Algorithmic analysis of intelligent electricity meter data for reduction of energy consumption and carbon emission

Intelligent Electricity Meters (IEMs) generate a considerable amount of household electricity usage data incrementally. Obviously, for the clustering task, it is better to incrementally update the new clustering results based on the old data rather than to recluster all the data from scratch. The gradational clustering is an essential way to accommodate the influx of new data seamlessly for accurate analysis. However, given the volume of IEM data and the number of data types involved makes the gradational clustering highly complex. Microsoft Azure provides the processing power necessary to handle gradational clustering analytics. The paper aim is to develop a Distributed Log-likelihood Based Gradational Clustering Algorithm on Microsoft Azure for analysis of IEM data. This research uses the real dataset of Irish households collected by IEMs and related socioeconomic data, including the geographic information, demographic data. It is visible from the study that algorithmic analysis helps the household customers to monitor and improvise electricity consumption patterns, Utility providers to reduce power outage and avoid capital expenses of building new plants. This research will be extremely useful for maintaining the environment by reducing pollution via carbon production by power plants. © 2019 Elsevier Inc.