Largest Industrial Deployment of AI & IoT Applications
Global Fortune 100 Enel is executing an enterprise-wide digitalization strategy aimed at increasing efficiency, developing new services, and spreading a digital culture across the organization. Central to achieving Enel’s goals is the large-scale deployment of C3 IoT’s big data, predictive analytics platform (PaaS) and SaaS applications. Enel operates the largest enterprise IoT system across 20 million smart meters across Italy and Spain.
Enel and C3 IoT have been working together since 2013. Two of Enel’s efforts with C3 IoT in this enterprise-wide digital transformation include fraud detection and predictive maintenance of distribution assets:
Fraud Detection – Identify and Recover of Electricity Theft
With C3 IoT, Enel transformed its approach to identifying and prioritizing electricity theft (non-technical loss) to drive a step change in the recovery of unbilled energy, while improving productivity. The effort required building AI/machine learning algorithm to match the performance delivered by Enel experts using a process honed over 30 years of experience. While this was a significant challenge in and of itself, Enel set an ambitious target to double the performance achieved in recent operating years.
A key innovation that enabled this transformation was to replace traditional non-technical loss identification processes, focused primarily on improving the success of field inspections, with C3 IoT’s advanced AI algorithms 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 7 Enel source systems and 22 data integrations into a unified, federated cloud image in near real-time, running on the AWS Cloud. Using analytics and more than 500 advanced machine learning features, C3 Fraud Detection continuously updates probability of fraud for each customer meter.
Predictive Maintenance – Improve Asset Performance
To improve grid reliability and reduce the occurrence of faults, Enel deployed the C3 Predictive Maintenance application for 5 control centers. The application applies advanced AI techniques to analyze real-time network sensor data, smart meter data, asset maintenance records, and weather data to predict feeder failure.
Key innovations in this project include the ability to construct Enel’s as-operated network state at any point in time using an advanced graph network approach, and the use of an advanced machine learning framework that continuously learns to improve prediction performance.