Concept of Using Cloud to Improve Accuracy and Metrological Reliability of IoT Based Data Acquisition Systems

This paper presents a conceptual system for collecting and storing measurement data in Cloud to enhance the metrological characteristics of IoT sensors. The influence of operating conditions on signal drift and measurement accuracy is analyzed, and an adaptive method for determining the intercalibration period (ICP) is developed. A predictive algorithm for changes in metrological characteristics is proposed based on historical data, statistical methods, and machine learning techniques. The system utilizes cloud technologies for centralized data analysis and adaptive calibration interval adjustment, reducing sensor maintenance costs and improving measurement accuracy. It is demonstrated that predictive modeling enables the extension of the intercalibration period without compromising accuracy. The findings are particularly relevant for decentralized IoT systems where physical calibration is challenging or costly. The use of cloud platforms for data collection and analysis allows real-time detection of deviations and measurement error correction, contributing to improved efficiency and reliability of measurement systems.