The use of digital technologies such as cloud computing, distributed energy resource management, big data and predictive analytics, are changing the future and the present of the Energy Market. But, is the required wind turbine data quality good enough?
Let’s start with an overview of the Wind Energy Market grading. This analysis has been done taking a representative sample of data coming from European Wind Farms.
The following figure represents the Wind Industry Grading Mix from a typical European utility, which represents the sample for the analysis of this article.
This grading takes into consideration the wind industry technology evolution, both, on turbines operations and the data variety that is needed for Big Data and Predictive Analytics services.
The 90 % of the wind turbines technology mix comes from assets with less than two MW capacity per turbine, where the developments at data variety measurements have evolved from 20-80 variables at the 1st generation turbines, up to 45-130 variables at the 2nd generation. The other 10 % turbines mix from the 3rd generation turbines, represents the latest industry developments in wind turbines technology and data variety, where it keeps a similar amount of measurement variables than the 2nd generation because some systems have decreased their sensor base or increased the amount of measurements, like the rotor (pitch), the gearbox and the converter.
Nevertheless, independently from the different generation of turbines, there are two Data Quality issues that appear across the 3 different groups (SCADA data which exclude cumulative and counter measurements), which are:
- Sensors Failures: Frozen sensor (example: bearing temperatures at “0” or at “999” value) and out of range (example: generator speeds at 5000 RPM).
- Data Reception: Communication lost or “Data Gaps”
Taking all this information into account, NEM has created the Wind Turbine data quality quadrant, where it can be easily classified the different OEM’s ranking positions in regards of the data quality required for a successful predictive analytic:
In addition, it is quite remarkable the connection between the data issue and the OEM:
This study is based on the knowledge generated by NEM Solutions after spending 10 years analysing and monitoring Wind Turbines all over the world. More than 80.000.000 operating hours monitored in A.U.R.A. back us up. Moreover, in the case of NEM’s expertise, our Wind Energy Data Scientist Team is aware of the different operational challenges the customers are facing while managing Wind Energy Assets.
The turbines data quality issues are a challenge for implementing big data and predictive analytics services, and so this is why it is important to rely on a partner that have experience on the typical issues related to the different wind technologies and the methodologies to provide a service even on challenging conditions.
Want more information? Please contact us.