Join the Asset Health Analytics Community on Wednesday, December 3, 2025 at 2:00 PM CT for a presentation with Q&A/open discussion on, “Enhancing Secondary Network Grid Resilience through Data-Driven Approaches” led by Amogh Mahadev Kokari, Data Scientist and Bradley Kittrell, Data Scientist at Con Edison.
Session Description:
Con Edison energizes New York City primarily through its vast underground distribution network system, which is exceptionally reliable. However, maintaining this reliability can be challenging due to silent cable degradation and breakages that are difficult to observe directly. When enough cables break, it can result in low voltage, customer power cuts, equipment damage, and significant grid damage – something the city that never sleeps cannot afford. With Con Edison’s fully deployed Advanced Metering Infrastructure (AMI) system, the availability of AMI voltage data presents both an opportunity and a challenge to proactively detect and repair these issues. This session will explore data-driven and advanced analytical approaches to gather information from noise in a highly unpredictable, constantly changing environment. We will begin with initial assumptions, exploratory data analysis (EDA), and machine learning (ML) modeling, followed by constant prototyping, expert feedback, and solution tweaking processes. The problem, which started as a simple ML classification, has undergone multiple iterations, while setting the stage to address other issues in the secondary grid. The session will emphasize understanding data, models, and active listening to stakeholders, which helped us rapidly progress and pivot from supervised to unsupervised ML modeling. We will dive deeper into data understanding, modeling, and cleaning efforts. Finally, the session will conclude with key takeaways for all stakeholders, highlighting data and explainable analytics as key drivers to success.
Key Takeaways: Understanding the critical role of data and analytics in maintaining grid reliability. Learning about the iterative process and its benefits in ML modeling. Gaining insights into effective stakeholder collaboration and feedback incorporation. Recognizing the importance of data cleaning and understanding in building reliable models. Identifying key drivers for success in proactive maintenance and grid management.
*UAI Utility Members can register and access all nine of our Analytics Communities via our Community Page. Not a part of the Asset Health Community and want to join this session? Please use our direct link here to request access. You will find the Teams meeting credentials to the upcoming meeting at the top of the feed on this page. If you have any questions or run into any issues, please contact us at info@utilityanalytics.com.
Responses