Network Traffic Estimation via Machine Learning Regression
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current network traffic estimation methods rely on manual analysis of large historical data sets, leading to increased labor requirements, higher margins of error, and low prediction accuracy, as they fail to efficiently utilize all relevant data for automated future traffic estimation.
Innovation Solution
A network traffic estimation system using machine learning regression methods that integrates current network performance indicators, historical data, and external factors like weather and customer complaints into a database for automated traffic forecasting, enabling efficient resource allocation and reduced investment costs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual analysis of large historical data sets is used, then labor requirements increase, but prediction accuracy remains low
Solution Approach 1:
The patent replaces manual mechanical analysis with automated machine learning regression systems. The system automatically processes large historical traffic datasets using regression algorithms, eliminating the need for manual data examination while significantly improving prediction accuracy through comprehensive data utilization rather than sampling.
Solution Approach 2:
The system enables self-service automation where the machine learning model independently performs data processing, pattern recognition, and traffic prediction without human intervention. The automated regression analysis system continuously learns from historical data and generates predictions autonomously, resolving the contradiction between labor efficiency and prediction accuracy.
2Productivity
If small samples are taken from millions of records, then labor requirement decreases, but margin of error increases
Solution Approach 1:
The patent replaces manual sampling with automated machine learning regression that processes complete datasets. The system uses regression algorithms to analyze all available historical traffic records simultaneously, eliminating sampling errors while maintaining high productivity through automation. This approach充分利用 all data points to improve estimation accuracy without requiring manual intervention.
3Measurement precision
If only historical traffic data is used, then data processing is simple, but rate of successful prediction is low
Solution Approach 1:
The patent merges multiple data sources including historical traffic data, current network performance indicators, weather conditions, and customer complaints into a unified regression analysis model. This integration of diverse datasets through machine learning algorithms significantly improves prediction success rates by capturing complex relationships that single-data-source approaches miss, while the automated system manages the complexity.
Solution Approach 2:
The regression analysis system serves multiple functions: processing historical traffic data, analyzing current network indicators, incorporating external factors like weather and complaints, and generating predictions. This multi-functional approach increases prediction success rates while the unified system architecture manages the inherent complexity efficiently.
Data Source
Figure 1
AI summary
The present invention relates to a network traffic estimation system (1) which provides a solution architecture for estimating future network traffic via regression methods from machine learning approaches by looking at historical traffic data. The inventive network traffic estimation system (1) handles the traffic estimation as a machine learning regression problem. Current network performance indicators, network configuration planning information, planned activities, currently planned works, current network alarms, weather forecasts, current customer and future campaign information are kept on the database (2) on the basis of location/cell.