SlideShare a Scribd company logo
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Easy Rider: How ML, Serverless, and IoT Drive Mobility as a Service
A M T 3 0 2
Indra(Neel) Mitra
Solutions Architect
AWS
Christopher Cerruto
Vice President
Avis Budget Group
Saken Kulkarni
ML / AI Practice Lead
Slalom
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Intro
Indra(Neel) Mitra
Solutions Architect
Amazon Web Services
Outside of work
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Agenda
1. Amazon in Automobiles
2. AWS Connected Vehicle Solution Overview
a. Greenfield Environments
b. Brownfield Environments
3. Avis Budget Group
a. Our Vision
b. Current State & Challenges
c. Future State on AWS
4. Slalom Consulting
a. Use case Deep Dive
b. Architecture
c. Demo
5. Q&A
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon’s approach to connected vehicles
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
AWS Connected Vehicle Solution Technology Stack
Platform APIs
Application services
Data services
Ingestion (AWS IoT)
Amazon API Gateway
AWS Lambda Amazon SNS Amazon SQS Amazon Cognito
Amazon S3 Amazon DynamoDB Amazon Kinesis Amazon ML
Device Gateway Registry Rules Engine Message Broker
Protocols
Connectivity
Vehicle
HTTP MQTT MQTT + WebSockets
Mobile Carrier
Telemetry Hardware AWS Greengrass x.509 certificates Automotive Grade Linux
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
AWS Connected Vehicle Solution Benefits
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
How do you get started?
Start prototyping with a ‘well architected’ architecture in
minutes using the AWS Connected Vehicle Quick Start
Deploy into your own AWS account
Customize use cases or develop your own
Remove or add other AWS and partner services
Easily connect your own data or your own devices
https://aws.amazon.com/answers/iot/connected-vehicle-solution/
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
AWS Connected Vehicle Solution Reference Architecture
Authentication
Connected Vehicle Data Ingestion
Device Gateway Rules Engine
AWS IoT
Connected Vehicles
Certificate
JSON
Just-in-Time Registration
Rule 1
Message Topic Action
OBD Telematics connectedcar/telemetry/<VIN> Publish
Vehicle Trip Info connectedcar/trip/<VIN> Publish
Diagnostic Trouble Code connectedcar/dtc/<VIN> Publish
Anomaly Alert connectedcar/alert/<VIN>/anomaly Subscribe
DTC Alert connectedcar/alert/<VIN>/dtc Subscribe
Driver Score Alert connectedcar/alert/<VIN>/driverscore Subscribe
Vehicle Provisioning connectedcar/vehicle/<VIN>/provision Publish
Sample Message Payload
{
"name": "speed", ”
value": 47.4,
"vin": "1NXBR32E84Z995078",
"trip_id": "799fc110-fee2-43b2-a6ed-a504fa77931a",
"timestamp": "2018-02-15 18:50:18.000000000"
}
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
AWS Connected Vehicle Solution Reference Architecture
Rule 2
Raw Data
Telemetry
Data
JSON
Manufacturers Dealers Consumers
Personas
Data Visualization
Telemetry Data
MQTT (near-real-time)
Reference Data Stores
DTC Reference Table Owner Data Table Vehicle Health
Report Table
Authentication
Connected Vehicle Data Ingestion
Device Gateway Rules Engine
AWS IoT
Connected Vehicles
Anomalous Data
Anomaly Detection & Alerting
Anomaly Table
User Pool
Logs
Web UI Mobile App
Microservices
DTC Detection & Alerting
Rule 5
DTC Data
JSON
DTC Table
Location-based Services
Geolocation Data
JSON
Rule 6
Marketing Table
Driver Safety Score Processing
Rule 4
Aggregated Telemetry Data
[ Ignition Status ]
JSON
Trip Aggregation Processing
Rule 3
Aggregated Telemetry Data
JSON
Trip Aggregation Table
Certificate
JSON
Just-in-Time Registration
Rule 1
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Data Ingestion
REST ENDPOINTS
WEBSOCKETS
LMPP
OTHER PROTOCOLSAmazon EC2 Amazon Elastic
Container Service
Elastic Load
Balancing
Authentication Device Gateway Rules Engine
AWS IoT
Connected Vehicle Data Ingestion
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Data Storage & Analysis
Raw Data
Reference Data Stores
DTC Reference Table Owner Data Table Vehicle Health
Report Table
Anomalous Data
Anomaly Detection & Alerting
Anomaly Table
DTC Detection & Alerting
DTC Table
Location-based Services
Marketing Table
Driver Safety Score Processing
Trip Aggregation Processing
Trip Aggregation Table
NOSQL
TSDB
Mainframe
APIs
Applications
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Data Consumption
Manufacturers Dealers Consumers
Personas
Data Visualization
User Pool
Logs
Web UI Mobile App
Microservices
Raw Data
Data analysts
Data scientists
Business users
Schemaless
Amazon ES
Direct Query
Amazon Athena
Semi/Unstructured
Amazon EMR
Enterprise Apps
Oracle, Teradata, SQL Server,
MySQL, et
Data Warehouse
Amazon Redshift
Automation / events
Engagement platforms
Data ServingData Lake
Machine Learning
Amazon SageMaker
ETL
AWS Glue
Business Intelligence
Amazon QuickSight
Data Warehouse
Amazon Redshift Spectrum
Enterprise Apps
Amazon Aurora
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Summary
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Learn more
Thurs, November 29
AMT303 – Deep Dive into the AWS Connected Vehicle Reference Solution
12:15PM – 2:30PM | Mirage, Grand Ballroom G
AMT304 – Building Volkswagen Group’s Digital Ecosystem
1:00PM – 2:00PM | MGM, Level 1, Grand Ballroom 111
Check the re:Invent website for videos of these 2018 Automotive sessions
AMT301 – Alexa, Where’s My Car? A Test Drive of the AWS Connected Vehicle Solution
AMT305 – Building BMW Group’s Digital Customer Engagement Platform
AMT201 – Automotive Leadership Session, Paving the Way for the Future of the Automotive Industry
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Intro
Christopher Cerruto
Vice President, Global Architecture and Analytics
Avis Budget Group
Things I love…
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
180
COUNTRIES
WORLDWIDE
650k
GLOBAL
FLEET
$9B
ANNUAL
REVENUE
30k
EMPLOYEES
WORLDWIDE
72
YEARS IN
BUSINESS
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
22 | AVIS BUDGET GROUP NEW MOBILITY 101
OUR VISION
“We envision a world
where mobility is
completely connected,
integrated and on-
demand.”
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Reinventing
Rental
Digitizing
the Business
Developing
New Models
OUR APPROACH
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
BUSINESS INTELLIGENCE ARCHITECTURE
OUR NEXT-GENERATION MOBILITY PLATFORM
Functional View
DATAINGESTIONARCHITECTURE
DATA LAKE
API, SERVICES &
ORCHESTRATION
DEVELOPMENT
PLATFORM
TELEMATICS
DATA/EVENT
STREAMS
3rd PARTY
DATA/EVENT
STREAMS
INTERNAL
DATA
SOURCES
EXTERNAL
DATA
SOURCES
OPERATIONAL
DATA STORES
WEB
APPLICATIONS
MOBILE
APPLICATIONS
OUTBOUND EVENT
STREAMS
DATA PUBLISHING
ARCHITECTURE
DATA QUERYING
ON-DEMAND DATA
EXTRACTION
DATA CACHES
ENTERPRISE DATA HUB
DEVELOPER API
PORTAL
3rd PARTY DATA
CONSUMERS
3rd PARTY API
CONSUMERS
DATA VISUALIZATION
BUSINESS RULES AND
COMPLEX EVENT
PROCESSING ENGINE
DATA WAREHOUSE
ANALYSIS AND
MODELING
SYSTEMS
REPORTING INSIGHTS
EXPLORATORY
ANALYSIS
MODELS
MACHINE
LEARNING
MODELS
API CATALOG
CONSENT/PRIVACY
DATA ARCHITECTURE BUSINESS SERVICES ARCHITECTURE
ANALYTICS & DATA SCIENCE ARCHITECTURE
CLOUD INFRASTRUCTURE, CODE AND RESOURCE ORCHESTRATION ARCHITECTURE
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
ABG CURRENT STATE OF THE WORLD
Pain Points
o Anchored to Legacy
Systems
o Rigid Infrastructure
o 3rd Party Supported
Data Center and
Ops
o “Big Data” Problem
• Size: Breadth
and Depth
• Normalization
• Pace of Change
o Limited/No Event
Handling and Event
Publishing
o No Real-Time
Operational Analytics
o Performance and
Scaling
o Time to Market
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
INITIAL
CONNECTED CAR
ARCHITECTURE INGESTION
SERVICES
RABBIT MQ
CSS
WebLogic
(Java)
JMS
Amazon EMR
CONNECTED CAR MANAGEMENT PLATFORM BATCH ANALYTICS PLATFORM
FRONT OFFICE
PROGRAMS
SERVICES
PORTAL
TELEMATICS
DATA
(limited, based
on geofence
event)
LIMITED DATA
(daily)
LIMITED DATA
(daily)
Oracle IMS DB2
BACK OFFICE
PROGRAMS
IBM MQ
Amazon
S3CASSANDRA
VEHICLE
SERVICES
OTHER
SERVICES
OMEGA PLATFORM (SOA) SYSTEM Z
TCU (UTP)
TCU (Z01)
Z01
Platform
UTP
Platform
…
COAP/UDP
LMPP
REST
WebSocket
REST
LMPP
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Edge Cloud Enterprise Applications
Telemetry
Endpoints/
Data Sources
Gateway
TCU (UTP)
TCU (Z01)
Z01
Platform
UTP
Platform
…
REST
WebSocket
COAP/UDP
LMPP
EC2
Containers
S3 Aurora PostgresCassandra
Rabbit
MQ
Ingest &
Real Time
Process
1 Data Analysis, Modeling &
Machine Learning
Raw
Data
Normalized
Data
Real Time
Services
Amazon
SageMaker
Lambda Amazon
EMR
Real Time & Batch Analysis
and Machine Learning
Lambda Kinesis Data
Analytics
Near Real Time /
Micro Batch Analysis
Kinesis Data
Streams
Lambda
(Data xForm)
Business
Intelligence &
Visualization
Amazon
Redshift
Athena
Tableau
Fleet
Management
Corporate Application
Legacy Data/
Services
5
Wizard
Mainframe
ODB Fleet Location
Edge Users
Enterprise
Users
REST
APIs
(HTTP/
SOAP)
OUR NEXT-GENERATION MOBILITY PLATFORM
Technical View
REST
LMPP
2 3 4
EC2
Containers
OMEGA
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
ABG DEVELOPER PROGRAM
The Avis developer platform
provides the products you need to
start building applications that
revolve around cars—from on-
demand luxury ride requests to
traditional rental car reservations
with access to our Avis, Budget and
Zipcar product catalog.
Use our simplified ReST APIs to
create memorable trip experiences
for your users across the globe.
http://developer.avis.com
JOIN US!
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Intro
Saken Kulkarni
Practice Area Lead, Advanced Analytics
Slalom
Things I love…
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
The Avis Budget Group, Slalom, and AWS teams had
several use cases to build on the Connected Car
platform
Use Case Description
1 Continually rent out Program (Re-purchase/ Lease) Cars
2 Load balance mileage across Risk Cars
3 Incorporate customer usage into car assignment logic
4 Incorporate mileage optimization into one way car assignments
Phase 1 focuses on
Use Case #1 and
Use Case #2
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
The challenge is clear – vehicles are not being utilized as
effectively as possible
Vehicles that are
underutilized
based on vehicle
age
• Each point is a vehicle
• Vehicles further from the slope and with a lower than optimized mileage require prioritization
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Initial deployment will take place at the Avis Budget Group parking lot at
Newark International Airport
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
The model assigns vehicles based on mileage accrued in order to load
balance vehicles
Vehicles are placed in priority lanes to be washed, cleaned, and prepared
for rental based on the model results
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Our model development followed an agile, sprint
based process
Identify data fields
required to build model
Reservation
Brand
Reservation Status
Booking Date
Check In/Out Date
Check In/Out Time
Car Class
Check In Location
Rental
Brand
MVA #
VIN #
Expected CI/CO Time
Length of Rental
Fuel Reading
Transform data
into a usable and
normalized state
analysis
Performing modeling in
Amazon SageMaker
• Integer Programming for
Optimization
• Regression (Load
Balancing)
Integrate model results
into new Rental
Application & Device
Obtain feedback and
implement changes in
subsequent model
iterations
Fleet
Vehicle Make & Model
Vehicle Purchase Date
Vehicle Delivery Date
Vehicle Manufacturer
Market Segment Indicator
Vehicle Age
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Mileage Optimization Machine Learning Architecture
On Premise Cloud
REST TLS 1.2/ HTTPS
Integer Programming &
Regression
TLS 1.2/ HTTPS
Key Points
• Leverages Amazon’s
Connected Vehicle
Framework as a
foundation and expands
upon it for key use cases
• Takes the modern
architecture stack into
consideration by
including both on
premise and AWS
architecture
• Designed for real time
analytics and for
operational efficiency
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Mileage Optimization Machine Learning
Architecture: On Premise
Component Usage
Operational
Client Server
& Databases
• Feed mileage optimization engine and AWS
components with transactional and operational
data, including reservation, rental, and fleet data
• Fleet, Reservation & Rental data will be fetched from
Oracle Operational Database.
• Java application would read data from MQ queue
and write above data set to ActiveMQ setup in ABG
Datacenter. Java application would also fetch
Readyline data from IMS DB through a Omega
service and store it as message on ActiveMQ.
• ActiveMQ would be setup to synchronize with
ActiveMQ on AWS.
Omega
Service
• Data will be synced with the AWS environment via
synchronous API Calls
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Mileage Optimization Machine Learning
Architecture: Data Processing
Component Usage
Amazon API
Gateway
• The station operator scans barcode on vehicle. This
triggers invocation of new Omega service.
• Omega service then invokes Private API on Amazon
API Gateway. Device_Id & Location_Id are sent to
this Private API.
• API Gateway invokes Lamba function
AWS Lambda
• Receives data inputs from API and logs request
details in Amazon S3 (future model analysis)
• Queries Postgres operational data store and
retrieves Fleet and Reservation information for that
particular location
Invocation and process will occur on a near-real time basis in order to ensure
that Avis Budget Group front line employees are able to obtain optimized
mileage results on an hourly basis
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Mileage Optimization Machine Learning
Architecture: Machine Learning
Cloud
Integer Programming &
Regression
Component Usage
Lambda
• Invokes Amazon SageMaker endpoint and sends
input data
• Receives optimized result from Amazon SageMaker
• Stores response in Amazon S3 bucket ( for future
model analysis)
• Sends response back to calling API
Amazon
SageMaker
• Imports relevant Python libraries
• Generates supply and demand for the specified time
horizon
• Incorporates upgrade and substitution logic
• Simulate slope and average miles per day (MPD)
• Calculates “ideal” mileage for any particular vehicle
• Calculates ideal vs actual ratio
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
The model takes key operational components into
consideration for deployment
Feature Description
Cars on
Readyline
Rentable cars that are already
parked in the Readyline
Demand
Horizon
Helps determine if there is a
demand (reservation) for a
particular car class in the next
horizon (particular number of
hours) of time
Primary vs.
Exclusive
The cars are divided into two (2)
cohorts, where substitutions can
happen within a cohort.
Exclusive Cars
by Class
Demand for an exclusive car class
can only be satisfied by that car
class.
Substitution
Demand for a primary class car can
be satisfied by other Primary class
cars.
Contention
Satisfying a reservation with an
upgrade car class if a better car is
available.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Dashboards powered by Uber’s deck.gl
Geolocation analysis
of intra-lot
movements, and
details associated
with those
movements
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Dashboards powered by Uber’s deck.gl
Geofenced location
and identification of
a set of vehicles
within that geofence
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
What is next?
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Thank you!
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.

More Related Content

What's hot

ML Workflows with Amazon SageMaker and AWS Step Functions (API325) - AWS re:I...
ML Workflows with Amazon SageMaker and AWS Step Functions (API325) - AWS re:I...ML Workflows with Amazon SageMaker and AWS Step Functions (API325) - AWS re:I...
ML Workflows with Amazon SageMaker and AWS Step Functions (API325) - AWS re:I...
Amazon Web Services
 
Announcing AWS RoboMaker: A New Cloud Robotics Service (ROB201-R1) - AWS re:I...
Announcing AWS RoboMaker: A New Cloud Robotics Service (ROB201-R1) - AWS re:I...Announcing AWS RoboMaker: A New Cloud Robotics Service (ROB201-R1) - AWS re:I...
Announcing AWS RoboMaker: A New Cloud Robotics Service (ROB201-R1) - AWS re:I...
Amazon Web Services
 
Edge Computing with AWS Greengrass
Edge Computing with AWS Greengrass Edge Computing with AWS Greengrass
Edge Computing with AWS Greengrass
Amazon Web Services
 
AI/ML with Data Lakes: Counterintuitive Consumer Insights in Retail (RET206) ...
AI/ML with Data Lakes: Counterintuitive Consumer Insights in Retail (RET206) ...AI/ML with Data Lakes: Counterintuitive Consumer Insights in Retail (RET206) ...
AI/ML with Data Lakes: Counterintuitive Consumer Insights in Retail (RET206) ...
Amazon Web Services
 
Dissecting Media Asset Management Architecture and Media Archive TCO (MAE301)...
Dissecting Media Asset Management Architecture and Media Archive TCO (MAE301)...Dissecting Media Asset Management Architecture and Media Archive TCO (MAE301)...
Dissecting Media Asset Management Architecture and Media Archive TCO (MAE301)...
Amazon Web Services
 
Managing Modern Infrastructure in Enterprises (ENT227-R1) - AWS re:Invent 2018
Managing Modern Infrastructure in Enterprises (ENT227-R1) - AWS re:Invent 2018Managing Modern Infrastructure in Enterprises (ENT227-R1) - AWS re:Invent 2018
Managing Modern Infrastructure in Enterprises (ENT227-R1) - AWS re:Invent 2018
Amazon Web Services
 
SRV304 IoT Building Blocks From Edge Devices to Analytics in the Cloud
SRV304 IoT Building Blocks From Edge Devices to Analytics in the Cloud SRV304 IoT Building Blocks From Edge Devices to Analytics in the Cloud
SRV304 IoT Building Blocks From Edge Devices to Analytics in the Cloud
Amazon Web Services
 
Shift-Left SRE: Self-Healing with AWS Lambda Functions (DEV313-S) - AWS re:In...
Shift-Left SRE: Self-Healing with AWS Lambda Functions (DEV313-S) - AWS re:In...Shift-Left SRE: Self-Healing with AWS Lambda Functions (DEV313-S) - AWS re:In...
Shift-Left SRE: Self-Healing with AWS Lambda Functions (DEV313-S) - AWS re:In...
Amazon Web Services
 
Serverless Video Ingestion & Analytics with Amazon Kinesis Video Streams (ANT...
Serverless Video Ingestion & Analytics with Amazon Kinesis Video Streams (ANT...Serverless Video Ingestion & Analytics with Amazon Kinesis Video Streams (ANT...
Serverless Video Ingestion & Analytics with Amazon Kinesis Video Streams (ANT...
Amazon Web Services
 
Under the Hood: How Amazon Uses AWS Services for Analytics at a Massive Scale...
Under the Hood: How Amazon Uses AWS Services for Analytics at a Massive Scale...Under the Hood: How Amazon Uses AWS Services for Analytics at a Massive Scale...
Under the Hood: How Amazon Uses AWS Services for Analytics at a Massive Scale...
Amazon Web Services
 
Operationalizing Your Analysis with AWS IoT Analytics (IOT358-R1) - AWS re:In...
Operationalizing Your Analysis with AWS IoT Analytics (IOT358-R1) - AWS re:In...Operationalizing Your Analysis with AWS IoT Analytics (IOT358-R1) - AWS re:In...
Operationalizing Your Analysis with AWS IoT Analytics (IOT358-R1) - AWS re:In...
Amazon Web Services
 
Implementing Multi-Region AWS IoT, ft. Analog Devices (IOT401) - AWS re:Inven...
Implementing Multi-Region AWS IoT, ft. Analog Devices (IOT401) - AWS re:Inven...Implementing Multi-Region AWS IoT, ft. Analog Devices (IOT401) - AWS re:Inven...
Implementing Multi-Region AWS IoT, ft. Analog Devices (IOT401) - AWS re:Inven...
Amazon Web Services
 
Leadership Session: AWS Semiconductor (MFG201-L) - AWS re:Invent 2018
Leadership Session: AWS Semiconductor (MFG201-L) - AWS re:Invent 2018Leadership Session: AWS Semiconductor (MFG201-L) - AWS re:Invent 2018
Leadership Session: AWS Semiconductor (MFG201-L) - AWS re:Invent 2018
Amazon Web Services
 
What's New with Amazon Redshift ft. McDonald's (ANT350-R1) - AWS re:Invent 2018
What's New with Amazon Redshift ft. McDonald's (ANT350-R1) - AWS re:Invent 2018What's New with Amazon Redshift ft. McDonald's (ANT350-R1) - AWS re:Invent 2018
What's New with Amazon Redshift ft. McDonald's (ANT350-R1) - AWS re:Invent 2018
Amazon Web Services
 
The Amazon.com Database Journey to AWS – Top 10 Lessons Learned (DAT326) - AW...
The Amazon.com Database Journey to AWS – Top 10 Lessons Learned (DAT326) - AW...The Amazon.com Database Journey to AWS – Top 10 Lessons Learned (DAT326) - AW...
The Amazon.com Database Journey to AWS – Top 10 Lessons Learned (DAT326) - AW...
Amazon Web Services
 
Using Amazon Kinesis Data Streams as a Low-Latency Message Bus (ANT361) - AWS...
Using Amazon Kinesis Data Streams as a Low-Latency Message Bus (ANT361) - AWS...Using Amazon Kinesis Data Streams as a Low-Latency Message Bus (ANT361) - AWS...
Using Amazon Kinesis Data Streams as a Low-Latency Message Bus (ANT361) - AWS...
Amazon Web Services
 
Migrate Your Hadoop/Spark Workload to Amazon EMR and Architect It for Securit...
Migrate Your Hadoop/Spark Workload to Amazon EMR and Architect It for Securit...Migrate Your Hadoop/Spark Workload to Amazon EMR and Architect It for Securit...
Migrate Your Hadoop/Spark Workload to Amazon EMR and Architect It for Securit...
Amazon Web Services
 
Security Challenges and Use Cases in the Modern Application Build-and-Deploy ...
Security Challenges and Use Cases in the Modern Application Build-and-Deploy ...Security Challenges and Use Cases in the Modern Application Build-and-Deploy ...
Security Challenges and Use Cases in the Modern Application Build-and-Deploy ...
Amazon Web Services
 
Machine Learning Inference at the Edge (IOT322-R1) - AWS re:Invent 2018
Machine Learning Inference at the Edge (IOT322-R1) - AWS re:Invent 2018Machine Learning Inference at the Edge (IOT322-R1) - AWS re:Invent 2018
Machine Learning Inference at the Edge (IOT322-R1) - AWS re:Invent 2018
Amazon Web Services
 
Supercell – Scaling Mobile Games (GAM301) - AWS re:Invent 2018
Supercell – Scaling Mobile Games (GAM301) - AWS re:Invent 2018Supercell – Scaling Mobile Games (GAM301) - AWS re:Invent 2018
Supercell – Scaling Mobile Games (GAM301) - AWS re:Invent 2018
Amazon Web Services
 

What's hot (20)

ML Workflows with Amazon SageMaker and AWS Step Functions (API325) - AWS re:I...
ML Workflows with Amazon SageMaker and AWS Step Functions (API325) - AWS re:I...ML Workflows with Amazon SageMaker and AWS Step Functions (API325) - AWS re:I...
ML Workflows with Amazon SageMaker and AWS Step Functions (API325) - AWS re:I...
 
Announcing AWS RoboMaker: A New Cloud Robotics Service (ROB201-R1) - AWS re:I...
Announcing AWS RoboMaker: A New Cloud Robotics Service (ROB201-R1) - AWS re:I...Announcing AWS RoboMaker: A New Cloud Robotics Service (ROB201-R1) - AWS re:I...
Announcing AWS RoboMaker: A New Cloud Robotics Service (ROB201-R1) - AWS re:I...
 
Edge Computing with AWS Greengrass
Edge Computing with AWS Greengrass Edge Computing with AWS Greengrass
Edge Computing with AWS Greengrass
 
AI/ML with Data Lakes: Counterintuitive Consumer Insights in Retail (RET206) ...
AI/ML with Data Lakes: Counterintuitive Consumer Insights in Retail (RET206) ...AI/ML with Data Lakes: Counterintuitive Consumer Insights in Retail (RET206) ...
AI/ML with Data Lakes: Counterintuitive Consumer Insights in Retail (RET206) ...
 
Dissecting Media Asset Management Architecture and Media Archive TCO (MAE301)...
Dissecting Media Asset Management Architecture and Media Archive TCO (MAE301)...Dissecting Media Asset Management Architecture and Media Archive TCO (MAE301)...
Dissecting Media Asset Management Architecture and Media Archive TCO (MAE301)...
 
Managing Modern Infrastructure in Enterprises (ENT227-R1) - AWS re:Invent 2018
Managing Modern Infrastructure in Enterprises (ENT227-R1) - AWS re:Invent 2018Managing Modern Infrastructure in Enterprises (ENT227-R1) - AWS re:Invent 2018
Managing Modern Infrastructure in Enterprises (ENT227-R1) - AWS re:Invent 2018
 
SRV304 IoT Building Blocks From Edge Devices to Analytics in the Cloud
SRV304 IoT Building Blocks From Edge Devices to Analytics in the Cloud SRV304 IoT Building Blocks From Edge Devices to Analytics in the Cloud
SRV304 IoT Building Blocks From Edge Devices to Analytics in the Cloud
 
Shift-Left SRE: Self-Healing with AWS Lambda Functions (DEV313-S) - AWS re:In...
Shift-Left SRE: Self-Healing with AWS Lambda Functions (DEV313-S) - AWS re:In...Shift-Left SRE: Self-Healing with AWS Lambda Functions (DEV313-S) - AWS re:In...
Shift-Left SRE: Self-Healing with AWS Lambda Functions (DEV313-S) - AWS re:In...
 
Serverless Video Ingestion & Analytics with Amazon Kinesis Video Streams (ANT...
Serverless Video Ingestion & Analytics with Amazon Kinesis Video Streams (ANT...Serverless Video Ingestion & Analytics with Amazon Kinesis Video Streams (ANT...
Serverless Video Ingestion & Analytics with Amazon Kinesis Video Streams (ANT...
 
Under the Hood: How Amazon Uses AWS Services for Analytics at a Massive Scale...
Under the Hood: How Amazon Uses AWS Services for Analytics at a Massive Scale...Under the Hood: How Amazon Uses AWS Services for Analytics at a Massive Scale...
Under the Hood: How Amazon Uses AWS Services for Analytics at a Massive Scale...
 
Operationalizing Your Analysis with AWS IoT Analytics (IOT358-R1) - AWS re:In...
Operationalizing Your Analysis with AWS IoT Analytics (IOT358-R1) - AWS re:In...Operationalizing Your Analysis with AWS IoT Analytics (IOT358-R1) - AWS re:In...
Operationalizing Your Analysis with AWS IoT Analytics (IOT358-R1) - AWS re:In...
 
Implementing Multi-Region AWS IoT, ft. Analog Devices (IOT401) - AWS re:Inven...
Implementing Multi-Region AWS IoT, ft. Analog Devices (IOT401) - AWS re:Inven...Implementing Multi-Region AWS IoT, ft. Analog Devices (IOT401) - AWS re:Inven...
Implementing Multi-Region AWS IoT, ft. Analog Devices (IOT401) - AWS re:Inven...
 
Leadership Session: AWS Semiconductor (MFG201-L) - AWS re:Invent 2018
Leadership Session: AWS Semiconductor (MFG201-L) - AWS re:Invent 2018Leadership Session: AWS Semiconductor (MFG201-L) - AWS re:Invent 2018
Leadership Session: AWS Semiconductor (MFG201-L) - AWS re:Invent 2018
 
What's New with Amazon Redshift ft. McDonald's (ANT350-R1) - AWS re:Invent 2018
What's New with Amazon Redshift ft. McDonald's (ANT350-R1) - AWS re:Invent 2018What's New with Amazon Redshift ft. McDonald's (ANT350-R1) - AWS re:Invent 2018
What's New with Amazon Redshift ft. McDonald's (ANT350-R1) - AWS re:Invent 2018
 
The Amazon.com Database Journey to AWS – Top 10 Lessons Learned (DAT326) - AW...
The Amazon.com Database Journey to AWS – Top 10 Lessons Learned (DAT326) - AW...The Amazon.com Database Journey to AWS – Top 10 Lessons Learned (DAT326) - AW...
The Amazon.com Database Journey to AWS – Top 10 Lessons Learned (DAT326) - AW...
 
Using Amazon Kinesis Data Streams as a Low-Latency Message Bus (ANT361) - AWS...
Using Amazon Kinesis Data Streams as a Low-Latency Message Bus (ANT361) - AWS...Using Amazon Kinesis Data Streams as a Low-Latency Message Bus (ANT361) - AWS...
Using Amazon Kinesis Data Streams as a Low-Latency Message Bus (ANT361) - AWS...
 
Migrate Your Hadoop/Spark Workload to Amazon EMR and Architect It for Securit...
Migrate Your Hadoop/Spark Workload to Amazon EMR and Architect It for Securit...Migrate Your Hadoop/Spark Workload to Amazon EMR and Architect It for Securit...
Migrate Your Hadoop/Spark Workload to Amazon EMR and Architect It for Securit...
 
Security Challenges and Use Cases in the Modern Application Build-and-Deploy ...
Security Challenges and Use Cases in the Modern Application Build-and-Deploy ...Security Challenges and Use Cases in the Modern Application Build-and-Deploy ...
Security Challenges and Use Cases in the Modern Application Build-and-Deploy ...
 
Machine Learning Inference at the Edge (IOT322-R1) - AWS re:Invent 2018
Machine Learning Inference at the Edge (IOT322-R1) - AWS re:Invent 2018Machine Learning Inference at the Edge (IOT322-R1) - AWS re:Invent 2018
Machine Learning Inference at the Edge (IOT322-R1) - AWS re:Invent 2018
 
Supercell – Scaling Mobile Games (GAM301) - AWS re:Invent 2018
Supercell – Scaling Mobile Games (GAM301) - AWS re:Invent 2018Supercell – Scaling Mobile Games (GAM301) - AWS re:Invent 2018
Supercell – Scaling Mobile Games (GAM301) - AWS re:Invent 2018
 

Similar to Easy Rider: How ML, Serverless, and IoT Drive Mobility as a Service (AMT302) - AWS re:Invent 2018

Alexa, Where's My Car? A Test Drive of the AWS Connected Vehicle Solution (AM...
Alexa, Where's My Car? A Test Drive of the AWS Connected Vehicle Solution (AM...Alexa, Where's My Car? A Test Drive of the AWS Connected Vehicle Solution (AM...
Alexa, Where's My Car? A Test Drive of the AWS Connected Vehicle Solution (AM...
Amazon Web Services
 
Deep Dive into the AWS Connected Vehicle Reference Solution (AMT303) - AWS re...
Deep Dive into the AWS Connected Vehicle Reference Solution (AMT303) - AWS re...Deep Dive into the AWS Connected Vehicle Reference Solution (AMT303) - AWS re...
Deep Dive into the AWS Connected Vehicle Reference Solution (AMT303) - AWS re...
Amazon Web Services
 
The Intelligent Edge for IoT: Help Customers Harness the Power of Connected I...
The Intelligent Edge for IoT: Help Customers Harness the Power of Connected I...The Intelligent Edge for IoT: Help Customers Harness the Power of Connected I...
The Intelligent Edge for IoT: Help Customers Harness the Power of Connected I...
Amazon Web Services
 
IoT Revolution - Unlocking Business Values in Vertical Markets
IoT Revolution - Unlocking Business Values in Vertical MarketsIoT Revolution - Unlocking Business Values in Vertical Markets
IoT Revolution - Unlocking Business Values in Vertical Markets
Amazon Web Services
 
Industrial IoT Applications: Making the Connection and Extracting Value (IOT3...
Industrial IoT Applications: Making the Connection and Extracting Value (IOT3...Industrial IoT Applications: Making the Connection and Extracting Value (IOT3...
Industrial IoT Applications: Making the Connection and Extracting Value (IOT3...
Amazon Web Services
 
Instrumenting Kubernetes for Observability Using AWS X-Ray and Amazon CloudWa...
Instrumenting Kubernetes for Observability Using AWS X-Ray and Amazon CloudWa...Instrumenting Kubernetes for Observability Using AWS X-Ray and Amazon CloudWa...
Instrumenting Kubernetes for Observability Using AWS X-Ray and Amazon CloudWa...
Amazon Web Services
 
AWSome Day Nairobi 2019
AWSome Day Nairobi 2019AWSome Day Nairobi 2019
AWSome Day Nairobi 2019
Amazon Web Services
 
AWS Smart Cities Webinar - April 2018
AWS Smart Cities Webinar - April 2018AWS Smart Cities Webinar - April 2018
AWS Smart Cities Webinar - April 2018
Amazon Web Services
 
Driving the Data Pipelines for Connected Vehicles with Spring Cloud Data Flow
Driving the Data Pipelines for Connected Vehicles with Spring Cloud Data FlowDriving the Data Pipelines for Connected Vehicles with Spring Cloud Data Flow
Driving the Data Pipelines for Connected Vehicles with Spring Cloud Data Flow
VMware Tanzu
 
Aws Tools for Alexa Skills
Aws Tools for Alexa SkillsAws Tools for Alexa Skills
Aws Tools for Alexa Skills
Boaz Ziniman
 
Introducing AWS App Mesh - MAD303 - Santa Clara AWS Summit
Introducing AWS App Mesh - MAD303 - Santa Clara AWS SummitIntroducing AWS App Mesh - MAD303 - Santa Clara AWS Summit
Introducing AWS App Mesh - MAD303 - Santa Clara AWS Summit
Amazon Web Services
 
Bringing Cloud to the Edge - AWS Summit Sydney
Bringing Cloud to the Edge - AWS Summit SydneyBringing Cloud to the Edge - AWS Summit Sydney
Bringing Cloud to the Edge - AWS Summit Sydney
Amazon Web Services
 
Microservices for Startups
Microservices for StartupsMicroservices for Startups
Microservices for Startups
Amazon Web Services
 
Starting your Cloud Journey - AWSomeDay Israel
Starting your Cloud Journey - AWSomeDay IsraelStarting your Cloud Journey - AWSomeDay Israel
Starting your Cloud Journey - AWSomeDay Israel
Amazon Web Services
 
Starting your cloud journey - AWSomeDay Israel
Starting your cloud journey - AWSomeDay IsraelStarting your cloud journey - AWSomeDay Israel
Starting your cloud journey - AWSomeDay Israel
Boaz Ziniman
 
[NEW LAUNCH!] Introducing AWS App Mesh – service mesh on AWS (CON367) - AWS r...
[NEW LAUNCH!] Introducing AWS App Mesh – service mesh on AWS (CON367) - AWS r...[NEW LAUNCH!] Introducing AWS App Mesh – service mesh on AWS (CON367) - AWS r...
[NEW LAUNCH!] Introducing AWS App Mesh – service mesh on AWS (CON367) - AWS r...
Amazon Web Services
 
Ripping off the Bandage: Re-Architecting Traditional Three-Tier Monoliths to ...
Ripping off the Bandage: Re-Architecting Traditional Three-Tier Monoliths to ...Ripping off the Bandage: Re-Architecting Traditional Three-Tier Monoliths to ...
Ripping off the Bandage: Re-Architecting Traditional Three-Tier Monoliths to ...
Amazon Web Services
 
AWSome Day 2018 Keynote
AWSome Day 2018 KeynoteAWSome Day 2018 Keynote
AWSome Day 2018 Keynote
Amazon Web Services
 
Build Business-Ready Blockchains with Intelligence (GPSTEC315) - AWS re:Inven...
Build Business-Ready Blockchains with Intelligence (GPSTEC315) - AWS re:Inven...Build Business-Ready Blockchains with Intelligence (GPSTEC315) - AWS re:Inven...
Build Business-Ready Blockchains with Intelligence (GPSTEC315) - AWS re:Inven...
Amazon Web Services
 
Building BMW Group's Customer Engagement Platform on AWS (AMT305) - AWS re:In...
Building BMW Group's Customer Engagement Platform on AWS (AMT305) - AWS re:In...Building BMW Group's Customer Engagement Platform on AWS (AMT305) - AWS re:In...
Building BMW Group's Customer Engagement Platform on AWS (AMT305) - AWS re:In...
Amazon Web Services
 

Similar to Easy Rider: How ML, Serverless, and IoT Drive Mobility as a Service (AMT302) - AWS re:Invent 2018 (20)

Alexa, Where's My Car? A Test Drive of the AWS Connected Vehicle Solution (AM...
Alexa, Where's My Car? A Test Drive of the AWS Connected Vehicle Solution (AM...Alexa, Where's My Car? A Test Drive of the AWS Connected Vehicle Solution (AM...
Alexa, Where's My Car? A Test Drive of the AWS Connected Vehicle Solution (AM...
 
Deep Dive into the AWS Connected Vehicle Reference Solution (AMT303) - AWS re...
Deep Dive into the AWS Connected Vehicle Reference Solution (AMT303) - AWS re...Deep Dive into the AWS Connected Vehicle Reference Solution (AMT303) - AWS re...
Deep Dive into the AWS Connected Vehicle Reference Solution (AMT303) - AWS re...
 
The Intelligent Edge for IoT: Help Customers Harness the Power of Connected I...
The Intelligent Edge for IoT: Help Customers Harness the Power of Connected I...The Intelligent Edge for IoT: Help Customers Harness the Power of Connected I...
The Intelligent Edge for IoT: Help Customers Harness the Power of Connected I...
 
IoT Revolution - Unlocking Business Values in Vertical Markets
IoT Revolution - Unlocking Business Values in Vertical MarketsIoT Revolution - Unlocking Business Values in Vertical Markets
IoT Revolution - Unlocking Business Values in Vertical Markets
 
Industrial IoT Applications: Making the Connection and Extracting Value (IOT3...
Industrial IoT Applications: Making the Connection and Extracting Value (IOT3...Industrial IoT Applications: Making the Connection and Extracting Value (IOT3...
Industrial IoT Applications: Making the Connection and Extracting Value (IOT3...
 
Instrumenting Kubernetes for Observability Using AWS X-Ray and Amazon CloudWa...
Instrumenting Kubernetes for Observability Using AWS X-Ray and Amazon CloudWa...Instrumenting Kubernetes for Observability Using AWS X-Ray and Amazon CloudWa...
Instrumenting Kubernetes for Observability Using AWS X-Ray and Amazon CloudWa...
 
AWSome Day Nairobi 2019
AWSome Day Nairobi 2019AWSome Day Nairobi 2019
AWSome Day Nairobi 2019
 
AWS Smart Cities Webinar - April 2018
AWS Smart Cities Webinar - April 2018AWS Smart Cities Webinar - April 2018
AWS Smart Cities Webinar - April 2018
 
Driving the Data Pipelines for Connected Vehicles with Spring Cloud Data Flow
Driving the Data Pipelines for Connected Vehicles with Spring Cloud Data FlowDriving the Data Pipelines for Connected Vehicles with Spring Cloud Data Flow
Driving the Data Pipelines for Connected Vehicles with Spring Cloud Data Flow
 
Aws Tools for Alexa Skills
Aws Tools for Alexa SkillsAws Tools for Alexa Skills
Aws Tools for Alexa Skills
 
Introducing AWS App Mesh - MAD303 - Santa Clara AWS Summit
Introducing AWS App Mesh - MAD303 - Santa Clara AWS SummitIntroducing AWS App Mesh - MAD303 - Santa Clara AWS Summit
Introducing AWS App Mesh - MAD303 - Santa Clara AWS Summit
 
Bringing Cloud to the Edge - AWS Summit Sydney
Bringing Cloud to the Edge - AWS Summit SydneyBringing Cloud to the Edge - AWS Summit Sydney
Bringing Cloud to the Edge - AWS Summit Sydney
 
Microservices for Startups
Microservices for StartupsMicroservices for Startups
Microservices for Startups
 
Starting your Cloud Journey - AWSomeDay Israel
Starting your Cloud Journey - AWSomeDay IsraelStarting your Cloud Journey - AWSomeDay Israel
Starting your Cloud Journey - AWSomeDay Israel
 
Starting your cloud journey - AWSomeDay Israel
Starting your cloud journey - AWSomeDay IsraelStarting your cloud journey - AWSomeDay Israel
Starting your cloud journey - AWSomeDay Israel
 
[NEW LAUNCH!] Introducing AWS App Mesh – service mesh on AWS (CON367) - AWS r...
[NEW LAUNCH!] Introducing AWS App Mesh – service mesh on AWS (CON367) - AWS r...[NEW LAUNCH!] Introducing AWS App Mesh – service mesh on AWS (CON367) - AWS r...
[NEW LAUNCH!] Introducing AWS App Mesh – service mesh on AWS (CON367) - AWS r...
 
Ripping off the Bandage: Re-Architecting Traditional Three-Tier Monoliths to ...
Ripping off the Bandage: Re-Architecting Traditional Three-Tier Monoliths to ...Ripping off the Bandage: Re-Architecting Traditional Three-Tier Monoliths to ...
Ripping off the Bandage: Re-Architecting Traditional Three-Tier Monoliths to ...
 
AWSome Day 2018 Keynote
AWSome Day 2018 KeynoteAWSome Day 2018 Keynote
AWSome Day 2018 Keynote
 
Build Business-Ready Blockchains with Intelligence (GPSTEC315) - AWS re:Inven...
Build Business-Ready Blockchains with Intelligence (GPSTEC315) - AWS re:Inven...Build Business-Ready Blockchains with Intelligence (GPSTEC315) - AWS re:Inven...
Build Business-Ready Blockchains with Intelligence (GPSTEC315) - AWS re:Inven...
 
Building BMW Group's Customer Engagement Platform on AWS (AMT305) - AWS re:In...
Building BMW Group's Customer Engagement Platform on AWS (AMT305) - AWS re:In...Building BMW Group's Customer Engagement Platform on AWS (AMT305) - AWS re:In...
Building BMW Group's Customer Engagement Platform on AWS (AMT305) - AWS re:In...
 

More from Amazon Web Services

Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...
Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...
Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...
Amazon Web Services
 
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...Big Data per le Startup: come creare applicazioni Big Data in modalità Server...
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...
Amazon Web Services
 
Esegui pod serverless con Amazon EKS e AWS Fargate
Esegui pod serverless con Amazon EKS e AWS FargateEsegui pod serverless con Amazon EKS e AWS Fargate
Esegui pod serverless con Amazon EKS e AWS Fargate
Amazon Web Services
 
Costruire Applicazioni Moderne con AWS
Costruire Applicazioni Moderne con AWSCostruire Applicazioni Moderne con AWS
Costruire Applicazioni Moderne con AWS
Amazon Web Services
 
Come spendere fino al 90% in meno con i container e le istanze spot
Come spendere fino al 90% in meno con i container e le istanze spot Come spendere fino al 90% in meno con i container e le istanze spot
Come spendere fino al 90% in meno con i container e le istanze spot
Amazon Web Services
 
Open banking as a service
Open banking as a serviceOpen banking as a service
Open banking as a service
Amazon Web Services
 
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...
Amazon Web Services
 
OpsWorks Configuration Management: automatizza la gestione e i deployment del...
OpsWorks Configuration Management: automatizza la gestione e i deployment del...OpsWorks Configuration Management: automatizza la gestione e i deployment del...
OpsWorks Configuration Management: automatizza la gestione e i deployment del...
Amazon Web Services
 
Microsoft Active Directory su AWS per supportare i tuoi Windows Workloads
Microsoft Active Directory su AWS per supportare i tuoi Windows WorkloadsMicrosoft Active Directory su AWS per supportare i tuoi Windows Workloads
Microsoft Active Directory su AWS per supportare i tuoi Windows Workloads
Amazon Web Services
 
Computer Vision con AWS
Computer Vision con AWSComputer Vision con AWS
Computer Vision con AWS
Amazon Web Services
 
Database Oracle e VMware Cloud on AWS i miti da sfatare
Database Oracle e VMware Cloud on AWS i miti da sfatareDatabase Oracle e VMware Cloud on AWS i miti da sfatare
Database Oracle e VMware Cloud on AWS i miti da sfatare
Amazon Web Services
 
Crea la tua prima serverless ledger-based app con QLDB e NodeJS
Crea la tua prima serverless ledger-based app con QLDB e NodeJSCrea la tua prima serverless ledger-based app con QLDB e NodeJS
Crea la tua prima serverless ledger-based app con QLDB e NodeJS
Amazon Web Services
 
API moderne real-time per applicazioni mobili e web
API moderne real-time per applicazioni mobili e webAPI moderne real-time per applicazioni mobili e web
API moderne real-time per applicazioni mobili e web
Amazon Web Services
 
Database Oracle e VMware Cloud™ on AWS: i miti da sfatare
Database Oracle e VMware Cloud™ on AWS: i miti da sfatareDatabase Oracle e VMware Cloud™ on AWS: i miti da sfatare
Database Oracle e VMware Cloud™ on AWS: i miti da sfatare
Amazon Web Services
 
Tools for building your MVP on AWS
Tools for building your MVP on AWSTools for building your MVP on AWS
Tools for building your MVP on AWSAmazon Web Services
 
How to Build a Winning Pitch Deck
How to Build a Winning Pitch DeckHow to Build a Winning Pitch Deck
How to Build a Winning Pitch DeckAmazon Web Services
 
Building a web application without servers
Building a web application without serversBuilding a web application without servers
Building a web application without serversAmazon Web Services
 
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...AWS_HK_StartupDay_Building Interactive websites while automating for efficien...
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...Amazon Web Services
 
Introduzione a Amazon Elastic Container Service
Introduzione a Amazon Elastic Container ServiceIntroduzione a Amazon Elastic Container Service
Introduzione a Amazon Elastic Container Service
Amazon Web Services
 

More from Amazon Web Services (20)

Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...
Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...
Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...
 
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...Big Data per le Startup: come creare applicazioni Big Data in modalità Server...
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...
 
Esegui pod serverless con Amazon EKS e AWS Fargate
Esegui pod serverless con Amazon EKS e AWS FargateEsegui pod serverless con Amazon EKS e AWS Fargate
Esegui pod serverless con Amazon EKS e AWS Fargate
 
Costruire Applicazioni Moderne con AWS
Costruire Applicazioni Moderne con AWSCostruire Applicazioni Moderne con AWS
Costruire Applicazioni Moderne con AWS
 
Come spendere fino al 90% in meno con i container e le istanze spot
Come spendere fino al 90% in meno con i container e le istanze spot Come spendere fino al 90% in meno con i container e le istanze spot
Come spendere fino al 90% in meno con i container e le istanze spot
 
Open banking as a service
Open banking as a serviceOpen banking as a service
Open banking as a service
 
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...
 
OpsWorks Configuration Management: automatizza la gestione e i deployment del...
OpsWorks Configuration Management: automatizza la gestione e i deployment del...OpsWorks Configuration Management: automatizza la gestione e i deployment del...
OpsWorks Configuration Management: automatizza la gestione e i deployment del...
 
Microsoft Active Directory su AWS per supportare i tuoi Windows Workloads
Microsoft Active Directory su AWS per supportare i tuoi Windows WorkloadsMicrosoft Active Directory su AWS per supportare i tuoi Windows Workloads
Microsoft Active Directory su AWS per supportare i tuoi Windows Workloads
 
Computer Vision con AWS
Computer Vision con AWSComputer Vision con AWS
Computer Vision con AWS
 
Database Oracle e VMware Cloud on AWS i miti da sfatare
Database Oracle e VMware Cloud on AWS i miti da sfatareDatabase Oracle e VMware Cloud on AWS i miti da sfatare
Database Oracle e VMware Cloud on AWS i miti da sfatare
 
Crea la tua prima serverless ledger-based app con QLDB e NodeJS
Crea la tua prima serverless ledger-based app con QLDB e NodeJSCrea la tua prima serverless ledger-based app con QLDB e NodeJS
Crea la tua prima serverless ledger-based app con QLDB e NodeJS
 
API moderne real-time per applicazioni mobili e web
API moderne real-time per applicazioni mobili e webAPI moderne real-time per applicazioni mobili e web
API moderne real-time per applicazioni mobili e web
 
Database Oracle e VMware Cloud™ on AWS: i miti da sfatare
Database Oracle e VMware Cloud™ on AWS: i miti da sfatareDatabase Oracle e VMware Cloud™ on AWS: i miti da sfatare
Database Oracle e VMware Cloud™ on AWS: i miti da sfatare
 
Tools for building your MVP on AWS
Tools for building your MVP on AWSTools for building your MVP on AWS
Tools for building your MVP on AWS
 
How to Build a Winning Pitch Deck
How to Build a Winning Pitch DeckHow to Build a Winning Pitch Deck
How to Build a Winning Pitch Deck
 
Building a web application without servers
Building a web application without serversBuilding a web application without servers
Building a web application without servers
 
Fundraising Essentials
Fundraising EssentialsFundraising Essentials
Fundraising Essentials
 
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...AWS_HK_StartupDay_Building Interactive websites while automating for efficien...
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...
 
Introduzione a Amazon Elastic Container Service
Introduzione a Amazon Elastic Container ServiceIntroduzione a Amazon Elastic Container Service
Introduzione a Amazon Elastic Container Service
 

Easy Rider: How ML, Serverless, and IoT Drive Mobility as a Service (AMT302) - AWS re:Invent 2018

  • 1.
  • 2. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Easy Rider: How ML, Serverless, and IoT Drive Mobility as a Service A M T 3 0 2 Indra(Neel) Mitra Solutions Architect AWS Christopher Cerruto Vice President Avis Budget Group Saken Kulkarni ML / AI Practice Lead Slalom
  • 3. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Intro Indra(Neel) Mitra Solutions Architect Amazon Web Services Outside of work
  • 4. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Agenda 1. Amazon in Automobiles 2. AWS Connected Vehicle Solution Overview a. Greenfield Environments b. Brownfield Environments 3. Avis Budget Group a. Our Vision b. Current State & Challenges c. Future State on AWS 4. Slalom Consulting a. Use case Deep Dive b. Architecture c. Demo 5. Q&A
  • 5. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon’s approach to connected vehicles
  • 6. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. AWS Connected Vehicle Solution Technology Stack Platform APIs Application services Data services Ingestion (AWS IoT) Amazon API Gateway AWS Lambda Amazon SNS Amazon SQS Amazon Cognito Amazon S3 Amazon DynamoDB Amazon Kinesis Amazon ML Device Gateway Registry Rules Engine Message Broker Protocols Connectivity Vehicle HTTP MQTT MQTT + WebSockets Mobile Carrier Telemetry Hardware AWS Greengrass x.509 certificates Automotive Grade Linux
  • 7. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. AWS Connected Vehicle Solution Benefits
  • 8. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 9. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. How do you get started? Start prototyping with a ‘well architected’ architecture in minutes using the AWS Connected Vehicle Quick Start Deploy into your own AWS account Customize use cases or develop your own Remove or add other AWS and partner services Easily connect your own data or your own devices https://aws.amazon.com/answers/iot/connected-vehicle-solution/
  • 10. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. AWS Connected Vehicle Solution Reference Architecture Authentication Connected Vehicle Data Ingestion Device Gateway Rules Engine AWS IoT Connected Vehicles Certificate JSON Just-in-Time Registration Rule 1 Message Topic Action OBD Telematics connectedcar/telemetry/<VIN> Publish Vehicle Trip Info connectedcar/trip/<VIN> Publish Diagnostic Trouble Code connectedcar/dtc/<VIN> Publish Anomaly Alert connectedcar/alert/<VIN>/anomaly Subscribe DTC Alert connectedcar/alert/<VIN>/dtc Subscribe Driver Score Alert connectedcar/alert/<VIN>/driverscore Subscribe Vehicle Provisioning connectedcar/vehicle/<VIN>/provision Publish Sample Message Payload { "name": "speed", ” value": 47.4, "vin": "1NXBR32E84Z995078", "trip_id": "799fc110-fee2-43b2-a6ed-a504fa77931a", "timestamp": "2018-02-15 18:50:18.000000000" }
  • 11. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. AWS Connected Vehicle Solution Reference Architecture Rule 2 Raw Data Telemetry Data JSON Manufacturers Dealers Consumers Personas Data Visualization Telemetry Data MQTT (near-real-time) Reference Data Stores DTC Reference Table Owner Data Table Vehicle Health Report Table Authentication Connected Vehicle Data Ingestion Device Gateway Rules Engine AWS IoT Connected Vehicles Anomalous Data Anomaly Detection & Alerting Anomaly Table User Pool Logs Web UI Mobile App Microservices DTC Detection & Alerting Rule 5 DTC Data JSON DTC Table Location-based Services Geolocation Data JSON Rule 6 Marketing Table Driver Safety Score Processing Rule 4 Aggregated Telemetry Data [ Ignition Status ] JSON Trip Aggregation Processing Rule 3 Aggregated Telemetry Data JSON Trip Aggregation Table Certificate JSON Just-in-Time Registration Rule 1
  • 12. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 13. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Data Ingestion REST ENDPOINTS WEBSOCKETS LMPP OTHER PROTOCOLSAmazon EC2 Amazon Elastic Container Service Elastic Load Balancing Authentication Device Gateway Rules Engine AWS IoT Connected Vehicle Data Ingestion
  • 14. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Data Storage & Analysis Raw Data Reference Data Stores DTC Reference Table Owner Data Table Vehicle Health Report Table Anomalous Data Anomaly Detection & Alerting Anomaly Table DTC Detection & Alerting DTC Table Location-based Services Marketing Table Driver Safety Score Processing Trip Aggregation Processing Trip Aggregation Table NOSQL TSDB Mainframe APIs Applications
  • 15. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Data Consumption Manufacturers Dealers Consumers Personas Data Visualization User Pool Logs Web UI Mobile App Microservices Raw Data Data analysts Data scientists Business users Schemaless Amazon ES Direct Query Amazon Athena Semi/Unstructured Amazon EMR Enterprise Apps Oracle, Teradata, SQL Server, MySQL, et Data Warehouse Amazon Redshift Automation / events Engagement platforms Data ServingData Lake Machine Learning Amazon SageMaker ETL AWS Glue Business Intelligence Amazon QuickSight Data Warehouse Amazon Redshift Spectrum Enterprise Apps Amazon Aurora
  • 16. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Summary
  • 17. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Learn more Thurs, November 29 AMT303 – Deep Dive into the AWS Connected Vehicle Reference Solution 12:15PM – 2:30PM | Mirage, Grand Ballroom G AMT304 – Building Volkswagen Group’s Digital Ecosystem 1:00PM – 2:00PM | MGM, Level 1, Grand Ballroom 111 Check the re:Invent website for videos of these 2018 Automotive sessions AMT301 – Alexa, Where’s My Car? A Test Drive of the AWS Connected Vehicle Solution AMT305 – Building BMW Group’s Digital Customer Engagement Platform AMT201 – Automotive Leadership Session, Paving the Way for the Future of the Automotive Industry
  • 18. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 19. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Intro Christopher Cerruto Vice President, Global Architecture and Analytics Avis Budget Group Things I love…
  • 20. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. 180 COUNTRIES WORLDWIDE 650k GLOBAL FLEET $9B ANNUAL REVENUE 30k EMPLOYEES WORLDWIDE 72 YEARS IN BUSINESS
  • 21.
  • 22. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. 22 | AVIS BUDGET GROUP NEW MOBILITY 101 OUR VISION “We envision a world where mobility is completely connected, integrated and on- demand.”
  • 23. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Reinventing Rental Digitizing the Business Developing New Models OUR APPROACH
  • 24. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 25. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. BUSINESS INTELLIGENCE ARCHITECTURE OUR NEXT-GENERATION MOBILITY PLATFORM Functional View DATAINGESTIONARCHITECTURE DATA LAKE API, SERVICES & ORCHESTRATION DEVELOPMENT PLATFORM TELEMATICS DATA/EVENT STREAMS 3rd PARTY DATA/EVENT STREAMS INTERNAL DATA SOURCES EXTERNAL DATA SOURCES OPERATIONAL DATA STORES WEB APPLICATIONS MOBILE APPLICATIONS OUTBOUND EVENT STREAMS DATA PUBLISHING ARCHITECTURE DATA QUERYING ON-DEMAND DATA EXTRACTION DATA CACHES ENTERPRISE DATA HUB DEVELOPER API PORTAL 3rd PARTY DATA CONSUMERS 3rd PARTY API CONSUMERS DATA VISUALIZATION BUSINESS RULES AND COMPLEX EVENT PROCESSING ENGINE DATA WAREHOUSE ANALYSIS AND MODELING SYSTEMS REPORTING INSIGHTS EXPLORATORY ANALYSIS MODELS MACHINE LEARNING MODELS API CATALOG CONSENT/PRIVACY DATA ARCHITECTURE BUSINESS SERVICES ARCHITECTURE ANALYTICS & DATA SCIENCE ARCHITECTURE CLOUD INFRASTRUCTURE, CODE AND RESOURCE ORCHESTRATION ARCHITECTURE
  • 26. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. ABG CURRENT STATE OF THE WORLD Pain Points o Anchored to Legacy Systems o Rigid Infrastructure o 3rd Party Supported Data Center and Ops o “Big Data” Problem • Size: Breadth and Depth • Normalization • Pace of Change o Limited/No Event Handling and Event Publishing o No Real-Time Operational Analytics o Performance and Scaling o Time to Market
  • 27. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. INITIAL CONNECTED CAR ARCHITECTURE INGESTION SERVICES RABBIT MQ CSS WebLogic (Java) JMS Amazon EMR CONNECTED CAR MANAGEMENT PLATFORM BATCH ANALYTICS PLATFORM FRONT OFFICE PROGRAMS SERVICES PORTAL TELEMATICS DATA (limited, based on geofence event) LIMITED DATA (daily) LIMITED DATA (daily) Oracle IMS DB2 BACK OFFICE PROGRAMS IBM MQ Amazon S3CASSANDRA VEHICLE SERVICES OTHER SERVICES OMEGA PLATFORM (SOA) SYSTEM Z TCU (UTP) TCU (Z01) Z01 Platform UTP Platform … COAP/UDP LMPP REST WebSocket REST LMPP
  • 28. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Edge Cloud Enterprise Applications Telemetry Endpoints/ Data Sources Gateway TCU (UTP) TCU (Z01) Z01 Platform UTP Platform … REST WebSocket COAP/UDP LMPP EC2 Containers S3 Aurora PostgresCassandra Rabbit MQ Ingest & Real Time Process 1 Data Analysis, Modeling & Machine Learning Raw Data Normalized Data Real Time Services Amazon SageMaker Lambda Amazon EMR Real Time & Batch Analysis and Machine Learning Lambda Kinesis Data Analytics Near Real Time / Micro Batch Analysis Kinesis Data Streams Lambda (Data xForm) Business Intelligence & Visualization Amazon Redshift Athena Tableau Fleet Management Corporate Application Legacy Data/ Services 5 Wizard Mainframe ODB Fleet Location Edge Users Enterprise Users REST APIs (HTTP/ SOAP) OUR NEXT-GENERATION MOBILITY PLATFORM Technical View REST LMPP 2 3 4 EC2 Containers OMEGA
  • 29. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. ABG DEVELOPER PROGRAM The Avis developer platform provides the products you need to start building applications that revolve around cars—from on- demand luxury ride requests to traditional rental car reservations with access to our Avis, Budget and Zipcar product catalog. Use our simplified ReST APIs to create memorable trip experiences for your users across the globe. http://developer.avis.com JOIN US!
  • 30. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 31. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Intro Saken Kulkarni Practice Area Lead, Advanced Analytics Slalom Things I love…
  • 32. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. The Avis Budget Group, Slalom, and AWS teams had several use cases to build on the Connected Car platform Use Case Description 1 Continually rent out Program (Re-purchase/ Lease) Cars 2 Load balance mileage across Risk Cars 3 Incorporate customer usage into car assignment logic 4 Incorporate mileage optimization into one way car assignments Phase 1 focuses on Use Case #1 and Use Case #2
  • 33. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. The challenge is clear – vehicles are not being utilized as effectively as possible Vehicles that are underutilized based on vehicle age • Each point is a vehicle • Vehicles further from the slope and with a lower than optimized mileage require prioritization
  • 34. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Initial deployment will take place at the Avis Budget Group parking lot at Newark International Airport
  • 35. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. The model assigns vehicles based on mileage accrued in order to load balance vehicles Vehicles are placed in priority lanes to be washed, cleaned, and prepared for rental based on the model results
  • 36. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Our model development followed an agile, sprint based process Identify data fields required to build model Reservation Brand Reservation Status Booking Date Check In/Out Date Check In/Out Time Car Class Check In Location Rental Brand MVA # VIN # Expected CI/CO Time Length of Rental Fuel Reading Transform data into a usable and normalized state analysis Performing modeling in Amazon SageMaker • Integer Programming for Optimization • Regression (Load Balancing) Integrate model results into new Rental Application & Device Obtain feedback and implement changes in subsequent model iterations Fleet Vehicle Make & Model Vehicle Purchase Date Vehicle Delivery Date Vehicle Manufacturer Market Segment Indicator Vehicle Age
  • 37. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Mileage Optimization Machine Learning Architecture On Premise Cloud REST TLS 1.2/ HTTPS Integer Programming & Regression TLS 1.2/ HTTPS Key Points • Leverages Amazon’s Connected Vehicle Framework as a foundation and expands upon it for key use cases • Takes the modern architecture stack into consideration by including both on premise and AWS architecture • Designed for real time analytics and for operational efficiency
  • 38. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Mileage Optimization Machine Learning Architecture: On Premise Component Usage Operational Client Server & Databases • Feed mileage optimization engine and AWS components with transactional and operational data, including reservation, rental, and fleet data • Fleet, Reservation & Rental data will be fetched from Oracle Operational Database. • Java application would read data from MQ queue and write above data set to ActiveMQ setup in ABG Datacenter. Java application would also fetch Readyline data from IMS DB through a Omega service and store it as message on ActiveMQ. • ActiveMQ would be setup to synchronize with ActiveMQ on AWS. Omega Service • Data will be synced with the AWS environment via synchronous API Calls
  • 39. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Mileage Optimization Machine Learning Architecture: Data Processing Component Usage Amazon API Gateway • The station operator scans barcode on vehicle. This triggers invocation of new Omega service. • Omega service then invokes Private API on Amazon API Gateway. Device_Id & Location_Id are sent to this Private API. • API Gateway invokes Lamba function AWS Lambda • Receives data inputs from API and logs request details in Amazon S3 (future model analysis) • Queries Postgres operational data store and retrieves Fleet and Reservation information for that particular location Invocation and process will occur on a near-real time basis in order to ensure that Avis Budget Group front line employees are able to obtain optimized mileage results on an hourly basis
  • 40. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Mileage Optimization Machine Learning Architecture: Machine Learning Cloud Integer Programming & Regression Component Usage Lambda • Invokes Amazon SageMaker endpoint and sends input data • Receives optimized result from Amazon SageMaker • Stores response in Amazon S3 bucket ( for future model analysis) • Sends response back to calling API Amazon SageMaker • Imports relevant Python libraries • Generates supply and demand for the specified time horizon • Incorporates upgrade and substitution logic • Simulate slope and average miles per day (MPD) • Calculates “ideal” mileage for any particular vehicle • Calculates ideal vs actual ratio
  • 41. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. The model takes key operational components into consideration for deployment Feature Description Cars on Readyline Rentable cars that are already parked in the Readyline Demand Horizon Helps determine if there is a demand (reservation) for a particular car class in the next horizon (particular number of hours) of time Primary vs. Exclusive The cars are divided into two (2) cohorts, where substitutions can happen within a cohort. Exclusive Cars by Class Demand for an exclusive car class can only be satisfied by that car class. Substitution Demand for a primary class car can be satisfied by other Primary class cars. Contention Satisfying a reservation with an upgrade car class if a better car is available.
  • 42. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 43. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Dashboards powered by Uber’s deck.gl Geolocation analysis of intra-lot movements, and details associated with those movements
  • 44. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Dashboards powered by Uber’s deck.gl Geofenced location and identification of a set of vehicles within that geofence
  • 45. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. What is next?
  • 46. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 47. Thank you! © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 48. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.