Network Quality Prediction Using Mobile Device Data Collection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems fail to predict network quality in wireless networks effectively, leading to data transmission errors as defective communication channels are only detected during or after data transmission, rather than being anticipated and avoided.
Innovation Solution
A system comprising mobile communication devices, data prediction units, and data collection units that measure and calculate network quality data, including delay, throughput, position, and environment factors, to provide predictive data for preventing data transfer errors by identifying potential issues before data transmission.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If network quality is only monitored during or after data transmission, then the monitoring system remains simple, but data transmission errors cannot be avoided
Solution Approach 1:
The system performs preliminary actions by collecting network quality data and training prediction models before actual data transmission occurs. The data collection unit continuously gathers network parameters, and the prediction unit prepares predictive models in advance, enabling the system to forecast channel quality before transmission, thus preventing errors rather than just detecting them afterward.
Solution Approach 2:
The system segments the network quality assurance function into distinct modules: a data collection unit for gathering network parameters, a data prediction unit for analyzing and predicting channel quality, and a transmission control mechanism for making decisions. This segmentation allows each component to specialize in specific tasks, improving overall reliability while maintaining manageable system complexity through modular architecture.
2Reliability
If network quality prediction is implemented, then data transfer errors can be prevented, but the system complexity increases
Solution Approach 1:
The prediction unit utilizes network quality data that is already being collected by the data collection unit, making the system self-sufficient. The same collected data serves dual purposes: for monitoring current network status and for training prediction models. This eliminates the need for separate data gathering mechanisms, reducing overall system complexity while enabling accurate prediction.
Solution Approach 2:
The system employs machine learning models that automatically adapt to changing network conditions by adjusting their internal parameters based on collected data. As network conditions evolve, the prediction models update their parameters to maintain accuracy, allowing the system to handle diverse and dynamic network environments without requiring manual reconfiguration or increased structural complexity.
3Measurement precision
If comprehensive network quality data is collected from multiple sources, then prediction accuracy improves, but data processing complexity increases
Solution Approach 1:
The data collection unit is designed with multi-functionality, serving both to monitor current network quality for immediate transmission decisions and to accumulate historical data for training prediction models. This universal data collection mechanism eliminates the need for separate monitoring and prediction data gathering systems, reducing complexity while maintaining comprehensive data coverage for accurate predictions.
Data Source
AI summary
A system for prediction of network quality in a wireless network. The system comprises at least one mobile communication device, at least one data prediction unit and a data collection unit. Furthermore, the at least one mobile communication device measures the network quality and transmits the measured network quality to the data collection unit. In addition to this, the at least one data prediction unit calculates prediction data with respect to the network quality based on data from the data collection unit.