Spinning Your Drones with Cadence Workflows, Apache Kafka and TensorFlow
Echidna (Gegair) | Wed 17 Apr 10:45 a.m.–11:30 a.m.
Presented by
-
Paul Brebner
https://www.linkedin.com/in/paul-brebner-0a547b4/
Paul is an Open Source Technology Evangelist at Instaclustr (now part of Spot by NetApp). For the past seven years, he has been learning new scalable Big Data technologies, building realistic demonstration applications, and blogging and talking about a growing list of open-source technologies including Apache Cassandra, Apache Spark, Apache Kafka, Apache ZooKeeper, Redis, OpenSearch, PostgreSQL, Cadence, and many more.
Since learning to program on a VAX 11/780, Paul has extensive R&D, teaching, and consulting experience in distributed systems, technology innovation, software architecture and engineering, performance engineering, grid and cloud computing, and data analytics and machine learning.
Paul has also worked at Waikato University (New Zealand), University of New South Wales (UNSW, Sydney), Commonwealth Scientific and Industrial Research Organisation (CSIRO, Australia), University College London (UCL, UK), National ICT Australia (NICTA), Australian National University (ANU), and several tech start-ups (including as a Founder/CTO). Paul has an MSc (1st Class Hons, Waikato) in Machine Learning and a BSc (Computer Science and Philosophy, Waikato).
Paul Brebner
https://www.linkedin.com/in/paul-brebner-0a547b4/
Abstract
In this talk we’ll build a Drone delivery application, and then use it to do some Machine Learning “on the fly”.
In the 1st part of the talk, we’ll build a real-time Drone Delivery demonstration application using a combination of two open-source technologies: Uber’s Cadence (for stateful, scheduled, long-running workflows), and Apache Kafka (for fast streaming data).
With up to 2,000 (simulated) drones and deliveries in progress at once this application generates a vast flow of spatio-temporal data.
In the 2nd part of the talk, we’ll use this platform to explore Machine Learning (ML) over streaming and drifting Kafka data with TensorFlow to try and predict which shops will be busy in advance.
In this talk we’ll build a Drone delivery application, and then use it to do some Machine Learning “on the fly”. In the 1st part of the talk, we’ll build a real-time Drone Delivery demonstration application using a combination of two open-source technologies: Uber’s Cadence (for stateful, scheduled, long-running workflows), and Apache Kafka (for fast streaming data). With up to 2,000 (simulated) drones and deliveries in progress at once this application generates a vast flow of spatio-temporal data. In the 2nd part of the talk, we’ll use this platform to explore Machine Learning (ML) over streaming and drifting Kafka data with TensorFlow to try and predict which shops will be busy in advance.