Internet of Things (IoT) is a pervasive technology covering many applications areas (Smart Mobility, Smart Industry, Smart Healthcare, Smart Building, etc.). Its success and the technology evolution allow targeting more complex and critical applications such as the management of critical infrastructures and cooperative service robotics, which requires real time operation and a higher level of intelligence in the monitoring-control command for decision-making. Furthermore, these applications type need to be fully validated in advance considering that bugs discovered during real operation could cause significant damages. In order to avoid these drawbacks, IoT developers and system integrators need advanced tools and methodologies. This paper presents a methodology and a set of tools, defined and developed in the context of the BRAIN-IoT European Union (EU) project. The overall framework includes both Open semantic models to enforce interoperable operations and exchange of data and control features; and Model-based development tools to implement Digital Twin solutions to facilitate the prototyping and integration of interoperable and reliable IoT system solutions. After describing the solution developed, this paper also presents concrete use cases based on the two critical systems mentioned above, leveraging the application scenarios used to validate the concepts developed and results obtained by the BRAIN-IoT project.

1. Location, DD/MM/YYYYPresentation Title
1

2. 2
CHALLENGES IN NEXT GENERATION IOT SYSTEMS
• More complex scenarios that
involves the cross IoT
platforms/device communication
• IoT systems management
and monitoring becoming harder
• Complexity of IoT
applications development
increased dramatically
• Cost-efficient requirement and
physical constraints on IoT System
validation
A Model-Based Engineering (MBE) approach to ease
the development of the IoT systems offering:
• Three abstraction layer modeling methodology
• IoT service composition supporting
interoperability among heterogenous systems
• Formal verification and validation of the models
• The automatic code generation
• Co-simulation approach with the mixed
virtual and real entities runtime
IoT applications monitoring
Challenges to Contributions

3. 3
BRAIN-IOT MODELING METHODOLOGY
System-level models
Software-level models
IoT Physical-level models
high
low
Three modeling abstraction layer

4. 4
BRAIN-IOT MODELING & VALIDATION FRAMEWORK

5. 5
FRAMEWORK IMPLEMENTATION
IoT-ML model
(system level)
BIP model
(software level)
SensiNact data model
(monitoring & control)
Metadata generationCode generation
Thing
Description
software
BRAIN-IoT Repository
Embedded
software
Connectivity
Cortex M4
STM32
Sensor
IoT physical
models

6. 6
USE CASE 1: SERVICE ROBOTIC
Goal: The carts in the load area
should be transferred to the storage
area by the Robots passing through
an automated door.
1. Door and carts are with the QR
code attached.
2. Robots are equipped with vision
cameras that allow the QR codes they
find.

7. 7
USE CASE 1：SERVICE ROBOTIC SYSTEM MODELS
BIP
model Java code
generator
Orchstror.java
Door.java
Robot.java
Orchstror.java
Door.java
Robot.java
IoT-ML system model
Wrapping
Model @ Runtime
Easy-development
Robot runtime status monitoring
- Warehouse runtime map coordinates monitoring
- Dynamic control of the robot numberin a fleet
OSGi bundles dynamic deployment

8. 8
USE CASE 2: CRITICAL WATER INFRASTRUCTURE MANAGEMENT
Goal: Develop an adaptive, smart automatic
controllable management system, leveraging
prediction models to:
1. Increase the security of water supplies
2. Optimize the underlaying cost
3. More accurate indicators for
decision making, real-time, smart and
adaptive control procedures

9. 9
USE CASE 2：CRITICAL WATER INFRASTRUCTURE MANAGEMENT
Anomalies detection
Modeled IoT devices
Control System
IoT devices
monitoring
resilience
control
enables the IoT digital twin solution
- generating a huge amount of data with simulated models and reduce the cost of the
physical devices.
allows adaptive behaviors in a critical environment
- implemented as a BRAIN-IoT system model to automatically react abnormal situation.
provides a user-friendly tool to visualize the runtime states of the critical devices
- the states of the valves and pumps can be supervised from the sensiNact Studio.
System modelsMachine Learning technology
1
2
3
1
2
3

10. 10
TAKE HOME MESSAGE
A Model based Methodology and Framework has been developed for the next
generation IoT systems:
• System-level model, which captures the system functionalities and behaviors to
help refinementof the software-layermodelling;
• Linking towards real devices and external services through meta-data
representation in WoT TD;
• The application code is generated from model for
monitoring and controlling the IoT infrastructure;
• System application validation leveraging the simulated
IoT devices developed with the BRAIN-IoT physical layer modeling language;
• Monitor the IoT system behaviours and its configurations in a human-friendly
graphical manner through the Models@Runtime approach at the execution
time.

11. CONTACTS
This project has received funding from the European Union’s Horizon 2020 research
and innovation programme under grant agreement No 780089.
Researcher
xu.tao@linksfoundation.com
LINKS Foundation – Leading Innovation & Knowledge for Society
CONTACT
XU TAO