For the past 25 years, Bonnie Brandreth has helped government and commercial organizations collect, analyze, and use data to build organizational strategies, drive decision-making, and optimize performance in the energy sector.
As part of her role, Bonnie leads teams delivering data collection, management, and analytics projects to energy stakeholders. She leads a team of data scientists specializing in energy sector services with unique research design expertise, including an in-house survey call center. Ms. Brandreth studied research methods and data analytics and holds a Master of Science in Sociology from the University of Wisconsin-Madison.
How has data analytics changed over the last few years?
Companies are moving from simple metrics that describe what has happened to using advanced analytics to diagnose current and past performance and predict future performance. Metrics can tell us what happened in the past, but analytics help to reveal why key performance metrics were or were not achieved. This is demonstrated by the difference between quantifying savings through energy efficiency measures and reducing future energy consumption by identifying equipment or processes with the most energy-saving potential.
There are other changes that support the greater use of analytics within the past few years. Improvements in sensor and connectivity technology enable the collection of more useful operational data to help firms make decisions. Cloud-based analytics allows us to leverage connected servers for massive amounts of computing power. Using open-source scripting languages and statistical tools enable us to leverage libraries to borrow and share application programming and solutions. Machine learning technologies have automated more operational processes and made us better at predicting outcomes.
Tetra Tech helps companies implement data analytics solutions to help them understand energy use and predict performance.
Does having more data translate to better decision-making?
It is not enough to have a lot of data. The more relevant the data, the better the analytics, the greater the insights, and the more effective the decision-making. Rather than collecting the most data, Tetra Tech helps organizations find the right data. For example, we help solar developers evaluate overall site performance by collecting meteorological data on-site and then adjusting analytical models of measured power output for weather conditions before comparing actual and expected performance. As a result, the analysis is more accurate and relevant to real-world conditions. Technicians can more accurately identify poorly performing solar sites, make proactive adjustments, and help investors make better decisions regarding site selection.
Data accuracy and integration are important as well. Data integration is one of the biggest challenges companies face when developing a cohesive and scalable sustainability plan. The perception of environmental, social, and governance (ESG) has shifted from a preferred to required feature that influences investors in the energy sector. Companies are looking for ESG datasets that will help them accurately identify ways to reduce risk, make operational improvements, and demonstrate marketing differentiation. Developing fit-for-purpose analytics may require integrating data across multiple facilities, departments, and operating systems that are currently in separate silos.
How else is data analytics changing the energy industry?
The use of data analytics is rapidly growing across the oil and gas (O&G) industry. Innovative analytics from data recording sensors are becoming more common as are recording sensors that can be used in wells to capture data on key operational variables like fluid temperature, pressure, and composition during production. For example, Tetra Tech is working with an integrated energy company to use wireless equipment sensors to generate data to manage assets across their business. Sensor data are generated on-site and analyzed in real-time using embedded microprocessors and code, which help O&G companies operate more sustainably and at improved efficiencies.
We are also seeing more on-site data collection and analytics on the renewable energy side. Tetra Tech recently installed a condition monitoring system at a utility-scale wind farm that uses data recording sensors and microprocessors embedded in equipment, including accelerometers, to detect vibration anomalies. They provide critical statistics for root-cause analysis of drive train component failures in a wind turbine. These alerts help to reduce downtime and prevent catastrophic failure, which can lead to costly replacement of the drive train.
How can data analytics help clients meet goals around decarbonization and energy optimization?
Companies can better understand their environmental impact and decarbonization progress when they have advanced reporting and analytic tools based on verifiable data. For example, we use machine learning techniques to detect patterns of energy consumption to help companies identify where changes can mitigate emissions and improve energy efficiency.
Data analytics help companies plan for future energy needs. Analytic models enable companies to evaluate and react to uncertainties around climate change, competition for renewables and offsets, and the impact of decentralized energy in the market. As more wind turbines, solar arrays, and other renewable energy installations are integrated, they generate a larger proportion of energy on the grid. However, the availability of renewable resources and their effectiveness depends on factors such as location, weather, and time of day. Batteries or other energy storage systems store power and keep the grid running when renewable systems are not generating electricity. The assumed rate at which renewables and batteries will improve in performance should be part of integrated resource forecasting and distributed energy models. These changes and unknowns create more uncertainty in planning future power needs and systems that must ensure power reliability, system security, lower emissions, and meet aggressive sustainability goals. Data analytics helps us plan for the unknowns.