By Maryana Pinchuk
From May 6 to 8, staff from US and international energy utilities gathered in Charlotte, North Carolina for the Utility Analytics Institute’s annual summit. The theme of the summit was “Accelerate Now,” and throughout the sessions, speakers highlighted how advanced analytics could be used to achieve a variety of goals for utilities, from making smarter business decisions to optimizing the productivity of operations staff and increasing customer benefits. Overall, the summit served as a rallying cry for companies like Xylem to develop more tools to help utilities overcome the obstacles of today and prepare to meet the challenges and opportunities of tomorrow.
Smart decision-making in the age of big data
Whether it’s coming from sensors, loggers, or smart assets, the amount of data available on each meter, customer, and square mile of utility distribution network continues to grow each year. For savvy utilities, this wealth of information presents an opportunity to make smarter business decisions. As one example, Mohamad Hussin, Senior Engineer at Dubai Electricity and Water Authority (DEWA), discussed building a machine learning model to understand the actual expected life of a transformer. When DEWA analyzed the data in their service area, they found that transformers were lasting an average of only 15 years in the field before replacement, even though the expected lifespan according to traditional industry guidance was 30-40 years. Through predictive modeling, DEWA was able to more accurately identify which transformers were truly likely to fail, versus ones that were functioning correctly but were likely to get taken out of service for other reasons, e.g., because of a lack of demand in that part of the grid. This knowledge allowed DEWA to prioritize testing and replacing the right assets, saving money on unnecessary field service.
This type of data-driven asset condition assessment is the approach advocated for by Xylem and demonstrated in solutions like Valor’s Hidden Revenue Locator for customer metering and data handling inaccuracies. When utilities use analytics to facilitate smarter asset management, they lower the cost of O&M and drive greater revenue recovery.
Test-and-learn mindset to get the most of out of operations
Brian Savoy of Duke Energy touched on the importance of implementing a data-driven operational process for increasing worker productivity. Brian, Senior Vice President of Business Transformation and Technology at Duke, discussed the recent evolution of Duke’s internal tool and process development practices from classic waterfall – i.e., a years-long R&D phase before any new product or process was built and operationalized – to a nimble agile process, where an idea could be formulated, developed, and tested in a matter of weeks. This new data-driven approach to operations allowed Duke to pilot radically transformative processes and see returns right away. An example Brian shared was developing an iPhone application to assist with field operations. The app doubled the productivity of Duke’s field crews when it replaced the clunky and expensive legacy tools Duke had been using to track personnel and materials during field maintenance.
Brian’s story provides a valuable lesson in how applying data-driven thinking and technology to basic utility operations practices can increase efficiency. Valor’s proven method of program delivery follows these principles, relying on a two-stage diagnosis and drill-down approach that allows utilities to optimize their deployment of personnel and realize efficiency gains.
Transforming customer service through data and technology
Together, advanced analytics and a data-driven mindset can also dramatically transform the relationship of the utility to its customers. In a panel Q&A discussion, representatives from Exelon, Evergy, and Duke discussed how they’ve implemented predictive customer analytics and chatbots to assist customers with frequently asked questions. Combined, these innovations have freed up their customer service staff to take on more complex customer communications that they previously would not have had time to engage in. Patty Durand, President and CEO of the Smart Energy Consumer Collaborative (SECC) presented findings from SECC consumer surveys that indicated an even greater desire from utility customers to get more meaningful, actionable communications from their utilities about their consumption, as well as ways to save money on their bills.
Xylem recognizes that the future of utility customer engagement – whether for customer leaks or nonpayment – relies on targeted, just-in-time, proactive communication strategies. Valor’s solutions suite includes tools for proactively identifying water leaks and anomalous gas usage behind the customer’s meter in order to facilitate notifications to customers. To tackle the tremendous and growing affordability challenge that utilities and their customers are facing, Valor also provides a predictive nonpayment management solution that can help utilities avert the vicious cycle of nonpayment and service shutoffs with proactive communication and intervention strategies.
Challenges to implementing data-driven solutions
In addition to the many success stories, speakers also discussed the obstacles they have faced when adopting advanced analytics. Their challenges included talent acquisition and retention; data quality and quantity; and siloed data – i.e., only being able to see insights from their own service area. While EPRI, the Electric Power Research Institute, has aggregated data from multiple energy utilities in order to help provide deeper insights on common issues and trends, many utilities are still limited to the data they have, which may be insufficient for building and training robust machine learning models.
Key takeaways for the water sector
Coming from a company that focuses primarily on water, the tools and practices shared by energy-focused utilities, vendors, and nonprofits at the UAI summit were excitingly cutting-edge. The water sector has many lessons to learn from its energy counterparts in advanced analytics and data adoption. But my key takeaway is that companies like Xylem that offer cross-cutting, hardware-agnostic solutions have a huge opportunity to help water utilities – which in the US tend to be smaller and more fragmented than electric and gas utilities – overcome their data quality and quantity challenges. With every program that we deploy, we build a database of best practices and rich insights into customer meters and behavior that can help the next utility we work with make smarter business decisions, optimize operations, and improve customer service. Together, we can help the utilities of today transform their data into insights that will guide them through the challenges and opportunities of the future.