Decreasing data analytics time : hybrid architecture mapreduce-massive parallel processing for a smart grid

الملخص EN

As our populations grow in a world of limited resources enterprise seek ways to lighten our load on the planet.

The idea of modifying consumer behavior appears as a foundation for smart grids.

Enterprise demonstrates the value available from deep analysis of electricity consummation histories, consumers’ messages, and outage alerts, etc.

Enterprise mines massive structured and unstructured data.

In a nutshell, smart grids result in a flood of data that needs to be analyzed, for better adjust to demand and give customers more ability to delve into their power consumption.

Simply put, smart grids will increasingly have a flexible data warehouse attached to them.

The key driver for the adoption of data management strategies is clearly the need to handle and analyze the large amounts of information utilities are now faced with.

New approaches to data integration are nauseating moment; Hadoop is in fact now being used by the utility to help manage the huge growth in data whilst maintaining coherence of the Data Warehouse.

In this paper we define a new Meter Data Management System Architecture repository that differ with three leaders MDMS, where we use MapReduce programming model for ETL and Parallel DBMS in Query statements(Massive Parallel Processing MPP).