Automated Metering Infrastructure (AMI) has increased the volume of utility data substantially which grows in magnitude after it is analyzed. And, with some utilities' considering five-minute reading intervals, the data volume will continue to grow.
The major attributes of big data are:
Volume - The vast amounts of data generated every second.
Velocity - The speed at which new data is generated and at which data moves. Big data technology allows for analysis of the data while it is being generated without being placed into databases.
Variety - The different types of data. About 80% of the world's data is unstructured and cannot be categorised easily.
Veracity – This is the “messiness” or trustworthiness of the data. With many forms of big data, quality and accuracy are less controllable.
Data analytics growth could be better
The industry is expected to spend US$7 billion in 2014, representing over 15% of the overall cross-industry spending, according to ABI Research. In 2019, the spending on energy analytics is expected to exceed US$21 billion, following a CAGR of 25%. [Engerati- The Energy Industry Sees Value in Data Analytics.]
Large-scale deployment of advanced metering infrastructure (AMI) and intelligent energy devices (IEDs), combined with grid edge power conditioning equipment and availability of sensor data, has created a growing need for data storage and analysis.
While data assimilation is growing rapidly, the application of analytics is somewhat slower and could be better, says ABI Research.
International Data Corp. (IDC), a provider of market intelligence in the information technology (IT), telecommunications and consumer technology markets, predicted big data will grow 30% this year by developing "data-optimized cloud platforms" that will leverage high volumes of real-time and nonreal-time data streams.
However, according to Gartner, big data won’t drive big growth in the worldwide business intelligence and analytics market. The analysis of large volumes of data appears to be one of the most critical, yet lacking elements of big data.
According to a SAP User Group survey, over 50% of respondents think they don’t have the necessary skills or technology to make use of all their data.
Wikibon Principal, a research contributor and big data analyst says that a lack of best practices for integrating big data analytics into existing business processes could also be to blame.
He lists other roadblocks as follows:
Concerns over security and data privacy
Continued “big data washing” by legacy IT vendors
Volatile and fast developing market
A lack of polished big data applications for solving certain business problems
The many uses of data analytics in the utility industry
Through the analysis of its big data, utilities can expect greater operational efficiencies such as quality assurance and quality control data which is done by improving the quality of connectivity information including phase. Analytics aids voltage correlation (links meters to transformers), as well as voltage deviation and transformer load management. Analytics can help to identify transformers that could be overloaded or even underused. By improving operational efficiency, utilities will enjoy greater revenue protection from both technical and non-technical losses (theft).
Energy efficiency levels can also be improved thanks to analytics. This can be used to target demand response by prioritizing customers for energy conservation and demand response programs using geospatial techniques, and energy density mapping for instance. This also includes distribution operations planning which helps utilities to target customers with high peak loads to help reduce peaks by staggering power for ventilation, heating, cooling and lighting.
Analytics also provides predictive intelligence which will of course aid operational efficiencies. By analysing usage patterns, utilities can create “energy models” based on unmetered usage from streetlights and other devices for instance. In addition, geospatial outage frequency analysis will help identify outage patterns geographically.
With the growth in electric vehicles, utilities will find predictive analysis useful as they are able to identify plug-in electric vehicle owners and predict demand patterns to ensure adequate transformer capacity.
To ensure sustainability, predictive maintenance programmes should be put into place to ensure the efficient use and management of utility assets.
“Analytics allow the early movers to gain a critical competitive advantage over laggards, in a field where competing by the end product is seldom an option,” says principal analyst Aapo Markkanen at ABI Research.