Time-Specific Data Processing Predictions with Correlated ML Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Artificial intelligence-based data processing load predictions are hindered by the complexity of obtaining high-quality data, the need for specialized knowledge to design and integrate solutions, and the difficulty in reviewing results due to obscured processes, leading to challenges in managing network resources efficiently.
Innovation Solution
The system uses multiple machine learning models to generate time-specific data processing predictions by analyzing real-time averages and additional data sets with non-homogeneous time dependencies, determining outlier predictions through correlation analysis, and adjusting resource allocation based on aggregate measures of correlation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple machine learning models with different data methodologies are used to generate predictions, then prediction accuracy and reliability are improved, but system complexity increases
Solution Approach 1:
The system divides the prediction task into multiple independent machine learning models, each processing different data characteristics (real-time averages, non-homogeneous time dependencies, etc.). Each model handles a specific aspect of the prediction problem, allowing the system to manage complexity through modular segmentation while improving overall reliability through diverse prediction perspectives.
Solution Approach 2:
The patent combines multiple machine learning models and their predictions into a unified prediction framework. By merging the outputs of different models and using correlation analysis to determine outlier predictions, the system achieves higher reliability while managing complexity through integrated processing rather than separate isolated systems.
2Measurement precision
If correlation analysis is performed on multiple model outputs to identify outliers, then prediction accuracy is improved, but processing time increases
Solution Approach 1:
The system performs correlation analysis between model outputs as a preliminary step before final prediction generation. By pre-calculating correlations and identifying outliers in advance, the system can quickly determine which predictions to trust and which to adjust, reducing overall processing time while maintaining high accuracy through proactive rather than reactive analysis.
Solution Approach 2:
The correlation analysis provides feedback about the relationships between different model predictions. This feedback mechanism allows the system to automatically adjust its prediction strategy, using the correlation information to identify and correct outlier predictions without requiring extensive reprocessing, thus improving accuracy while controlling processing time through intelligent feedback-driven optimization.
Data Source
AI summary
Methods and systems use an additional determination to generate predictions of future data processing load predictions. Specifically, the methods and systems generate additional predictions based on other data sets and data calculation methodologies (e.g., data with non-homogeneous time dependencies). The methods and systems then use these additional predictions to determine whether or not the prediction of the real-time average of data processing loads is an outlier. Thus, the methods and systems generate a time-specific data processing prediction.