摘要：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).
