Prediction Of Street Lights In Metro Cities Using Time Series Analysis In Machine Learning Algorithm

In the current scenario, the substitution of man power becomes liable in theurban area where more sustainable projects have been developed to implement the smartcity environment. In this venture, the smart lighting in the streets are getting popular tomaintain the operations of the street lights. There are different other constraints in whichthe smart lighting can be addressed in monitoring the usage of the resources of theparticular LED bulbs and replacement time period of the LED Bulbs placed in thedifferent location. A device designed to monitor the LED bulbs intensity and usage time ofthe LED bulbs in the particular location will be sent through the Message QueuingTelemetry Transport –SN (MQTT-SN) protocol to the IOT web environment. Theinformation is maintained in the real time database where time based autoregressiveintegrated algorithm with moving average is used to predict the usage of the particularbulb and alerts the replacement of the particular bulb before the bulb gets worn out. Theanalysis is performed with respect to the life time of the bulb andtheir usage in the particular environmental factors such as temperature and humidity atthe location.