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
The integration of Distributed Energy Resources (DERs) into low-voltage (LV) distribution grids poses significant challenges for grid management, particularly regarding the need for accurate information on the connection phases of installations to ensure proper load balancing and to enhance hosting capacity. This paper presents a novel voltage-based phase mapping approach using the Mahalanobis-Wasserstein (MW) distance - a metric that exploits voltage time series data to accurately assign users to their corresponding phases without requiring additional hardware or prior knowledge of the grid's topology. The proposed method demonstrates strong resilience to missing data, a frequent issue in real-world deployments, and incorporates a confidence score to quantify the reliability of the phase assignments. © 2025 IEEE.

Abstract
The topology of low-voltage (LV) distribution grids is often partially known or inaccurately documented by grid operators, including line and cable characteristics, hindering the effective integration and management of Distributed Energy Resources (DERs). This paper presents a data-driven method to reconstruct LV grid topologies using only voltage measurements from customers' smart meters. The approach relies on an adapted genetic algorithm (GA) that iteratively explores candidate configurations, guided by a score function that evaluates both the physical plausibility of estimated line impedances and their consistency with noisy voltage data, which is progressively corrected throughout the process, i.e., the method also filters out errors affecting the initial measurements. The method requires no prior information on grid connectivity and demonstrates robustness to measurement noise, making it well suited for real-world deployment. © 2025 IEEE.

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.