Entries for Digitizing Utilities Prize

PingThings' interest in this initiative is to support the other applicants as an extension of the Dominion Energy team.

Our ML models enable utility companies to accurately forecast power loads and building electrification to mitigate weather-driven outages.

Automate and extend Dominion Energy’s data analysis capabilities and processes for assessing grid dynamics performance - oscillations & IBRs

This project will enable Seattle City Light to prioritize and value grid modernization investments with respect to climate resilience.

To develop a model mismatch root cause recommendation system through combining domain knowledge with first principles and data analytics

Scalable creation of labels that enrich large volumes of multivariate time series data making efficient use of domain knowledge information.

Physics-based data-analytics that reduce effort to parametrize transmission lines & diagnose unexpected grid behavior such as oscillations

Taking forgotten, hardcopy information and turning it into digital knowledge to improve employee efficiency and quality of life.

Risk prioritization of critical infrastructure, helping utility operators harden sites against malicious acts efficiently and effectively.

Data agnostic platform that ingests data from sensors and prepares it for AI-powered predictive models for failure detection & prediction.

To develop data analytics functions using PMU and point-on-wave data for asset diagnostics and performance evaluation system.

ALERT uses Machine Learning and Artificial Intelligence to create an outage warning system to reduce or avoid outage impacts.

QRAM estimates building, feeder, and substation level loads and their uncertainty information using quantile regression on historical data.

This project develops a data-driven planning platform to accelerate the integration of electric vehicles in power distribution systems.

A tool to analyze, visualize and customize IRP modeling outputs for various audiences to improve decision making and public engagement.

The project aims to estimate load composition and forecast load using machine learning and regression methods.