To increase efficiency, develop new services, and spread a digital culture across the organization, Enel is executing an enterprise-wide digitalization strategy. Central to achieving the Fortune 100 company’s goals is the large-scale deployment of the C3 AI Suite and applications. Enel operates the world’s largest enterprise IoT system with 20 million smart meters across Italy and Spain.
Enterprise Digital Transformation
Enel and C3.ai have been working together since 2013. Two of Enel’s enterprise-wide digital transformation efforts with C3.ai are fraud detection and predictive maintenance of distribution assets.
With C3.ai, Enel transformed its approach to identifying and prioritizing electricity theft (non-technical loss), with a goal to double the recovery of unbilled energy while improving productivity. The effort required building AI/machine learning algorithms to match the performance delivered by Enel experts using a process honed over 30 years of experience.
To accomplish this, the teams worked together to replace traditional non-technical loss identification processes with the C3 Fraud Detection application. The new application uses advanced AI capabilities to prioritize potential cases of non-technical loss at service points, based on a blend of the magnitude of energy recovery and likelihood of fraud.
The system integrates and correlates 10 trillion rows of data from seven Enel source systems and 22 data integrations into a unified, federated cloud image in near real-time, running on Amazon Web Services. Using analytics and more than 500 advanced machine learning features, C3 Fraud Detection continuously updates probability of fraud for each customer meter.
To improve grid reliability and reduce the occurrence of faults, Enel deployed the C3 Predictive Maintenance application for 5 control centers. The application uses AI to analyze real-time network sensor data, smart meter data, asset maintenance records, and weather data to predict feeder failure.
The system provides a holistic view of Enel’s operating assets by integrating data from 8 disparate systems (SCADA, Grid Topology, Weather, Power Quality, Maintenance, Workforce, Work Management, and Inventory) and presenting relevant, actionable insights. Key innovations in this project include a time-based view of Enel’s as-operated network state using an advanced graph network approach, and the use of an advanced machine learning framework that continuously learns to improve prediction performance.