From the Facebook ability to curate information flow designed for you, to the ability to read the human genome, modern data analytics has a lot of applications in different forms and shapes. So does the energy sector.
Businesses can apply analytics for reaching insights into every process and to explore optimization opportunities. Starting with better-managed operations to the demand side of commercial channels but analytics also is opening a lot of new opportunities related to smart grids, smart homes, renewable energy, etc. Since at A4E we are tempted by all things analytics, in this blog post we share real-life application of energy data analytics.
Big users as industrial companies rely on specific energy supply contracts where exact loads are a key variable. Take or pay schemes often used by energy suppliers might be really expensive for the business if it needs less or more than already contracted. Here comes data analytics which easily outperforms linear and exponential forecasting trends generated by the purely statistical approach. Predictive analytics is capable of forecasting energy consumption with greater accuracy which is beneficial for big users.
Improved Customer Support
Mercury Energy, an American utility company deployed a program to forecast high bills way before they are issued and to deliver personalized customer alerts. In addition, a cost savings tips were added to the customers facing energy efficiency opportunities. This data analytics-driven approach led to 9% fewer customer calls which mean improved customers support. This resulted in a reduction of customers churn by 10% which is the direct contribution to the company business performance.
By applying streaming analytics, utility companies are able to fight frauds, says Scott Zoldi in an article published in Information Management. This is a big problem for energy companies losing as much as $6 billion a year in the USA alone because of bypass lines installed by homeowners and contracting customers. Such thefts can be easily detected by proper measuring energy usage and modeling such data is showing where the fraud is likely to occur on the network.
There are typical fluctuations in electric usage, voltage, weather conditions and other parameters suggesting that a failure is going to occur. Such data can be modeled in order to predict potential network failures. The same is viable not just for energy providers but users too. If an energy consumer, an electric motor, for instance, shows unusual consumption growth, this is a signal that a belt or bearing is worn and it generates more resistance that it should. This way the failure might be prevented.
Intelligent efficiency technologies, constant data flow, and streaming analytics made energy automation not just possible but also recommended. Schneider Electric shared recent study, quoted by Greentech Media and showing that 1 of 4 energy leaders’ surveyed says that building automation is among their primary efficiency approaches. In fact, automation solutions are able to create 10 to 30% annual savings in energy consumption for mid to large scale users.