Method and system to optimize performance and determine end of life of edge devices of an internet of things network
Described herein are methods and a system for that monitors the performance, and provides reporting including replacement of IoT edge devices in an edge computing network. Data is received by an AI/ML model from multiple IoT edge devices which is process in time series. Analysis services and engines determine the performance of the multiple IoT edge devices. Severity and weightage are applied to the data, and algorithms determine performance and replacement recommendations.
1. A computer-implementable method for monitoring the performance of IoT edge devices comprising:
receiving data by an AI/ML model implemented in an API gateway, from multiple IoT edge devices in an edge computing network through the API gateway, wherein the AI/ML model is trained by:
processing the data in time series with a data processing component of the AI/ML model, wherein data received by the AI/ML model is segmented into data from an RMQ listener by a data listener;
providing the segmented data to an RMQ broker that provides RMQ queues for processing analysis engines of the AI/ML model;
analyzing the processed data with the analysis engines of the AI/ML model, wherein the analysis engines include services and engines to determine performance of the IoT devices based on the processed data;
determining severity and weightage of the processed and analyzed data by the AI/ML model; and
applying algorithms of the AI/ML model to the data with severity and weightage to provide performance metrics and replacement recommendations; and
providing by the AI/ML model performance metrics and recommendations through the API gateway as to performance metrics and recommendations for the IoT edge devices.
2. The computer-implementable method of claim 1 , wherein the received data is stored for future processing by the AI/ML model.
3. The computer-implementable method of claim 1 , wherein the data includes feature sets as to state of an IoT edge device, time received, error messages, category, frequency, CVSS, nearby device error status, error probability, and severity of error.
4. The computer-implementable method of claim 1 , wherein analyzing the processed data includes noisy neighbor detection, health score, performance impact time range detection, residual lifetime calculation, and faulty device detection.
5. The computer-implementable method of claim 1 further comprising storing processed and analyzed data in a data farm that includes current and historical data.
6. The computer-implementable method of claim 1 further comprising reporting performance metrics and replacement recommendations through one or more services including email notification, SMS message, REST message, and printed reports.
7. A system comprising:
a plurality of processing systems communicably coupled through a network, wherein the processing systems include non-transitory, computer-readable storage medium embodying computer program code interacting with a plurality of computer operations monitoring the performance of IoT edge devices comprising:
receiving data by an AI/ML model implemented in an API gateway, from multiple IoT edge devices in an edge computing network through the API gateway, wherein the AI/ML model is trained by:
processing the data in time series with a data processing component of the AI/ML model, wherein data received by the AI/ML model is segmented into data from an RMQ listener by a data listener;
providing the segmented data to an RMQ broker that provides RMQ queues for processing analysis engines of the AI/ML model;
analyzing the processed data with the analysis engines of the AI/ML model, wherein the analysis engines include services and engines to determine performance of the IoT devices based on the processed data;
determining severity and weightage of the processed and analyzed data by the AI/ML model; and
applying algorithms of the AI/ML model to the data with severity and weightage to provide performance metrics and replacement recommendations; and
providing by the AI/ML model performance metrics and recommendations through the API gateway as to performance metrics and recommendations for the IoT edge devices.
8. The system of claim 7 , received data is stored for future processing by the AI/ML model.
9. The system of claim 7 , wherein the data includes feature sets as to state of an IoT edge device, time received, error messages, category, frequency, CVSS, nearby device error status, error probability, and severity of error.
10. The system of claim 7 , wherein analyzing the processed data includes noisy neighbor detection, health score, performance impact time range detection, residual lifetime calculation, and faulty device detection.
11. The system of claim 7 further comprising storing processed and analyzed data in a data farm that includes current and historical data.
12. The system of claim 7 further comprising reporting performance metrics and replacement recommendations through one or more services including email notification, SMS message, REST message, and printed reports.
13. A non-transitory, computer-readable storage medium embodying computer program code for monitoring the performance of IoT edge devices, the computer program code comprising computer executable instructions configured for:
receiving data by an AI/ML model implemented in an API gateway, from multiple IoT edge devices in an edge computing network through the API gateway, wherein the AI/ML model is trained by:
processing the data in time series with a data processing component of the AI/ML model, wherein data received by the AI/ML model is segmented into data from an RMQ listener by a data listener;
providing the segmented data to an RMQ broker that provides RMQ queues for processing analysis engines of the AI/ML model;
analyzing the processed data with the analysis engines of the AI/ML model, wherein the analysis engines include services and engines to determine performance of the IoT devices based on the processed;
determining severity and weightage of the processed and analyzed data by the AI/ML model; and
applying algorithms of the AI/ML model to the data with severity and weightage to provide performance metrics and replacement recommendations; and
providing by the AI/ML model performance metrics and recommendations through the API gateway as to performance metrics and recommendations for the IoT edge devices.
14. The non-transitory, computer-readable storage medium of claim 13 , wherein the received data is stored for future processing by the AI/ML model.
15. The non-transitory, computer-readable storage medium of claim 13 , wherein the data includes feature sets as to state of an IoT edge device, time received, error messages, category, frequency, CVSS, nearby device error status, error probability, and severity of error.
16. The non-transitory, computer-readable storage medium of claim 13 , wherein analyzing the processed data includes noisy neighbor detection, health score, performance impact time range detection, residual lifetime calculation, and faulty device detection.
17. The non-transitory, computer-readable storage medium of claim 13 further comprising storing processed and analyzed data in a data farm that includes current and historical data.