SLA Maintenance in Telecom Networks via Dynamic Policy Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for SLA assurance in telecom networks are simplistic and static, leading to the execution of unnecessary policy actions that can disturb other services in the network.
Innovation Solution
A method that models each policy action by its effects and pre-conditions, derives a desired network state from alarms, and uses AI and machine learning to optimize the selection and execution of policy actions, thereby improving the precision and efficiency of SLA maintenance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional static policy mapping methods are used, then the system is simple to operate, but the precision of policy action selection deteriorates leading to unnecessary actions
Solution Approach 1:
The patent transforms the static policy mapping into a dynamic system that adapts to current network state. The policy engine now considers real-time alarm conditions, network state, and learned patterns to dynamically select and sequence policy actions, rather than following fixed static mappings. This dynamic approach improves precision while managing complexity through structured decision frameworks.
Solution Approach 2:
The system changes the parameters used for policy selection from simple alarm-type matching to multi-dimensional parameters including current network state, alarm severity, historical performance data, and predicted outcomes. This parameter enrichment enables more precise policy action selection by evaluating multiple factors simultaneously rather than relying on single-dimensional static mappings.
2Object-affected harmful factors
If broad-grained policy actions are executed, then the coverage of SLA resolution is comprehensive, but the harmful side effects on other services increase
Solution Approach 1:
The patent applies local quality by tailoring policy actions to the specific local context of each alarm and network state. Instead of applying broad-grained actions uniformly, the system selects and sequences policy actions that are locally optimized for the specific SLA violation scenario, considering only the affected network functions and services. This reduces harmful side effects on unrelated services while maintaining effectiveness for the specific issue.
Solution Approach 2:
The system performs preliminary analysis to predict potential harmful side effects before executing policy actions. By evaluating the current network state and simulating policy action outcomes, the system can prevent or mitigate adverse effects on other services. The structured approach includes checking for potential conflicts and sequencing actions to minimize disruption to non-affected services.
3Adaptability or versatility
If static policy lists are used, then the system complexity is low, but the adaptability to different alarm scenarios deteriorates
Solution Approach 1:
The patent implements dynamics by enabling the policy engine to adapt its behavior based on current network conditions, alarm characteristics, and historical learning. The system dynamically adjusts policy selection and sequencing to match the specific alarm scenario, rather than relying on fixed static lists. This adaptability is achieved through structured decision-making frameworks that evaluate multiple factors in real-time.
Solution Approach 2:
The system incorporates feedback mechanisms where the outcomes of executed policy actions are monitored and fed back into the policy engine. This feedback loop enables the system to learn from past performance and continuously improve its policy selection and sequencing for different alarm scenarios. The feedback-driven adaptation enhances versatility while managing complexity through systematic learning processes.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method for operating a telecom network having an SLA agreement is disclosed. The method comprises obtaining annotated alarm data comprising an indication of a threshold crossing of at least one state variable of the telecom network defined by the SLA. The annotated alarm data further comprises an indication of a desired value of the at least one state variable of the telecom network. Moreover, the method comprises determining a desired state of the telecom network based on the desired value of at least one state variable, and selecting a set of policy actions from a policy action bank. The policy action bank comprises a plurality of policy actions, where each policy action is associated with at least one estimated action effect. The selection of the set of policy actions is accordingly based on the estimated action effects of the plurality of policy actions and on the determined desired state of the telecom network such that the desired state is reachable upon execution of the selected set of policy actions. The method further comprises sending the selected set of policy actions to an action orchestrating module for execution of the selected set of policy actions. Moreover, a corresponding computer program product and system are disclosed.