Cognitive Function Confidence Scoring for Erroneous Network Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Cognitive Autonomous Networks (CAN) face performance degradation due to erroneous and incomplete data, which affects the accuracy of optimal configuration calculations by Cognitive Functions (CFs), leading to suboptimal network performance.
Innovation Solution
Implementing Value Quality Score (VQS) and Confidence Score (CCS) mechanisms to assess and mitigate the quality of input data, along with training CFs to handle inconsistencies, and using these scores to filter and weight input configurations in the controller's decision-making process.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If Cognitive Functions use learned data to generate optimal configuration values, then network automation and adaptability are improved, but erroneous data causes incorrect OCRS and UF generation leading to suboptimal decisions
Solution Approach 1:
The system performs preliminary actions by training the Cognitive Function on both clean and noisy data before deployment. This pre-training prepares the CF to handle erroneous input data gracefully, allowing it to distinguish between reliable and unreliable data patterns when making configuration decisions.
Solution Approach 2:
The patent introduces an intermediary evaluation mechanism that assesses the quality of input data before it is processed by the CF. This intermediary layer filters and validates data, preventing erroneous information from directly influencing the OCRS and UF generation, thus protecting the decision-making process.
2Device complexity
If the system processes all CF suggestions equally, then simplicity is maintained, but erroneous data from any CF can significantly affect the final optimal value
Solution Approach 1:
The patent applies local quality by assigning different weights to different CF suggestions based on the quality assessment of their input data. Instead of treating all inputs uniformly, the system evaluates each CF's data quality locally and adjusts the influence of each suggestion accordingly, giving more weight to suggestions derived from high-quality data.
Solution Approach 2:
The system dynamically changes the weighting parameter for each CF suggestion based on data quality metrics. When a CF processes high-quality data, its suggestion receives a higher weight; when it processes erroneous data, the weight is reduced. This parameter adjustment allows the system to maintain simplicity while improving reliability.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
It is provided a method comprising: receiving one or more received data sets, wherein each of the received data sets comprises data each representing a value of a respective status parameter of a system, and at least one of the data sets comprises a respective value quality score representing a quality of the value of the respective status parameter; calculating, by a cognitive function, an optimal configuration range set and a confidence score of the optimal configuration range set based on the one or more received data sets; providing the calculated optimal configuration range set and the confidence score to a controller.