Ariel Santamaria is the vice president of Reliability 360 Operations at Advanced Technology Services, and is responsible for leading and executing reliability-centered initiatives.
Rapid changes in the utility industry have left many teams struggling to catch up. Increases in consumption from innovations like AI data centers, along with pressure to reduce waste and improve operational efficiency, call for enterprising solutions. Although plenty of utilities are stepping up to upgrade their monitoring systems, they don’t always have the tools or the processes to make the new data useful.
This situation can leave teams collecting data without a clear or consistent way to turn it into actionable insights. The use of analytics tools and creation of stronger data management processes can take that data and put it to effective use.
Utilities face a host of challenges to successfully utilizing data, including data overload and disconnected systems.
For utilities that have set up the collection of data, overload can be a major hazard. Without the right structure and processes to handle the information, teams can be overwhelmed by a stream of alerts that never seems to slow down. Instead of focusing on the real problems that require prompt solutions or getting ahead of system failures, teams get stuck reading and classifying alerts.
Utilities working to bring their technological infrastructure into the 2020s may face disconnected systems and siloed data that can become a significant obstacle. Older technologies often did not allow for centralization of data or processes, which meant that utilities had information stuck in a variety of places. This obsolete arrangement causes teams to spend more time than necessary trying to find critical information. Even worse, they may miss more serious issues because no one was receiving alerts from a particular server.
And data collection can feel meaningless when utilities lack the analytics tools necessary to turn that data into tasks that improve performance or efficiency. Data integration involves the collection of data, but the next step involves analytics. Analytics tools can help take the data and filter noise to identify the critical elements that require human attention. If teams have not implemented these tools, or if the tools they use are not integrated properly, they won’t get optimal results.
Unclear processes also present issues. Even if utilities teams have a good system for data management and analytics, unclear processes can mean that work still doesn’t get done. Data analytics upgrades require somewhat of a paradigm shift, specifically from reactive to predictive action.
Utilities may not have the processes in place to establish who is responsible for reading and responding to relevant alerts. And unclear processes make it difficult to assign ownership, delaying response and increasing the risk that critical issues are missed.
Turning data into action
Utilities can utilize stronger data integration to implement actionable insights.
Data-powered insights are only as strong as the integration. Utilities that still rely on obsolete data management should consider upgrading to centralized systems, along with other infrastructure improvements. This may involve shifting to enterprise systems that automate data collection and centralize data repositories. That way, every team has access to the same data and insights, for prompt action even in the field.
Utilities can also increase the quality of their data analysis.
Effective data analysis doesn’t happen overnight, so utilities teams must be prepared to put in the work to improve the quality of the outputs. This means looking at each asset in a new way, determining aspects to capture and how to report the data. Implementation requires significant investment in infrastructure, particularly in sensors to collect data and controls for the physical attributes of the system. The result is that useful information rises above the noise, providing better insights.
Structured decision-making can be integrated into workflows, and older approaches can be reconsidered. Utilities relying on processes meant for older systems should recognize that the shift to predictive action changes how teams respond to information. As such, the workflows must change. Each team must have someone responsible for attending to alerts and directing others to take action based on priority. With greater structure in workflows and response hierarchies, each member of the team has points of contact and knows what they are supposed to do.
There are advantages to data-driven decision making, including reduced downtime and helping utilities prioritize actionable insights
Downtime of equipment and systems represents a major liability for utilities, making its reduction a significant advantage. A strong data management and integration system yields insights that help utilities teams get ahead of maintenance responsibilities and failing systems. With predictive maintenance services, utilities can stop the reactive processes that push teams to keep responding to crises. Instead, they can put their efforts toward upkeep that increases efficiency and keeps systems online, improving performance and customer satisfaction.
Improved analytics transform massive amounts of data into useful insights. Signal increases as routine alerts are processed by an automated system, and teams spend less time sorting through alerts and determining how to spend their work hours. This arrangement leads to improved response time, less frustration among utilities teams and higher adherence to organizational protocols.
For utilities, operations can be a great source of efficiency improvements with an effective system for data collection and integration. Operational bottlenecks drop when teams have access to data at their fingertips, instead of waiting for a single person to process information and send a request. Separate divisions see who is working on which task, so they can move on to other responsibilities. The entire organization runs more smoothly, promoting a view of optimal performance from inside and outside the utility.
Data isn’t useful if it doesn’t go anywhere. Utilities teams often face challenges when trying to collect and process data, particularly if they lack data centralization or appropriate workflows to handle issues as they arise. Although these obstacles take effort to clear, the work yields important rewards. Strong data integration can contribute to a reduction in downtime, improved processes for individual teams and increases in operational efficiency.
