Predictive Model Deployment for Network Traffic Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Network traffic often includes redundant data packets that are poorly synchronized in time, leading to inefficiencies as the same data packets are transmitted multiple times, especially for popular content like videos or songs.
Innovation Solution
A predictive model, trained using incoming data packets, is deployed to network devices to predict subsequent data packets, allowing for the cessation of forwarding redundant packets once the model's accuracy meets a threshold, thereby reducing network traffic.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If data packets are forwarded to network devices, then network devices receive complete data, but redundant data packets increase network traffic and reduce efficiency
Solution Approach 1:
The patent creates a copy of the predictive model at the network device, enabling it to generate predicted data packets locally. This copy mechanism allows the network device to replace receiving redundant packets with generating equivalent packets from the model, reducing network traffic while maintaining data completeness.
Solution Approach 2:
The predictive model is trained in advance using historical data packets and deployed to the network device before actual prediction is needed. This preliminary training enables the network device to autonomously generate predicted packets without requiring real-time communication with the training system, reducing ongoing network traffic.
2Loss of energy
If a predictive model is deployed to network devices, then redundant data transmission is reduced, but the complexity of the network system increases
Solution Approach 1:
The patent extracts the predictive model from the central training system and deploys it to the network device. This extraction moves the prediction functionality to the edge, reducing the need for continuous communication between the training system and network devices, thereby simplifying the overall system architecture while maintaining prediction capabilities.
Solution Approach 2:
The network device is equipped with the predictive model to serve itself by generating predicted data packets autonomously. This self-service capability eliminates the need for the network device to receive and process redundant packets from external sources, reducing network traffic without requiring additional centralized control infrastructure.
3Loss of energy
If incoming data packets are ceased to be forwarded, then network traffic is reduced, but network devices need alternative sources for data packets
Solution Approach 1:
The predictive model is copied to the network device, enabling it to generate predicted data packets locally. This local generation capability provides an alternative data source that replaces the need to forward incoming packets, maintaining data availability while reducing network traffic.
Solution Approach 2:
The predictive model acts as an intermediary between the training data and the network device's prediction needs. It translates historical patterns into predicted packets that the network device can use autonomously, bridging the gap between ceased packet forwarding and continued data availability.
Data Source
AI summary
Apparatuses, methods, systems, and program products are disclosed for data packet prediction. An apparatus includes a processor and a memory that stores code executable by the processor. The code is executable by the processor to train a predictive model using incoming data packets. The incoming data packets are forwarded to one or more network devices. The predictive model is trained to predict a subsequent data packet based on an input data packet. The code is executable by the processor to forward the predictive model to the one or more network devices in response to the predictive accuracy of the predictive model satisfying a threshold accuracy. The predictive model generates predicted data packets at the one or more network devices. The code is executable by the processor to cease forwarding incoming data packets to the one or more network devices.