Machine Learning for Improving Renewable Energy: Integrating Solar Power for Continuous Operation of Smart Sensors During Natural Calamities

作     者：Ahmed Refaie Ali F. Zhara Sakinah Mohd Shukri Mohd Abdullah Al Mamun S. Iqbal Amit Ved 

作者机构：Department of Mathematics and Computer Science Faculty of Science Menoufia University Shebin El Kom 32511 Menofia Governorate Egypt School of Electro-Mechanical Engineering Xidian University Xi’an 710071 P. R. China Management and Science University Shah Alam 40100 Selangor Malaysia Department of Master’s of Business Administration in Information Technology Management Westcliff University Irvine CA USA Centro Studi Attività Motore Biology and Biomechanics Department Via di tiglio 94 Lucca Italy Department of Electrical Engineering Faculty of Engineering and Technology Marwadi University Rajkot 360003 Gujarat India 

出 版 物：《Biophysical Reviews and Letters》 

年 卷 期：1000年

主　　题：Sensors energy utilization machine learning sustainability 

摘      要：This research tackles the critical issue of ensuring reliable data collection during natural disasters, such as floods, by calibrating and integrating smart sensors with renewable energy systems. Natural disasters often disrupt power supplies, posing significant challenges to the continuous operation and data availability of these sensors. To address this challenge, the study proposes leveraging renewable solar energy as a sustainable and reliable power source for smart sensors. By incorporating solar energy systems, the framework guarantees that sensors remain operational even in extreme conditions, ensuring that crucial environmental data is consistently accessible for rescue and recovery efforts. The research introduces an innovative approach that employs renewable energy to sustain the functionality of smart sensors during disasters. The framework includes models designed to manage uncertainties in disaster scenarios and optimize energy use for sensor operation. Additionally, the machine learning forecasting tool Prophet is utilized to improve the accuracy of predictions related to energy consumption and sensor performance. Prophet’s strength in handling time series data and generating reliable forecasts is vital for this application.