Enterprise Analytics Community
The journey to enterprise analytics nirvana is not an easy one. Join this community to learn about... View more
Organizer:
- Organized by
-
-
Upcoming January (2024) Community Conversation
-
Upcoming January (2024) Community Conversation
Hello Enterprise Analytics Community Members,
I hope all is well! We are just under one week away from our January (2024) Enterprise Analytics Community Conversation and want to get you excited about the session taking place. On Thursday, January 25 at 1:00 PM CT, we’ll be joined by John Blachford, Product Owner, Data Science at San Diego Gas & Electric (SDG&E) and Thomas Loeber, Senior Machine Learning Engineer at Logic20/20 who will be leading a discussion on, “Lessons Learned in MLOps.”
Learn more about this session and our speakers below!
Session Description:
In this session, our presenters will be sharing experiences and insights on MLOps, highlighting some of the key lessons learned in the process. Topics will include the importance of proper data management, version control, and automation in developing and deploying machine learning models at scale. Attendees will come away with a better understanding of the challenges and best practices involved in MLOps at the enterprise level, enabling them to optimize their own workflows and deliver more impactful results.
Speaker: John Blachford, Product Owner, Data Science at San Diego Gas & Electric (SDG&E)
John Blatchford is a Product Owner at San Diego Gas & Electric where he leads a team of machine learning engineers in the development of production grade systems that are used during fire season to inform emergency response and wildfire mitigation activities. John has a background in networking and cyber security and previously served in the United States Navy as a Network Engineer. John is passionate about technical work and has previously worked as a data engineer and machine learning engineer.Speaker: Thomas Loeber, Senior Machine Learning Engineer (Logic20/20)
Thomas is a Senior ML Engineer at Logic2020, a business and technology consulting firm, where he helps companies productionize ML models by adopting MLOps practices. He is passionate about applying engineering principles to effectively manage the complexity that quickly arises in production ML systems. Thomas initially came from the statistics and data science side, but has also worked in software and data engineering, searching for lessons from these more mature disciplines for how to create maintainable and scalable software systems. The rise of MLOps prompted him to return to ML to bring the insights from this journey back together. After helping a generative AI startup to reliably productionize their LLMs, Thomas has now established his niche in consulting. In this role, he not only collaborates closely with specific clients but also contributes to the design of a reusable process that standardizes the implementation of MLOps across various projects, enabling easy adoption while building in best practices from the outset.__________________________________________________________________________________________________________________________________________________________________
A calendar placeholder for this community conversation was sent out via my alternate email address (kpraet@sg.utilityanalytics.com). I’ve noticed these invites can sometimes be flagged as spam, so please check your junk folders if you’re not seeing right away. For your convenience I have also attached the placeholder to this message as an easy download. If you are not seeing a placeholder on your calendar for Thursday, January 25 at 1:00 PM CT, or are having trouble downloading the placeholder from this message, please reach back out to me so I can be sure you are forwarded the invite an alternate way.
Thanks and we look forward to connecting next week!
——————————
Kevin Praet
Membership Coordinator
Utility Analytics Institute (UAI)
Boulder CO
315-440-3033
—————————— -
2 Replies
-T.jpeg "John")
-T.jpeg "TL")
-
At KCPL, we are rolling out Oracle BI technology company-wide, see attached. Each division is appointing a business lead to implement the reporting tool for their business reporting. I am currently working as business lead with our T&D delivery people to implement BI related to asset management. We are working with Oracle ETL and ODI certified vendor to help us with the warehouse functions… Reports fall in line with KPIs for each division…
-
- Who is responsible for building….a specific group? Everyone across the company?
Analytics and Data Services is a specific dedicated group within CNP’s Electric Operations. We help our constituent clients deliver to their vision be it operational improvement, Financial awareness, security controls, etc. Our department helps the clients define their requirements and we are supported by a dedicated team from IT that delivers the technical requirements. Many groups from across the company come to my group for data support.
- What is the purpose of the analytics?
Mission of Analytics and Data Services
Turning Data into Information and Information into Insight supporting CenterPoint Energy’s mission to become America’s Leading Energy Delivery Company…and more…
We also view “Analytics as a Discipline”™
“Analytics” is the key word of the day. Definitions vary and all contain kernels of the truth but they do not sum up what analytics really is.
Analytics is neither a tool, a vendor solution or a great idea.
“Analytics is a discipline, or a craft,”™ something to be studied, trained in and practiced like the law or medicine.”™ Analytics as a discipline is the practice of taking data in any form and from whatever resource and turning that data into actionable information and enabling automation for the benefit of our constituent clients in whatever business venture they may be involved.”™.
“Analytics Discipline”™ takes systems, data, speed of delivery, etc. into account applies the training, learning and out of the box thinking to turn data into information and information into insight and insight into action which includes automation to deliver economical and viable results for the constituent clients”™.
- How do you build a narrative or story in the sea of numbers and statistics?
It depends upon the needs of the various clients. We grow with them from data at rest, complex correlations to real time awareness and automated alerting. Some example initiatives for 2013 are as follows:
- Provide real time situational awareness and correlations for Telecomms, Outage, Distribution Dispatching and Distribution Operations
(“Correlating data in real time to enable Operations to Affect the Outcome”)
- Enhanced Diversion Detection and Dispositioning combined with Usage
(“Stop the tax of energy theft in days rather than months or years”)
- Enhanced Transformer Load Management, Connectivity and Predictive Loading also enabling Fuse and Step Transformer Load Management
(“Protect the assets before they fail, enable preventative maintenance”)
- Support for Business Transformation Initiatives, Right Crew, Right Place at Right Time, Proactive Resolution of Equipment Issues and Fleet Support
- Financial and Regulatory Month End Revenue Estimation to Include IDR Meters (“Move from 90% estimation to a .01% estimation, Know your revenues” )
- Provide Instant Replay Capabilities for Training and Storm Preparedness
- Provide Real Time Solutions to Identify Data Anomalies in support of Corporate Security (“Eyes on the Horizon Threat Detection”)
- How do you lead the report audience to discover the gaps and needs from the analytics? …know-how in the drill down
Use the tools, start with small quick wins, learn from the data and revise the process, then iterate on the tool delivery the repeat to continuously improve.
- Do you use a warehouse approach connecting various systems eg. Financial, operational, performance? Any challenges?
Yes for Meter Data we use the eMeter eMA Analytics engine. For SAP “financial data” we use Business Warehouse, for complex correlations of data from multiple disparate sources we use the IBM ISAS appliance, for real time analytics we use Info Sphere Streams and for geospatial displays we use Google Earth.
Shelly Cotton can give you my contact information and we can discuss directly.
Thanks
Log in to reply.