by Bradley Williams, Oracle Utilities
As operational processes and tools within the electric grid have increased and matured, so too has the amount of data being collected by intelligent grid devices. Focused analysis of this data is providing utilities with many opportunities to manage the enterprise better based on data-driven decisions.
There are many opportunities in which data analytics can play a pivotal role in improving a utility’s overall focus on its mandate of safety, reliability, operational excellence and enhanced customer service.
Analytics provides utilities with the increased ability to manage their businesses and customer relationships better across the enterprise. Utility analytics best practices support a broad range of areas from meter operations, billing support and call center support to revenue protection, demand-side management and distribution operations and planning.
Step 1: Ask the Right Questions
First, utilities must decide what they want analytics to do for them. A good, enterprisewide exercise begins with questions like these: What are our current business needs? Where are our areas of opportunity? What else can we do? How else can we achieve value? How can we leverage our analytics to change our business processes? How can we better drive our decision making?
Answering these questions will mean looking more deeply at what you want analytics to do for you and then sharing data and collaborating across the utility enterprise silos and experimenting with mash-ups of the disparate types of data you have collected. For example:
- What data can we aggregate and then analyze across all silos to give us a deeper, more holistic understanding of our businesses?
- How can we use data to identify more accurately where and why excessive line losses or nontechnical losses (theft) are occurring?
- Where and why do customers experience the most power quality and voltage problems?
- How can we use data to optimize our assets better?
- How is customer segmentation affected by load profile?
- How can we best use meter data to identify overloaded distribution transformers and other assets at risk?
The possible questions are limited only by a utility’s needs, interests and imagination. These what-if questions lay the groundwork to provide increasingly stronger business cases for the utility to pursue.
There are numerous drivers at play, broadly categorized into four pillars: customer satisfaction, reliability, operational efficiency and safety.
Drivers will change based on each utility’s needs but each provides a compelling argument for using analytics. From customer satisfaction drivers–such as insights into customer usage (individual or aggregated) and the ability to target specific programs to specific customer groupings–to increased reliability, operational efficiency and safety drivers, there are numerous reasons to implement analytics processes across the utility enterprise.
Step 2: Define and Build Your Use or Business Cases
Vast opportunities exist for using analytics in all areas of the utility value chain. Utilities are finding solid returns in everything from customer service and billing to nontechnical losses and power distribution.
But there is no silver bullet, no one analytics solution for all utilities. Although adding analytics to the enterprise can seem overwhelming, there are many ways in which to go about it. For example, some utilities have used cloud solutions to go after quick wins first, tackling revenue protection or reliability issues, and then moved on to other areas within the business. One advantage of using a cloud solution at the outset is that it is less expensive and far faster to implement than traditional approaches to utility data analytics. In the race to build viable business cases for further analytics usage throughout the enterprise, being able to leverage the data already on hand for the greatest opportunity in the shortest time–and without a large capital expense–is often a deciding factor.
Examining other utilities’ best practices in analytics–and there are many solid, viable, utility-proven use cases from which to choose–is a practical first step to be able to show investors, regulators, customers and other shareholders the intrinsic value of the project. This is the value of collaborative analytics.
Let’s briefly look at basic use cases for analytics. Whether you want to increase customer satisfaction through more clearly targeted interactions, improve reliability through more effective monitoring and proactive maintenance, enhance operational efficiency aided by better planning and execution, or increase safety through a clearer understanding and mitigation of hidden risks, there are compelling arguments for leveraging analytic processes to create value-added insights on the customer and operational sides of the enterprise.
- Improved customer satisfaction through segmentation and communication personalization. Customer data analytics, encompassing both structured meter data and more unstructured customer data (such as social media and customer relationship data), can provide the utility with a means to better provide its customers with information about their usage patterns, target them for new programs that better fit their individual needs, establish new pricing programs based on usage, and implement more effective demand response and demand-side management programs. Analytics also can provide information to enable the utility to be more proactive with its customer service. For example, it easily could alert customers to usage spikes that might indicate a water or gas leak or an issue with an electrical appliance within a customer’s home or business.
- Improved reliability through monitoring and proactive maintenance. Operational data analytics can aid a utility by providing both an historic and a real-time view of the utility’s operations. Bring predictive analytics into the mix, and the utility then can begin to compare historical data to identify trends in usage and asset health, overlay weather maps and forecasts, and forecast demand to predict more accurately energy or water usage, grid impact of renewable generation, and more. Being able to analyze and predict asset health better and manage potential outages or leaks can turn what has been a reactive, run-to-failure utility approach to asset and outage management into a much more proactive, predictable, cost-reductive process.
- Improve operational efficiencies through better planning and execution. From revenue assurance and employee utilization and prioritized fieldwork to the reduction of infrastructure and asset replacement costs, predictive analytics can leverage data from multiple sources across organizational departments for new insights into utility operational performance.
- Improve safety by understanding and mitigating risks. Analytics can be used to approach vegetation management proactively, as well as asset management, and eliminate unnecessary outages. Public safety is improved, as well. Besides being able to analyze usage spikes for the benefit of the customer (a potential water or gas leak or a malfunctioning appliance), usage spikes also can indicate a potential public safety hazard a utility can act upon quickly as soon as it is identified.
Step 3: Consider an Enterprise Analytics Strategy
Just as the specific drivers for each utility will be different, so will its approach to enterprise analytics. Again, as more than one utility has pointed out in analytics discussions recently, it will involve questioning the usefulness of your utility’s historic approach to data: How do we approach data as a valuable enterprise resource in a project-oriented culture?
As many utilities complete their advanced metering infrastructure deployments and begin to bring more frequent interval data back to the enterprise to better feed transactional applications such as customer information systems, customer care and billing, and operational applications such as the advanced distribution management and outage management systems, it becomes increasingly more important that the whole picture is seen and drives additional value, rather than simply the siloed needs within each particular program or project.
But beyond the overall need to use the new data to improve the utility’s enterprise capabilities, utilities’ specific data analytics needs and approaches likely will remain as individual as the utility itself, whether that is in specific projects or its approach to enterprise analytics.
Operational reporting and tracking of key performance indicators are a must. Beyond this, there are many opportunities in which across-the-enterprise analytics can play pivotal roles in improving a utility’s overall focus on its mandate.
Utility leaders must create a culture that embraces analytics to drive continuous improvement.
Technology integration, including a strong foundational information management platform and business infrastructure for analytics, has become increasingly important in this enterprisewide approach.
And, just like the introduction of quick-win, project-based use cases within the utility, quick-win enterprise analytics use cases need to be developed, as well.
The list of use cases and utility benefits will continue to grow. Using data and data analytics is an evolution of learning and integrating.
New analytics processes will migrate into standard operating procedures and will be replaced by even more potentially complex, compelling analytics issues as utilities finely hone their processes and pursue new opportunities.
Bradley Williams is vice president of industry strategy at Oracle Utilities.