Big data analysis for hydro-electric powerplant

The content of this nugget is about big data analysis for a hydroelectric powerplant and is developed by the Czech Technical University of Prague. The intended learning outcomes are basic understanding of Big Data, implement and train multi-layer perceptron (MLP) models and use Neural Net model to predict output of dependent variables. The three main characteristics of Big Data are volume, velocity and variety. Big data can also be characterized based on the requiring of non-relational representation or horizontal scalability. Input data from a hydro-electric power plant is used to explain data analytics. The goal is to find variables that influence the turbine power using a correlation analysis.
The data analysis tasks in a neural network are explained, including an evaluation. Python practice is part of the nugget.