Being part of a municipality-owned electric utility offers a unique opportunity to lead in the area of big data analytics. What moves the electric utility of the 7th largest city in the U.S.? The answer is, people. For years, CPS Energy has invested in development of local talent, local technology development, city growth, its employees, and an asset infrastructure that is setting the stage for continued success. At CPS Energy, when such investments are topped by a data infrastructure and applications conducive to creation of business insights, we can justify and prioritize investments. For us, the biggest people opportunities in big data analytics are around operations, customer and employee engagement, and safety. The presenter will provide examples and share how his views have evolved from those of a researcher to global renewable energy consultant to technology innovator and more recently a “harvester of value” from within people, process, and technology assets. Lastly, current and anticipated future states with regards to San Antonio’s electric utility big data enablement platform will be presented...
Speaker
Rolando Vega, Manager of Analytics and Business Insight, CPS Engery
1. San Antonio’s Electric Utility
Making Big Data Analytics
the Business of the People
…for the People
J U N E 17 - 21, 2018
B y: R olando Vega, Ph.D ., P.E.
Manager of analy tic s and bus ines s ins ight
2. AGENDA
1. Notions of scale and time in Texas utility
industry (VIDEO)
2. The making of a market – protocols and
people’s role
3. Observations on the finality of Technology
4. CPS Energy “People First” philosophy
5. A turning point in Machine Learning /
Artificial Intelligence
6. New market opportunities
7. Big data analytics @ CPS Energy
3. Scale & time notions in
utility big data analytics
4. Some considerations for
ERCOT market protocols
• energy scheduling and
dispatch
• ancillary services
• congestion management
• outage coordination
• settlement and billing
• metering
• data acquisition and
aggregation
• market information systems
• transmission and
distribution losses
• renewable energy credit
trading
• registration and
qualification
• market data collection
• load profiling and
alternative dispute
resolution
4
5. Technology Finality is…
by and for people
• Technology investment decisions in
electric utilities are made by and
for people with a keen eye for
creating value for its customers.
Element
6. Big Data Analytic System
Dimensions
• System components:
– Hardware/Software
– Data
– Methods
– Intangible components, such
as processes, relationships,
company policies, information
flows, interpersonal
interactions, and internal
states of mind such as
feelings, values and beliefs.
7. Perspectives: Genesis of
Big Data Analytic Systems
Events
Patterns
Structure
State of Mind
React
to snapshot
Understand/Adapt
changes in events over
time
Design/Predict
causal connections
Transform
the system
8. People in Big Data Analytic
System Dimensions
Events
Patterns
Structure
State of Mind
12. CPS Energy
• What moves the electric
utility of the 7th largest
city in the U.S.? The
answer is, People.
• For years, CPS Energy
has invested in
development of local
talent, local technology
development, city
growth, its employees
and an asset
infrastructure that is
setting the stage for
continued success.
13. A turning point for
Machine Learning
• Open-source software has helped
machine learning mature passed
the point of academic research
and inflated expectations.
• Faster and more transparent
technology deployment now
possible
• Machine learning techniques
could be conveniently trained and
deployed to predict more optimal
solutions
• But ONLY IF data inputs
behave within reasonable
range and with normal
variability.
15. Big data analytics
enablement at CPS Energy
• San Antonio’s electric utility big data enablement
platform effort started in 2016.
• We anticipate to have production-ready
environment in June 2018.
• HDFS used for data storage and
Spark/BigDL+Tensorflow for advanced analytics
• 2018 year to demonstrate what is possible
• 2019+ time to scale predictive analytic
technologies
• Hybrid integration platform to accelerate API
technology adoption production ready June 2018.
• In process to implement data governance program.
After having matched the space and time progression, a point needs to be made about how a utility matures into adopting new technologies…in an effort to illustrate whre many of the dat leaders should put their attention in participating in some of the groups that create the protocols that dictate what we adopt and do as an industry.
People is not only in the input and output…people is also into the system dimensions. Power plant goes into a forced outage, plant operators communicate and go to investigate what happened and fix the problem ASAP, while customer in Market Operations is trying to find second best alternative
Power plant operators collect sufficient information and map all events into a common axis to contrast with all other forced outages quantitatively, and realize that there is a commonality with all events, temperature in boilers changes at a rate faster than 100 F in 15-minutes in all events.
Power Plant operators note that generally the rate of temperature change is only exceeded when the turbine is not given maintenance in more than 3-months and therefore communicate with market operations and design a process where all plants will undergo maintenance based on signals from temperature rate of change and when certain threshold is reached.
Power plant and market operation managers start discussions about whether solving this problem is the sustainable solution since the plant has generated more financial losses than gains in the last 2-years and there might be a different market this power plant may serve that does not expose the unit to fail.