SDN Path Suggestion Using LSTM-RNN Prediction and DBM Routing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional communication networks struggle to adapt to dynamic data traffic demands due to their static architecture, failing to consider historical usage trends and future utilization of routers/switches in SDN architectures, which limits efficient routing path selection.
Innovation Solution
Implementing a Long Short-Term Memory Recurrent Neural Network (LSTM-RNN) model to predict future router usage and a Deep Boltzmann Machine (DBM) model to recommend routing paths based on predicted usage patterns, providing a plug-and-play analytical framework for SDN networks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If traditional static network architecture is used, then network simplicity is maintained, but adaptability to dynamic data traffic demands deteriorates
Solution Approach 1:
The patent implements dynamic routing path selection by using LSTM-RNN to predict future router usage patterns and DBM to select optimal paths in real-time. The system continuously adapts routing decisions based on predicted traffic patterns, transforming the static routing architecture into a dynamic one that responds to changing network conditions.
Solution Approach 2:
The system performs preliminary action by using LSTM-RNN to predict future router usage patterns before actual traffic arrives. This predictive capability allows the network to proactively adjust routing paths in advance, preventing congestion and optimizing performance before dynamic traffic demands materialize.
2Productivity
If historical usage data is not considered, then routing decision speed is maintained, but routing path optimization deteriorates
Solution Approach 1:
The LSTM-RNN model performs preliminary analysis of historical usage data to predict future router patterns. By processing historical data in advance and storing predictions, the system enables fast real-time routing decisions without repeatedly analyzing raw historical data, thus optimizing routing efficiency while managing complexity.
Solution Approach 2:
The system implements feedback by continuously analyzing historical usage data through LSTM-RNN, comparing predicted patterns with actual traffic, and using DBM to select routing paths that optimize performance. This closed-loop feedback mechanism continuously improves routing decisions based on learned patterns from historical data.
3Reliability
If future router usage is not predicted, then current routing simplicity is maintained, but network capacity utilization deteriorates
Solution Approach 1:
The LSTM-RNN model performs preliminary prediction of future router usage patterns by analyzing historical data. These predictions are made in advance and stored, enabling the DBM to select routing paths that optimize future capacity utilization rather than just reacting to current conditions, thus improving network reliability and capacity planning.
Data Source
AI summary
A path suggestion tool in a Software-Defined Networking (SDN) architecture to predict a router's future usage based on an analysis of the router's historical usage over a given period of time in the past and to recommend a routing path within the network in view of the predicted future usages of the routers/switches in the network. The path suggestion tool is an analytical, plug-and-play model usable as part of an SDN controller to provide more insights into different routing paths based on the future usage of each router. A Long Short-Term Memory Recurrent Neural Network (LSTM-RNN) model in the suggestion tool analyzes the historical usage data of a router to predict its future usage. A Deep Boltzmann Machine (DBM) model in the suggestion tool recommends a routing path within the SDN-based network upon analysis of the LSTM-RNN based predicted future usages of routers/switches in the network.