The document outlines the advancements and specifications of Industry 4.0, emphasizing the transition to software-defined industrial systems and the importance of open-source solutions in creating intelligent factories. It highlights key components such as real-time flexibility, automated machine communication, and intrinsic security while detailing various projects and platforms contributing to this technological evolution. The content also includes legal disclaimers and encourages collaboration in the time-critical edge compute blueprint initiated by Akraino.

1. Shane Dewing
Snr. Director SW Strategy and Open Source
Industrial Solutions Division, Internet of Things Group
Photo: https://unsplash.com/@robin_sommer

2. 2
Legal Disclaimers
No license (express or implied, by estoppel or otherwise) to any intellectual property rights is granted by this document.
Intel disclaims all express and implied warranties, including without limitation, the implied warranties of merchantability,
fitness for a particular purpose, and non-infringement, as well as any warranty arising from course of performance, course
of dealing, or usage in trade.
This document contains information on products, services and/or processes in development. All information provided here
is subject to change without notice. Contact your Intel representative to obtain the latest forecast, schedule, specifications
and roadmaps.
The products and services described may contain defects or errors known as errata which may cause deviations from
published specifications. Current characterized errata are available on request.
Copies of documents which have an order number and are referenced in this document may be obtained by calling 1-800-
548-4725 or by visiting www.intel.com/design/literature.htm.
Intel, the Intel logo, are trademarks of Intel Corporation in the U.S. and/or other countries.
*Other names and brands may be claimed as the property of others
Copyright © 2017 Intel Corporation. All rights reserved.

3. 3
Industry 4.0 – The Intelligent Factory
 Real-time flexibility in software-defined production
lines without human interaction or process interruption
 Data-driven machine automation at high tolerance
levels
 Multi-way communication between all constituents in
the process
 Analytics that provide visibility into machine status to
predict and prevent problems
 Sensor-equipped wearables that boost worker
productivity and safety
 Open, fully interoperable systems at both the
control plane and the data plane
 Intrinsic, end-to-end security and safety
 Automated, software defined networking and
manageability
1784 1870 1969 Today
Steam
Simple mechanization
Electricity
Mass production,
assembly lines
Silicon based
microprocessors
Computers, electronics
The Automated Factory
Cyber Physical Systems
Internet of Things
Networking
The Intelligent Factory

4. 4
process
ShifttoSoftwareDefinedIndustrialSystems
Controller
Edge Compute
Platform
Advanced Control Platform
L1
•••
Controller
•••
•••
L2
SCADA
Historian
HMI
Engineering
Tools
Legacy
App
L3
App Server Analytics Workflow Historian
SoftPLC
Legacy
App Eng. Tools
Analytics
•••
Edge Compute
Platform
Real Time Bus
process
•••
Portable Workload
Open Platform
Virtual Environment
Proprietary Platform
Analytics
SofPLC
SofPLCSCADA
HMI
Fixed
Function
BECOMES
Portable
WorkloadGateway
Gateway
Firewall
Routing
SoftPLC
ISA95
layers
*Other names and brands may be claimed as the property of others

5. Open Source Landscape for Industry 4.0
OpenStack* Foundation Linux Foundation*
StarlingX*
Project
Software defined
infrastructure and
management
OpenStack
Project
kata containers
Project
Low latency, HA and
additional software
defined infrastructure
components
Open Source Robotics
Foundation
ROS2 project
(autonomous, FuSA, TSN,
distributed, connectivity, multi-
modal)
lightweight VM’s that
seamlessly plug into
the containers
ecosystem
Eclipse Foundation*
Eclipse IOT
Working Group
27+ projects
CoAP, DTLS, MQTT, ISO/IEC 15118, IEC 61499,
OMA LWM2M, oneM2M, OPC Unified Architecture
(UA), Production Performance Management
Protocol (PPMP), OGC SensorThings API
open62541
OPC-UA with
pub/sub
Xenomai
Siemens
Real-time
Linux
Haystack
Data
interoperability
OSADL
OPC-UA
over TSN
Open Container
Initiative*
Docker* project
Cloud Native Computing
Foundation*
Kubernetes*
project
EdgeX Foundry*
Project
Akraino Edge
Stack*
Project
Data Ingest and
Management
for
edge deployments
Integration project for
Carrier, Provider and
IOT networks. ETSI
MEC
ACRN
Project*
Real-time, safety
critical, lightweight
type 1 hypervisor
DPDK
Project
accelerate packet
processing
workloads
ONAP*
Project
real-time, policy-
driven orchestration
Zephyr*
Project
IoTivity*
Project
Yocto
Project*
custom embedded
linux distro’s
LF* Edge (GB + TAC)
Project EVE
Distributed edge-
cloud workload
management
(Zededa)
scalable RTOS for
safety critical
systems
reference
implementation of
OCF Spec
“Blueprint” solution
projects focused on
edge-cloud to far
edge use cases
Rancher
K3s –K8s
optimized for
edge
LF* Networking
OPNFV
Project
Network function
virtualization
*Other names and brands may be claimed as the property of others
OpenPLC
IEC 61131-3
runtime

6. 6
THINGS EDGE COMPUTE NETWORK CLOUD
IOT Endpoints
(IPCs, PLCs, Cameras)
Networked Appliances
(Gateways, Firewalls)
Private Cloud Servers
(Control, Insights)
Network Infrastructure
“Infrastructure-as-a –
Service”
Value –add IOT
Edge Platform Services
HW
Real-time + HA Inference
“Control-as-a-service”
CSP Connectors
HW
Value-add Gateway
Platform Services
Value-add Network
Platform Services
HW
End computing
devices
Internetworking
devices
Value-add
Apps & Services
“as-a-Service”
Connectors
Data Mngt, Analytics, ML/DL
“Platform-as-a-Service”
HW
Basic IT Endpoint Services
Value –add Edge Server
Platform Services
Compute + Storage +Network
Basic IT Infrastructure Services IT Services
Safety
Open Source
Akraino*
EdgeX Foundry*
StarlingX*
ACRN*
*Other names and brands may be claimed as the property of others<1ms 100ms 500ms >500ms

7. 7*Other names and brands may be claimed as the property of others
Source – Linux Foundation

8. 8*Other names and brands may be claimed as the property of others
Source – Linux Foundation

9. 9*Other names and brands may be claimed as the property of others
Source – Linux Foundation

10. 10*Other names and brands may be claimed as the property of others
Source – Linux Foundation

11. 11*Other names and brands may be claimed as the property of others
Source – Linux Foundation

12. 12
Sharing Mode
Partition Mode
*Other names and brands may be claimed as the property of others

13. 13
Hybrid Mode
*Other names and brands may be claimed as the property of others

14. 14*Other names and brands may be claimed as the property of others
Source – Linux Foundation

15. 15
Time-critical Edge Compute
blueprint
https://wiki.akraino.org/display/AK/Time-
Critical+Edge+Compute
*Other names and brands may be claimed as the property of others
Source – Linux Foundation

16. 16
CLOUDTHINGS EDGE COMPUTE NETWORK
IOT Endpoints
(IPCs, PLCs, Cameras)
Networked Appliances
(Gateways, Firewalls)
Private Cloud Servers
(Control, Insights)
“Infrastructure-as-a –
Service”
Value –add IOT
Edge Platform Services
HW
Real-time + HA
Control-as-a-service
CSP Connectors
HW
Value-add Gateway
Platform Services
Value-add Network
Platform Services
HW
End computing
devices
Internetworking
devices
Value-add
Apps & Services
“as-a-Service”
Connectors
Network Infrastructure
Data Mngt + Analytics
“Platform-as-a-Service”
HW
Basic IT Endpoint Services
Value –add Edge Server
Platform Services
Compute + Storage +Network
Basic IT Infrastructure Services IT Services
Safety
<1ms 100ms 500ms >500ms *Other names and brands may be claimed as the property of others

17. 17
Time-critical Edge Compute Blueprint:
Use Cases
• Use cases in Manufacturing, Smart Buildings, general IIOT
• Virtualized PLC
• Computer vision inference
• Machine, sensor data inference
• Process or discrete manufacturing closed loop control
• Ethernet TSN
• Functional Safety capable use cases
• Discrete manufacturing soft PLC
• Onramp for 5G-URLLC
*Other names and brands may be claimed as the property of others
Source – Linux Foundation

18. Time-critical Edge Compute Blueprint: Base Architecture
18
Open Source and
Functionally Safe capable
Open Source
Open Source or
potentially proprietary
*Other names and brands may be claimed as the property of others
Hardware Platform
ACRN*
Kata, Docker*
Service/Guest OS (Linux*,
Windows*, Android*)
Zephyr*
SafetyOS
TC and Quality Managed
Workloads e.g. EdgeX Foundry*,
OpenPLC.org
DPDK
TC/Safe
workloads
Ethernet TSN
OSADL / OPC-UA over TSN
Open62541.org
5G NR (URLLC)

19. 19
Time-critical Edge Compute Blueprint:
Workloads
Sample workloads include:-
• TensorFlow* via Kubeflow
• OpenVINO™ Toolkit for Video and Inference
• Closed loop control (e.g. IEC 61131-3 function blocks)
• EdgeX Foundry*
• Building automation controller
*Other names and brands may be claimed as the property of others
Source – Linux Foundation

20. 20
SW Contributors
• Intel
• IOTech
• Huawei
• WiPro
Hardware Contributors
• Dell (x86), HPE (x86), Huawei (ARM)
Time-critical Edge Compute Blueprint
*Other names and brands may be claimed as the property of others
Source – Linux Foundation

21. 21
Summary and Call To Action…
• Industry 4.0 is driving software defined and cloud native at the
Industrial manufacturing edge
• Exciting open source consolidation underway at LF Edge*
• Come join us in the Time-Critical Edge Compute blueprint at Akraino*
– https://wiki.akraino.org/display/AK/Time-Critical+Edge+Compute
*Other names and brands may be claimed as the property of others

22. 22
Legal Disclaimers
No license (express or implied, by estoppel or otherwise) to any intellectual property rights is granted by this document.
Intel disclaims all express and implied warranties, including without limitation, the implied warranties of merchantability,
fitness for a particular purpose, and non-infringement, as well as any warranty arising from course of performance, course
of dealing, or usage in trade.
This document contains information on products, services and/or processes in development. All information provided here
is subject to change without notice. Contact your Intel representative to obtain the latest forecast, schedule, specifications
and roadmaps.
The products and services described may contain defects or errors known as errata which may cause deviations from
published specifications. Current characterized errata are available on request.
Copies of documents which have an order number and are referenced in this document may be obtained by calling 1-800-
548-4725 or by visiting www.intel.com/design/literature.htm.
Intel, the Intel logo, are trademarks of Intel Corporation in the U.S. and/or other countries.
*Other names and brands may be claimed as the property of others
Copyright © 2017 Intel Corporation. All rights reserved.

25. Collapsing of
Capabilities at the Edge
CONSOLIDATION of traditional industrial functions PLUS
integration of NEW use cases at the edge, without
compromising the operational mission
Edge
Compute
Platform
Intrinsic
Security
Real Time
Analytics
Machine
Vision
Autonomous
Learning
Orchestration
•••
Open Source/
Interoperability
ISA95 Picture credit to Dennis Brandl & Peter Owen
IT-like
Management

26. Pneumatic
Controller
Pneumatic
Controller
Electronic
Controller
Electronic
Controller
DCN
Digital
Controller
Central
Computer
…
Electronic
Controller
Pneumatic
Controller
Supervisory
Control
Operator
HMI
Operator
HMI
Process
Historian
Digital
Controller
…
Central
Computer
General
Computing
Virtualized
System
DCN
Distributed
Control
Node
L3
L1
Control
Control, HMI
& Historian
1920
Reliability
& speed
History, networking,
flexible configuration,
smaller HMI footprint, &
wiring cost
1959 1970s 1980s
Stability &
productivity
2020
L1: High-capacity multi-function
controllers w/HART
1 1 8
100
# control
loops
L2
L1
low-cost scalability & replacement, access to
leading edge performance, app portability,
integration of best-in-class components, market
for 3rd party software
High-availability, real-
time data center
Single-channel,
modular,
distributed, edge
device
Computer
Gateway
Operator
HMI
Process
Historian
Digital
Controller
…
1000
L1
App
Server
App
Server
Supervisory
Control
App
Server
App Market Liquidity
& Sophisticated
Development Tools
Real-Time,
Deterministic
& Reliable
2000s
L1: function blocks, sequence control
& self-diagnostics
L2: scalability/availability
Open
L3: access to COTS technology
L3: Low-cost servers
MPC,
Historians
L2
Proprietary
Open
L2
L3
Evolution of the Industrial Control System
The ascent of automation
Source:
*Other names and brands may be claimed as the property of others