Enhanced Public Safety and Well-Being through IoT-Enabled Light Pollution Mitigation with Reinforcement Learning
Santosh Kumar Sahoo, N. Mohankumar, K. K. Manivannan, K. Sindhuja, S K Mouleeswaran, Cidambi Srinivasan
Abstract
Light pollution is becoming a more series issue in cities, threatening people's health and safety. An efficient approach to deal with light pollution in real-time by using reinforcement learning (RL) algorithms and the Internet of Things (IoT) is presented. It optimizes safety and energy efficiency by utilizing RL methods and integrating sensors to acquire environmental data. It dynamically changes lighting settings based on data. It shows that the strategy can decrease light pollution and improve public safety and well-being via simulations and tests. The results show that the machine learning algorithms and technologies with IoT sensors gives a solution towards sustainable urban development. Urban areas may be made safer and more habitable with the help of the proposed system, which would enhance public health and people's quality of life.