IoT Traffic Prediction via Dual-Granularity Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current IoT network traffic prediction systems face challenges in accurately predicting traffic trends due to limitations in single-position prediction modules and time granularity configurations, leading to instability and reduced accuracy.
Innovation Solution
A system and method for IoT nodes that include access nodes and a cloud platform, where access nodes collect and cluster traffic data, input it into an access traffic prediction model, and upload results to the cloud platform, which then uses network traffic prediction models to forecast traffic trends, combining short-term and long-term predictions for improved accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a single-position prediction module is used in the network, then the system complexity is reduced, but the traffic prediction accuracy deteriorates due to one-sidedness and limitation
Solution Approach 1:
The patent divides the prediction system into two independent prediction modules: one deployed at access nodes for short-term access traffic prediction, and another at the cloud platform for long-term network traffic prediction. Each module operates independently with its own model and data processing, eliminating the one-sidedness of single-position prediction while maintaining manageable system complexity through clear functional segmentation.
2Device complexity
If a single time granularity configuration is used, then the prediction system is simplified, but the ability to capture both short-term changes and long-term trends is lost
Solution Approach 1:
The patent introduces a dual-time-granularity dimension by implementing separate prediction models for short-term (access traffic at access nodes) and long-term (network traffic at cloud platform) predictions. This multi-dimensional time scale approach enables the system to simultaneously capture both rapid short-term fluctuations and gradual long-term trends, significantly improving prediction reliability without requiring complex single-model configurations.
Data Source
AI summary
A system of traffic prediction for IoT nodes includes at least one access node, a transmission network and a cloud platform. The access node is configured to collect traffic data, cluster the traffic data into access traffic data and network traffic data, input the access traffic data into an access traffic prediction model to obtain a prediction result of the access traffic at a next moment, and upload the network traffic data and the prediction result of the access traffic to the cloud platform; the cloud platform is configured to input the network traffic data into a network traffic prediction model to obtain a prediction result of the network traffic for each access node at the next moment, and obtain a prediction result of traffic for each node according to the prediction result of the network traffic and the prediction result of the access traffic.