An Automated Smart Street Lighting Model Using Integrated Systems With Deep Learning and Cloud Deployment

Street lights are uneconomically used from 7pm in the evening to 6am the next morning, each and every day. This makes them extremely maintenance-heavy for the government. Smart cities create ideal lives. Smart street lights create smart cities. By combining street lights with deep learning, self-orienting solar panels, intensity varying Sodium-vapor lamps, and cloud deployment, they can be made much smarter and economical. A vehicle approaching the street light is detected by the image processing camera located on each street light. Then, through the deep learning model, the number of vehicles and the distance between the vehicles is measured and transferred to the microcontroller. Simultaneously, the LDRs on each street light also measure the amount of sunlight present in the surrounding. Based on the values obtained through these two processes, the intensity of the street light is determined and executed. To power these street lights, a self-orienting solar panel is used on each one. These solar panels, with 360-degree rotational possibility, move in the direction of maximum sunlight, in order to provide maximum electricity. All of these processes are connected to a cloud-based app, which displays these values for the relevant authorities. The app’s main functionality lies in the fact that it has the ability to send notifications whenever any street light in a given domain is malfunctioning, along with the location of the street light and the specific component that needs to be repaired/replaced. But could this system be cost-efficient? There is a simple answer to that – much more than you can imagine. Together, these systems work in perfect harmony to provide, potentially, a viable solution to a major global problem.