Value of Real-Time Data Is Blowing in the Wind

PinIt
Silhouette of wind turbine generating electricity on sunset

Envision, a power producer, uses Parstream software to crunch real-time data from wind and solar panels. The predictive analytics solution enhances energy output and assists with predictive maintenance of equipment.

Name of Organization: Envision

Industry: Energy

Location: New York, NY USA

Business Opportunity or Challenge Encountered:

Envision Energy, one of the world’s ten largest wind turbine companies, has a growing Big Data challenge. Along with focusing on producing wind turbines, the company also has a software business which manages up to 13 gigawatts of renewable energy assets—both wind and solar—globally.

The energy business can no longer be differentiated just by mechanical engineering, but by an ability to monitor and maintain high performance of energy assets. Each of Envision’s 20,000 wind turbines are built with over 150 advanced sensors that continually assess acceleration, temperature and vibration of the turbines. Extracting data from their wind turbine sensors lets them see trends and create predictions for performance optimization and maintenance to minimize downtime.

Envision’s Smart Wind Farm System is an integrated asset management solution, providing predictive and preventive services and maintenance support to optimize performance. Strategically developed from the ground up by wind experts to incorporate industry best practices and cater to the unique needs of wind farm operators.

“Envision is a renewable energy company in the wind-power business, but we also have a software business,” says Dr. Guido Jouret, President of Envision Digital Innovation Center, in a video. “So we’re becoming a smart-energy company. “Our main business challenges are that we operate devices like wind turbines and solar panels, which are very complex, and we have to operate those devices for decades—which means maximizing availability, but also maximizing power.”

With more than 3 million sensors, the company is managing massive amounts of real-time data— more than 20 terabytes of data at a time—to help continuously monitor this vast wind turbine network. In addition, the data volume is growing at over 50 percent annually as Envision continues to collect more data, more frequently from each of their wind turbines. To complicate things even further, the wind farms which house their turbines are geographically dispersed.

How This Business Opportunity or Challenge Was Met:

The key to managing all this real-time data and making it available to the business boiled down to analyzing turbine sensor data with greater granularity, Envision’s technology planners concluded. To better address this challenge, they have moved from analyzing turbine data every 10 minutes to every minute, and then on to every few seconds. By immediately analyzing real-time sensor data from their wind turbines, Envision is able to quickly identify actionable insights with significant business benefits.

“We’re taking the raw data and turn it into trends,” says Jouret. “Then we can take the trends and turn them into predictions about what will happen based on what we’ve seen in the past, to minimize downtime and take advantage of performance increases.”

Envision needed an analytics solution which enabled them to handle these multiple terabytes of data with sub-second response time, along with the capability to run distributed queries/edge analytics closer to the source of data. The company also needed to be able to continuously import and store large amounts of real-time sensor data with the ability run fast and flexible queries locally, in their central data center, or in the cloud. “We wanted to run the data queries in our data center or in the cloud,” Jouret says, adding that Envision’s goal was to employ analytics to help “reduce our customers’ total energy output by 50%.”

The energy company employed ParStream’s Analytics Platform, which handles massive volumes and high velocity of IoT data, to manage data streaming from its highly distributed network. “Our wind farms and solar farms are all spread out,” says Jouret. “We needed to ingest the data at the source and also run queries against huge data sets.”

Envision continuously improves the mechanical aspects of its turbines, “but first examines historical operational data for potential design improvements,” according to Syed Hoda, chief marketing officer for Parstream. “Envision’s strategies around ‘how many sensors?’, ‘where to place sensors?’, ‘what data to collect and how often?’ are perfect examples of collaboration between the physical and digital worlds.”

Measurable/Quantifiable and “Soft” Benefits from This Initiative:

As a result of employing the distributed analytics platform, Envision was able to address both performance optimization and predictive maintenance within its wind and solar network, which combined, help to deliver an overall 15 percent improvement in productivity.

For performance optimization, Envision uses sensor data to make smart decisions about altering the angle and speed of the turbine blades in order to optimize performance at any given time, based on changing environmental conditions. “Through the use of real-time sensor data, we can boost a customer’s total energy output by up to 15% from their wind farms,” says Jouret. In addition, for predictive maintenance, Envision’s sensor technology helps the company perform checks for any irregularities in operational performance for its 20,000 wind turbines, enabling technicians to predict potential failures before they happen. Real-time data is matched against historical data to determine which parts need adjustments or replacements, significantly reducing downtime.

(Sources: Envision, ParStream)


Want more? Check out our most-read content:

Anticipatory Sensors: Your Office’s Sixth Sense
The Big Data Continuum: From Data Scientists to Empowered Business People

Frontiers in Artificial Intelligence for the IoT: White Paper
Building Energy Management: An Optimization Challenge

Liked this article? Share it with your colleagues using the links below!

Leave a Reply