Systems and methods for supporting event-based demand in a private network
A device may detect events associated with users of a public network and a private network, and may process the events, with a first machine learning model, to define the events and assign priorities to the events to generate prioritized events. The device may process the prioritized events and policies associated with the private network and the public network, based on the priorities and with a second machine learning model, to determine actions to perform in the private network and the public network. The device may cause resources to be allocated in the private network and the public network for performance of the actions.
1 . A method, comprising:
detecting, by a device, events associated with users of a public network and a private network;
processing, by the device, the events, with a first machine learning model, to define the events and assign priorities to the events to generate prioritized events,
wherein processing the events comprises:
categorizing the events based on different user categories associated with the public network and the private network;
processing, by the device, the prioritized events and policies associated with the private network and the public network, based on the priorities and with a second machine learning model, to determine actions to perform in the private network and the public network; and
causing, by the device, resources to be allocated in the private network and the public network for performance of the actions based on the different user categories.
2 . The method of claim 1 , further comprising:
receiving feedback associated with performance of the actions by the private network and the public network; and
updating the first machine learning model and the second machine learning model based on the feedback and to generate an updated first machine learning model and an update second machine learning model.
3 . The method of claim 1 , wherein the actions to perform include one or more of:
a traffic steering action in the private network or the public network,
a policy based action in the private network or the public network,
a packet classification action in the private network or the public network, or
an update action for a user equipment associated with one of the users.
4 . The method of claim 1 , wherein the actions to perform include an action to manage user plane traffic in the private network.
5 . The method of claim 1 , further comprising:
determining the different user categories for the users within the private network based on network access privileges associated with the private network.
6 . The method of claim 1 , further comprising:
receiving feedback associated with performance of the actions by the private network and the public network; and
causing allocation of the resources in the private network and the public network to be adjusted based on the feedback.
7 . The method of claim 1 , further comprising:
training the first machine learning model with historical event definitions and historical event occurrences associated with the private network.
8 . A device, comprising:
one or more processors configured to:
detect events associated with users of a public network and a private network;
process the events, with a first machine learning model, to define the events and assign priorities to the events to generate prioritized events,
wherein the one or more processors, to process the events, are to:
categorize the events based on different user categories associated with the public network and the private network;
process the prioritized events and policies associated with the private network and the public network, based on the priorities and with a second machine learning model, to determine actions to perform in the private network and the public network;
cause resources to be allocated in the private network and the public network for performance of the actions based on the different user categories;
receive feedback associated with performance of the actions by the private network and the public network; and
cause allocation of the resources in the private network and the public network to be adjusted based on the feedback.
9 . The device of claim 8 , wherein the one or more processors are further configured to:
initiate a performance management function in the private network to monitor network performance metrics associated with the private network; and
cause allocation of the resources in the private network to be adjusted based on the network performance metrics.
10 . The device of claim 8 , wherein the one or more processors, to cause the resources to be allocated in the private network and the public network for performance of the actions, are configured to:
cause the resources to be allocated in the private network to throttle traffic in the private network or to prioritize the users in the private network.
11 . The device of claim 8 , wherein the one or more processors, to cause the resources to be allocated in the private network and the public network for performance of the actions, are configured to:
cause resources to be allocated in the private network to update a policy associated with at least one of the users.
12 . The device of claim 8 , wherein the one or more processors, to cause the resources to be allocated in the private network and the public network for performance of the actions, are configured to:
cause resources to be allocated in the private network and the public network to push traffic associated with a first class of the users to the private network and to push traffic associated with a second class of the users to the public network.
13 . The device of claim 8 , wherein the one or more processors, to cause the resources to be allocated in the private network and the public network for performance of the actions, are configured to:
cause the resources to be allocated in the private network to rate limit, deflect, or load balance traffic in the private network.
14 . The device of claim 8 , wherein the one or more processors are further configured to:
train the second machine learning model with historical policy data and historical actions associated with the private network.
15 . A non-transitory computer-readable medium storing a set of instructions, the set of instructions comprising:
one or more instructions that, when executed by one or more processors of a device, cause the device to:
detect events associated with users of a public network and a private network;
process the events, with a first machine learning model, to define the events and assign priorities to the events to generate prioritized events,
wherein the one or more instructions, that cause the device to process the events, cause the device to:
categorize the events based on different user categories associated with the public network or the private network;
process the prioritized events and policies associated with the private network and the public network, based on the priorities and with a second machine learning model, to determine actions to perform in the private network and the public network,
wherein the actions include one or more of:
a traffic steering action in the private network or the public network,
a policy based action in the private network or the public network,
a packet classification action in the private network or the public network, or
an update action for a user equipment associated with one of the users; and
cause resources to be allocated in the private network and the public network for performance of the actions based on the different user categories.
16 . The non-transitory computer-readable medium of claim 15 , wherein the one or more instructions further cause the device to:
receive feedback associated with performance of the actions by the private network and the public network; and
update the first machine learning model and the second machine learning model based on the feedback and to generate an updated first machine learning model and an update second machine learning model.
17 . The non-transitory computer-readable medium of claim 15 , wherein the actions to perform include an action to manage user plane traffic in the private network.
18 . The non-transitory computer-readable medium of claim 15 , wherein the one or more instructions further cause the device to:
determine different user categories for the users within the private network based on network access privileges associated with the private network.
19 . The non-transitory computer-readable medium of claim 15 , wherein the one or more instructions further cause the device to:
initiate a performance management function in the private network to monitor network performance metrics associated with the private network; and
cause allocation of the resources in the private network to be adjusted based on the network performance metrics.
20 . The non-transitory computer-readable medium of claim 15 , wherein the one or more instructions, that cause the device to cause the resources to be allocated in the private network and the public network for performance of the actions, cause the device to:
cause the resources to be allocated in the private network to throttle traffic in the private network or to prioritize the users in the private network.