, the tenant's application can achieve network connectivity between the virtual machine (VM) server and the bare metal (BM) server in the same VPC.

[0073] Figure 2 The figure is a schematic diagram of a server managed TOR switch in the related art. In the prior art, the computing resource pool selects the computing instance to a physical server node, and currently schedules the optimal computing node based on the computing properties of the server's central processing unit (CPU), memory, hard disk, affinity, etc. The network or network card of the computing instance can only be pre-planned based on the physical connection. The user selects the port of the network device to which the server is connected, and it is impossible to recommend the optimal network scheduling solution based on the latest business priority and the actual business traffic carried. For example, server 1 distributes data through TOR switch 1 of channel 1, and server 1 distributes data through TOR switch 2 of channel 2. When channel 1 is in a busy state and channel 2 is in an idle state, the server can only distribute data based on fixed channels 1 and 2, and cannot partially transfer or balance the load of channel 1 when it is busy to channel 2 which is currently in an idle state.

[0074] In the field of cloud computing, for the life cycle management of bare metal servers, there are optimal scheduling algorithms and solutions for the scheduling and selection of computing storage (CPU, storage, hard disk). In terms of network management, related technologies include the following steps to achieve network allocation for tenants in bare metal servers:

[0075] 1. Administrator registers the switch

[0076] 1) Connect the switch and bring the switch online.

[0077] 2) Collect switch port and link information.

[0078] 2. Administrator registers a bare metal server

[0079] 1) Register the bare metal server and its specifications.

[0080] 2) Collect bare metal server network cards and access links.

[0081] 3. Tenants apply for bare metal servers

[0082] 1) Tenants apply for bare metal servers according to specifications and deploy bare metal servers.

[0083] 2) Automatic bare metal deployment and switch to the tenant network.

[0084] 4. Tenants randomly select networks

[0085] 1) Tenant network selection: randomly select a subnet1|vlan1 network card.

[0086] 2) The tenant selects this network segment and VLAN. The location where SDN opens the network is currently to randomly select an access location for a network card from multiple network cards.

[0087] 5. Tenants use bare metal servers

[0088] 1) Tenants use bare metal servers.

[0089] The above steps can only provide networks for bare metal server tenants. The network is selected by the tenants themselves. SDN cannot recommend the best network for bare metal servers to tenants.

[0090] The method proposed in the present disclosure is applied to the network recommendation task in the bare metal server, and its application has a rich variety of scenarios. In cloud computing and data center scenarios, in cloud service providers and large data centers, automatically recommending the optimal network can help tenants choose the best network configuration to optimize performance and cost. This is particularly important for resource-intensive applications that require high-performance computing, big data analysis, and artificial intelligence training. In the content distribution network (CDN) scenario, CDN providers can use this technology to automatically select the best network path for content providers to ensure fast and reliable content delivery and improve user experience. In financial service scenarios, such as in financial transactions and online payment platforms, automatically recommending the optimal network can ensure low latency and high reliability of transactions, improve the overall performance of the system and user satisfaction. In the gaming industry, online games and e-sports platforms can provide a smoother gaming experience through automatic network optimization, reduce latency and freezes, and attract more players. In the field of distance education and telemedicine, automatically recommending the optimal network can provide more stable communication quality and ensure smooth transmission of teaching content and medical services. In the field of Internet of Things (IoT), IoT devices and platforms can improve the stability of connections and the efficiency of data transmission through automatic network optimization, especially in large-scale IoT deployments. For enterprises and government agencies, automatic recommendation of the optimal network can help them optimize their internal network structure and improve office efficiency and data security. In disaster recovery and business continuity planning scenarios, automatic network optimization can ensure that critical applications and services can run through the optimal network path at all times. In the fields of broadcasting and online live broadcasting, automatic recommendation of the optimal network can provide high-quality real-time video transmission, reduce buffering and interruptions. In the field of e-commerce, e-commerce platforms can improve website loading speed and transaction processing capabilities through automatic network optimization, thereby improving user experience and sales. In general, these scenarios require fast, reliable and secure network connections, and automatic recommendation of the optimal network can meet these needs and improve service quality and customer satisfaction. In the embodiments disclosed herein, there is no limitation on the application scenarios or application fields.

[0091] The network recommendation method provided by the present disclosure is described in detail below with reference to the accompanying drawings.

[0092] Figure 3 FIG. 1 is a flow chart of a network recommendation method according to an embodiment of the present disclosure. The method is executed in SDN. Figure 3 In the illustrated embodiment, the network recommendation method includes:

[0093] Step 301, collecting network characteristic factors of the bare metal server in multiple dimensions, where the multiple dimensions include at least two of data traffic, network networking, network configuration, overlay network, and tenant services.

[0094] In this embodiment, the network characteristic factor refers to an indicator used in network analysis to describe and measure various attributes of network nodes or edges, and these characteristic factors can reflect the topological structure, dynamic behavior and functional characteristics of the network. In the present disclosure, the current network is described by network characteristic factors of multiple dimensions, and the multiple dimensions include at least two of data traffic, network networking, network configuration, overlay network Overlay and tenant business, wherein network networking refers to connecting and configuring multiple computers or devices into a network that can communicate with each other and share resources, including local area networks, wide area networks and wireless networks. Network configuration refers to the specific settings of network devices (such as routers, switches and firewalls, etc.) to adapt to specific network environments and requirements. Overlay network Overlay refers to one or more virtual logical networks built on a basic physical network through virtualization technology. Tenant business refers to various applications and services running in bare metal servers and belonging to specific tenants. To make network recommendations, it is necessary to collect network characteristic factors of bare metal servers in multiple dimensions as preparation data.

[0095] Step 302: Based on the network characteristic factors, a network recommendation model is used to recommend a target location for accessing the network to the bare metal server.

[0096] In this embodiment, the network recommendation model refers to a method for recommending the optimal network location or path to tenants based on a machine learning algorithm and using network characteristic factors, including a case-based reasoning (CBR) algorithm. The target location of the access network refers to the optimal network location that the tenant of the bare metal server can currently access. After obtaining the network characteristic factors, the access network and target location are recommended to the bare metal server through the network recommendation model, which can provide the tenant with the optimal network location or path.

[0097] In summary, according to the network recommendation method proposed in the present invention, network characteristic factors of bare metal servers in multiple dimensions are collected, and the multiple dimensions include at least two of data traffic, network networking, network configuration, overlay network and tenant services, which provides data preparation for network recommendation for tenants of bare metal servers; based on the network characteristic factors, the target location for accessing the network is recommended to the bare metal server through the network recommendation model, which provides the optimal network location or path for tenants in the bare metal server, and improves the tenants' network usage experience.

[0098] Figure 4 The present invention is a flowchart of a method for recommending a target location for accessing a network to a bare metal server through a network recommendation model based on network characteristic factors according to an embodiment of the present invention. Figure 4 Yes Figure 3 Further description of step 302 is based on Figure 4 The embodiment shown comprises the following steps:

[0099] Step 401, based on the network characteristic factor, the network similarity is determined one by one with each case feature in the case library of the network recommendation model through a similarity algorithm, and the case library includes the characteristic factors of the existing network links of the network where the bare metal server is located.

[0100] In this embodiment, the network recommendation model stores a case library consisting of a large number of past case samples, which includes characteristic factors of existing network links in the network where the bare metal server is located. Based on the recorded current network characteristic factors, the network similarity is determined one by one with each case feature in the case library of the network recommendation model through a similarity algorithm, and the obtained network similarities can constitute a similarity set.

[0101] Step 402: Taking the maximum value in the set of network similarities as the target similarity, and taking the network position corresponding to the target similarity as the target position.

[0102] In this embodiment, the maximum value in the set of network similarities is taken as the target similarity, and the network position corresponding to the target similarity is taken as the target position.

[0103] Step 403: Connect the bare metal server to the target location.

[0104] In this embodiment, the network card of the bare metal server is connected to the target location. The tenants in the bare metal server can obtain the current optimal network location or path, thereby achieving the balance of network resources in the bare metal server.

[0105] Figure 5 The present invention is a flowchart of a case library for building a network recommendation model according to an embodiment of the present invention. Figure 5 Yes Figure 4 The description before step 401 is based on Figure 5 The embodiment shown comprises the following steps:

[0106] Step 501, record different network links in the network where the bare metal server is located.

[0107] In this embodiment, different network links in the network where the bare metal server is located are recorded, that is, different network links formed by network nodes at the upper layer of the bare metal server in the network topology and each virtual network node in the bare metal server are recorded.

[0108] Step 502: convert the network links into network characteristic factors of multiple dimensions.

[0109] In this embodiment, the recorded data of different network links are converted into network characteristic factors of multiple dimensions, and the network link data includes monitoring switches in preset time periods, collecting port traffic changes and port traffic occupancy rates; analyzing the online locations and specific distribution statistics of tenant bare metal servers and virtual machine servers by collecting the media access control (MAC) table of the switch port; collecting the bare metal server network card status and switch port status, as well as the online status of the associated tenant services; measuring the bandwidth and latency of the network through network measurement tools; and counting the number of tenant services and network segment distributions and the number of online connections of tenant services. The above collected, measured or statistical data are converted into network characteristic factors of multiple dimensions, that is, converted into at least two dimensions of data traffic, network networking, network configuration, overlay network, and tenant services to form network characteristic factors.

[0110] Step 503: Based on the network characteristic factors of multiple dimensions, different network links are classified by a clustering algorithm to obtain classification results.

[0111] In this embodiment, the network characteristic factors of multiple dimensions are clustered. Optionally, the characteristic data of different network links are classified by K Nearest Neighbor (KNN) to obtain different classification results.

[0112] Step 504: Add the classification results to the case library.

[0113] In this embodiment, the classification results obtained by clustering are added to the case library of the network recommendation model to provide reference cases for future network recommendations, so that tenants can obtain more refined and accurate network link recommendations.

[0114] Figure 6 The present invention is a flowchart of a method for collecting network characteristic factors of a bare metal server in multiple dimensions according to an embodiment of the present invention. Figure 6 Yes Figure 3 The specific description of step 301 is based on Figure 6 The embodiment shown comprises the following steps:

[0115] Step 601, collect the traffic parameters of the bare metal server's network card and the switch connected to the bare metal server as network characteristic factors of the data traffic dimension. The traffic parameters include the real-time traffic of the network card and the switch, the bandwidth of the target port of the network card accessing the switch, and the MAC address table of the switch.

[0116] In this embodiment, the traffic parameters of the bare metal server network card and the switch connected to the bare metal server are collected, and the traffic parameters include the real-time traffic of the bare metal server network card and the switch, the bandwidth of the target port of the network card accessing the switch, and the MAC address table of the switch. That is, the real-time traffic and port bandwidth indicators of the port between the switch and the bare metal server network card are obtained.

[0117] Step 602: Determine the number of tenants and network access points of all ports of the switch according to the MAC address table.

[0118] In this embodiment, the number of tenants and network access points of all ports of the switch can be obtained according to the MAC address table, and the number of port users and the index of the terminal access point of the network characteristic factor can be obtained.

[0119] Step 603: Obtain tenant priorities of all tenants of the bare metal server.

[0120] In this embodiment, the tenant priority refers to the priority assigned to the tenant in the bare metal server according to the tenant's level. For example, if the tenant is a gold user, or the tenant has rented for a long time or a large amount, then the tenant's priority is higher. The tenant priority indicators of all tenants are obtained in the user management database of the system.

[0121] Step 604: In the tenant service dimension, the service priority and online status of each tenant of all tenants are obtained.

[0122] In this embodiment, in the tenant service dimension, the service priority of each tenant preset by the system and the online status of each tenant are obtained.

[0123] Step 605: Collect the network bandwidth and latency of the tenant in the overlay network dimension.

[0124] In this embodiment, in the overlay dimension, the network bandwidth and latency values ​​of the tenants are collected to obtain the network bandwidth and latency of each tenant in the virtual network.

[0125] Step 606: In the network networking dimension, the status of all ports of the switch is collected.

[0126] In this embodiment, in the network networking dimension, the server name connected to the switch and the status of all ports of the switch are collected.

[0127] Step 607: In the network configuration dimension, collect the status of the network card.

[0128] In this embodiment, in the network configuration dimension, the status of the network card is collected, including the status of the network card device of the bare metal server or virtual machine server, the network card device of the virtual subnet or virtual local area network, etc.

[0129] Step 608, traffic parameters, bandwidth of the target port, number of tenants of all ports, network access point, tenant priority, service priority, online status, network bandwidth, latency, status of all ports and status of the network card are used as network characteristic factors of the bare metal server.

[0130] In this embodiment, the traffic parameters, bandwidth of the target port, number of tenants of all ports, network access point, tenant priority, service priority, online status, network bandwidth, latency, status of all ports and status of the network card collected in the above steps are used as network characteristic factors of the bare metal server, which provide case characteristic data for the case library of the network recommendation model. At the same time, it also provides input data for the network recommendation model, thereby making optimization recommendations for the network.

[0131] Figure 7 The present invention is a flowchart of a method for collecting network bandwidth and latency of tenants according to an embodiment of the present invention. Figure 7 Yes Figure 6 The specific description of step 605 is based on Figure 7 The embodiment shown comprises the following steps:

[0132] Step 701: Dynamically measure the network bandwidth and latency of the tenant in the overlay dimension of the overlay network through ping and trace.

[0133] In this embodiment, ping refers to a basic network command used to detect the connectivity between two network nodes. It checks whether the host is reachable by sending an ICMP echo request and waiting for a response, and measures the round-trip time of the data packet. Trace refers to tracking and displaying the IP addresses of all routers that the data packet passes through during the transmission from the source host to the target host, as well as the delay time of each transmission. The ping and trace measurement tools are used to dynamically measure the network bandwidth and latency values ​​of the tenant in the overlay dimension of the overlay network. The network information of the tenants in the bare metal server in the overlay dimension of the overlay network is collected.

[0134] Figure 8 This is a flowchart of an embodiment of the present disclosure for recommending a target location for accessing a network to a bare metal server through a network recommendation model based on network characteristic factors. Figure 8 Yes Figure 3 Another description of step 302 is based on Figure 8 The embodiment shown comprises the following steps:

[0135] Step 801: Determine a list of selectable target networks in a virtual local area network or virtual subnet of a bare metal server based on the service priority and the status of the network card.

[0136] In this embodiment, the optional target network list refers to a list of network links or locations in a virtual local area network (vlan) or a virtual subnet (subnet), including the optimal network location or path. The optional target network list in the virtual local area network or virtual subnet is listed according to the tenant's service priority and the status of the network card in the bare metal server.

[0137] Step 802: Determine the access point location of the target network in the optional target network list according to the bandwidth of the target port, the real-time traffic of the switch, and the number of tenants of all ports.

[0138] In this embodiment, the optimal access point position of the current target network is determined in the optional target network list according to the bandwidth of the target port, the real-time traffic of the switch, and the number of tenants of all ports of the switch.

[0139] Step 803: Use the access point location as the target location.

[0140] In this embodiment, the access point location of the target network is used as the target location, providing the tenant with an optimal network, thereby improving the tenant's experience of using the network in the bare metal server.

[0141] In one embodiment of this embodiment,

[0142] Fig. 9 FIG. 1 is a schematic diagram of a bare metal server performing network recommendation for a tenant in an embodiment of the present disclosure. Fig. 9As shown in the figure, the MAC address of the bare metal server (bare metal) and the port of the switch connected to the bare metal are collected, the MAC address and host node of the container in the bare metal server are collected, and the MAC address and host node of the virtual machine (VM) in the bare metal server are collected. Based on the network data collected from the bare metal, container and VM, a service is provided using the network evaluation recommendation model to provide the best network recommendation for tenants. The best network recommendation model is composed of model factors and KNN algorithm. The model factors include four types, namely business, configuration, networking and traffic. Business types include tenant 1, application 1, virtual network network1, virtual subnet subnet1, and virtual LAN vlan1. Configuration types include bare metal server port port1, virtual network network1, virtual LAN vlan1, switch device device1 and all switch ports device_port1. Networking types include the upper-layer host name host connected to the bare metal server, the network card and port of the bare metal server. Traffic types include the device name device1 of the switch device or bare metal server device, all the ports device_port1 of the switch, the bandwidth bandwidth (bw) of the switch port connected to the bare metal server, the number of data packets rate_counter, and the MAC address. Through the weighted summation of the four types of variables of business, configuration, networking, and traffic, the KNN algorithm is used to train the model in the cloud using the data set formed by the four types of variables to obtain a case library of the network recommendation model, and online reasoning is performed on the edge to intelligently decide an optimal network solution. Decision input is made based on the data of the network solution, and network parameters are issued to tenants and applications through the Neutron network based on the parameters of tenants, applications, virtual networks, virtual subnets, and virtual LANs. The network configuration of tenants is completed by updating the ports, virtual networks, virtual LANs, bare metal servers and switches, and bare metal servers and switches. Continuous monitoring of the network is completed through the ports, port bandwidth, number of data packets, and MAC addresses of bare metal servers and switches, and bare metal servers and switches. This is to complete the configuration of the optimal network for tenants using bare metal servers and update the optimal network for other times or other tenants, ensuring that all tenants can receive recommendations for the optimal network.

[0143] Fig.10 FIG. 1 is a flow chart of a network recommendation method according to an embodiment of the present disclosure. Fig.10 As shown, for the administrator, it includes the following steps:

[0144] 1. Administrator registers the switch

[0145] 1) Connect the switch and bring the switch online.

[0146] 2) Collect switch port and link information.

[0147] 3) Monitor the mac table learned by the switch port.

[0148] 4) Monitor the traffic statistics of the switch port.

[0149] 2. Administrator registers a bare metal server

[0150] 1) Register the bare metal server and its specifications.

[0151] 2) Collect bare metal server network cards and access links.

[0152] 3) Collect bare metal server network card bandwidth and status information.

[0153] For tenants, the steps include:

[0154] 1. Tenants apply for bare metal servers

[0155] 1) Tenants apply for bare metal servers according to specifications and deploy bare metal servers.

[0156] 2) The bare metal server is automatically installed and deployed, and switched to the tenant network.

[0157] 2. Tenants randomly select networks

[0158] 1) For tenant network selection, select a network card with the best subnet1, vlan1, host1, and bandwidth usage.

[0159] 2) The tenant selects this network segment and VLAN, and the SDN opens the network and selects the optimal network card access location from multiple network cards.

[0160] 3. Tenants use bare metal servers

[0161] Tenants use bare metal servers.

[0162] Among them, the overall architecture of the optimal network recommendation is:

[0163] 1. Data analysis

[0164] 1) Find the port where the bare metal server's network card is connected to the switch (network card mac->switch port->switch uplink port).

[0165] 2) Based on the bandwidth, traffic statistics, and mac table of the switch port, determine whether the port is idle and obtain the idle index.

[0166] 3) This shows that the switch connected to NIC 1 of this bare metal server is relatively busy, while the switch connected to NIC 2 is relatively idle.

[0167] 2. Control surface analysis

[0168] 1) Find the number of tenants and applications already in use by the current network VLAN and subnet.

[0169] 2) Calculate a weighted index based on tenant level and business level.

[0170] 3) Calculate the weighted index based on the configuration usage frequency of network VLANs and subnets.

[0171] 3. Best network recommendation

[0172] 1) First, calculate the currently available optimal network VLAN or subnet based on the control plane tenant service level and configuration.

[0173] 2) Then, based on the data plane bandwidth, traffic, and the actual number of users carried, the location for instantiation of this network (switch port or bare metal network card) is recommended.

[0174] Fig.11 It is a schematic diagram of a decision tree model of an embodiment of the present disclosure. The optimal location and path are recommended through the case reasoning technology CBR+ similarity algorithm (KNN / KD tree / Bayesian), and the path with small data plane forwarding traffic, online status, and small number of port mac users within a certain time period is selected. Select a location with high tenant service priority, small number of network segments used, and small number of online business connections. Select a location with few network configurations for services, small number of business connections, and small number of online port macs within a certain period of time. Through the decision tree model, network characteristic factors include tenant priority, service priority, tenant service configuration, real-time traffic of equipment, port bandwidth, number of port users, and correlation analysis and comprehensive weighting of terminal access points and equipment configuration services. Fig.11As shown, the tenant priority of the service is fully traversed to obtain the tenants with high priority and tenants with low priority. For the high priority tenants and low priority tenants, the strategy is optimized in the forwarding traffic, configuration status, network delay, number of service configurations, and number of online users. If the forwarding traffic is less than 80%, it is more likely to be selected (yes), otherwise, it is more likely not to be selected (no), indicating that there is a lot of unoccupied bandwidth in the data channel for a period of time, and the network recommendation will recommend the network with smaller forwarding traffic to the tenant. For the configuration status, online is preferred rather than offline. For the network delay, if it is less than 0.1ms, the network recommendation will recommend the network with low network delay to the tenant. For the number of service configurations, if the number of configured services is less than 10, the network recommendation recommends the network with fewer service configurations to the tenant, so as to obtain more resources to run the application or service of this tenant. For the number of online users, if it is less than 20, the network recommendation recommends the network with fewer online users to the tenant, so as to obtain more network resources available to the tenant. By making a group decision based on the comprehensive weighting of forwarding traffic, configuration status, network latency, number of business configurations and number of online users, and using preset values ​​or conditional judgments to implement conflict strategies, the preferred choice of network recommendation can be obtained. Based on the decision tree and the preset rule script, the network recommendation weight is obtained and saved in the case library of the network recommendation model. The network access point of the case with the highest similarity to the network recommendation weight in the real-time collected network data is used as the access point for recommending the optimal network, thereby improving the tenant's experience of using the network in the bare metal server.

[0175] Fig.12 FIG. 1 is a schematic diagram of implementing network traffic load balancing in a bare metal server according to an embodiment of the present disclosure. Fig.12 As shown, for the top-of-rack switches TOR1 and TOR2, the traffic distributed by the SDN server 1 is 100 and 0 respectively. Through the network recommendation method proposed in the present invention, the TOR2 network can be recommended to the tenant, so that the TOR2 with no traffic can be used for fast network communication, and the full load of traffic in TOR1 can be alleviated, thereby achieving load balancing of network traffic between TOR1 and TOR2.

[0176] Fig.13 This is an intention to achieve load balancing of the number of tenants in a bare metal server in an embodiment of the present disclosure. Fig.13 As shown in the figure, for the top-of-rack switches TOR1 and TOR2, server 1 distributes 3 tenants, namely tenants 1, 2 and 3, to TOR1, while TOR2 is not used by any tenant. After recommending the network to tenant 3, tenant 3 connects the network to the network of TOR2, and obtains a faster network experience. At the same time, the network load of TOR1 is reduced, and the network load balance of TOR1 and TOR2 is achieved.

[0177] The disclosed embodiment proposes a network recommendation method, which collects network characteristic factors of bare metal servers in multiple dimensions, including at least two of data traffic, network networking, network configuration, overlay network and tenant services, and provides data preparation for network recommendation for tenants of bare metal servers; based on the network characteristic factors, a target location for accessing the network is recommended to the bare metal server through a network recommendation model, and the optimal network location or path is provided for tenants in the bare metal server, thereby improving the network usage experience of the tenants.

[0178] Corresponding to the methods provided in the above-mentioned embodiments, the present disclosure further provides a network recommendation device. Since the device provided in the embodiment of the present disclosure corresponds to the methods provided in the above-mentioned embodiments, the implementation method of the method is also applicable to the device provided in this embodiment and will not be described in detail in this embodiment.

[0179] Fig.14 FIG. 1 is a schematic diagram of the structure of a network recommendation device 1400 according to an embodiment of the present disclosure. Fig.14 As shown, the network recommendation device includes:

[0180] The collection module 1410 is used to collect network characteristic factors of the bare metal server in multiple dimensions, including data traffic, network networking, network configuration, overlay network, and tenant services;

[0181] The recommendation module 1420 is used to recommend a target location for accessing the network to the bare metal server through a network recommendation model based on network characteristic factors.

[0182] In some embodiments, the recommendation module 1420 is used to:

[0183] Based on the network characteristic factors, the network similarity is determined one by one with each case feature in the case library of the network recommendation model through a similarity algorithm. The case library includes the characteristic factors of the existing network links of the network where the bare metal server is located;

[0184] The maximum value in the set of network similarities is taken as the target similarity, and the network position corresponding to the target similarity is taken as the target position;

[0185] Connect the bare metal server to the target location.

[0186] In some embodiments, before determining the network similarity one by one with each case feature in the case library of the network recommendation model through a similarity algorithm based on the network feature factor, the recommendation module 1420 is further used to:

[0187] Record the different network links in the network where the bare metal server is located;

[0188] Convert network links into network characteristic factors of multiple dimensions;

[0189] Based on the network characteristic factors of multiple dimensions, different network links are classified through clustering algorithms to obtain classification results;

[0190] Add the classification results to the case library.

[0191] In some embodiments, the acquisition module 1410 is used to:

[0192] Collect the traffic parameters of the bare metal server's network card and the switch connected to the bare metal server as network characteristic factors in the data traffic dimension. The traffic parameters include the real-time traffic of the network card and the switch, the bandwidth of the target port of the network card to access the switch, and the MAC address table of the switch.

[0193] Based on the MAC address table, determine the number of tenants and network access points for all ports of the switch;

[0194] Get the tenant priorities of all tenants of the bare metal server;

[0195] In the tenant business dimension, obtain the business priority and online status of each tenant of all tenants;

[0196] In the overlay dimension, collect the network bandwidth and latency of tenants;

[0197] In the network networking dimension, collect the status of all ports of the switch;

[0198] In the network configuration dimension, collect the status of the network card;

[0199] Traffic parameters, bandwidth of target ports, number of tenants on all ports, network access points, tenant priority, service priority, online status, network bandwidth, latency, status of all ports, and status of network cards are taken as network characteristic factors of bare metal servers.

[0200] In some embodiments, the collection module 1410 collects the network bandwidth and latency of the tenant in the following manner:

[0201] Use ping and trace to dynamically measure tenants' network bandwidth and latency in the overlay dimension.

[0202] In some embodiments, the recommendation module 1420 is further configured to:

[0203] Based on the service priority and the status of the network card, determine the list of selectable target networks in the virtual LAN or virtual subnet of the bare metal server;

[0204] Determine the access point location of the target network in the selectable target network list according to the bandwidth of the target port, the real-time traffic of the switch, and the number of tenants of all ports;

[0205] The access point location is used as the target location.

[0206] In summary, the network recommendation device collects network characteristic factors of bare metal servers in multiple dimensions, including at least two of data traffic, network networking, network configuration, overlay network and tenant services; based on the network characteristic factors, the network recommendation model recommends the target location for accessing the network to the bare metal server. This device solves the problem that tenants in bare metal servers cannot obtain the optimal network, and improves the user experience of tenants using bare metal servers.

[0207] In the above embodiments provided by the present disclosure, the methods and devices provided by the embodiments of the present disclosure are introduced. In order to implement the functions in the methods provided by the above embodiments of the present disclosure, the electronic device may include a hardware structure and a software module, and implement the above functions in the form of a hardware structure, a software module, or a hardware structure plus a software module. One of the above functions may be executed in the form of a hardware structure, a software module, or a hardware structure plus a software module.

[0208] Fig.15 is a block diagram of an electronic device 1500 for implementing the above network recommendation method according to an exemplary embodiment.

[0209] For example, the electronic device 1500 may be a mobile phone, a computer, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0210] Reference Fig.15 , the electronic device 1500 may include one or more of the following components: a processing component 1502 , a memory 1504 , a power component 1506 , a multimedia component 1508 , an audio component 1510 , an input / output (I / O) interface 1512 , a sensor component 1514 , and a communication component 1516 .

[0211] The processing component 1502 generally controls the overall operation of the electronic device 1500, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 1502 may include one or more processors 1520 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 1502 may include one or more modules to facilitate the interaction between the processing component 1502 and other components. For example, the processing component 1502 may include a multimedia module to facilitate the interaction between the multimedia component 1508 and the processing component 1502.

[0212] The memory 1504 is configured to store various types of data to support operations on the electronic device 1500. Examples of such data include instructions for any application or method operating on the electronic device 1500, contact data, phone book data, messages, pictures, videos, etc. The memory 1504 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0213] The power supply component 1506 provides power to the various components of the electronic device 1500. The power supply component 1506 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the electronic device 1500.

[0214] The multimedia component 1508 includes a screen that provides an output interface between the electronic device 1500 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 1508 includes a front camera and / or a rear camera. When the electronic device 1500 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0215] The audio component 1510 is configured to output and / or input audio signals. For example, the audio component 1510 includes a microphone (MIC), and when the electronic device 1500 is in an operation mode, such as a call mode, a recording mode, and a speech recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 1504 or sent via the communication component 1516. In some embodiments, the audio component 1510 also includes a speaker for outputting audio signals.

[0216] I / O interface 1512 provides an interface between processing component 1502 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: home button, volume button, start button, and lock button.

[0217] The sensor assembly 1514 includes one or more sensors for providing various aspects of status assessment for the electronic device 1500. For example, the sensor assembly 1514 can detect the open / closed state of the electronic device 1500, the relative positioning of components, such as the display and keypad of the electronic device 1500, and the sensor assembly 1514 can also detect the position change of the electronic device 1500 or a component of the electronic device 1500, the presence or absence of user contact with the electronic device 1500, the orientation or acceleration / deceleration of the electronic device 1500, and the temperature change of the electronic device 1500. The sensor assembly 1514 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 1514 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 1514 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0218] The communication component 1516 is configured to facilitate wired or wireless communication between the electronic device 1500 and other devices. The electronic device 1500 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, 4G LTE, 5G NR (NewRadio) or a combination thereof. In an exemplary embodiment, the communication component 1516 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 1516 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0219] In an exemplary embodiment, the electronic device 1500 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above methods.

[0220] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 1504 including instructions, and the instructions can be executed by the processor 1520 of the electronic device 1500 to perform the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0221] The embodiments of the present disclosure further provide a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute the network recommendation method described in the above embodiments of the present disclosure.

[0222] An embodiment of the present disclosure further provides a computer program product, including a computer program, which executes the network recommendation method described in the above embodiment of the present disclosure when a processor is used to execute the computer program.

[0223] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0224] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "illustrative embodiments", "examples", "specific examples" or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiments or examples are included in at least one embodiment or example of the present disclosure. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0225] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present disclosure includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present disclosure belong.

[0226] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processing module, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (control method), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or otherwise processing in a suitable manner if necessary, and then stored in a computer memory.

[0227] It should be understood that the various parts of the embodiments of the present disclosure can be implemented by hardware, software, firmware or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0228] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0229] In addition, each functional unit in each embodiment of the present disclosure may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium. The above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0230] Although the embodiments of the present disclosure have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present disclosure. A person skilled in the art may make changes, modifications, substitutions and variations to the above embodiments within the scope of the present disclosure.

Claims

1. A network recommendation method, characterized in that: The method comprises: Collect network characteristic factors of the bare metal server in multiple dimensions, where the multiple dimensions include at least two of data traffic, network networking, network configuration, overlay network, and tenant services; Based on the network characteristic factors, a target location for accessing the network is recommended to the bare metal server through a network recommendation model.

2. The method according to claim 1, characterized in that The recommending a target location for accessing the network to the bare metal server through a network recommendation model based on the network characteristic factor includes: Based on the network characteristic factor, determining the network similarity one by one with each case feature in the case library of the network recommendation model through a similarity algorithm, wherein the case library includes characteristic factors of existing network links of the network where the bare metal server is located; The maximum value in the set of network similarities is taken as the target similarity, and the network position corresponding to the target similarity is taken as the target position; Connect the bare metal server to the target location.

3. The method according to claim 2, characterized in that Before determining the network similarity one by one with each case feature in the case library of the network recommendation model based on the network feature factor through a similarity algorithm, it also includes: Record different network links in the network where the bare metal server is located; Converting the network links into network characteristic factors of the multiple dimensions; Based on the network characteristic factors of the multiple dimensions, classifying the different network links by a clustering algorithm to obtain a classification result; The classification result is added to the case library.

4. The method according to claim 1, characterized in that: The network characteristic factors of the bare metal server in multiple dimensions are collected, including: Collecting traffic parameters of the network card of the bare metal server and the switch connected to the bare metal server as the network characteristic factor of the data traffic dimension, the traffic parameters including the real-time traffic of the network card and the switch, the bandwidth of the target port of the network card connected to the switch, and the MAC address table of the switch; Determine the number of tenants and network access points of all ports of the switch according to the MAC address table; Obtain tenant priorities of all tenants of the bare metal server; In the tenant service dimension, obtaining the service priority and online status of each tenant of all the tenants; In the overlay network dimension, the network bandwidth and latency of the tenant are collected; In the network networking dimension, collecting the status of all ports of the switch; In the network configuration dimension, collecting the status of the network card; The traffic parameters, the bandwidth of the target port, the number of tenants of all ports, the network access point, the tenant priority, the service priority, the online status, the network bandwidth, the latency, the status of all ports and the status of the network card are used as the network characteristic factors of the bare metal server.

5. The method according to claim 4, characterized in that The collecting of the network bandwidth and latency of the tenant includes: The network bandwidth and latency of the tenant in the overlay network are dynamically measured through ping and trace.

6. The method according to claim 4, characterized in that The recommending a target location for accessing the network to the bare metal server through a network recommendation model based on the network characteristic factor also includes: Based on the service priority and the state of the network card, determine a list of optional target networks in the virtual local area network or virtual subnet of the bare metal server; Determine the access point location of the target network in the optional target network list according to the bandwidth of the target port, the real-time traffic of the switch and the number of tenants of all ports; The access point location is used as the target location.

7. A network recommendation device, characterized in that: The device comprises: A collection module is used to collect network characteristic factors of bare metal servers in multiple dimensions, including data traffic, network networking, network configuration, overlay network, and tenant services; A recommendation module is used to recommend a target location for accessing the network to the bare metal server through a network recommendation model based on the network characteristic factors.

8. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-6.

10. A computer program product, characterized in that The invention comprises a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 6.

Images