On-Prem Solution for the Selection of Wind Energy Models
•
0 recomendaciones•564 vistas
This document summarizes Vestas Wind Systems' work on using deep learning models to improve wind resource modeling. Vestas has developed a tool called SiteHunt that provides wind resource data at different resolutions to help identify potential wind farm sites. The company is exploring using deep learning models to downscale lower resolution wind data to higher resolutions. An initial proof of concept showed a deep neural network improved downscaling accuracy compared to traditional methods. Ongoing work includes testing more advanced neural network architectures and automating the end-to-end modeling process.
Recomendados
Más contenido relacionado
Similar a On-Prem Solution for the Selection of Wind Energy Models
Similar a On-Prem Solution for the Selection of Wind Energy Models (20)
Más de Databricks
Más de Databricks (20)
Último
Último (20)
On-Prem Solution for the Selection of Wind Energy Models
- 1. WIFI SSID:Spark+AISummit | Password: UnifiedDataAnalytics
- 2. Ana M. Martinez, Vestas Wind Systems A/S On-Prem Solution for the Selection of Wind Energy Models #UnifiedDataAnalytics #SparkAISummit
- 3. 3 Is this a good piece of art? pixabay.com Classification: Public
- 4. 4 Is this a good piece of art? pixabay.com Classification: Public
- 5. 5 Is this a good site? Classification: Public
- 6. 6 Is this a good site? Classification: Public
- 7. SiteHunt® • Enables early identification of potential wind farms 7 SiteHunt® FirstView 3km resolution Classification: Public
- 8. SiteHunt® • Enables early identification of potential wind farms 8 SiteHunt® FirstView 3km resolution SiteHunt® CloseUp 1km – 300m resolution Classification: Public
- 9. SiteHunt® • Enables early identification of potential wind farms 9 SiteHunt® FirstView 3km resolution SiteHunt® CloseUp 1km – 300m resolution SiteHunt® DeepDive 10 – 25m resolution Classification: Public
- 10. Wind resources enrichment Existing modelling options: – Physical modelling leads to time-consuming simulations. – Sub-optimal geostatistical approaches. 10Classification: Public
- 11. Motivation • DL technology has been recently proved successful on similar tasks with data that has hierarchical structure. • What tools and data do we have at Vestas for this task? • What is missing? 11Classification: Public
- 12. HPC is our primary tool • 650 compute nodes (Lenovo). • ~ 16000 CPU cores. • Total memory > 100 TB. • >5 PB HDD storage (EMC Isilon). • 56Gb/s IB. • ~500 TFLOPS. • 20 GPU nodes. • Sun Grid Engine scheduler. 12 Classification: Public
- 13. Data is our spine • Vestas Climate Library (peta-byte scale). – Hourly wind resource data from 2000-01-01 to present in 3km horizontal resolution. – More than 50 parameters. – From ground level to beyond 500m. – ORC database, started in 2012. • Elevation database. • Roughness database. 13Classification: Public
- 15. US: Avg. 80m wind, terrain below 1500m, wspd > 3m/s 15Classification: Public 15
- 16. US: Exclude National Parks, protected areas, national forests and federal land 16Classification: Public 16
- 17. US: Remove urban areas and airports 17Classification: Public 17
- 18. High-voltage grid proximity (up to 30 km from the grid) 18Classification: Public 18
- 19. Siting • Improve siting by not relying on point estimates from meteorological masts. • Wind resources in higher resolution. 19Classification: Public 19
- 21. Wind resource downscale PoC Example 21Classification: Public 21
- 22. Data Extraction & Preparation 22 Wind data (HR/LR) orc format ~1.5PB Elevation Data (VHR) hgt format ~400GB Roughness (HR) GeoTIFF format Apache Spark* (pyspark) Apache Spark* Derived features vector field Curl, divergence, laplacian * All product names, logos and brands are property of their respective owners. All company, product and service names used in this document are for identification purposes only. Use of these names, logos and brands does not imply endorsement. Classification: Public Apache Hive* python
- 23. VCL 3km point – global coverage (19 years). 3km 23 Data Extraction & Preparation 23Classification: Public
- 24. VCL 3km point – global coverage (19 years). VCL 1km point – Saudi Arabia coverage (1 year). 1km 3km 24 Data Extraction & Preparation 24Classification: Public
- 25. VCL 3km point – global coverage (19 years). VCL 1km point – Saudi Arabia coverage (1 year). Terrain data - SRTM (very high resolution, up to 30m). 25 Data Extraction & Preparation 25Classification: Public
- 26. 26 Each red point generates 1 row per timesptamp on the dataset VCL 3km point – global coverage (19 years). VCL 1km point – Saudi Arabia coverage (1 year). Terrain data - SRTM (very high resolution, up to 30m). Data Extraction & Preparation 26Classification: Public
- 27. Data Extraction & Preparation 27 INPUT TARGET swdown u_HR xhour/yhour v_HR temperature u_LR v_LR heights_HR roughness_HR INPUT TARGET heights u_HR u_LR v_HR v_LR DNN BASELINE u v wind speed q Classification: Public
- 28. Feed Forward neural network 28 Input parameters Output parameters Hidden layers first_neuron (width) Shape(brick) Classification: Public
- 29. Hyperparameter selection 29 48 combinations #neurons #hidden layers #epochs dropout 12 1 200 0.2 56 1 200 0.2 128 1 200 0.2 256 1 200 0.2 12 5 200 0.2 56 5 200 0.2 … … 256 10 400 0.5 Classification: Public
- 30. Hyperparameter search Existing tools not directly applicable: – Talos. – KubeFlow. – MLflow. – Elephas. 30Classification: Public
- 31. Model Selection 31 Job Scheduler qsub array TensorBoard* Configuration + train/val data C onfiguration + train/val data Output keras_model.h5 Tensorboard logs params.json * All product names, logos and brands are property of their respective owners. All company, product and service names used in this document are for identification purposes only. Use of these names, logos and brands does not imply endorsement. docker containers docker containers docker containers docker containers docker containers docker containers talos* * Classification: Public
- 32. Model Training & Evaluation 32 Evaluation measures MAE, RMSE, BIAS, STDE Riemann sum between the CDF* differences (CDF diff.) Pearson correlation coefficient (Pearson’s r) TestValidationTrain Train baseline & wining DNN model Learn hyperpara meters Learn candidate models Time- consecutive data kept to evaluate * Cumulative distribution function Classification: Public
- 33. Do we downscale? PoC Example 33Classification: Public 33
- 42. Quantitative results Method RMSE Bias Pearson’s R CDF diff. closest 3km point 0.0305 -0.0063 0.9827 0.0077 Linear regression 0.0315 0.0080 0.9836 0.0114 DNN 0.0294 0.0022 0.9853 0.0093 42Classification: Public 42
- 50. Quantitative results Method RMSE Bias Pearson’s R CDF diff. closest 3km point 0.0752 -0.021 0.9223 0.0218 Linear regression 0.0663 0.0009 0.9236 0.0178 DNN 0.0538 0.0021 0.9459 0.0075 50Classification: Public 50
- 51. Do we downscale? PoC Example 51Classification: Public 51
- 52. Ongoing work • Use of convolutional + recurrent neural networks. • Test different evaluation scenarios. • Test higher resolution terrain information. • Connect and automate the end-to-end cycle. 52Classification: Public
- 53. Potential • ML importance across the whole value chain. – Power forecasting. – Long-term correction of wind measurements. – Wind resources enrichment. – Troubleshooting turbine errors. – Condition monitoring. – Wind farm control. – Wind Turbine Surface Damage Detection. – … 53Classification: Public
- 54. Vestas Team 54 Ana M. Martinez Hjalte Vinther Kiefer Hans Harhoff Andersen Tiago Miguel da Costa Luna Classification: Public
- 55. DON’T FORGET TO RATE AND REVIEW THE SESSIONS SEARCH SPARK + AI SUMMIT