Abstract
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.

Abstract
This article proposes a methodology for high loss detection in LV network, based on a very small set of commonly available data/metadata from networks connected to an MV/LV substation. The approach is based on a combination of predictors from several distinct categories, including network data, metadata, and measured smart meter data. Several independent groups of unranked real networks were simulated, and it was possible to find the top ten networks with the highest level of losses with a very satisfactory success rate (76% to 98%), depending on selected groupings folds. Due to the impracticability of analyzing all LV networks, the identification of the highest loss ones is essential for the definition of loss reduction planning since, with this list filtering, it is possible to determine with a good degree of certainty which networks require maintenance or upgrade.

Abstract
The electrification of the transport sector is a critical element in the transition to a low-emissions economy, driven by the widespread adoption of electric vehicles (EV) and the integration of renewable energy sources (RES). However, managing the increasing demand for EV charging infrastructure while meeting carbon emission reduction targets is a significant challenge for charging station operators. This work introduces a novel carbon-aware dynamic pricing framework for EV charging, formulated as a chance-constrained optimization problem to consider forecast uncertainties in RES generation, load, and grid carbon intensity. The model generates day-ahead dynamic tariffs for EV drivers with a certain elastic behavior while optimizing costs and complying with a carbon emissions budget. Different types of budgets for Scope 2 emissions (indirect emissions of purchased electricity consumed by a company) are conceptualized and demonstrate the advantages of a stochastic approach over deterministic models in managing emissions under forecast uncertainty, improving the reduction rate of emissions per feasible day of optimization by 24 %. Additionally, a surrogate machine learning model is proposed to approximate the outcomes of stochastic optimization, enabling the application of state-of-the-art explainability techniques to enhance understanding and communication of dynamic pricing decisions under forecast uncertainty. It was found that lower tariffs are explained, for instance, by periods of higher renewable energy availability and lower market prices and that the most important feature was the hour of the day.

Abstract
Accurate power forecasting from renewable energy sources (RES) is crucial for integrating additional RES capacity into the power system and realizing sustainability goals. This work emphasizes the importance of integrating decentralized spatio-temporal data into forecasting models. However, decentralized data ownership presents a critical obstacle to the success of such spatio-temporal models, and incentive mechanisms to foster data-sharing need to be considered. The main contributions are a) a comparative analysis of the forecasting models, advocating for efficient and interpretable spline LASSO regression models, and b) a bidding mechanism within the data/analytics market to ensure fair compensation for data providers and enable both buyers and sellers to express their data price requirements. Furthermore, an incentive mechanism for time series forecasting is proposed, effectively incorporating price constraints and preventing redundant feature allocation. Results show significant accuracy improvements and potential monetary gains for data sellers. For wind power data, an average root mean squared error improvement of over 10% was achieved by comparing forecasts generated by the proposal with locally generated ones.

Abstract
Foundation models (FMs) currently dominate news headlines. They employ advanced deep learning architectures to extract structural information autonomously from vast datasets through self-supervision. The resulting rich representations of complex systems and dynamics can be applied to many downstream applications. Therefore, advances in FMs can find uses in electric power grids, challenged by the energy transition and climate change. This paper calls for the development of FMs for electric grids. We highlight their strengths and weaknesses amidst the challenges of a changing grid. It is argued that FMs learning from diverse grid data and topologies, which we call grid foundation models (GridFMs), could unlock transformative capabilities, pioneering a new approach to leveraging AI to redefine how we manage complexity and uncertainty in the electric grid. Finally, we discuss a practical implementation pathway and road map of a GridFM-v0, a first GridFM for power flow applications based on graph neural networks, and explore how various downstream use cases will benefit from this model and future GridFMs.

Abstract
This study aims to improve the accuracy of wind power generation forecasting by selecting the potential locations for weather stations, which serve as crucial data sources for wind predictions. The proposed method is based on using Shapley values. First, they are assigned to stations that are already available in the region based on their contribution to forecasting error. Second, the values are interpolated to cover the area of interest. We test the hypothesis that taking weather measurements in areas with negative Shapley values leads to a decrease in the error of forecasting the volume of wind power generation. We estimate the method's impact on forecasting error by using long short-term memory neural network and linear regression with quadratic penalization. The results of this proof-of-concept study indicate that it is possible to improve the short-term wind power forecasts using additional weather observations in the selected regions. The future research should be dedicated to the expansion of the case study area to other locations, including offshore power plants.