Cellular Circuit Bandwidth Prediction from Channel Conditions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing SASE architectures face challenges in accurately predicting cellular circuit bandwidth due to the dynamic and uncontrolled nature of radio phenomena, leading to sub-optimal path selection and policy compliance issues.
Innovation Solution
A system that collects and analyzes cellular circuit data, including channel conditions and usage patterns, to train a model for predicting current channel conditions, which adjusts bandwidth measurements to account for cyclical and seasonal behaviors, ensuring accurate path selection and policy compliance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional bandwidth measurement methods are used in SASE architectures, then the system structure remains simple, but the bandwidth prediction accuracy deteriorates due to dynamic radio phenomena
Solution Approach 1:
The system performs preliminary actions by collecting cellular circuit data including channel conditions and usage patterns before bandwidth prediction is needed. This historical data is stored and later used by the trained model to predict current channel conditions, allowing the system to anticipate bandwidth availability rather than merely measuring it after the fact.
Solution Approach 2:
A trained model serves as an intermediary between raw cellular circuit data and bandwidth predictions. The model processes channel conditions, usage patterns, and other parameters to generate accurate bandwidth predictions, acting as a mediator that transforms complex cellular data into actionable network management information.
2Productivity
If manual bandwidth configuration is used, then the system complexity remains low, but path selection becomes sub-optimal due to inability to account for cyclical and seasonal behaviors
Solution Approach 1:
The system implements dynamic bandwidth prediction that adapts to changing cellular network conditions. The trained model continuously processes new data and updates predictions based on current channel conditions, usage patterns, and historical trends, allowing path selection to respond dynamically rather than relying on static manual configurations.
Solution Approach 2:
The system incorporates feedback mechanisms where bandwidth predictions are continuously refined based on actual network performance and usage patterns. The trained model learns from historical data and adjusts its predictions to account for cyclical and seasonal behaviors, creating a feedback loop that improves path selection efficiency over time.
3Reliability
If simple bandwidth measurement is used, then the measurement process is simple, but reliability deteriorates due to uncontrolled radio phenomena
Solution Approach 1:
The system performs preliminary data collection and model training to establish a reliable foundation for bandwidth predictions. By gathering extensive cellular circuit data including channel conditions, usage patterns, and historical performance before predictions are needed, the system builds a robust knowledge base that improves reliability despite radio phenomenon variability.
Solution Approach 2:
The trained model acts as a reliable intermediary that filters out the variability introduced by uncontrolled radio phenomena. It processes multiple parameters including channel conditions, usage patterns, and historical data to produce stable and reliable bandwidth predictions that are not unduly influenced by temporary radio conditions.
Data Source
AI summary
A system generates reliable bandwidth predictions which account for the dynamic behavior of cellular circuits. The system performs ongoing data collection of cellular parameters indicative of channel conditions of cellular circuits, cellular circuit performance and/or usage, bandwidth measurements of network paths that include the cellular circuits, and locations of edge devices with interfaces with cellular circuits attached. The collected data is stored as time series data to allow for repeating patterns to be detected and/or accounted. When a bandwidth prediction is triggered for a cellular circuit, the system retrieves most recent and historical data corresponding to cyclical/seasonal behavior and runs a trained model to generate a value representing likely current channel conditions of the cellular circuit. The system then uses the predicted current channel conditions value that accounts for repeating usage/performance patterns to calculate an estimated/predicted bandwidth of the cellular circuit.