Abstract
The rapid proliferation of uncontrolled resources poses significant voltage regulation challenges in low-voltage (LV) distribution grids. In this condition, conventional charging strategies, often based on fixed or static schedules, may lead to adverse voltage deviations under unpredictable load conditions and variable renewable generation. To address these challenges, this paper studies a hybrid deep reinforcement learning (DRL) framework based on a Proximal Policy Optimization (PPO) policy network enriched by a Graph Convolution Variation (GCV) feature extractor to improve voltage regulation issues in LV grids. In addition to ensuring that electric vehicles (EVs) achieve their required state-of-charge (SoC), the framework dynamically adjusts charging rates in real time to maintain LV-grid voltage within acceptable limits. Extensive simulation results, including detailed analysis and comparisons with the static charging method, demonstrate significant improvements in voltage regulation, and enhanced overall grid performance. The obtained results demonstrate the effectiveness of controlling EVs' charging controls in an intelligent manner to address the voltage regulation issue in low-voltage grids. © 2025 Elsevier B.V., All rights reserved.

Abstract
Low voltage (LV) grids face a challenge of effectively managing the growing presence of new loads like electric vehicles and heat pumps, along with the equally growing installation of rooftop photovoltaic panels. This paper describes practical applications of sensitivity factors, extracted from smart meter data (i.e., without resorting to grid models), to i) link voltage problems to different costumers/devices and their location in the grid, ii) manage the flexibility provided by distributed energy resources (DERs) to regulate voltage, and iii) assess favorable locations for DER capacity extensions, all with the aim of supporting the decision-making process of distribution system operators (DSOs) and the design of incentives for customers to invest in DERs. The methods are tested by running simulations based on historical meter data on six grid models provided by the EU-Joint Research Center. The results prove that it is feasible to implement advanced LV grid analysis and management tools despite the typical limitations in its electrical and topological characterisation, while avoiding the use of computationally heavy tools such as optimal power flows.

Abstract
This paper presents a novel solution integrated into the Eneida DeepGrid® platform for real-time voltage and active power estimation in low voltage grids. The tool utilizes smart grid infrastructure data, including historical data, real-time measurements from a subset of meters, and exogenous information such as weather forecasts and dynamic price signals. Unlike traditional methods, the solution does not require electrical or topological characterization and is not affected by observability issues. The performance of the tool was evaluated through a case study using 10 real networks located in Portugal, with results showing high estimation accuracy, even under scenarios of low smart meter coverage. © The Institution of Engineering and Technology 2023.

Abstract
According to the European Clean Energy Package (2019) Distribution System Operators (DSOs) shall effectively use flexibility services from local and regional assets to safely host more renewable energy sources in the electricity grid. Electricity prosumers become crucial players due to their potential to provide flexibility by adapting their production and consumption behaviour. Yet, integrating new types of assets into the distribution grid to use flexibility creates complexity and hardly predictable power flows in the distribution networks. The European H2020 demonstration project EUniversal aims to overcome the existing limitations in the use of flexibility. For that purpose, smart grid tools for grid state assessment and active system management are developed. A demonstration pilot is set up to test the flexibility value chain from congestion detection to market-based flexibility procurement via a local flexibility market. The pilot is conducted in the LV grids of the German DSO MITNETZ STROM, examining the use of flexible resources in the LV grid for congestion management. The article describes the set-up of the flexibility value chain and shows how all individual parts are integrated into the complete process. © The Institution of Engineering and Technology 2023.

Abstract
The EUniversal project, funded by the European Union, aims to establish a universal approach to the utilization of flexibility by Distribution System Operators (DSOs) and their engagement with new flexibility markets. To achieve this objective, the project team has focused on developing the Universal Market Enabling Interface (UMEI) concept. This paper presents an overview of the process of adapting grid core systems to interact with different market platforms and agents, which is a key aspect of the real-world demonstration set to take place in Portugal. © The Institution of Engineering and Technology 2023.