Flow Rate Prediction Device Stationarity Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing communication throughput prediction technologies face reduced accuracy due to unstable communication throughput fluctuations, as they rely on Brownian motion models that overpredict stochastic diffusion when throughput is stable or unstable.
Innovation Solution
A flow rate prediction device and method that determine stationarity in communication throughput using time-series data, identifying appropriate stochastic process models and calculating probability distributions to accurately predict stochastic diffusion regardless of throughput stability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If Brownian motion model is used to predict communication throughput, then prediction is accurate when throughput fluctuates randomly, but prediction accuracy deteriorates when throughput is stable
Solution Approach 1:
The patent applies dynamics by making the prediction model adaptable to different states of communication throughput. The system dynamically switches between Brownian motion model (for unstable/random fluctuations) and ARIMA model (for stable fluctuations) based on the actual characteristics of throughput variations. This resolves the contradiction by making the prediction system flexible rather than fixed, allowing it to adapt its behavior to match the current state of the network.
Solution Approach 2:
The patent changes the model parameters by selecting different stochastic process models based on the observed characteristics of throughput fluctuations. When throughput shows stable patterns, the system transitions from Brownian motion model to ARIMA model with appropriate parameters. This parameter change enables accurate prediction across both stable and unstable throughput conditions, resolving the adaptability issue.
2Measurement precision
If single stochastic process model is used, then model complexity is low, but prediction accuracy deteriorates under varying network conditions
Solution Approach 1:
The patent segments the prediction task by dividing it into different model selection based on throughput characteristics. Instead of using a single complex model for all conditions, the system segments the approach into: (1) Brownian motion model for unstable/random throughput, and (2) ARIMA model for stable throughput. This segmentation maintains simplicity within each segment while achieving high accuracy across diverse conditions.
Solution Approach 2:
The patent creates a universal prediction system that can handle multiple types of throughput behaviors through model selection. The system serves multiple functions by selecting appropriate models for different network conditions - acting as a Brownian motion predictor when needed and as an ARIMA predictor when needed. This multi-functionality resolves the contradiction between simplicity and accuracy.
Data Source
AI summary
A flow rate prediction device to predict a flow rate determines, based on time-series data of a measured flow rate, whether the state of the flow rate is stationary or non-stationary. The flow rate prediction device identifies a stochastic process model defining the flow rate as a stochastic variable based on the result of determination of whether the state is stationary or non-stationary and calculates a parameter for use in the identified stochastic process model based on the time-series data. The flow rate prediction device calculates a probability distribution function or a probability density function defining the flow rate to be predicted as the stochastic variable based on the identified stochastic process model and the parameter.