Monitoring Electrical Power Consumption with Kieker 9 th Symposium - - PowerPoint PPT Presentation

monitoring electrical power consumption with kieker
SMART_READER_LITE
LIVE PREVIEW

Monitoring Electrical Power Consumption with Kieker 9 th Symposium - - PowerPoint PPT Presentation

Monitoring Electrical Power Consumption with Kieker 9 th Symposium on Software Performance 2018 Sren Henning, Kiel University Todays Industrial Production Environments Industrial Internet of Things Monitoring Production Environments


slide-1
SLIDE 1

Monitoring Electrical Power Consumption with Kieker

Sören Henning, Kiel University

9th Symposium on Software Performance 2018

slide-2
SLIDE 2

Today‘s Industrial Production Environments

Industrial Internet

  • f Things
slide-3
SLIDE 3

Monitoring Production Environments

slide-4
SLIDE 4

Printer 2 Fan 1 Server 2 Printer 1 Server 1

Requirements for a Monitoring Infrastructure

Monitoring Integration Analysis Visualization

Computing Printing Cooling

slide-5
SLIDE 5

Architectural Requirements

Horizontal Scalability Real-Time Data Processing Extendability & Flexibility for different-sized production environments and varying loads for immediate reactions and continuous evaluation for integration of different formats, protocols and metrics

slide-6
SLIDE 6

Architecture

<<microservice>> Record Bridge <<microservice>> Configuration <<microservice>> History <<messaging system>> Asynchronous Event Exchange Visualization <<web browser>> Visualization Frontend <<web server>> Visualization Backend <<database>> Time Series Storage <<database>> Key-Value Store <<application>> History Logic <<application>> Configuration Logic <<application>> Record Bridge Logic

slide-7
SLIDE 7

Messaging System

Deployment Architecture

/

Record Bridge A Configuration History Record Bridge C Record Bridge B Sensors Type A Sensors Type B Sensors Type C

slide-8
SLIDE 8

Architecture

<<microservice>> Record Bridge <<microservice>> Configuration <<microservice>> History <<messaging system>> Asynchronous Event Exchange Visualization <<web browser>> Visualization Frontend <<web server>> Visualization Backend <<database>> Time Series Storage <<database>> Key-Value Store <<application>> History Logic <<application>> Configuration Logic <<application>> Record Bridge Logic

slide-9
SLIDE 9

Implementation

<<microservice>> Record Bridge <<microservice>> Configuration <<microservice>> History Visualization

slide-10
SLIDE 10

Defining Record Types

Instrumentation Record Language

package titan.ccp.models.records entity ActivePowerRecord { string identifier long timestamp double valueInW // Watts }

slide-11
SLIDE 11

Transmitting & Storing Records

Existing Readers & Writers

slide-12
SLIDE 12

Hierarchical Model of Consumer for Aggregation

Computing Printing Cooling Factory Server 1 Server 2 Power Supply 1 Printer 1 AC System Fan 1 Power Supply 2 AC 1 AC 2

slide-13
SLIDE 13

Continuous Aggregation with Kafka Streams

Kafka Topic

aggregated- records

Kafka Topic

records

flatMap

by copying

groupByKey

for repartitioning to internal Kafka topic

aggregate

with history

map

to records

slide-14
SLIDE 14

Web-based Visualization

slide-15
SLIDE 15
slide-16
SLIDE 16

Pilot Deployment

medium-sized enterprise • part of the data center 16 servers • powered by 3 PDUs • over a period of 3 weeks

slide-17
SLIDE 17

Conclusions

Infrastructure for monitoring, aggregation & visualization Scalable & extendable architecture Implementation of a prototype

Future Work

Further consumption, production & business metrics Advanced analyses and visualizations Correlate power consumption with performance

slide-18
SLIDE 18
slide-19
SLIDE 19
slide-20
SLIDE 20
slide-21
SLIDE 21
slide-22
SLIDE 22

Continuous Aggregation Method

slide-23
SLIDE 23

Continuous Aggregation with Kafka Streams