Data Analytics


Energy and Utilities

The energy and utilities industry is undergoing a major transformation with the advent of smart sensors, smart meters, and IoT-based technologies. This transformation is mainly driven by the opportunity to use the massive amount of data generated from oil wells, generation stations, utility grids, gas grids and other sensors in distributed generations to derive meaningful insights for operational decision making. Used properly, this data can provide unprecedented insights into asset utilization (and downtimes), real-time demand and supply gaps and consumption behavior patterns – parameters key for business growth.

Data gathered from smart devices across the network can provide better understanding of customer segmentation, behavior and the influence of pricing on usage. Of course, this is possible only if enterprises build capabilities to use the data. For example, ‘time-of-use’ pricing encourages cost-savvy retail customers to run their washing machines, dryers and dishwashers at off-peak times. This not only saves the customer money but also reduces pressure on their energy company, which means lower capital outlay for new generation and overall greater operational efficiency.

Here are some key imperatives driving energy and utilities companies to transform into a data-driven enterprise and engage with customers in highly personalized ways:

Optimize expensive assets – The ability to identify potential problems in wells, power generation, grids and power distribution equipment can extend the life of expensive assets and help avoid unplanned service interruptions.

Dynamic forecasting and load management – Accurate and real-time energy demand forecasting is critical for timely and economical demand and supply management. Utilities need to leverage data on consumption, weather and supply constraints to effectively manage their wholesale operations and minimize the need for expensive spot market power purchases.

Fraud and loss prevention – Real-time information about load can help detect system energy losses through fraud or theft, helping realize significant financial benefits.

Customer service level management – Utilities are now expected to provide customers with self-service intelligence capabilities to view and manage all aspects of their relationships well beyond the basic enrollment, billing, payment and historical usage.

However, many energy and utilities companies we spoke to expressed system limitations to handle their enterprise data – smart meters and smart grids are generating an unprecedented volume, speed and complexity of data. For example, smart meter generates about 96 million reads per day for every million meters, resulting in a 3,000 fold increase in data that must be managed. And this flow of data and sources is bound to increase as time goes on.

To realize the full potential of their smart networks (smart grids and smart meters) and thereby improve ROI on their capital investments, utilities need the ability to perform more complex analysis on all the available data. They need the ability to ingest and process petabyte-scale data from multiple sources simultaneously. Analytics plays a critical role in turning vast amounts of data from these information assets (meters, sensors and SCADA) into actionable insight, foresight and prescriptions for critical decision making – outage management, Quality of Service (QoS), preventive maintenance activities and more.

Infosys point of view

Energy and utilities enterprises need to adopt analytics for data-driven decision making and smart operations management. With greater availability and access to data, utilities can have more insight into their most mission-critical processes than ever before.

This transformation warrants organizations to innovate their business processes and create a data-driven progressive culture in the organization. Our data analytics service offerings empowers them to seamlessly integrate enterprise data, turn it into intelligent insights and aid in real-time decision making thereby increasing their operation efficiency and reducing costs.

Customer intimacy – Intelligence from smart grids, enriched with customer demographic, behavioral and weather data streams would provide much-needed insights into customers’ energy consumption, thereby ensuring best possible customer experience.

  • Empower consumers with usage insights and influence their consumption behavior – Utilities can build intelligence around customer consumption patterns to provide cost-effective plans delivering tailored experience, thereby reducing customer churn, improving loyalty and customer lifetime value.
  • Segmentation and micro segmentation for effective customer acquisition and retention – Building an insights discovery platform integrating customer profile, energy consumption habits, mode of payments, associated risk etc. will help develop a 360-degree view of the customer and identify the customers at risk of losing. This platform will also help discover new patterns to model new segments and sub-segments for effective marketing campaigns and to yield desired conversion rates.

Operational efficiency and risk – Analytics of data streaming from oil wells and sensor data from grids provide real-time insights on operational performance. It facilitates organizations to reduce operating costs through preventive maintenance.

  • Reduce fraud and leakage using intelligence from smart devices As massive volumes of machine-generated data from smart sensors/ smart meters/ smart grids becomes readily available, energy and utilities companies can gain real-time insights to detect anomalies and patterns in supply, consumption and leaks, thereby optimizing energy distribution.
  • Improve asset performance and utilization with preventive and prescriptive insights  Analytics solutions for smoother operations by reducing the risk of asset failure and predicting any potential failure in real-time ensures assets at peak performance. We apply analytics integrating data historian with streaming data from machine logs and other operational data.
  • Improve QoS with predictive modeling of grid performance – Building a data lake of streams of multi-structured data in a scalable and cost-effective manner and machine learning algorithms to draw insights from this data and identify patterns based on massive historic data helps in accurate and dependable forecasting of asset performance, failures and determine causality and correlation between utility conditions and grid performance. It serves as a modeling platform to spot trends and determine patterns and predictable behavior to ramp up overall efficiency, SLAs and QoS.

Success Stories

Implemented self-service, business intelligence (BI) capabilities to support business groups and product lines spread over several geographic regions for a major oil field services company

Reduced 30% workload by defining and deploying data federation capabilities for a global energy major

Share the page

  • Tweet
  • Share on Facebook
  • Share on LinkedIn
  • Google+