Explore the vast range of titles available.

The massive integration of variable renewable energy sources (RESs) poses the gradual necessity for new power system architectures with wide implementation of distributed battery energy storage systems (BESSs), which support power system stability, energy management, and control. This research presents a methodology and realization of a set of 11 BESS models based on different machine learning methods. The performance of the proposed models is tested using real-life BESS data, after which a comparative evaluation is presented. Based on the results achieved, a valuable discussion and conclusions about the models’ performance are made. This study compares the results of feedforward neural networks (FNNs), a homogeneous ensemble of FNNs, multiple linear regression, multiple linear regression with polynomial features, decision-tree-based models like XGBoost, CatBoost, and LightGBM, and heterogeneous ensembles of decision tree modes in the day-ahead forecasting of an existing real-life BESS in a PV power plant. A Bayesian hyperparameter search is proposed and implemented for all of the included models. Among the main objectives of this study is to propose hyperparameter optimization for the included models, research the optimal training period for the available data, and find the best model from the ones included in the study. Additional objectives are to compare the test results of heterogeneous and homogeneous ensembles, and grid search vs. Bayesian hyperparameter optimizations. Also, as part of the deep learning FNN analysis study, a customized early stopping function is introduced. The results show that the heterogeneous ensemble model with three decision trees and linear regression as main model achieves the highest average R2 of 0.792 and the second-best nRMSE of 0.669% using a 30-day training period. CatBoost provides the best results, with an nRMSE of 0.662% for a 30-day training period, and offers competitive results for R2—0.772. This study underscores the significance of model selection and training period optimization for improving battery performance forecasting in energy management systems. The trained models or pipelines in this study could potentially serve as a foundation for transfer learning in future studies.

The success of the energy transition in Europe depends on the engagement of citizens and the sustainable replacement of conventional generation with renewable production. Highlights of the PAN European Technology Energy Research Approach (PANTERA) project, a H2020 coordination and support action, are presented in this paper. In broad terms, PANTERA offers a forum for actors in the smart grid to support the expansion of activities in smart grid research, demonstration, and innovation, especially in the below-average spending member states in the European Union (EU). The focus of this paper is on those activities of the project consortium related to the identification of gaps and barriers in regulations, standards, and network codes that hinder the sustainable engagement of energy citizens in the energy transition. The paper summarises the challenges to citizen engagement in the energy transit and considers the enablers that make the engagement of citizens viable, e.g., demand response (DR), renewable energy resources (RESs), and modern designs for local energy markets (LEMs). We focus on the barriers to the enablers that are explicitly and implicitly related to regulations, standards, and network codes and explore aspects of the relevant regulations and standards of the sample below-average spending member states. A specific case study of a research and demonstration project in Ireland for updating the network codes is also presented to demonstrate the ways in which member states are attempting to remove the barriers and enable citizen participation in the smart energy transition. Finally, the opportunities to foster smart grid research and innovation through shared knowledge and insights offered by the PANTERA European Interconnection for Research Innovation and Entrepreneurship (EIRIE) platform are highlighted.

The integration of smart grid technologies in interconnected power system networks presents multiple challenges for the power industry and the scientific community. To address these challenges, researchers are creating new methods for the validation of: control, interoperability, reliability of Internet of Things systems, distributed energy resources, modern power equipment for applications covering power system stability, operation, control, and cybersecurity. Novel methods for laboratory testing of electrical power systems incorporate novel simulation techniques spanning real-time simulation, Power Hardware-in-the-Loop, Controller Hardware-in-the-Loop, Power System-in-the-Loop, and co-simulation technologies. These methods directly support the acceleration of electrical systems and power electronics component research by validating technological solutions in high-fidelity environments. In this paper, members of the Survey of Smart Grid International Research Facility Network task on Advanced Laboratory Testing Methods present a review of methods, test procedures, studies, and experiences employing advanced laboratory techniques for validation of range of research and development prototypes and novel power system solutions.

While the number of the vehicle actuated with liquid fuels are settled, the count of electric vehicles is increasing. For the present moment most of them are scheduled for daily urban usage. This paper presents an analytical approach for estimation of the impact of electrical vehicle (EV) battery charging on the distribution grid. Based on the EV charge profile, load curve and local distributed generation the grid nodes, the time variation of grid parameters is obtained. A set of typical load profiles of EV charging modes is studied and presented. A software implementation and a 24h case study of low voltage distribution network with EV charging devices is presented in order to illustrate the approach and the impacts of EV charging on the grid. In the current paper an approach using variable nonlinear algebraic equations for dynamic time domain analysis of the charge of the electric vehicles is presented. Based on the results, the challenges due to EV charging in distribution networks including renewable energy sources are discussed. This approach is widely applicable for various EV charging and distributed energy resources studies considering control algorithms, grid stability analysis, smart grid power management and other power system analysis problems.