ISGT 2014 Panel Presentation CELLULAR COMPUTATIONAL NETWORKS FOR SITUATIONAL INTELLIGENCE IN SMART GRIDS G. Kumar Venayagamoorthy, PhD, FIET, FSAIEE Duke Energy Distinguished Professor & Director & Founder of the Real-Time Power and Intelligent Systems Laboratory The Holcombe Department of Electrical & Computer Engineering Clemson University E-mail: [email protected]http://people.clemson.edu/~gvenaya http://rtpis.org NSF: EFRI #1238097, IIP # 1312260, and ECCS #1231820, #1216298, & #1232070
20
Embed
CELLULAR COMPUTATIONAL NETWORKS FOR SITUATIONAL ...sites.ieee.org/isgt2014/files/2014/03/Day3_Panel3A2... · CELLULAR COMPUTATIONAL NETWORKS FOR SITUATIONAL INTELLIGENCE IN ... “Decentralized
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
ISGT 2014 Panel Presentation
CELLULAR COMPUTATIONAL NETWORKS FOR SITUATIONAL INTELLIGENCE IN SMART GRIDS
G. Kumar Venayagamoorthy, PhD, FIET, FSAIEEDuke Energy Distinguished Professor &
Director & Founder of the Real-Time Power and Intelligent Systems LaboratoryThe Holcombe Department of Electrical & Computer Engineering
Cellular computational networks (CCNs) consists of computational units connected to each other in a distributed manner.
CCNs are suited to model systems with temporal and spatial dynamics.
Cellular Computational Networks
111 1 1( ) ( ( ), ( ),..., ( ), ( ))N
i i n n
Nss i SS n nSS SS
O k f O k O k O k u k
ISGT 2014 Panel Presentation
Decentralized Asynchronous Learning - CCNs
Luitel B, Venayagamoorthy GK, “Decentralized Asynchronous Learning in Cellular Neural Networks”, IEEE Transactions on Neural Networks, November 2012, vol. 23. no. 11, pp. 1755-1766,
ISGT 2014 Panel Presentation
Cellular Computational Networks
CCN
Luitel B, Venayagamoorthy GK, “Decentralized Asynchronous Learning in Cellular Neural Networks”, IEEE Transactions on Neural Networks, November 2012, vol. 23. no. 11, pp. 1755-1766,
ISGT 2014 Panel Presentation
Wide Area Predictive Monitoring Systems (WAPMS)
• Each cell represents one generator of a multi‐machine power system ‐Each cell predicts speed. deviation of one generator
• The cells are connected to each other in the same way as the components in the physical system.
• Nearest neighbors topology is used (n=2) to reduce complexity. G1
1 5 6
7 8 9
10 11 3
42
25km10km
25km10km
110km 110km
G2 G4
G3
)(1 kVrefG )(2 kVrefG )(4 kVrefG )(3 kVrefG)(1 kG )(2 kG )(4 kG )(3 kG
)1(1
kG )1(2
kG )1(3
kG)1(4
kG
Z-1
)(1 kG
)(1 kVrefG
)(2 kVrefG
)(2 kG
)(4 kVrefG
)(4 kG
)(3 kG
)(3 kVrefG
Z-1Z-1
Z-1Z-1
C2
C1 C3
C4
ISGT 2014 Panel Presentation
C7
C3C2
C5
C4
C6
C9
C8 C1
C11
C10
C12
C13
C16
C15
C14
Scalable Online CCN based Monitoring Systems
Luitel B, Venayagamoorthy GK, “Decentralized Asynchronous Learning in Cellular Neural Networks”, IEEE Transactions on Neural Networks, November 2012, vol. 23. no. 11, pp. 1755-1766,
ISGT 2014 Panel Presentation
Scalable Online Monitoring Systems
C7
C3C2
C5
C4
C6
C9
C8 C1
C11
C10
C12
C13
C16
C15
C14MLP SRN
ISGT 2014 Panel Presentation
Asynchronous Learning in CCNs
Luitel B, Venayagamoorthy GK, “Decentralized Asynchronous Learning in Cellular Neural Networks”, IEEE Transactions on Neural Networks, November 2012, vol. 23. no. 11, pp. 1755-1766,
ISGT 2014 Panel Presentation
Scalable WAPMS based on CCN
Luitel B, Venayagamoorthy GK, “Decentralized Asynchronous Learning in Cellular Neural Networks”, IEEE Transactions on Neural Networks, November 2012, vol. 23. no. 11, pp. 1755-1766,
ISGT 2014 Panel Presentation
August 14, 2003 Blackout
Regular Night August 14, 2003
• > 60 GW of load loss; • > 50 million people affected;• Import of ~2GW caused reactive
power to be consumed;• Eastlake 5 unit tripped;• Stuart-Atlanta 345 kV line tripped;• MISO was in the dark;• A possible load loss (up to 2.5 GW)• Inadequate situational awareness.
ISGT 2014 Panel Presentation
Situational Awareness (SA)
ISGT 2014 Panel Presentation
Situational Intelligence• Integrate historical and real-time data to implement near-future
situational awarenessIntelligence (near-future) =
function(history, current status, some predictions)
Real‐Time Power and Intelligent Systems Lab (http://rtpis.org) 16
C7
C3C2
C5
C4
C6
C9
C8 C1
C11
C10
C12
C13
C16
C15
C14
ISGT 2014 Panel Presentation
17
C1
C11
C10
C12
C14C10C15C16
C10C12
C2C10C13C16
C3C10
C2
Computational Network for Generator G10
ISGT 2014 Panel Presentation
18
Generator G10 Responses
ISGT 2014 Panel Presentation
ISGT 2014 Panel Presentation
Summary
• Advanced computational and information technologies are needed for planning and optimization, fast control of power system, processing of field data and fast coordination across the grid.
• The CCN is a scalable high performance learning system for situational intelligence, and distributed energy management and control for smart grids.
• Foresight (from predictions) through insight (data) will results in situational awareness and intelligence.
ISGT 2014 Panel Presentation
Thank You!G. Kumar Venayagamoorthy
Director and Founder of the Real-Time Power and Intelligent Systems Laboratory &Duke Energy Distinguished Professor of Electrical and Computer Engineering