Bde sc3 2nd_workshop_2016_10_04_p05_bde_system_monitoring

16
Big Data Europe System Monitoring: Data acquisition challenge BigDataEurope 2nd SC3 Workshop, Brussels 4/10/16 4-oct.-16 D. Foussekis, F. Mouzakis (CRES)

Transcript of Bde sc3 2nd_workshop_2016_10_04_p05_bde_system_monitoring

Page 1: Bde sc3 2nd_workshop_2016_10_04_p05_bde_system_monitoring

Big Data EuropeSystem Monitoring: Data acquisition challenge

BigDataEurope 2nd SC3 Workshop, Brussels 4/10/164-oct.-16

D. Foussekis, F. Mouzakis (CRES)

Page 2: Bde sc3 2nd_workshop_2016_10_04_p05_bde_system_monitoring

BigDataEurope 2nd SC3 Workshop, Brussels 4/10/16System monitoring p.2

General requirements in System monitoring Modular distributed system using standard Ethernet network.

Specs compliant with International Standards.

Robust and reliable for 24/7 standalone non-stop operation.

Scalable and reconfigurable.

Time Synchronization across all modules (GPS or Master module).

Embedded processing capabilities.

Send notifications and alarms.

Data storagewww.big-data-europe.eu

Page 3: Bde sc3 2nd_workshop_2016_10_04_p05_bde_system_monitoring

BigDataEurope 2nd SC3 Workshop, Brussels 4/10/16System monitoring p.3

Typical DAQ system core component (1/2) NI-CompactRIO platform http://www.ni.com/compactrio/

Designed for harsh environments-20º to -55ºC temperature, 5grms vibration, 30g shock

Low power requirements~10W at 9-30V for battery powered standalone operation

Data acquisition based on FPGA hardware offering fast I/O response times and increased reliability

www.big-data-europe.eu

Source: NI.com

Page 4: Bde sc3 2nd_workshop_2016_10_04_p05_bde_system_monitoring

BigDataEurope 2nd SC3 Workshop, Brussels 4/10/16System monitoring p.4

Typical DAQ system core component (2/2) Various modules for Analogue I/O and Digital I/O

High precision (24-bit delta-sigma) A/D converters (s.g. modules)16-bit 100kHz Simultaneous Sampling AI modules.

XML - Configuration file

Raw (high speed) data sent over the Ethernet and stored on a NAS.

All data packets are time-stamped with common GPS or local time.

Backup storage on each module USB port, in case of network loss.

www.big-data-europe.eu

Source: NI.com

Page 5: Bde sc3 2nd_workshop_2016_10_04_p05_bde_system_monitoring

BigDataEurope 2nd SC3 Workshop, Brussels 4/10/16System monitoring p.5

Typical CMS configuration

www.big-data-europe.eu

. . .Gigabit Local Area Network (LAN)

Network Attached Storage (NAS)System Monitoring PC

Page 6: Bde sc3 2nd_workshop_2016_10_04_p05_bde_system_monitoring

BigDataEurope 2nd SC3 Workshop, Brussels 4/10/16System monitoring p.6

Distributed system

www.big-data-europe.eu

Photo: Courtesy of Vestas Wind Systems A/S

Tower (bending)Tower (torsion)

Electrical generator Gearbox

Blades

Page 7: Bde sc3 2nd_workshop_2016_10_04_p05_bde_system_monitoring

BigDataEurope 2nd SC3 Workshop, Brussels 4/10/16System monitoring p.7

Architecture

www.big-data-europe.eu

Real-Time microprocessor:• Runs a real-time OS (NI Linux Real-Time)• Communicates and uploads data• Performs statistical analysis• Stores and compresses raw data

FPGA microprocessor:• Acquires signals (analogue & digital I/O)• Runs without OS at high clock rates and no jitter• Executes different tasks with true parallelism• Performs low-level signal processing

(i.e.: filtering, control)• Assures non-stop operation

Source: NI.com

Page 8: Bde sc3 2nd_workshop_2016_10_04_p05_bde_system_monitoring

BigDataEurope 2nd SC3 Workshop, Brussels 4/10/16System monitoring p.8

Field-Programmable Gate Array (FPGA)

www.big-data-europe.eu

- Reconfigurable Hardware chip. - Analogous to a printed circuit board with unconnected components on it. - Connections in an FPGA circuit are dynamically defined in software.

Page 9: Bde sc3 2nd_workshop_2016_10_04_p05_bde_system_monitoring

BigDataEurope 2nd SC3 Workshop, Brussels 4/10/16System monitoring p.9

Example of FPGA implementation

www.big-data-europe.eu

Boolean operations (green lines) based on digital I/O (A,B,C,D,F) execute in parallel with math operations (orange lines) based on analogue I/O (W, X, Y, Z).

The compiler produces an optimized bitstreamfile, with all the routing paths, between millions of logic gates, memory blocks and I/O channels.

Page 10: Bde sc3 2nd_workshop_2016_10_04_p05_bde_system_monitoring

BigDataEurope 2nd SC3 Workshop, Brussels 4/10/16System monitoring p.10

Raw Data storage – Existing File Formats

www.big-data-europe.eu

ASCII files

Characteristics• Human-readable• Easily portable to other applications such as

Microsoft Excel

Considerations• Significantly larger disk footprint• Slow read and write

Page 11: Bde sc3 2nd_workshop_2016_10_04_p05_bde_system_monitoring

BigDataEurope 2nd SC3 Workshop, Brussels 4/10/16System monitoring p.11

Raw Data storage – Existing File Formats

www.big-data-europe.eu

Binary files

Characteristics• Compact file size• Fast streaming (read & write)

Considerations• Not human-readable• Not easily exchangeable

Page 12: Bde sc3 2nd_workshop_2016_10_04_p05_bde_system_monitoring

BigDataEurope 2nd SC3 Workshop, Brussels 4/10/16System monitoring p.12

Raw Data storage – Existing File Formats

www.big-data-europe.eu

XML files

Characteristics• Stores complex data structures• Shows display in a Web browser or in a text

editor

Considerations• Even larger disk footprint• Front-end schema design• Does not stream

Page 13: Bde sc3 2nd_workshop_2016_10_04_p05_bde_system_monitoring

BigDataEurope 2nd SC3 Workshop, Brussels 4/10/16System monitoring p.13

Raw Data storage – Existing File Formats

www.big-data-europe.eu

Database filesCharacteristics• Store data centrally• Organize and query test results with MySQL

or Access

Considerations• Time intensive startup effort• Requires maintenance• Potentially high cost

Page 14: Bde sc3 2nd_workshop_2016_10_04_p05_bde_system_monitoring

BigDataEurope 2nd SC3 Workshop, Brussels 4/10/16System monitoring p.14

Raw Data storage – Existing File Formats

www.big-data-europe.eu

Binary Structured (TDMS – NI Technical Data Management Technology)

Characteristics• Single streaming binary file• Three levels of hierarchy for better organization

File, groups, and channels• Customizable, descriptive properties at each level• User-defined Meta data for campaign properties

Considerations• Third party format

Page 15: Bde sc3 2nd_workshop_2016_10_04_p05_bde_system_monitoring

BigDataEurope 2nd SC3 Workshop, Brussels 4/10/16System monitoring p.15

File Format Comparison

www.big-data-europe.eu

Page 16: Bde sc3 2nd_workshop_2016_10_04_p05_bde_system_monitoring

BigDataEurope 2nd SC3 Workshop, Brussels 4/10/16System monitoring p.16

(Instead of) Conclusion

www.big-data-europe.eu

Ron MusickLead Researcher at Lawrence LivermoreNational Laboratory