Context
Distribution system operators manage large medium‑voltage (MV) asset bases where targeted refurbishment can improve reliability outcomes and reduce outage‑related costs.
Challenge
DSOs face the challenge to identify which assets are most likely to fail and should be refurbished first, while accounting for both failure probability and the associated risk.
AI Solution
AIAM applies an AI‑based approach to prioritise MV cable refurbishment by combining (i) the probability of failure and (ii) the associated risk (monetised). Different renewal scenarios are identified and evaluated, and the route selection criteria are based on these two variables to support the refurbishment decision.
The mixed approach makes it possible to offset current limitations in the calculation of the impact or consequence of failure, particularly with regard to quality of supply, which represents a significant component in the evaluation formula.
Impact & evidence
Utilities refurbish assets that are more likely to fail, with the stated intent of reducing outages and repair costs. The solution’s success is measured by reliability of supply of every kind of asset.
Implementation / Adoption
Implementation follows a yearly update cycle, in which asset and outage data are analysed using machine‑learning techniques.
Replication requires accurate assets and outages information.
Data
The solution relies on internal data for development.
Future enhancements
Planned enhancements include the addition of new asset types to the methodology.
