Predictive Intent Handling for Multi-KPI Network Stability
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In communications networks, multiple intents with KPI targets can lead to conflicts where satisfying one KPI target may negatively affect other KPIs, causing instability and inefficient resource utilization.
Innovation Solution
A method involving a node in the network that predicts the impact of actions on measurable properties using empirical relationships, calculates predicted KPI values, and compares them to targets to determine if the action will satisfy the intent, thereby avoiding conflicts and optimizing network performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a proposal agent proposes an action to solve a KPI issue, then the specific KPI target is improved, but other KPIs may be negatively affected
Solution Approach 1:
The system applies preliminary anti-action by predicting the negative side effects of proposed actions before they are executed. The prediction module uses empirical relationships to forecast how an action intended to improve one KPI might adversely affect other KPIs, allowing the system to prevent or mitigate these harmful effects in advance by selecting alternative actions or adjusting the proposed action parameters.
Solution Approach 2:
The system implements feedback by continuously monitoring the actual outcomes of executed actions and comparing them with predicted outcomes. This feedback loop allows the system to learn from past experiences, refine its empirical relationships, and improve its prediction accuracy over time, thereby better avoiding actions that would negatively impact multiple KPIs.
2Reliability
If multiple KPI targets are enforced simultaneously, then comprehensive network performance is improved, but conflicts arise causing instability
Solution Approach 1:
The prediction module acts as an intermediary between the proposal agent and the action execution process. It mediates by evaluating proposed actions against multiple KPI targets simultaneously using empirical relationships, identifying potential conflicts before execution, and providing guidance on which actions will achieve the best overall balance across all KPIs rather than optimizing individual targets in isolation.
Solution Approach 2:
The system performs preliminary action by evaluating and predicting the outcomes of proposed actions before they are executed. This advance assessment allows the system to identify and resolve potential KPI conflicts prior to action execution, preventing instability from arising in the first place rather than reacting to conflicts after they occur.
3Speed
If actions are taken to satisfy KPI targets without prediction, then response speed is improved, but resource utilization becomes inefficient
Solution Approach 1:
The system applies partial action by evaluating multiple proposed actions and selecting only the most appropriate one based on predicted outcomes across all KPIs, rather than executing all proposed actions or taking no action. This selective approach avoids the waste of resources that would result from executing suboptimal or conflicting actions while maintaining rapid response times.
Data Source
AI summary
A method performed by a first node in a communications network for satisfying a first intent set for a system in the communications network, the first intent includes expectations, each expectation corresponding to a Key Performance Indicator, KPI, target. The method includes: predicting values of measurable properties that would be observed if a first action were performed in the system, using empirical relationships between actions and the measurable properties; calculating predicted KPI values that are predicted to be measured in the system if the first action were to be performed, from the predicted values of the measurable properties; and comparing the predicted KPI values to the KPI targets in the first intent to predict whether performing the first action would lead to the first intent being satisfied for the system.