Deep Learning Approach for Optimum Power Management Using IoT in EV Battery Management System

Tracking of energy consumption has become more difficult as demand and value for energy have increased. In such a case, energy consumption should be monitored regularly, and the power consumption want to be reduced to ensure that the needy receive power promptly. Our objective is to identify the energy consumption of an electric vehicle from battery and track the daily usage of it. We have to send the data to both the user and provider. We have to optimize the power usage by using anomaly detection technique by implementing deep learning algorithms. Here we are going to employ a LSTM auto-encoder algorithm to detect anomalies in this case. Estimating the power requirements of diverse locations and detecting harmful actions are critical in a smart grid. The work of identifying aberrant power consumption data is vital and it is hard to assure the smart meter’s efficiency. The LSTM auto-encoder neural network technique is used here for predicting power consumption and to detect anomalies. Anomaly detection technique is the most important to identify any abnormal events of power consumption in electric vehicle battery. This approach can be validated by comparing the identified anomalous usage with the usual power consumption during the same period, and the results show a considerable increase in power consumption during the unusual times. Real time data of power consumption can be seen by the user and the user can track the daily usage of his/her power consumption using some user interface applications like Blynk. In Real-time a dataset is taken from smart energy meter hardware setup and the data is given as testing data to the already trained LSTM auto-encoder deep learning model and using anomaly detection technique abnormal energy consumption was identified.