20. Artificial Intelligence


Artificial Intelligence (AI) is an interdisciplinary field that combines theory and practice. It is about assisting human activities, mainly via software and, in some cases, even replacing them. AI involves the use of information systems, data within management systems and dedicated algorithms. AI performance is based on the combination of the availability of a large amount of data, large computing capacity, and machine learning algorithms. As distribution networks are generating a growing amount of data, due to the deployment of smart meters and increased measurement and communication capabilities, DSOs have early on considered AI solutions.


For the European Parliament, artificial intelligence represents any tool used by a machine to ‘reproduce human-related behaviours, such as reasoning, planning and creativity’. The AI Act is a proposed European law on artificial intelligence – the first law on AI by a major regulator anywhere. The law assigns applications of AI to three risk categories. First, applications and systems that create an unacceptable risk are banned. Second, high-risk applications are subject to specific legal requirements. Lastly, applications not explicitly banned or listed as high-risk are largely left unregulated.

Challenges and opportunities for DSOs


  • Enhance demand/supply forecasting and decision-making: adjust distribution, increase flexibility and minimise the risk of blackouts.
  • Support DSOs in integrating (distributed) renewable energy sources into the grid.
  • Reduce the risk of grid failures by performing timely maintenance by using intelligent, predictive algorithms detecting anomalies in the grid.
  • Enhance the productivity of employees by automating & augmenting repetitive and data-intensive tasks.


  • Data Privacy. Handling sensitive grid data while maintaining privacy is essential.
  • Cybersecurity. Protecting AI systems from cyber threats is critical to ensure grid reliability.
  • Data quality. AI relies on high-quality training and input data (e.g. grid data).
  • Integrating AI into distribution grids involves managing distributed energy resources (DERs), ensuring seamless coordination and optimisation.

EDSO considerations

  • The performance of AI solutions is directly based on data availability and quality and increasing data privacy concerns.
  • Facilitating and accelerating the industrialisation of AI solutions into core information systems has become one of the main challenges of industrial AI.
  • AI algorithm performance control requires special attention and dedicated monitoring tools.
  • As AI technologies require specific skills, companies should develop dedicated training programs.
  • The development and implementation of AI solutions must be carried out with the aim of reducing carbon footprint.
  • Particular attention must be paid to the ethical aspect of AI (potential concerns about justice, fairness, accountability, etc.).
  • European legal texts under preparation must account for the specificities of DSOs.

Potential use cases

  • Production and demand forecast: AI combined with classical solutions may improve forecast quality.
  • Congestion management prediction: determining how much flexibility is needed in the future.
  • Distributed Energy Resources (DER)/Flexibility: AI allows handling the increasing complexity of network control due to DER variability, e.g. determining the available power for charge point providers.
  • Network development studies: AI enables the realisation of network development studies accounting for technical constraints, and technological and sociological hypotheses.
  • Asset management: the performance of AI in image processing enables automatic diagnosis to enhance programmed renovation. The learning capacity of AI allows, in some cases, to perform predictive maintenance.
  • Image recognition: for instance, electricity energy meter & components recognition from meter photos, detecting assets on technical drawings.
  • Operation and employee support: AI could augment the capabilities of maintenance technicians, customer advisors and support function employees.
  • Network control & outage prediction: AI could augment the capabilities of control rooms (fault location, DER integration). AI solutions will enable precise LV massive control.

Ongoing projects

  • Production and demand forecast:
    • SYPEL predicts consumption, production, and losses in Enedis’ electrical network on a national scale.
    • PREDIS by E-REDES provides short-term forecasts of load and generation in the high voltage (HV) and medium voltage (MV) network through advanced analytics models allowing behavioural estimation for around 100’000 customers up to 5 days in advance (more info).
  • Congestion management prediction:
    • Stedin uses AI to determine future flexible power needs for congestion management and to predict transformer and (sub)station load through day-ahead forecasting.
    • O-One (Ores Operation Network Expert) is used by Ores to manage congestion (from risk assessment in the short-term to curtailment and monitoring) at the TSO-DSO interface in the HV network due to connected generation (more info).
  • Distributed Energy Resources (DER)/Flexibility:
    • Stedin currently uses AI to determine available power for electric vehicle charging on more than 400 charging poles in the Utrecht and Rotterdam provinces in the Netherlands.
    • To cope with the low availability of monitoring technologies at lower voltage levels, EnBW AG uses AI to read available measurement data (20 to 30% of all nodes) to predict network utilisation in the whole region. The application supports grid monitoring in a context of high DER penetration and increasing regional load peaks.
  • Network development studies:
    • Stedin uses AI to automatically create grid designs for newly built residential areas and define the optimal location of MV stations, reducing engineering time and shortening grid length.
  • Asset management:
    • The Analytics4Assets initiative by E-REDES uses advanced analytics models to forecast the behaviour of technical assets (AT/MV Power Transformers, HV Circuit Breakers and HV Lines), anticipating failures and optimising investment and maintenance plans.
    • Several DSO initiatives make use of AI combined with drone visual inspections to detect anomalies on HV and MV overhead lines. Examples include the GridDrone project by E-Redes (more info here and here), the DALI project from UFD (more info here and here) and Enedis’ DORA platform.
  • Image recognition:
    • With Dataposte, Enedis uses image recognition to control and ensure the reliability of network equipment image collection.
    • E-REDES uses a neural network algorithm to detect meter installations in photographs sent by service providers and validate their work.
  • Operation and employee support:
    • Netze BW uses AI to independently evaluate meter readings reported by customers and record plausibility checks for correctness (more info).
    • ESO developed a machine learning model to assess the quality of network documentation, identify errors (e.g., inaccuracies in electrical addresses, lengths, diagrams, etc.) and take corrective actions.
    • The Analytics4Vegetation initiative, fully deployed on the E-REDES network in Portugal, predicts vegetation growth with respect to the surrounding electrical infrastructure to automatically plan, prioritise and generate vegetation cut orders (more info).
    • Enedis AI-based tool ARIIA analyses requests for field intervention and assigns a probability of non-success (e.g. due to poor definition), limiting unnecessary travel for field operators.
    • E-REDES is piloting a project to automate the validation of grid connection request documents, reducing process time and improving result consistency.
    • An AI tool for determining the probability of network damage and excavation risk due to digging activities is planned to go live on the entire Stedin network.
  • Network control & outage prediction:
    • Before a storm, the Windy tool of Enedis uses meteorological data to predict the number of outages on overhead power lines with 90% accuracy, enabling better crisis preparation and faster restoration.
    • E-Redes developed a solution to predict possible neutral loss situations based on the events generated by smart meters before their occurrence.
    • ESO created a machine learning-based system that provides alerts for potential large-scale mass power outages in the 10 kV overhead line network considering weather forecasts, historical data, and technical network parameters.
    • Enedis’ Cartoline Low Voltage uses AI to analyse voltage-related data observed by Linky smart meters to foresee future incidents that could lead to power outages and schedule preventive interventions from field technicians (more info).

Last update: 17 May 2024