Data Power

guest editorial

Mladen Kezunovic

data analytics

creating information and knowledge

T

THE FEATURE ARTICLES IN THIS The described process of converting this issue due to the practical publish-

issue are devoted to the emerging data to knowledge using data analytics ing limitations.

field of data analytics, which is a is illustrated in Figure 1. A careful selection of the article

computational capability to extract a Many existing applications in authors and topics illustrates emerg-

cause effect understanding of power power systems are also focused on ing data analytics for control center

system events. This knowledge gets processing data, but only a few are us- applications, enhanced security as-

extracted from field measurements ing innovative monitoring and control sessment and management, tuned state

through analytical methods and, in concepts enabled by data analytics estimation, automated fault analysis,

many cases, involves the use of vari- solutions. To illustrate the trend, this and renewable resource integration.

issue of IEEE Power & Energy Maga-

ous data and power system models. As The topics of the articles shown in the

zine provides several examples of the

it links the cause of an event with its context of automated data analytics are

consequence, it may be readily used by advanced solutions. Since this is an depicted in Figure 1.

operators or in designing controllers emerging field, the articles are select- The fi rst article, The Situation

to enhance power system operation. ed from the user and research groups Room, discusses a suite of advanced

The data analytics solutions use field that closely collaborate with industry data analytics solutions based on phasor

data obtained from various intelligent in demonstrating the benefits. The ex- measurement unit (PMU) measurements:

electronic devices located in substa- amples that follow are an important a) angular separation, b) oscillatory sta-

tions and a variety of databases spread step forward and illustrative of the bility, c) disturbance location identifica-

across the utility enterprise. The data new trend, but there are many other tion, and d) islanding and resynchroni-

analytics tools then convert the data to similar ideas that did not make it into zation. The authors illustrate how such

information and eventually informa-

tion to knowledge. In this process, the

knowledge of experts is formulated as

d

Extracte

set of rules or equations and combined e

nowledg

K

with computational models to provide

the match between measured data and

Wind

event hypothesis. Once the data and State t

Forecas

tor

Estima

the hypothesis are matched, the de-

er Data

al

Situation Weath

sired knowledge about the cause ef- Stability ss

Awarene

g Data ent Fault

fect relationship is inferred. Since the Assessm

Lightnin

Analysis

process of matching prior experience

with measured data to obtain knowl-

Pool of Real-Time Data

edge is done often in an automated

phical

Geogra

way, the results of the process are typi- ta

rket Da Data

Ma

cally made available online and may

System

Power

be used in real-time decision making. Data

Digital Object Identifier 10.1109/MPE.2012.2204795

figure 1. Data analytics for the conversion of data to knowledge.

Date of publication: 16 August 2012

14 september/october 2012

IEEE power & energy magazine

advanced solutions may be integrated development leads to the new concept of POC included a PMU, as well as the sta-

with the legacy emergency management enhanced situational awareness. bility and EMS analytics, and allowed

system (EMS) design to The authors indicate for ample testing of equipment and soft-

provide a major enhance- that such an improvement ware. As a result, a long list of benefits

SE is an

ment in operator s ability maximized human un- of the POC is experienced and shared

to make decisions. This derstanding and com- with readers.

indispensable

requires advanced graphi- prehension without in- The second article, Operating in the

cal representation of the creasing operator stress. Fog, provides broad user perspective of

tool for

data analytics results. This is achieved through the new data analytics. The Pan-Euro-

matching the

The article provides the analytics that offer pean network plans are outlined and the

operator views that incor- enhanced perception, com- main conclusion is that the uncertainty in

measurements

porate combined graphi- prehension, and projec- short term planning requires new tools

cal and geographical views. tion leading to better in- to handle operation decisions. This addi-

with models

Correlating electrical and formed decision making tional knowledge for decision making is

spatial components of de- and action. Since the im- envisioned coming from better descrip-

to account for

cision making enhances plementation of the new tion of neighboring systems, improved

erroneous and

the ability to make pru- EMS solutions carries a forecasting and enhanced model accura-

dent decisions. As ex- substantial risk, the au- cy. This led to a discussion of the overall

missing data.

amples of the synergies thors use an example toolbox structure for the future operator

that have occurred due to from a utility company needs that includes existing application

the advanced analytics deployment to illustrate and new data analytics for security as-

and visualization framework, the opera- how the risk may be managed. The sessment. The security assessment tools

tors ability to monitor operating limits, company has decided to first implement are envisioned as being used for on-line

understand complex events, and enhance a proof of concept (POC), and then decisions, but they will be widely sup-

post-mortem analysis are discussed. This proceed with full implementation. The ported by off-line tools helping define

CAPESoftware security rules, validate dynamic models and outline

defense plan and restoration strategy. To achieve this

for Protection Engineering new way of handling uncertainties, the framework for

contingency assessment including corrective and pre-

ventive actions is proposed. This approach is illustrated

though several examples of how the tools may be used

in some critical operating conditions. While given at

a high abstraction level, the new data analytics clearly

indicate the reliance on better models, more up-to-date

data, and knowledge from the past experiences.

The next article, Metrics for Success, illustrates

data analytics applied to evaluate state estimator (SE)

performance. As well known, SE is an indispensable

tool for matching the measurements with models to

account for erroneous and missing data. The knowl-

edge of the authors used to evaluate SEs comes from

combining the experience with designing measure-

ments in existing SEs with new experience of us-

ing synchrophasor data. This leads to a concept of

a synchrophasor assisted state estimation (SPASE),

which allows for improvements based on statistical

properties of the measurements while taking into ac-

count model uncertainties. To make the point about

how the new approach differs from the traditional

one, the article explores the issue of network observ-

ability and bad data detection, two key design com-

CAPE s more accurate protection

ponents of an SE. This leads to an analysis of what

system modeling helps you nd lurking

affects the accuracy of an SE, and the measurement

misoperations that other products can t. design and selection of critical measurements are

CAPE is the only protection software detailed recognized as the key impacts.

enough to support comprehensive wide As noted by the authors, the two issues are be-

area protection coordination reviews. coming difficult to handle as the size of the SE de-

sign grows. The scaling up of the SE design hap-

CAPE has the world s largest library

pens when attempts are made to represent the entire

of detailed, manufacturer-speci c relay

transmission and distribution system or an entire

styles. And CAPE s many shortcuts and

electricity market with all the participating players

productivity features make all that detail using one unified power system model and a gener-

manageable. Plus your investment in alized SE. As the critical need to improve existing

CAPE keeps getting better, with ongoing, SE is elaborated upon, the authors point to the im-

responsive software development. portance of metrics that should be used to evaluate

any improvements. The recommended metric for

Try the CAPE 60-day demo. We can

an SE solution is the number of iterations for the

help you convert your existing protection

results to converge. While this was always known,

database to CAPE. It s a great way to take

the additional insight is given to distinguish such

a better look at your protection system. reasons and the quality of measurements and their

design were pinpointed as the focus of additional

metric. The impacts that are quantified by the met-

ric are: a) the objective function and largest normal-

ized residual impact on quality of measurements

and b) the measurement system vulnerability, pseu-

domeasurements ratio, and SE accuracy that impact

measurement design. With such insight, data ana-

lytics for the extensive evaluation of SE solutions

have been developed and demonstrated using cases

www.electrocon.com

from a utility company. It becomes obvious that this

***@**********.***

type of data analytics is quite useful in making decisions

about SE improvements using new measurements and their

optimal placement. The use of the proposed data analytics as

the metric for assessment of measurement quality and design

enables SE designers to make the right choices as the new

measurement infrastructures such as PMUs become avail-

able for the use in SEs in the future.

The following article, Measures of Value, points out

how understanding the manual for the disturbance analysis

can be translated into the data analytics solution executed

automatically online. The core benefit is the ability to deter-

mine a cause effect relationship between an event such as a

transmission line fault and a consequence such as an incor-

rect relay or breaker operation in a matter of seconds. This

way the nonoperational data obtained from digital relays

and transient recorders is actually turned into operational

knowledge available for operator decision making. The re-

sults of the data analytics processing can tell operators the

basic information about the fault type and location, as well

as whether the fault clearing sequences were executed cor-

rectly and whether they included auto reclosing that cleared

a temporary fault or circuit breaker operation that isolated

a permanent fault. Based on this result obtained in seconds

after the event has occurred, operators are able to make key

decisions whether to restore the line or whether to issue a

work order request for the repair crew to go to a very accu-

rately located site and repair the damage.

To provide such a powerful processing capability, this

data analytics function utilizes the knowledge of experts to

develop a model of expert reasoning that links cause effect

rules in a software solution called an expert system, which,

in this case, is the core of the data analytics approach. The

article illustrates how once the experts knowledge is em-

bedded in a software solution, the rules formulated by ex-

perts get fi red automatically for each new set of measure-

ments. The measurements come from intelligent electronic

devices (IEDs) located in substations that are triggered by

such events. The firing of the rules results in the cause effect

analysis that presents operators with clear decision-making

options to react in the case that inferior performance of the

relaying system and/or circuit breakers require their action.

This data analytics benefit should be compared with the

events of the blackout in 2003 when it took days and weeks

to actually perform a post-mortem analysis of the events that

could have been identified in a matter of second with the

proposed data analytics enabling operators to react and per-

haps contain the cascade that led to the blackout.

The final article, One Step Ahead, focuses on data analyt-

ics needed for the integration and use of renewable resources

such as wind power. Since it is widely known that the wind is

intermittent, the authors are proposing new data analytics for

wind power forecasts that may be utilized for predictive con-

trol. This idea is already attracting several research groups, and

many approaches using different forecasting technique are be-

ing proposed. The authors introduce a simplified forecasting

The applications are helping op-

method that uses just the outputs of ac- development that will enhance future

erators in more accurate plan-

tive and reactive power from wind tur- EMS solutions. It will, however, re-

ning and robust operations.

bines to predict the next control action. quire close attention to the methods

Since the software tools for data

A neural network based data analytics for capturing experts knowledge and

analytics are new, their integra-

tool is developed and tested using data translating it into analytical tools that

tion in legacy solutions is critical.

from multiple wind farms in Germany. can produce new value out of abun-

An optimization scheme that takes into In closing, this special issue has dance of data about the power system.

account load tap changers and shunt re- targeted data analytics as a promising p&e

actors is developed and tested using sev-

eral cases of reactive power controllers

embedded with the wind generators.

This new data analytics tool for predic-

tive control is incorporated in a system

solution that, besides the wind farm,

also has access to the battery storage

Enjoy your newfound

and wind power balancing controller.

The authors acknowledge the need

for new data analytics to perform short-

spare time.

term wind power prediction in the order

of seconds, minutes and a few hours and

its application in control centers. They

also state that This will become critical

for the real-time operation of the elec-

tricity supply system as more and more

wind power penetrates into it. The value

of short-term wind power forecasting is

high considering the reduction in power But be prepared to explain how you accomplished so much

losses, as is maximizing the security and with so little time and effort.

stability of the power system, especially

Just tell them you got a little help from EasyPower: the fastest, easiest-to-use, most

when stochastic security-constrained automated power system software available.

optimal power flow is far from reaching

EasyPower automates everything:

control centers in the near future. They One-line creation and templates Fulldocument set drawings

also recognize that this solution may be- NEC code design Arc flash calculations and analysis

Protective device coordination IEEE-1584 & NFPA 70E compliance

come quite attractive to wind power pro-

ANSI and IEC solution standards Seamless CAD output

viders once short-term wind power fore-

Explore more online and download a free demo copy at www.easypower.com/demo

cast based system applications become

common in control centers as the results

enable the maximization of revenue by

minimizing penalties.

In summary, all the articles have

Power System Software Turn Days into Minutes

something in common that paves the

way for future thinking about new data

analytics.

Almost all of the applications

use some new data not used in

legacy solutions

The analytics take advantage of

the formulation of experts knowl-

edge and improved models.

The advantages are obtained

from being able to better under-

stand cause effect relationships.

The combined physical, electrical,

and data model views of the re-

sults enhances decision-making.

september/october 2012 23

IEEE power & energy magazine

Contact this candidate