Driving network efficiency and fraud detection efforts

Project Challenge

In 2014, Baltimore Gas and Electric Company (BGE), a subsidiary of Exelon Corporation, launched C3.ai applications across all two million sensors and devices in its service territory. BGE now uses three C3.ai applications to deliver an annual economic benefit of $20 million to BGE and its customers. C3 AMI Operations™ optimizes the deployment and ongoing health of its advanced metering infrastructure (AMI) network. C3 Revenue Protection™ identifies and reduces unbilled energy usage. C3 Energy Intelligence™ provides business intelligence analysts with ad-hoc reporting and dashboarding functionality across 12 unique source systems.

About BGE

  • Founded in 1816, Maryland’s largest utility, 
a subsidiary of Exelon Corporation
  • $13B Annual Revenue
  • 1.9M Electric and natural gas customers in central Maryland
  • 3,200 Employees
  • 2M Smart meters installed

Integrating Existing Systems

C3.ai delivered the three applications on schedule, in six months from project kick-off to launch. The three applications are built on the C3 AI Suite and run on the AWS Cloud.

Deployment involved developing 42 integrations to 12 unique source systems. C3.ai loaded two years of historical BGE data in a 10 TB unified cloud image with 35 billion rows of data aggregated, federated, and analyzed. To build the three applications and match BGE’s requirements and available data, the C3.ai team configured more than 140 complex machine learning features, comprised of 650 individual rules, that provide ongoing predictive recommendations in a live production application. In total, more than 8 GB and 220 million rows of new data are delivered each day to the C3 AI Suite on AWS. The machine learning algorithms leverage Amazon EC2 instances, running on Intel® Xeon® processors designed to power compute-intensive workloads

Project Highlights

  • 12 Unique Source Systems
  • 8GB of New Data Analyzed Each Day
  • 10TB Federated Cloud Image of Data
  • 140 Complex Analytics In Use

Results

28
Weeks from project kickoff to launch
3
C3.ai Applications
90%
Accuracy rate, growing to 99%
150%
of target business value $15.4M to date

Solution Architecture

Proven results in weeks, not years

timeline
Get insights into C3.ai’s capabilities, enterprise AI best practices, and highest-value use cases.
Gain insights into the C3 AI Suite's capabilities, its model-driven architecture, and test it against your company's sample data set.
Identify a high-impact business problem and collaborate with the C3.ai team to rapidly build an AI application that solves it.
Scale and deploy a tested C3.ai application into production. Incorporate user feedback and optimize algorithms to drive maximum economic value.

Thank you for your interest in C3.ai

We'll review your information and a team member will get back to you within 24-48 hours.

Return to home