big data in power systems - tcipgbig data in power systems kenta kirihara and kevin larson ......

15
TRUSTWORTHY CYBER INFRASTRUCTURE FOR THE POWER GRID | TCIPG.ORG UNIVERSITY OF ILLINOIS | DARTMOUTH COLLEGE | UC DAVIS | WASHINGTON STATE UNIVERSITY FUNDING SUPPORT PROVIDED BY DOE-OE AND DHS S&T 1 BIG DATA IN POWER SYSTEMS KENTA KIRIHARA AND KEVIN LARSON 11/21/2014 UNIVERSITY OF ILLINOIS

Upload: others

Post on 28-May-2020

0 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: BIG DATA IN POWER SYSTEMS - TCIPGBIG DATA IN POWER SYSTEMS KENTA KIRIHARA AND KEVIN LARSON ... COMPANIES WORKING WITH BIG DATA . 1. IBM 2. HP 3. EMC 4. Teradata 5. Oracle 6. SAP 7

TRUSTWORTHY CYBER INFRASTRUCTURE FOR THE POWER GRID | TCIPG.ORG

UNIVERSITY OF ILLINOIS | DARTMOUTH COLLEGE | UC DAVIS | WASHINGTON STATE UNIVERSITY FUNDING SUPPORT PROVIDED BY DOE-OE AND DHS S&T 1

BIG DATA IN POWER SYSTEMS

KENTA KIRIHARA AND KEVIN LARSON

11/21/2014

UNIVERSITY OF ILLINOIS

Page 2: BIG DATA IN POWER SYSTEMS - TCIPGBIG DATA IN POWER SYSTEMS KENTA KIRIHARA AND KEVIN LARSON ... COMPANIES WORKING WITH BIG DATA . 1. IBM 2. HP 3. EMC 4. Teradata 5. Oracle 6. SAP 7

TRUSTWORTHY CYBER INFRASTRUCTURE FOR THE POWER GRID | TCIPG.ORG

OUTLINE

1. What is Big Data? 2. Companies working with Big Data 3. Examples of Big Data in Power System 4. Human Perception 5. Example Solutions in Power System 6. General Strategies/Solution 7. General Big Data Analysis 8. Challenges 9. Cloud Computing

Page 3: BIG DATA IN POWER SYSTEMS - TCIPGBIG DATA IN POWER SYSTEMS KENTA KIRIHARA AND KEVIN LARSON ... COMPANIES WORKING WITH BIG DATA . 1. IBM 2. HP 3. EMC 4. Teradata 5. Oracle 6. SAP 7

TRUSTWORTHY CYBER INFRASTRUCTURE FOR THE POWER GRID | TCIPG.ORG

WHAT IS BIG DATA?

We need a volunteer!

Page 4: BIG DATA IN POWER SYSTEMS - TCIPGBIG DATA IN POWER SYSTEMS KENTA KIRIHARA AND KEVIN LARSON ... COMPANIES WORKING WITH BIG DATA . 1. IBM 2. HP 3. EMC 4. Teradata 5. Oracle 6. SAP 7

TRUSTWORTHY CYBER INFRASTRUCTURE FOR THE POWER GRID | TCIPG.ORG

WHAT IS BIG DATA?

Big Data

Volume

Velocity

Variety

Variability

Presenter
Presentation Notes
-Data with large volume -Variability (changes a lot, uncertainty) -Velocity (streams at a fast rate) - Variety Reference: http://www.sas.com/en_us/insights/big-data/what-is-big-data.html
Page 5: BIG DATA IN POWER SYSTEMS - TCIPGBIG DATA IN POWER SYSTEMS KENTA KIRIHARA AND KEVIN LARSON ... COMPANIES WORKING WITH BIG DATA . 1. IBM 2. HP 3. EMC 4. Teradata 5. Oracle 6. SAP 7

TRUSTWORTHY CYBER INFRASTRUCTURE FOR THE POWER GRID | TCIPG.ORG

COMPANIES WORKING WITH BIG DATA

1. IBM 2. HP 3. EMC 4. Teradata 5. Oracle 6. SAP 7. Microsoft 8. Amazon 9. Vmware 10.Google

Presenter
Presentation Notes
http://www.datamation.com/applications/30-big-data-companies-leading-the-way-1.html
Page 6: BIG DATA IN POWER SYSTEMS - TCIPGBIG DATA IN POWER SYSTEMS KENTA KIRIHARA AND KEVIN LARSON ... COMPANIES WORKING WITH BIG DATA . 1. IBM 2. HP 3. EMC 4. Teradata 5. Oracle 6. SAP 7

TRUSTWORTHY CYBER INFRASTRUCTURE FOR THE POWER GRID | TCIPG.ORG

SYNCHROPHASORS

Each PMU ~100GB/year

Page 7: BIG DATA IN POWER SYSTEMS - TCIPGBIG DATA IN POWER SYSTEMS KENTA KIRIHARA AND KEVIN LARSON ... COMPANIES WORKING WITH BIG DATA . 1. IBM 2. HP 3. EMC 4. Teradata 5. Oracle 6. SAP 7

TRUSTWORTHY CYBER INFRASTRUCTURE FOR THE POWER GRID | TCIPG.ORG

SMART METERS/AMI

Sensor

Sensor

Sensor

Sensor

Control Center

Page 8: BIG DATA IN POWER SYSTEMS - TCIPGBIG DATA IN POWER SYSTEMS KENTA KIRIHARA AND KEVIN LARSON ... COMPANIES WORKING WITH BIG DATA . 1. IBM 2. HP 3. EMC 4. Teradata 5. Oracle 6. SAP 7

TRUSTWORTHY CYBER INFRASTRUCTURE FOR THE POWER GRID | TCIPG.ORG

HUMAN PERCEPTION: THE LIMITING REAGENT

“The Magical Number Seven, Plus or Minus Two: Some Limits on Our Capacity for Processing Information” Information from Big Data Analytics should aim to take information to this level.

Grouping

Page 9: BIG DATA IN POWER SYSTEMS - TCIPGBIG DATA IN POWER SYSTEMS KENTA KIRIHARA AND KEVIN LARSON ... COMPANIES WORKING WITH BIG DATA . 1. IBM 2. HP 3. EMC 4. Teradata 5. Oracle 6. SAP 7

TRUSTWORTHY CYBER INFRASTRUCTURE FOR THE POWER GRID | TCIPG.ORG

GOAL OF BIG DATA

Take complex information……

Then present it in a way that can be understood!

Page 10: BIG DATA IN POWER SYSTEMS - TCIPGBIG DATA IN POWER SYSTEMS KENTA KIRIHARA AND KEVIN LARSON ... COMPANIES WORKING WITH BIG DATA . 1. IBM 2. HP 3. EMC 4. Teradata 5. Oracle 6. SAP 7

TRUSTWORTHY CYBER INFRASTRUCTURE FOR THE POWER GRID | TCIPG.ORG

EXAMPLE SOLUTION #1: VISUALIZATION

Voltage Gradient

A

V

Playback

Real-time

Page 11: BIG DATA IN POWER SYSTEMS - TCIPGBIG DATA IN POWER SYSTEMS KENTA KIRIHARA AND KEVIN LARSON ... COMPANIES WORKING WITH BIG DATA . 1. IBM 2. HP 3. EMC 4. Teradata 5. Oracle 6. SAP 7

TRUSTWORTHY CYBER INFRASTRUCTURE FOR THE POWER GRID | TCIPG.ORG

EXAMPLE SOLUTION #2: EVENT DETECTION

Atypical Events Captured: double capacitor bank switching (left) and tap changer switching (right)

Page 12: BIG DATA IN POWER SYSTEMS - TCIPGBIG DATA IN POWER SYSTEMS KENTA KIRIHARA AND KEVIN LARSON ... COMPANIES WORKING WITH BIG DATA . 1. IBM 2. HP 3. EMC 4. Teradata 5. Oracle 6. SAP 7

TRUSTWORTHY CYBER INFRASTRUCTURE FOR THE POWER GRID | TCIPG.ORG

HANDLING BIG DATA • Making sense requires computation – often

lots of it.

• How to organize and distribute that computation is still a challenging subject

• Hadoop • Open source implementation of

MapReduce • Lots of research

Page 13: BIG DATA IN POWER SYSTEMS - TCIPGBIG DATA IN POWER SYSTEMS KENTA KIRIHARA AND KEVIN LARSON ... COMPANIES WORKING WITH BIG DATA . 1. IBM 2. HP 3. EMC 4. Teradata 5. Oracle 6. SAP 7

TRUSTWORTHY CYBER INFRASTRUCTURE FOR THE POWER GRID | TCIPG.ORG

HADOOP

How do we break data into pieces and send them to computers? Map – filtering and sorting Reduce – summary operation Example – word count Maps – sort clusters of words Recudes – count instances of words

Page 14: BIG DATA IN POWER SYSTEMS - TCIPGBIG DATA IN POWER SYSTEMS KENTA KIRIHARA AND KEVIN LARSON ... COMPANIES WORKING WITH BIG DATA . 1. IBM 2. HP 3. EMC 4. Teradata 5. Oracle 6. SAP 7

TRUSTWORTHY CYBER INFRASTRUCTURE FOR THE POWER GRID | TCIPG.ORG

HADOOP 1.X

Pig Tasks

HIVE Tasks

Custom Map Reduce Jobs

1. Generated MR Job 1 • 50 Map Tasks • 20 Reduce Tasks

2. 1’s Output + Generated MR Jobs 2 • 12 Maps • 3 reducers

Comp 1

Comp 2

Comp n

Animation Courtesy: Read Sprabery

Page 15: BIG DATA IN POWER SYSTEMS - TCIPGBIG DATA IN POWER SYSTEMS KENTA KIRIHARA AND KEVIN LARSON ... COMPANIES WORKING WITH BIG DATA . 1. IBM 2. HP 3. EMC 4. Teradata 5. Oracle 6. SAP 7

TRUSTWORTHY CYBER INFRASTRUCTURE FOR THE POWER GRID | TCIPG.ORG

YARN

YARN Jobs (Type A)

Comp 1

Comp 2

Comp n

App Manager Type A

App Manager Type B

App Manager Type C

YARN Jobs (Type B)

YARN Jobs (Type C)

Animation Courtesy: Read Sprabery