Abstract
The increasing integration of renewable energy sources (RES) at different voltage levels of the distribution grid has led to technical challenges, namely voltage and congestion problems. Conversely, the integration of new Distributed Energy Resources (DER) provides the necessary flexibility to accommodate higher RES integration levels. This work describes the development of innovative functional modules, based on optimal power flow calculations and grid forecasting, dedicated to the predictive management of the distribution grid considering DER flexibility, which are integrated into a commercial SCADA/DMS solution. © The Institution of Engineering and Technology 2023.

Abstract
This article presents original probabilistic forecasting models for day-ahead hourly energy generation forecasts for a photovoltaic (PV) plant, based on a semi-parametric approach using three deterministic forecasts. Input information of these new models consists of data of hourly weather forecasts obtained from a Numerical Weather Prediction model and variables related to the sun position for future instants. The proposed models were satisfactorily applied to the case study of a real-life PV plant in Portugal. Probabilistic benchmark models were also applied to the same case study and their forecasting results compared with the ones of the proposed models. The computer results obtained with these proposed models achieve better point and probabilistic forecasting evaluation indexes values than the ones obtained with the benchmark models. (c) 2023 The Author(s). Published by Elsevier Ltd. This is an open access article under theCCBY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

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
In a photovoltaic power plant (PVPP), the DC-AC converter (inverter) is one of the components most prone to faults. Even though they are key equipment in such installations, their fault detection techniques are not as much explored as PV module-related issues, for instance. In that sense, this paper is motivated to find novel tools for detection focused on the inverter, employing machine learning (ML) algorithms trained using a hybrid dataset. The hybrid dataset is composed of real and synthetic data for fault-free and faulty conditions. A dataset is built based on fault-free data from the PVPP and faulty data generated by a digital twin (DT). The combination DT and ML is employed using a Clarke/space vector representation of the inverter electrical variables, thus resulting in a novel feature engineering method to extract the most relevant features that can properly represent the operating condition of the PVPP. The solution that was developed can classify multiple operation conditions of the inverter with high accuracy.

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
Artificial intelligence (AI) brings great potential but also risks to the electricity industry. Following the EU's current regulatory proposal, the EU Regulation for Artificial Intelligence (AI Act), there will be direct, potentially adverse effects on companies of the electricity industry in Europe and beyond, as well as those active in the development of AI systems. In this paper, we develop a replicable framework for estimating compliance costs for different electricity market agents that will need to comply with the numerous requirements the AI Act imposes. The electricity systems of Austria, Greece and Switzerland are used as case-studies. We estimate annual, aggregated costs for electricity market agents ranging from less than one million to almost 200 million Euros per country, depending on compliance costs scenarios. Results suggest that a profit growth of 10% through AI utilization is needed to offset the highest added compliance cost of the AI Act on electricity market agents. Eventually, we further show how to assess the regional differences of these costs added to system operation, providing spatially disaggregated compliance costs estimates that consider the structural differences of the electricity industry within 26 Swiss cantons.