Written by Anne McEntee, Ph.D. CEO, Digital Services
GE Renewable Energy
The wind energy operations and maintenance (O&M) market is expected to grow to more than $27 billion by 2026 from about $13 billion in 2017. The sheer scale of the opportunity, coupled with increasingly competitive energy markets, has drawn the attention of asset owners seeking cost optimization.
It is also attracting component suppliers pursuing larger market shares and software providers attempting to optimize the industry through digital transformations.
Every year, wind-farm operators lose countless kilowatt-hours to unplanned downtime, operational inefficiency, and inaccurate forecasting. A lack of data-driven forecasting means wind farms are unable to adequately adapt to changing weather patterns and electric grid demands, or recognize faulty turbine components before they fail. Data and analytics are enabling digital changes that more quickly and efficiently address O&M concerns.
However, the range of optimistic promises that accompany many digital claims can obscure the most important focus: less turbine downtime and greater wind-farm ROIs. To be effective, data must induce actionable results and drive value. In other words, outcomes matter more than insights.
A successful digital platform for wind farms is one that predicts components failures, avoids unnecessary downtime, and ideally saves long-term O&M costs. To remain viable in the market, the question is no longer whether to digitalize operations but how. This means results may vary on if wind asset owners self-perform or outsource digital O&M functions.
Typically, wind asset owners wrestle with three questions when investing in digital platforms:
- How to best evaluate the many digital choices available.
- What digital features are accessible and, therefore, outcomes attainable?
- Where can I find examples of successful digital results?
An ideal digital solution provider partners with a wind-farm owner or operator to identify the key performance indicators essential for an effective O&M strategy.
Self-performing asset owners typically expect digital providers to offer a proven track record of delivering outcomes at scale and across similar use cases. Additionally, a digital provider should:
- Understand the outcomes asset owners aim to achieve
- Demonstrate staying power in the industry
- Present a commercial model aligned with the asset owners desired outcomes
For those who outsource O&M, a hybrid digital and O&M service capability ensures operations and data transparency and improved risk management in a single service agreement. A hybrid service is unlike digital-only services where turbine and fleet data are attained but then transferred to a separate O&M team to decipher and translate into action. Instead, a hybrid contract enables guaranteed service outcomes through one source of reliable data and maintenance approach.
In addition, it is important to understand how a digital provider will use and protect your fleet data. Ensuring open access to data and information about turbines is increasingly a business differentiator for wind fleet owners and operators.
Ultimately, accurate data and actionable, transparent insights are critical, enabling stronger accountability, reduced O&M costs, and greater energy production.
A day in the life
To fully appreciate the value of a digital platform to deliver expected outcomes, consider a typical day in digital wind-farm operation.
- Advanced analytics of wind assets (which are accessible by cloud) simulate future wind conditions and identify early wear in the gearbox, for example.
- Next, advanced algorithms automatically create a ticket in the case management system, comparing similar gearbox anomalies and recommend a corrective action.
- This triggers a digitized workflow queueing up in the site operations manager’s daily maintenance schedule.
- The field service management system prioritizes maintenance activities for the day based on weather conditions, revenue loss probability for respective turbine downtime, crew availability and skillsets, and tools and spare-parts inventory.
Using an intuitive interface, the operations manager approves the recommended corrective action and the system assigns an up-tower maintenance task to the service technician.
- The technician receives not just the assigned workflow on his or her mobile device, but also a history of similar correctives on other turbines of the equivalent model, along with a smartly curated list of other maintenance activities that can be completed in the same tower climb.
The outcome: A combination of physics and machine-learning models provide early detection and recommend an inexpensive, crane-less, up-tower repair, preventing revenue loss associated with extended downtime, and enables higher productivity through combined maintenance activities. Machine learning is a type of artificial intelligence and method of data analysis that automates model building or computer “learning.”
The difference: An outcome-focused service culture, whether that of the asset owner or the O&M service provider, leverages digital tools to improve operational metrics and change technician behaviors, further driving operational excellence.
A digital solution provider’s organizational capabilities and digital differentiators play a key role in delivering outcomes that matter to asset owners.