Case Study


Project overview


  • Serves 36 million customers with only 38,507 employees
  • Develops, operates, modernizes, and maintains 1.4 million kilometers of low and medium voltage and medium-voltage electricity network (220 and 20,000 volts) and manages the associated data
The largest production deployment of vision AI in France
Enedis is the public electricity distribution network operator for 95% of the French territory and the largest in Europe.

A significant portion of the 330,000 km of overhead lines they operate have been in place for three to four decades. Must they be entirely replaced, with the acute ecological impact that would entail?

Therefore, Enedis was looking for the most responsible way to extend their lifespan by replacing only the components that warrant replacement.


In 2020, Enedis has decided to deploy artificial intelligence across its organization by leveraging the Æther AI platform. This partnership allows Enedis to accelerate its digital transformation with the systemic use of visual data and AI to verify operations of its medium voltage overhead network. Deployed on 10,000 kilometers of lines in the first year alone, this move towards AI at scale is a world first in the electrical network management sector.

A good way to boost both responsible use of material and efficiency, with a view to optimizing electricity costs for end consumers.



savings on inspection costs


savings on downtime (cost of downtime = 1MEUR/h/section)

Alteia Platform

Project highlights

  • Centralize all heterogeneous data on a physical asset (BIM / CAD models, IoT, Lidar, images, etc.) onto the cloud
  • Access data from anywhere, at all levels of the company
  • Detect defects, hazards, and maintenance needs with a 90 +% accuracy with automated visual inspection leveraging our pre-built ML models
  • Standardize, control, and optimize asset inspections. Do so with long and short-term scheduling and adaptation to the local field requirements, such as various collection methodologies (helicopter, drone, or a dedicated mobile application)
  • Decrease operational costs continuously with an iterative improvement cycle based on AI asset default detection and reporting
  • Assess risk in real-time for better planning with optimized work orders pushed directly into management systems
  • Evaluate asset health and related maintenance costs with asset tracking for defective assets by type and location
unnamed (7)
unnamed (8)
unnamed (9)

Next Customer