Internet Traffic Data Loss Estimation for Bulk Ingested Patterns
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional internet traffic data loss reporting systems are inaccurate and inflexible, particularly when dealing with bulk ingested data that lacks strong periodicity, leading to overestimation of data loss and inefficient resource usage.
Innovation Solution
A data loss estimation system utilizing an internet traffic forecasting model to predict data loss during outage periods, accounting for recovery periods and non-outage related traffic changes, by converting and decomposing data to accurately determine lost traffic volume.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional internet traffic data loss reporting systems are used, then data loss can be reported, but accuracy deteriorates due to overestimation when dealing with bulk ingested data lacking strong periodicity
Solution Approach 1:
The patent changes the fundamental parameter assumption from requiring strong periodicity to accommodating variable periodicity in bulk ingested data. The system dynamically adjusts to different data ingestion patterns and outages by modifying how traffic volume is extrapolated and compared, allowing accurate data loss measurement even when data arrives in bulk without regular periodic patterns
Solution Approach 2:
The system dynamically adapts to varying data conditions by adjusting its analysis approach based on whether data is continuously streamed or bulk ingested. It dynamically calculates expected traffic volumes based on available historical data and compares against actual volumes during outages, maintaining accuracy across different operational modes and data patterns
2Measurement precision
If strong periodicity is required in data reporting, then measurement accuracy can be maintained, but adaptability deteriorates for bulk ingested data scenarios
Solution Approach 1:
The system achieves universality by designing a data loss reporting mechanism that functions effectively across multiple data ingestion scenarios. It can handle both continuously streamed data with strong periodicity and bulk ingested data with variable or weak periodicity, making the system adaptable to different operational modes without sacrificing measurement accuracy
Solution Approach 2:
The system changes its operational parameters dynamically based on the data pattern detected. When strong periodicity is present, it uses periodic-based extrapolation; when bulk ingestion patterns are detected, it switches to alternative methods that don't rely on periodic assumptions, thereby maintaining accuracy across diverse scenarios
3Ease of manufacture
If conventional reporting systems are used, then implementation is simple, but resource efficiency deteriorates due to overestimation and unnecessary processing
Solution Approach 1:
The system dynamically adjusts its processing intensity and methodology based on the detected data pattern and outage characteristics. By identifying whether data is bulk ingested or continuously streamed, the system optimizes its resource allocation, avoiding unnecessary processing steps while maintaining accurate data loss measurement, thereby improving resource efficiency without complicating implementation
Data Source
AI summary
The present disclosure relates to systems, methods, and non-transitory computer readable media that determine internet traffic data loss from internet traffic data including bulk ingested data utilizing an internet traffic forecasting model. In particular, the disclosed systems detect that observed internet traffic data includes bulk ingested internet traffic data. In addition, the disclosed systems determine a predicted traffic volume for an outage period from the bulk ingested internet traffic data utilizing an internet traffic forecasting model. The disclosed systems further generate a decomposed predicted traffic volume for the outage period. The disclosed systems also determine an internet traffic data loss for the outage period from the decomposed predicted traffic volume while calibrating for pattern changes and late data from previous periods.