Central Computer Failure Probability Model for Radio Networks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Large-scale radio networks, especially in industrial settings, face challenges in maintaining reliability due to configuration errors or overloading, which can lead to production interruptions and economic damage, as existing methods focus primarily on power adjustments and configuration optimization without comprehensive failure prediction.
Innovation Solution
A method where devices in the radio network transmit cyclical operating parameters to a central computer, which creates a model to determine failure probabilities by correlating operating constellations with failures using pattern recognition algorithms, allowing for timely detection and prediction of impending network failures and generation of warning signals when thresholds are exceeded.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If power adjustment methods are used to optimize radio network operations, then network configuration and control are improved, but comprehensive failure prediction capability deteriorates
Solution Approach 1:
The system performs preliminary actions by continuously collecting operating parameters and creating a model that assigns failure probabilities to operating constellations before actual failures occur. This allows proactive identification of critical situations and preventive measures to be taken, resolving the contradiction by enabling both operational control and failure prediction capability simultaneously.
Solution Approach 2:
The system implements feedback by continuously monitoring operating parameters, comparing current operating constellations against the trained model, and generating warnings when failure probabilities exceed thresholds. This closed-loop feedback mechanism enhances both network control and reliability by providing real-time insights and enabling corrective actions before failures occur.
2Duration of action of stationary object
If transmission power is adjusted to maintain network operations, then network continuity is improved, but comprehensive monitoring of failure risks deteriorates
Solution Approach 1:
The system achieves multi-functionality by integrating both network control functions (power adjustment) and failure prediction functions into a single comprehensive monitoring system. The central computer performs both operational parameter adjustment and failure probability assessment, eliminating the need for separate systems and enabling simultaneous improvement of network continuity and failure risk detection.
Solution Approach 2:
The system introduces an intermediary element - the trained model that assigns failure probabilities to operating constellations - which mediates between raw operating parameters and failure predictions. This intermediary enables comprehensive failure risk monitoring without interfering with network continuity maintenance, as it processes information separately and provides independent risk assessments.
3Measurement precision
If pattern recognition algorithms are implemented for failure prediction, then failure detection accuracy is improved, but system complexity deteriorates
Solution Approach 1:
The system implements self-service by automatically collecting operating parameters, training the pattern recognition model using historical data, and performing failure predictions without requiring external intervention. The central computer autonomously manages the entire process from data collection to failure detection, improving accuracy while managing complexity through automation rather than manual processes.
Solution Approach 2:
The system applies periodic action by cyclically collecting operating parameters from radio network devices and periodically updating the failure probability model. This structured periodic data collection and model updating approach improves detection accuracy through consistent monitoring while managing system complexity through regular, predictable operations rather than continuous complex processing.
Data Source
AI summary
The present application relates to a method for detecting and determining a failure probability (pA) of a radio network. The method is characterized in that devices of the radio network cyclically transmit operating parameters to a central computer wherein each transmitted operating parameter comprises an operating value of the respective device and a detection time point (t) of the operating value. All transmitted parameters and values can be viewed at any time by accessing the central computer. The central computer cyclically stores the operating values of all operating parameters detected within a predefined time interval (T) as the respective operating constellation and checks the radio network for a failure (A). The central computer cyclically creates a model based on the stored operating constellations and failures (A), which assigns a failure probability (pA) to each possible operating constellation.