Enabling edge computing-based coverage hole detection framework for lossless data tracking
Anitha Christy Angelin, Salaja Silas · Journal of Autonomous Intelligence · 2023
Countries throughout the world were experimenting with novel approaches to prevent the spreading of the Coronavirus pandemic illness (COVID-19). The use of IoT and cloud computing for data collection and analysis to avoid disease transmission via smartphone applications was a significant hurdle. Existing cloud services that are that retain the information of the victim to address severe challenges such as excessive latency and poor spectral performance. Furthermore, the likelihood of coverage gaps might result in the loss of genuine data, leading the technology to present inaccurate data. Motivated to solve these challenges, this paper addresses a new edge computing framework with a coverage hole detection module to detect and prevent the primary spread of pandemics like COVID-19 in an energy-efficient way. Experimental results exhibit excellent performance in terms of energy consumption under edge based and cloud based scenarios in the existence of coverage holes. The experimental findings demonstrate that the proposed structure has improved energy economy and reduced time to process while detecting coverage holes accurately.