Action recommendation engine (ARE) of a closed-loop machine learning (ML) system for controlling a network
Systems and methods for recommending actions in a closed-loop system are provided. In one embodiment, an Action Recommendation Engine (ARE) may include a processor and memory configured to store computer programs having instructions that cause the processor to obtain input data pertaining to a state of a network and obtain information regarding one or more historical actions performed on the network. Also, the instructions may cause the processor to utilize a Machine Learning (ML) model for imposing one or more current actions on the network, the one or more current actions selected from the group of procedures consisting of: a) suggesting one or more remediation actions that, when performed, transition the network from a problematic state to a normal state, and b) identifying one or more root causes in response to detecting a transition in the network from a normal state to a problematic state.
1. An Action Recommendation Engine (ARE) comprising
a processing device, and
a memory device configured to store a computer program having logic instructions configured to cause the processing device to
obtain input data that is time-series data pertaining to a state of a network,
obtain information regarding one or more historical actions performed on the network, and
utilize a Machine Learning (ML) model for imposing one or more current actions on the network using a delay that accounts for when the one or more current actions are executed until the one or more current actions produce an effect on the state of the network, the one or more current actions selected from the group of procedures consisting of
suggesting one or more remediation actions that, when performed, transition the network from a problematic state to a normal state, and
identifying one or more root causes in response to detecting a transition in the network from a normal state to a problematic state.
2. The ARE of claim 1 , wherein the logic instructions are further configured to cause the processing device to train the ML model.
3. The ARE of claim 2 , wherein training the ML model uses one or more processes selected from the group of processes consisting of
implementing a supervised ML technique, and
implementing a collaborative filtering technique.
4. The ARE of claim 3 , wherein the supervised ML technique includes a classification process for classifying the state of the network and classifying the one or more historical actions performed on the network.
5. The ARE of claim 3 , wherein the collaborative filtering technique comprises the processes of
collecting action information regarding the one or more historical actions executed by a plurality of components of the network,
comparing the action information associated with the plurality of components, and
ranking and recommending the one or more remediation actions based on comparing the action information.
6. The ARE of claim 1 , wherein the input data is captured from the network by one of a Network Management System (NMS) and a Network Configuration and Change Management (NCCM) device.
7. The ARE of claim 6 , wherein the input data includes one or more of alarms, Key Performance Indicators (KPIs), network traffic information, service flow information, Quality of Service (QoS) information, and Quality of Experience (QoE) information.
8. The ARE of claim 7 , wherein the one or more historical actions include one or more of a channel addition process, a channel deletion process, a software upgrade, and a protection switch process.
9. The ARE of claim 1 , wherein the procedure of suggesting one or more remediation actions includes one or more of
recommending a plan for re-routing network traffic through an alternative path in the network,
recommending a change to a Quality of Service (QoS) policy on a port in the network to prioritize network traffic, and
recommending migrating a payload closer to a source in the network.
10. The ARE of claim 1 , wherein the procedure of suggesting one or more remediation actions includes
determining a probability parameter associated with each of the one or more remediation actions,
comparing each probability parameter with a predetermined threshold level,
providing an output recommending that no remediation action be imposed on the network in response to determining that the probability parameter associated with each remediation action is below the predetermined threshold level, and
responsive to determining that one or more probability parameters exceed the predetermined threshold level, providing an output recommending that one or more selected remediation actions be imposed on the network based on a predefined rule, the one or more selected remediation actions being selected from the one or more remediation actions having a probability parameter that exceeds the predetermined threshold level.
11. The ARE of claim 1 , wherein the procedure of identifying the one or more root causes includes
determining a probability parameter associated with each of the one or more root causes,
comparing each probability parameter with a predetermined threshold level,
providing an output indicating that no root cause is likely in response to determining that the probability parameter associated with each root cause is below the predetermined threshold level, and
responsive to determining that one or more probability parameters exceed the predetermined threshold level, providing an output, based on a predefined rule, that one or more root causes are likely.
12. A non-transitory computer-readable medium configured to store computer logic having instructions that, when executed, cause one or more processing devices to
obtain input data that is time-series data pertaining to a state of a network,
obtain information regarding one or more historical actions performed on the network, and
utilize a Machine Learning (ML) model for imposing one or more current actions on the network using a delay that accounts for when the one or more current actions are executed until the one or more current actions produce an effect on the state of the network, the one or more current actions selected from the group of procedures consisting of
suggesting one or more remediation actions that, when performed, transition the network from a problematic state to a normal state, and
identifying one or more root causes in response to detecting a transition in the network from a normal state to a problematic state.
13. The non-transitory computer-readable medium of claim 12 , wherein the instructions, when executed, further cause the one or more processing devices to train the ML model using one or more processes selected from the group of processes consisting of
implementing a supervised ML technique, and
implementing a collaborative filtering technique.
14. The non-transitory computer-readable medium of claim 13 , wherein the supervised ML technique includes a classification process for classifying the state of the network and classifying the one or more historical actions performed on the network.
15. The non-transitory computer-readable medium of claim 13 , wherein the collaborative filtering technique comprises the processes of
collecting action information regarding the one or more historical actions executed by a plurality of components of the network,
comparing the action information associated with the plurality of components, and
ranking and recommending the one or more remediation actions based on comparing the action information.
16. A method comprising the steps of
obtaining input data that is time-series data pertaining to a state of a network,
obtaining information regarding one or more historical actions performed on the network, and
utilizing a Machine Learning (ML) model for imposing one or more current actions on the network using a delay that accounts for when the one or more current actions are executed until the one or more current actions produce an effect on the state of the network, the one or more current actions selected from the group of procedures consisting of
suggesting one or more remediation actions that, when performed, transition the network from a problematic state to a normal state, and
identifying one or more root causes in response to detecting a transition in the network from a normal state to a problematic state.
17. The method of claim 16 , wherein the input data is captured from the network by one of a Network Management System (NMS) and a Network Configuration and Change Management (NCCM) device.
18. The method of claim 17 , wherein the input data includes one or more of alarms, Key Performance Indicators (KPIs), network traffic information, service flow information, Quality of Service (QoS) information, and Quality of Experience (QoE) information, and wherein the one or more historical actions include one or more of a channel addition process, a channel deletion process, a software upgrade, and a protection switch process.
19. The method of claim 17 , wherein the procedure of suggesting one or more remediation actions includes one or more of
recommending a plan for re-routing network traffic through an alternative path in the network,
recommending a change to a Quality of Service (QoS) policy on a port in the network to prioritize network traffic, and
recommending migrating a payload closer to a source in the network.
20. The method of claim 16 , wherein
the procedure of suggesting one or more remediation actions includes
determining a probability parameter associated with each of the one or more remediation actions,
comparing each probability parameter with a predetermined threshold level,
providing an output recommending that no remediation action be imposed on the network in response to determining that the probability parameter associated with each remediation action is below the predetermined threshold level, and
responsive to determining that one or more probability parameters exceed the predetermined threshold level, providing an output recommending that one or more selected remediation actions be imposed on the network based on a predefined rule, the one or more selected remediation actions being selected from the one or more remediation actions having a probability parameter that exceeds the predetermined threshold level, and
wherein the procedure of identifying the one or more root causes includes
determining a probability parameter associated with each of the one or more root causes,
comparing each probability parameter with a predetermined threshold level,
providing an output indicating that no root cause is likely in response to determining that the probability parameter associated with each root cause is below the predetermined threshold level, and
responsive to determining that one or more probability parameters exceed the predetermined threshold level, providing an output, based on a predefined rule, that one or more root causes are likely.