Incremental Learning of Electricity Smart Meter Data

Utility companies in India still rely on manual electricity meter reading to track consumption at residential and industrial locations. Local utility companies send employees to read these meters each month and then generate monthly electricity bills. Generation of data regarding consumption patterns compiled from manual readings is prone to errors, time consuming and not as widely comprehensive as may be needed to arrive at planning for providing sufficient energy at maximum efficiency and economical cost. 

This book focuses on ESM data analysis by proposed Cloud for Closeness-based Gaussian Mixture Incremental Clustering Algorithm (Cloud4CGMIC). The proposed system can capture and generate the hidden pattern of consumption based on day-time and night-time, season-wise, and area-specific learning. 

The distributed incremental clustering system identifies the change in residential energy consumption and provides valuable data to utility companies to optimize electricity load management. 

This book helps us to know about -
    The newly implemented incremental clustering algorithm
    How incremental learning is achieved via incremental clustering
    How knowledge augmentation is achieved via incremental clustering
    How to implement distributed incremental clustering algorithm using Microsoft Azure platform
    How to analyze electricity smart meter data from varied locations and find hidden patterns, estimate load profiles, forecasts energy requirements and work on carbon emissions too

Who should read the book:
    Researchers in energy sectors, 
    Data or business analytics team, 
    Electricity generation and distribution team, and 
    All those who are interested in electricity energy varied sources data analysis