with kubernetes and tensorflow
play

with Kubernetes and Tensorflow Daniel van der Ende & Tim van - PowerPoint PPT Presentation

Data Council NYC 2019 Reducing Flight Delays with Kubernetes and Tensorflow Daniel van der Ende & Tim van Cann o IT Consultancy o 40 Data Scientists, Machine Learning Engineers, and Data Engineers o Based in Amsterdam o We help


  1. Data Council NYC 2019 Reducing Flight Delays with Kubernetes and Tensorflow Daniel van der Ende & Tim van Cann

  2. o IT Consultancy o 40 Data Scientists, Machine Learning Engineers, and Data Engineers o Based in Amsterdam o We help organisations be successful with data and AI Tim van Cann Daniel van der Ende Data Engineer Data Engineer timvancann@godatadriven.com danielvanderende@godatadriven.com

  3. 499,444 499,444 Mission Mission Connecting the Netherlands Air Transport Movements at Schiphol Ambition Ambition 71.1 71.1 Europe’s Preferred Airport Million Passengers at Schiphol 79.2 79.2 Million Passengers 1.6 1.6 Billion Euro Real Estate

  4. What’s a turnaround?

  5. What’s a turnaround?

  6. What’s a turnaround?

  7. More predictable Less predictable

  8. Monitoring a turnaround

  9. High level Design Magic Magic Eve Event nts

  10. High level Design FuelingStart Fuel Fuelin ingEnd gEnd Magic Magic Eve Event nts

  11. High level Design Magic Magic Eve Event nts

  12. Streaming! Even Events ts Unific Unification ation Object Object Det Detecti ection on Even Event t Gene Generation ration

  13. Streaming! Even Events ts Unific Unification ation Object Object Det Detecti ection on Even Event t Gene Generation ration

  14. Unification of camera’s

  15. Unification of camera’s T1 T1 T0 T1

  16. Unification of camera’s T1 T1 T0 T1

  17. Unification of camera’s T1 T1 T0 T1

  18. Unification of camera’s T1 T1 T0 T1

  19. Unification of camera’s T1 T1

  20. Unification of camera’s T3 T1 T1

  21. Unification of camera’s T3 T6 T1 T1

  22. Unification of camera’s T3 T6 T1 T8 T1

  23. Unification of camera’s T6 T1 T3 T8 T1

  24. Unification of camera’s T6 T1 T8 T1

  25. Unification of camera’s T1 T8 T6 T1

  26. Unification of camera’s T1 T1

  27. Streaming! Even Events ts Unific Unification ation Object Object Det Detecti ection on Even Event t Gene Generation ration

  28. Object Detection

  29. aircraft open_cargo_door catering_truck conveyor_belt_loader fuel_tank_truck high_loader lavatory_truck pallet_transporter open_pax_door fuel_pump_truck pushback_truck container

  30. "Batches are for Barbecues" Fokko Driesprong

  31. Object detection iterations

  32. Object detection iterations 1

  33. Object detection iterations 1 2 Serving Serving

  34. Object detection iterations 1 2 3 Serving Serving

  35. Object detection: GPUs or CPUs? Approximate inference time per image(s) Iteration 1 Iteration 2 Iteration 3 CPU GPU

  36. Streaming! Even Events ts Unific Unification ation Object Object Det Detecti ection on Even Event t Gene Generation ration

  37. Why we need Event Generation {“objects”: [“aircraft”], “timestamp”: “2019 -11- 13 09:45:05”} Object Object Detection Detection

  38. Why we need Event Generation {“objects”: [“aircraft”], “timestamp”: “2019 -11- 13 09:45:05”} Object Object {“objects”: [“aircraft”], “timestamp”: “2019 -11- 13 09:45:10”} Detection Detection {“objects”: [“aircraft”], “timestamp”: “2019 -11- 13 09:45:15”} {“objects”: [“aircraft”], “timestamp”: “2019 -11- 13 09:45:20”} {“objects”: [“aircraft”], “timestamp”: “2019 -11- 13 09:45:25”} {“objects”: [“aircraft”], “timestamp”: “2019 -11- 13 09:45:30”} {“objects”: [“aircraft”], “timestamp”: “2019 -11- 13 09:45:35”} {“objects”: [“aircraft”], “timestamp”: “2019 -11- 13 09:45:40”}

  39. Event Generation Aircraft present Aircraft Absent

  40. Event Generation Aircraft present Aircraft Absent

  41. Event Generation { “event”: “ AircraftArrives ”, “timestamp”: “2019 -11- 13 09:43:25”, “ramp”: “X99”, “airport: “AMS” } Aircraft present Aircraft Absent

  42. Event Generation Aircraft present Aircraft Absent

  43. Event Generation { “event”: “ AircraftDeparts ”, “timestamp”: “2019 -11- 13 11:59:10”, “ramp”: “X99”, “airport: “AMS” } Aircraft present Aircraft Absent

  44. Event Generation “ Business Rules ” if fuel_truck is present or aircraft is not present: return num_present = 0 for observation in window: if fuel_truck_detected: num_present += 1 num_present_ratio = num_present / window_size if num_present_ratio > presence_threshold_ratio: trigger_event(fuel_truck_arrives)

  45. Other Dragons to Slay Photo by Mateus Campos Felipe on Unsplash

  46. General Advice

  47. General Advice

  48. General Advice Photo by Quino Al on Unsplash

  49. General Advice Photo by Hunter Haley on Unsplash

  50. (General) Advice is welcome 15:15 – 16:00 Room 568

  51. Contact Deep Turnaround Team Aafke Jongsma Tim van Cann Product Owner Data Engineer aafke.jongsma@schiphol.nl tim.van.cann@schiphol.nl timvancann@godatadriven.com Daniel van der Ende Data Engineer daniel.van.der.ende@schiphol.nl danielvanderende@godatadriven.com

Recommend


More recommend