It may not be apparent to most energy consumers, but big changes are happening in the utility industry – innovation fueled by the Internet of Things (IoT) and smart grid analytics. Consider these examples:
- Smart network devices trigger actions that minimize or avoid power outages.
- Smart home appliances and HVAC systems keep you comfortable at lower cost, with no human intervention.
- Smart power generation systems optimize cost and efficiency across a diverse portfolio of renewables, microgrids, batteries and traditional sources.
It’s a new day in an industry that hasn’t seen much major evolution until now. The fundamental architecture of the utility grid hasn’t changed much over the course of 100 years. Historically, utility companies generated power in one central location and then used their own dedicated grid to deliver electricity to customers. That model is changing.
Tomorrow’s smart grid will be a constellation of many generation sources working together, delivering energy in multiple directions – including from the customer back to the utility (“prosumers”). It will be reshaped by technologies, such as low-cost battery storage, rooftop photovoltaics and microgrids that can operate in grid-connected or island mode, and IoT connectivity of smart devices.
These new technologies not only deliver more capabilities for energy providers to tap into new power gen sources, they also provide more data. Smart grid analytics is the application of advanced analytics methodologies to the data – including predictive and prescriptive analytics, forecasting and optimization. The opportunities for smart grid analytics are expanding because there’s exponentially more data available to develop analytical models.
Read how utilities are using IoT and machine learning today
Check out the results of a Zpryrme and SAS survey – learn how 200 North American utilities are using the latest technologies, and what they’re planning for the future.
Exploring the possibilities
Analysts can mine data such as real-time asset metrics and weather factors, then apply smart grid analytics to optimize performance of connected devices in the field. Smart grid analytics is key to controlling operating costs, improving grid reliability and delivering personalized energy services to consumers.
Utilities are not new to data analysis in general, but smart grid analytics enables a more direct link between IT and OT – the ability to embed analytical insights into operational systems, often for automated responses. Here are some areas where utilities are already seeing success:
Utility companies have been modernizing power plants and substations by putting sensors on the main components, such as turbines and transformers, looking for vibration or other anomalies that could predict future failures. Duke Energy and other utilities claim that these asset analytics have already paid off in big ways by preventing major outages related to equipment.
Analytics makes it possible to track the paths of storms to a greater extent than ever. By incorporating third-party data, utilities can predict the potential impact of storms to customers and infrastructure, which supports more proactive planning.
Technicians can’t be everywhere in a service territory, so analytics needs to be their eyes in the field. For example, in the past a technician might read gauges at remote equipment once a month. But a serious condition, such as a methane buildup in a transformer, needs to be addressed now. Today, sensors pull in real-time data for immediate identification of impending trouble.
To take advantage of such technology, Duke Energy is using synchrophasors in the transmissions system to look for any disturbance that might indicate a voltage collapse or asset failure. Some utilities are beginning to look at the application of synchrophasor technology in the distribution system as well, catching early indicators of trees touching the lines, lightning or underperforming transformers.
Utilities around the world lose an estimated $89.3 billion a year in revenue from customers who do not pay their bills or who tamper with meters to avoid charges. Smart grid analytics can detect this theft and fraud.
About half of your utility bill each month is for fuel consumption; it’s a pass-through cost. When utilities manage fuel better, it has a big influence on your bill. Analytics helps by supporting smarter decisions about unit commitment, outage planning, fuel procurement, rate and regulatory factors.
Customer research and analytics
Utilities today are acting more like a services business as they seek to fill the gap left by declining sales of kilowatt hours. Analytics is driving the work of designing new products and services that will improve value to customers.
A common theme among many use cases is the ability to analyze data at the edge. Computing capacity once available on servers has moved to routers and gateways – and what used to be available on routers and gateways now happens on local devices and even the sensors themselves. Analytics is moving to the edge as well. There’s no need to backhaul the data for analysis; analytics can go to the data while it’s still in motion.
Getting full utility out of smart grid data
As these examples demonstrate, smart grid analytics plays a role in several different parts of the utility business, and a single analytical technique can answer very different questions. For example, you can use predictive modeling to anticipate asset failure and predict which customers will adopt a new service offering. You can use forecasting to plan for the aftermath of a storm or plan for staffing needs and fuel costs.
A utility company that capitalizes on smart grid analytics will soon find itself managing a wide portfolio of analytical models. These models should be treated as company assets, which calls for cross-functional governance to ensure consistency, repeatability, sharing and reuse. Managing models is just one piece of maximizing the return on smart grid analytics. Utilities also need a systematic way to track progress on analytics projects, measure their impact, manage models across their life cycles, and provide access to the right data and technology.
Many utilities – especially those with more than a million meters – have adopted a center of excellence approach to provide this enterprise-level oversight. An analytics center of excellence (ACE) typically coordinates:
- Data governance.
- Skills development and resources.
- Alignment with mobile strategy.
- Use of standard analytics solutions.
After several years of trial and error, most utilities have established both centralized and decentralized analytics resources that are tied to an ACE in a hub-and-spoke model. Tools and processes are centralized, while model development remains close to domain experts in the lines of business.
Analytics Powers the IoT
Watch this short video to learn how analytics helps utility companies make sense of all the data being generated by the smart grid.
Smart grid analytics is proving its value
From optimizing marketing campaigns to forecasting weather and storm response, analytics is becoming a core part of today’s utility business. And it’s changing how utilities will do business in the future.
“The analytics movement is really taking hold for us,” said Jason Handley, PE, Director of Smart Grid Emerging Technology and Operations for Duke Energy. “About five years ago we had only six data scientists at Duke Energy. Today we have 41. We’re continuing to see an upswing, because we’re seeing more and more value out of these roles.”
In most geographies, load growth is flat while competitive pressure from new market entrants and alternative energy sources is up. Insights generated from smart grid analytics will be critical for delivering safe and reliable power, and providing value-added services in the most cost-effective manner. The direct financial benefits are already quantified for many areas of application. Now, the real question becomes: Can utilities afford not to invest in smart grid analytics?
About the author
Alyssa Farrell leads product marketing for the SAS Global Energy Practice. In this role, she focuses on the SAS solutions that help optimize our energy infrastructure by applying predictive analytics to complex data. She currently serves on the Advisory Committee of the Research Triangle Cleantech Council and co-leads the Program and Communications Action Committee, as well as a Working Group of the Utility Analytics Institute. Follow Alyssa on Twitter @alyssa_farrell and LinkedIn at http://Linkedin.com/in/alyssafarrel.
- Article SAS CIO: Why leaders must cultivate curiosity in 2021With the change we’re all facing this year, CIOs should be counting on curiosity to play a crucial role in how we’re going to meet the challenges that lie ahead. From the moment COVID-19 hit, our IT organization has relied on curiosity – that strong desire to explore, learn, know - to fuel the urgent changes required. And it’s curiosity that will enable us to meet the needs of the future of work post-pandemic.
- Article ModelOps: How to operationalize the model life cycleModelOps is where analytical models are cycled from the data science team to the IT production team in a regular cadence of deployment and updates. In the race to realizing value from AI models, it’s a winning ingredient that only a few companies are using.
- Article AI in government: The path to adoption and deploymentThe government sector is lagging in AI adoption, but awareness of the importance of AI in the public sector is increasing. Our survey indicates that operational issues are requiring governments to turn their attention to AI projects as a way to address important public issues.
- Article IFRS 17 : 방치는 해답이 아닙니다.IFRS 17은 보험 계약의 미래 지향적 평가를 위한 원칙을 중요하게 여기는 회계 기준입니다. 재무 투명성을 높이기 위해 설계된 IFRS 17은 보험사에게 보험 및 재보험 계약이 재무 및 위험에 미치는 영향에 대해 더 자세히 보고하도록 요구합니다.