ML-Based Network Capacity Planning for Proactive Dimensioning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing capacity planning in network environments is reactive and sub-optimal due to reliance on manual analysis and failure to predict changes in customer base or network events, leading to inefficient adjustments.
Innovation Solution
Implementing a system that uses machine learning (ML) to process network and historic dimensional data, generating capacity predictions and adjusting dimensioning parameters proactively based on these predictions, reducing the need for manual intervention.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual analysis and reactive capacity planning is used, then human intervention and control are maintained, but the capacity planning is sub-optimal and fails to predict upcoming changes
Solution Approach 1:
The patent replaces manual mechanical analysis processes with machine learning-based automated prediction systems. The ML model analyzes network data and historical dimensional data to predict future capacity requirements, substituting human expert analysis with algorithmic prediction to achieve proactive capacity planning.
Solution Approach 2:
The system performs capacity planning actions in advance by predicting future network capacity requirements before actual demand occurs. The ML model forecasts upcoming changes in customer base or network events and adjusts dimensioning parameters proactively, rather than reacting after problems occur.
2Productivity
If automated ML-based prediction is implemented, then proactive capacity planning is achieved, but system complexity increases
Solution Approach 1:
The patent creates a multi-functional system where the machine learning model performs multiple tasks: analyzing network data, processing historical dimensional data, predicting capacity requirements, and generating adjustment recommendations. This universal approach consolidates multiple functions into a single integrated system, managing complexity through functional consolidation.
Solution Approach 2:
The system introduces an intermediary data processing layer that transforms raw network data and historical dimensional data into meaningful predictions. This intermediary ML model acts as a mediator between raw data and capacity planning decisions, simplifying the overall system architecture by centralizing the complex prediction logic in a dedicated component.
3Productivity
If frequent network adjustments are made based on real-time predictions, then network optimization is improved, but network stability may be compromised
Solution Approach 1:
The system implements periodic capacity planning adjustments based on predicted trends rather than continuous real-time changes. The ML model analyzes data over time periods and recommends adjustments at appropriate intervals, balancing optimization with stability by avoiding excessive frequent changes while maintaining proactive planning.
Data Source
AI summary
An apparatus for capacity planning in a network includes at least one memory storing instructions and at least one processor configured to execute the instructions to obtain network data corresponding to at least one network node and historic dimensional data corresponding to the network, generate transformed data from the network data and the historic dimensional data based on at least one configuration parameter, input the transformed data into a machine learning (ML) model, generate, by the ML module, at least one capacity prediction of the network based on the transformed data, and adjust at least one dimensioning parameter of the network based on the at least one capacity prediction.