Advanced control, operation, and planning tools of electrical networks with ML are not straightforward. 110 experts were surveyed to show where and how ML algorithms could advance. This paper assesses this survey and research environment. Then, it develops an innovation roadmap that helps align our research community with a goal-oriented realisation of the opportunities that AI upholds. This paper finds that the R&D environment of system operators (and the surrounding research ecosystem) needs adaptation to enable faster developments with AI while maintaining high testing quality and safety. This roadmap serves system operators, academics, and labs advancing next-generation electrical network tools.

Today's power systems are seeing a paradigm shift under the energy transition, sparkled by the electrification of demand, digitalisation of systems, and an increasing share of decarbonated power generation. Most of these changes have a direct impact on their control centers, forcing them to handle weather-based energy resources, new interconnections with neighbouring transmission networks, more markets, active distribution networks, micro-grids, and greater amounts of available data. Unfortunately, these changes have translated during the past decade to small, incremental changes, mostly centered on hardware, software, and human factors. We assert that more transformative changes are needed, especially regarding humancentered design approaches, to enable control room operators to manage the future power system. This paper discusses the evolution of operators towards continuous operation planners, monitoring complex time horizons thanks to adequate real-time automation. Reviewing upcoming challenges as well as emerging technologies for power systems, we present our vision of a new evolutionary architecture for control centers, both at backend and frontend levels. We propose a unified hypervision scheme based on structured decision-making concepts, providing operators with proactive, collaborative, and effective decision support.

Artificial agents are promising for real-time power network operations, particularly, to compute remedial actions for congestion management. However, due to high reliability requirements, purely autonomous agents will not be deployed any time soon and operators will be in charge of taking action for the foreseeable future. Aiming at designing assistant for operators, we instead consider humans in the loop and propose an original formulation. We first advance an agent with the ability to send to the operator alarms ahead of time when the proposed actions are of low confidence. We further model the operator's available attention as a budget that decreases when alarms are sent. We present the design and results of our competition “Learning to run a power network with trust” in which we evaluate our formulation and benchmark the ability of submitted agents to send relevant alarms while operating the network to their best.