Network resource recommendation using a machine learning model
Resource utilization information including one or more of central processor utilization, memory utilization, and device load values are received from each of a plurality of network devices that compose an access network that is communicatively coupled to a core network. The resource utilization information is provided to a machine learning model to receive an output, wherein the machine learning model has been trained with historical resource utilization information associated with network devices that compose an access network, predetermined thresholds, and an impact to the access network of network resources being added to a core network. A recommended increase in network resources of the core network or the access network is sent to a destination based on the output.
1 . A method comprising:
receiving, by a computing system comprising one or more processor devices, from each of a plurality of network devices that compose an access network that is communicatively coupled to a core network and facilitates communications between the core network and user devices, resource utilization information comprising one or more of central processor utilization, memory utilization, and device load values;
providing the resource utilization information to a machine learning model to receive an output, wherein the machine learning model has been trained with historical resource utilization information associated with network devices that compose an access network, predetermined thresholds, and an impact to the access network of network resources being added to a core network;
based on the output, sending, to a destination a recommended increase in hardware network resources of the core network or the access network; and
based on the recommended increase in network resources, causing, by the computing system, a plurality of virtual network function (VNF) instances to be generated on a plurality of general-purpose computing devices of a simulation environment that is separate from the access network and the core network to implement the core network or the access network with the recommended network resources on the plurality of general-purpose computing devices, each VNF instance corresponding to one of the plurality of network devices in the core network or the access network.
2 . The method of claim 1 wherein receiving, from each of the plurality of network devices that compose an access network, resource utilization information further comprises:
iteratively polling, over a period of time, the plurality of network devices via SNMP to obtain the resource utilization information.
3 . The method of claim 1 wherein the resource utilization information includes network segment utilization values.
4 . The method of claim 1 wherein the device load values comprises one or more of a number of users currently connected to the network device and a peak usage of the network device.
5 . The method of claim 1 wherein the additional network resources comprises one or more of an additional mobile management entity (MME), a serving gateway, a home subscriber server and a packet data network gateway.
6 . The method of claim 1 wherein the additional network resources comprises an identified amount of additional memory for an existing network device.
7 . The method of claim 1 further comprising:
configuring, by the computing system based on configuration information, at least some of the VNF instances of the plurality of VNF instances;
obtaining, by the computing system, testing data and testing criteria;
submitting, by the computing system, the testing data to the network; and
outputting network test results based on the testing data and the testing criteria.
8 . A computing system comprising:
one or more processor devices of one or more computing devices, the one or more processor devices configured to:
receive, from each of a plurality of network devices that compose an access network that is communicatively coupled to a core network and facilitates communications between the core network and user devices, resource utilization information comprising one or more of central processor utilization, memory utilization, and device load values;
provide the resource utilization information to a machine learning model to receive an output, wherein the machine learning model has been trained with historical resource utilization information associated with network devices that compose an access network, predetermined thresholds, and an impact to the access network of network resources being added to a core network;
based on the output, send, to a destination a recommended increase in hardware network resources of the core network or the access network; and
based on the recommended increase in network resources, cause a plurality of virtual network function (VNF) instances to be generated on a plurality of general-purpose computing devices of a simulation environment that is separate from the access network and the core network to implement the core network or the access network with the recommended network resources on the plurality of general-purpose computing devices, each VNF instance corresponding to one of the plurality of network devices in the core network or the access network.
9 . The computing system of claim 8 wherein to receive, from each of the plurality of network devices that compose the access network, resource utilization information, the one or more processor devices are further configured to:
iteratively poll, over a period of time, the plurality of network devices via SNMP to obtain the resource utilization information.
10 . The computing system of claim 8 wherein the resource utilization information includes network segment utilization values.
11 . The computing system of claim 8 wherein the device load values comprises one or more of a number of users currently connected to the network device and a peak usage of the network device.
12 . The computing system of claim 8 wherein the additional network resources comprises one or more of an additional mobile management entity (MME), a serving gateway, a home subscriber server and a packet data network gateway.
13 . The computing system of claim 8 wherein the additional network resources comprises an identified amount of additional memory for an existing network device.
14 . The computing system of claim 8 wherein the one or more processor devices are further configured to:
configure, based on configuration information, at least some of the VNF instances of the plurality of VNF instances;
obtain testing data and testing criteria;
submit the testing data to the network; and
output network test results based on the testing data and the testing criteria.
15 . A non-transitory computer-readable storage medium that includes executable instructions configured to cause one or more processor devices to:
receive, from each of a plurality of network devices that compose an access network that is communicatively coupled to a core network and facilitates communications between the core network and user devices, resource utilization information comprising one or more of central processor utilization, memory utilization, and device load values;
provide the resource utilization information to a machine learning model to receive an output, wherein the machine learning model has been trained with historical resource utilization information associated with network devices that compose an access network, predetermined thresholds, and an impact to the access network of network resources being added to a core network;
based on the output, send, to a destination a recommended increase in hardware network resources of the core network or the access network; and
based on the recommended increase in network resources, cause a plurality of virtual network function (VNF) instances to be generated on a plurality of general-purpose computing devices of a simulation environment that is separate from the access network and the core network to implement the core network or the access network with the recommended network resources on the plurality of general-purpose computing devices, each VNF instance corresponding to one of the plurality of network devices in the core network or the access network.
16 . The non-transitory computer-readable storage medium of claim 15 wherein to receive, from each of the plurality of network devices that compose the access network, resource utilization information, the instructions further cause the one or more processor devices to:
iteratively poll, over a period of time, the plurality of network devices via SNMP to obtain the resource utilization information.
17 . The non-transitory computer-readable storage medium of claim 15 wherein the resource utilization information includes network segment utilization values.
18 . The non-transitory computer-readable storage medium of claim 15 wherein the device load values comprises one or more of a number of users currently connected to the network device and a peak usage of the network device.
19 . The non-transitory computer-readable storage medium of claim 15 wherein the additional network resources comprises one or more of an additional mobile management entity (MME), a serving gateway, a home subscriber server and a packet data network gateway.
20 . The non-transitory computer-readable storage medium of claim 15 wherein the additional network resources comprises an identified amount of additional memory for an existing network device.