Developed for analysing and visualizing trends related to electricity and energy consumption

The project worked on a dataset containing more than 2 million records about electricity consumption on a per minute basis. The plethora of data was read and processed using Apache Spark Streaming. Spark Machine Learning Library (MLlib) was used for analyzing the usage patters, clustering the data points, and predicting the trends in electricity consumption.

Technology used: Apache Hadoop, Apache Spark, Spark MLlib, Java

Data: https://archive.ics.uci.edu/ml/datasets/individual+household+electric+power+consumption