IoT Device Purging via Data Profile Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The increasing number of IoT devices connected to cellular networks leads to a burden on these networks due to non-functioning devices that continue to attempt registration, transmit meaningless or corrupted data, and consume resources unnecessarily.
Innovation Solution
The system generates a model using machine learning approaches or statistical models to identify non-functioning IoT devices by analyzing data transmission patterns, allowing for their removal from the network, thereby optimizing resource utilization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If the number of IoT devices connected to cellular networks is increased, then network coverage and service capability are improved, but network resource consumption and load increase due to non-functioning devices
Solution Approach 1:
The system performs preliminary identification of non-functioning IoT devices by analyzing data transmission patterns before they consume excessive network resources. Machine learning models predict device functionality status in advance, allowing the network to proactively manage resources by identifying and removing non-functioning devices before they become a significant burden on network capacity
Solution Approach 2:
The system implements continuous feedback mechanisms by monitoring data transmission patterns from IoT devices and using machine learning models to update device functionality assessments in real-time. This feedback loop enables the network to dynamically adjust resource allocation based on actual device performance, removing non-functioning devices that fail to meet expected transmission patterns
2Measurement precision
If machine learning models are used to identify non-functioning devices, then device purification accuracy is improved, but computational complexity and processing time increase
Solution Approach 1:
The system applies partial action by using machine learning models selectively - not all IoT devices are analyzed with full computational complexity. Instead, the system focuses computational resources on devices showing anomalous patterns or at risk of becoming non-functional, applying simplified analysis to clearly functioning devices and reserved complex analysis only where needed, thus balancing accuracy with computational efficiency
Data Source
AI summary
Processes and systems for identifying and removing non-functional Internet-of-Things (IoT) devices from a cellular network are discussed herein. In one example, a probability distribution function of a data profile transmitted by a type of IoT devices is generated. The probability distribution function may be chosen based on a known distribution such as a Gaussian, Bessel, or linear regressive model. The probability distribution function may be empirically generated by applying data received from IoT devices to a machine learning model using supervised or unsupervised learning. After generating the model representing the expected data profile of data received from a type or class IoT devices, data transmitted by the IoT devices may be applied to the model to determine whether the IoT devices are functional or non-functional. Non-functional IoT devices may be removed from the cellular network.