Using data to predict and optimise street furniture maintenance
The solution offered technician a predictive model along with a visual interface in order to anticipate and react to malfunctions before they appear.
// OUTCOMES & KEY RESULTS
Thanks to this solution, repair timeframes and the number of malfunctions reported by residents can be reduced. The goal is to reduce the number of unforseen breakdowns.
The experimentation took place in Paris' 13th district
// PARTNERS INVOLVED
Partners provided the following data sets: hourly data from 16,000 units controlling street lights, georeferenced data on street lighting in the experiment area, external data such as weather information The selected startup – Saagie - defines itself as an " open data fabric", specializing in business process automation, customer journey and risk & fraud. Saagie raised 10 million in 2018 to accelerate its development.
// PAIN POINT & OPPORTUNITY
In Paris, technicians servicing street lights, traffic lights and other street furniture typically follow predetermined schedules which could be optimized with this data and real-time approach.
This solution is scalable to any street furniture consuming electricity, inside and outside of France. From a more general perspective, any operator handling electric infrastructure may be interested in optimizing predictive maintenance on its facilities.