The session was about open architecture using IoT Edge, Azure Cognitive Services, Mosquitto MQTT, Influx DB and GraphQL web services to develop advanced architecture for early detection of forest fires that integrates sensor networks and mobile (drone) technologies for data collection and processing. Unmanned air vehicles (UAVs) will allow coverage of larger areas to raise the percentage of forest fires detections, monitor areas with high fire weather index and such already affected by forest fires. All information is forwarded and stored in cloud computing platform where near real-time processing and alerting is performed.

1. Advanced Open IoT Platform
for Prevention and Early
Detection of Forest Fires
Ivelin Andreev
March 27-29, 2018 (Naples, Italy)
1

2. 2
About me
Software Architect @
16+ years professional experience
Microsoft Azure MVP
External Expert Horizon 2020
External Expert Eurostars-Eureka & IFD
Business Interests
Web Development, SOA, Integration
IoT, Machine Learning
Security & Performance Optimization
Contact
ivelin.andreev@icb.bg
www.linkedin.com/in/ivelin
www.slideshare.net/ivoandreev

3. Agenda
Objectives
Platform Benefits
Platform Overview
State of the Art
Validation
3

4. Objectives
 Early detection of forest fires
 Open and interoperable
 Wide range of interfaces, protocols and devices
 Existing Crisis Management Systems (National, EU-level)
 Continuous monitoring of disaster related data
 Retrospective disaster assessment
 New methods for fire detection (AI, drones, sensors)
 Command devices in surrounding area (i.e. barriers)
 Automatic processing and alert generation
 Decision making support
 Cost efficient monitoring
4

5. Platform Benefits
 Open source and free license components
 Deployment on-premises and public cloud
 Adaptable – multiple abstraction points
 Cutting edge technologies
 AI, Machine Learning, Time Series data, Drones support
 High performance
 30’000+ simultaneous agents/things on node, 1M sensor parameters
 Built with security in mind
 TRL 6 (test in relevant environment)
With sensors, thermal cameras and state of the art AI algorithms,
the platform aims to combine the best approaches
and achieve 10% better fire assessment and prevention.
5

6. 6
ASPires
Distributed & Open
IoT Platform
Funded by
EUROPEAN CIVIL PROTECTION AND
HUMANITARIAN AID OPERATIONS
ECHO/SUB/742906/PREV03 (ASPIRES)

7. Ingestion Scope
 Field gateway (On-premises)
 Local aggregation point for range of sensors (on-site, drone mounted)
 Features: Device specific protocol conversion (i.e. Lora-Modbus TCP)
 Cloud gateway (On-premises)
 Cross-platform SW gateway based on Azure IoT Edge with 2-way communication
 Features: Buffering, Processing, Protocol adapters (i.e. Profinet, Profibus, OPC, ZigBee…)
 Ingestion hub
 Entry point of the cloud platform (MQTT broker)
 Features: Secure 2-way communication over MQTT and HTTP
7

8. Cloud Scope
 Stream Processor
 Real-time data simple analytics (i.e. threshold, anomaly detection, data conversion)
 Features: Device specific protocol conversion (i.e. Lora-Modbus TCP)
 Data Persisters
 Data storage engine abstraction (RDBMS, Time Series)
 Features: Read/Write operations on persistence storage
 Data Storage
 Asset Configuration, Raw Data, Time Series Data
 Features: Performance (40x-60x faster than SQL and NoSQL) and TS data functions
 Analyzer services
 Generic and specific pluggable custom logic components
 Features: Asynchronous data processing 8

9. Consumer Scope
 Platfrom Micro-services
 Open format scalable APIs (GraphQL)
 Features: Identity Management, Data Retrieval & Manipulation, Alerts
 Configuration Portal
 Web application with limited access (i.e. organization administrators)
 Features: Platform configuration and asset management (i.e. GW, sensors, users)
 Presentation and Visualization
 Mobile apps, Web apps, Hybrid apps
 Features: Responsive, administration, dashboarding
 Third Party Platform Integration
 Crisis Management Systems, Recourse Management
 Features: Raw data, trends, analytics and alerts visualization
9

10. State of the Art
10

11. Drone Support
 Complement other infrastructure (i.e. towers)
 Rapid deployment almost anywhere
 Sensor data collection (fixed, mobile)
 Visual image and thermography
 Near real-time transmission
 Low cost
 Protocols (ZigBee, WiFi, 3G/4G)
11

12. Computer Intelligence
 Seas of data are generated by sensors
 How to gain insight on hidden relations?
 How to get actionable results?
 How to make platform provide business value?
 Open issues
 Cameras are diagnostic and not predictive approach
 Thermal cameras cannot detect fire behind hills
 FWI is not able to model hidden relations and thresholds
 Human operators are required
12

13. Computer Vision (Positive Sample)
13
 Computer intelligence and computer vision could be used for
automated alerting for camera capture
 Works on predefined description tags
 Less operators could control larger area

14. Computer Vision (Negative Sample)
14
 Computer vision can process low resolution images (VGA)
 Computer vision is capable to distinguish clouds from smoke
 Alerts could be raised based on confidence level

15. Forest Fire Prediction ML Model
15
 ML model could be used for prediction of
fire state with certain confidence level
 Model features are result of in-depth
analysis of other crisis management systems
 Model consumed as web service from Azure
(ML Studio & Azure Experimentation Service)

16. Platform Openness
 Open source technologies
 Azure IoT Edge
 Influx DB
 Mosquitto MQTT
 Open protocols
 Inbound & Outbound Interfaces
 Data & Alerts Services
 CMS Systems: EFFIS, MKFFIS
16

17. Validation
17

18. Validation Setup
InfluxDB v1.3.0 single node SQL Server 2016 Standard
CPU: Intel Core i7 3.40GHz (quad, 8MB cache)
Memory: 16GB DDR3 1333MHz
OS: Windows 10 Enterprise, 64 bit
SSD: Samsung 850 EVO 250GB
HDD: Seagate 7200RPM, 16MB cache, 500GB
Name Type Indexed
ID (PK) int Yes
TagID int Yes
Value int No
Timestamp DateTime Yes
Name Type
tagID Int Tag Key
value Int Field Key
time DateTime TimeStamp
InfluxDB schema: SQL Server schema:

19. Write Performance (writes/sec)
0
50000
100000
150000
200000
250000
0 20,000,000 40,000,000 60,000,000 80,000,000 100,000,000
Influx
Insertspersecond
• Influx average write speed of 200,000 writes/second
• SQL Server average write speed of 5,000-8,000 writes/second
• Memory optimized tables increases write performance by 1.4x
• Write trend unaffected by the amount of data (in this volumes)
• Influx outperforms SQL Server 40x
0
1000
2000
3000
4000
5000
6000
7000
8000
9000
0 20,000,000 40,000,000 60,000,000 80,000,000 100,000,000
SQL In-Memory OLTP

20. Disk Storage
• 27% improvement is SQL Server page compression is enabled (1883MB)
• Influx has 19x-26x less disk requirements for the same functionality
2579MB
98MB
0
500
1000
1500
2000
2500
3000
On-Disk Storage
SQL Server
Influx
DiskSpaceUsed(megabytes)DiskSpaceUsed(megabytes)

21. Read Performance (queries/sec)
0
500
1000
1500
2000
2500
3000
3500
4000
1 2 4 8
InfluxDB
SQL Server
QueriesperSecond
Concurrency
Benchmark query:
Aggregate samples of 10,000 points, average over 1,000 runs.
• SQL Server mean query response time – 78ms (13 queries/sec)
• Influx mean query response time – 1,3ms (769 queries/sec)
• Influx has 59x better query throughput than SQL Server

22. Read Performance (rows at a time)
• SQL Server relatively unaffected by SSD (due to caching)
• Influx performance improves up to 100% on SSD, chunk size 10’000
• SQL Server is up to 2x better on HDD (Influx is better up to 600K)
• Relatively equal on SSD (Influx is better up to 1.6M)
0
500,000
1,000,000
1,500,000
2,000,000
2,500,000
3,000,000
3,500,000
0 5 10 15 20 25 30
HDD Performance
SQL Influx
Queriedresults
Seconds to execute (lower is better)
0
500,000
1,000,000
1,500,000
2,000,000
2,500,000
3,000,000
3,500,000
0 5 10 15 20 25 30
SSD Performance
SQL Influx
Seconds to execute (lower is better)

23. Thank You!
23