The European Union’s vision for energy transition not only foresees decarbonization of the electricity sector, but also requires commitment across different sectors such as gas, heating, and cooling through an integrated approach. It also sets local energy communities at the center of the energy transition as a bottom-up approach to achieve these ambitious decarbonization goals. The energy hub is seen as a promising conceptual model to foster the optimization of multi-carrier energy systems and cross-sectoral interaction. Especially in the context of local energy communities, the energy hub concept can enable the optimal design, management, and control of future integrated and digitalized networks where multiple energy carriers operate seamlessly and in complementarity with each other. In that sense, the optimal design and operation of energy hubs are of critical importance, especially under the effect of multiple objectives taking on board not only technical, but also other aspects that would enable the sustainability of local energy communities, such as economic and environmental. This paper aims to provide an in-depth review of the literature surrounding the existing state-of-the-art approaches that are related to the design and operation optimization of energy hubs by also exploring their interaction with the external network and multiple markets. As the planning and operation of an energy hub is a multifaceted research topic, this paper covers issues such as the different optimization methods, optimization problems formulation including objective functions and constraints, and the hubs’ optimal market participation, including flexibility mechanisms. By systematizing the existing literature, this paper highlights any limitations of the approaches so far and identifies the need for further research and enhancement of the existing approaches.

The main goal of eNeuron H2020 project (Nov 2020-Oct. 2024, ID: 957779) is to develop innovative tools for the optimal design and operation of local energy communities, integrating distributed energy resources and multiple energy carriers at different scales. This paper presents a review study of the enabling conditions for the deployment of integrated local energy communities (ILECs) in Europe, performed within the project. The enabling conditions are addressed by defining the key actors and their interests in the implementation of an energy community at local level and through a detailed mapping of the enabling and emerging energy and information and communication technologies at both household and community levels. Special focus is also on mapping of the demand-side flexibility technologies to understand the benefits of local flexibility and impacts on the larger systems. In such analysis, the key issues for implementation and adaptation of this new energy paradigm are investigated through covering technological, socio-economic, environmental, and regulatory aspects.

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.