Intent-Based Network Automation for Reliable Route KPI Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing route prediction technologies in wireless communication systems have limited accuracy due to reliance on historical data and patterns, which can be disrupted by unexpected events, limiting their applicability and reliability.
Innovation Solution
Implementing intent-based automation (IBA) to stabilize and improve the accuracy of KPI predictions by assigning temporary intents to the network to actively manage resource allocation and prioritize service levels, ensuring that predicted performance is maintained.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If route prediction technologies rely on historical data and patterns, then they can provide baseline predictions, but their accuracy is limited when unexpected events disrupt historical patterns
Solution Approach 1:
The system performs preliminary actions by proactively identifying potential service level violations before they occur through service level predictions. It then preemptively generates and assigns intents to prevent these violations, rather than merely reacting to historical patterns after disruption has occurred.
Solution Approach 2:
The system implements continuous feedback loops where service level predictions are monitored, and when violations are anticipated, corrective intents are generated and assigned. The network then executes these intents and the results feed back into the prediction system, continuously improving accuracy by learning from both historical data and real-time corrections.
2Measurement precision
If intent-based automation assigns temporary intents to manage resource allocation, then prediction accuracy improves, but system complexity increases
Solution Approach 1:
The system enables self-service automation where the network autonomously generates intents from service level predictions and automatically assigns them to manage resource allocation. This reduces the need for manual configuration and complex external control systems, as the network serves itself by translating predictions into actionable intents and monitoring their execution.
Solution Approach 2:
The system changes operational parameters dynamically by generating temporary intents that modify network behavior based on predicted service level requirements. These intents adjust resource allocation parameters in real-time without requiring permanent system reconfiguration, thereby improving prediction accuracy while maintaining system flexibility and reducing inherent complexity.
3Adaptability or versatility
If traditional KPI predictions are used in areas with insufficient historical data, then wider applicability is achieved, but prediction reliability decreases
Solution Approach 1:
The system performs preliminary service level predictions even in areas with insufficient historical data, and proactively generates intents to ensure service level compliance. By acting preemptively rather than relying on past performance patterns, the system can provide predictions in new geographies before sufficient historical data has accumulated.
Solution Approach 2:
The system introduces service level predictions and intents as intermediary mechanisms that bridge the gap in areas with insufficient historical data. These predictions act as mediators that translate limited available information into actionable resource allocation decisions, enabling reliable predictions in geographies where traditional historical analysis would fail.
Data Source
AI summary
A network node in a communications network can determine a service level prediction. The network node can further generate an intent based on the service level prediction. The network node can further assign the intent to a set of intents used by the communications network.