Intensive energy consumption in the building sector remains one of the primary contributors to climate change and global warming. Within Renewable Energy Communities (RECs), improving energy management is essential for promoting sustainability and reducing environmental impact. Accurate forecasting of energy consumption at the community level is a key tool in this effort. Traditionally, engineering-based methods grounded in thermodynamic principles have been employed, offering high accuracy under controlled conditions. However, their reliance on exhaustive building-level data and high computational costs limits their scalability in dynamic REC settings. In contrast, Artificial Intelligence (AI)-driven methods provide flexible and scalable alternatives by learning patterns from historical consumption and environmental data. This study investigates three Machine Learning (ML) models, Decision Tree (DT), Random Forest (RF), and CatBoost, and one Deep Learning (DL) model, Convolutional Neural Network (CNN), to forecast community electricity consumption using real smart meter data and local meteorological variables. The study focuses on a REC in Loureiro, Portugal, consisting of 172 residential users from whom 16 months of 15 min interval electricity consumption data were collected. Temporal features (hour of the day, day of the week, month) were combined with lag-based usage patterns, including features representing energy consumption at the corresponding time in the previous hour and on the previous day, to enhance model accuracy by leveraging short-term dependencies and daily repetition in usage behavior. Models were evaluated using Mean Squared Error (MSE), Mean Absolute Percentage Error (MAPE), and the Coefficient of Determination $R^2$. Among all models, CatBoost achieved the best performance, with an MSE of 0.1262, MAPE of 4.77%, and an $R^2$ of 0.9018. These results highlight the potential of ensemble learning approaches for improving energy demand forecasting in RECs, supporting smarter energy management and contributing to energy and environmental performance.

In recent years, the frequency of extreme events such as floods, droughts, and heat waves has been increasing due to climate change. To mitigate and reduce the devastating effects of these phenomena, finding a common solution that directly involves citizens in the energy transition process is crucial. In this context, the European Union, through the Green Deal, has set the ambitious goal of achieving carbon neutrality by 2050, and, through the REPowerEU plan, covering at least 42.5% of total energy consumption with renewable energy sources by 2030. The renewable energy communities, introduced by the EU Directive 2018/2001, represent a key tool for achieving these European targets. Renewable energy communities are based on a bottom-up business model as they directly engage citizens and facilitate the expansion of renewable energy generation. Moreover, in several countries, including Italy, economic support schemes have been introduced to incentivize the development of these energy-sharing configurations. This paper analyzes a specific fair revenue distribution model among community members, taking the renewable energy community in Benevento (Southern Italy) province as a case study. The analysis highlights how variations in user types and energy consumption impact individual contributions. This underscores the need for an economic distribution model with a dynamic and flexible structure, allowing adaptation to different configurations. Therefore, the used algorithm should incorporate specific parameters that account for the different operating conditions, such as the presence of third-party producers, prosumers, and high-energy consumers, as well as solidarity-based objectives, such as addressing energy poverty. All these factors are crucial, as the implementation of an inaccurate economic distribution model could favor some users at the expense of others and, at the same time, promote environmentally and energetically unsustainable behaviors.

Renewable energy communities (RECs) have emerged as one of the most promising instruments for advancing the social, economic, and environmental dimensions of the energy transition. Based on the principles of open participation, non-profit governance, and local value creation, RECs hold significant potential to alleviate energy poverty, revitalize inland areas, foster local employment, enhance the social acceptance of renewable energy infrastructure, and support sustainable mobility. Despite a well-defined regulatory framework, the deployment of RECs in Italy remains limited in both scale and scope. Current configurations are typically characterized by fewer than two generation units, a median installed capacity of approximately 12 kW, and around ten members. The paper aims to demonstrate that the gap between the theoretical potential of REC and their current implementation reflects a structural issue, which has led to the proliferation of models driven primarily by incentive schemes rather than by strategic, community-centered planning. Through a systematic review of the multidimensional benefits associated with RECs and an analysis of the structural barriers hindering their development, the study identifies the aggregator as a key missing organizational enabler. This actor can bridge citizens, institutions, industry, and the public sector, thereby translating regulatory intent into sustainable and scalable community energy initiatives.

Residential batteries in energy communities usually run local rule-based controllers whose community-level effect is rarely checked against measured data. This study uses one year of smart-meter, PV and battery records from a real 20-household Irish community (24 kWp PV, 200 kWh storage) to test how much can be achieved with locally available data only. The existing controllers charged all batteries in the same night-tariff hours. With household flows netted hourly at the community level, this raised grid import by 14.5% and CO₂ emissions by 15.8% compared with no batteries, raised the maximum hourly import from 33 to 83 kW, and created a new morning peak. A lightweight framework, combining a drift-adaptive LightGBM load forecast and a mixed-integer dispatch with real-time correction, reduced grid import by 10.5–13.5%, emissions by 11.6–14.6%, and energy imported above a 14.1 kW reference threshold by 87% relative to the measured operation, with each scenario computed in seconds. A forecast-free controller acting on the same threshold reduced this exceedance at least as much, while the forecast-based optimisation lowered the import by a further 2.6%. LightGBM was 10.9% more accurate than a seven-day average, yet its dispatch did not differ significantly (Wilcoxon p = 0.53); correcting the systematic underestimation of daily peaks reduced the energy above the threshold by 14%. Sharing PV reduced imports by 9.7% and benefited mainly households without PV, whereas pooled storage mainly relieved the grid, with the effect increasing with better information.

Renewable Energy Communities (RECs) are a key mechanism for accelerating the transition toward decentralised, low-carbon electricity systems. However, designing community photovoltaic (PV) and battery storage systems requires balancing conflicting objectives spanning technical performance, economic viability, environmental sustainability, and equitable benefit distribution. This paper proposes a unified 4E optimisation framework that integrates energy, economic, environmental, and equity objectives for residential PV--battery RECs. The framework couples hourly energy dispatch, thermo-economic assessment, carbon-emission accounting, and a Hybrid Capped benefit-allocation mechanism within a common optimisation environment. Two complementary techniques are employed: the Non-dominated Sorting Genetic Algorithm II (NSGA-II) for Pareto-optimal solutions and the Tree-structured Parzen Estimator (TPE) for single-objective cost optimisation. The methodology is demonstrated on two RECs under contrasting regulatory environments, a 102-household community in Italy and a 20-household community in Ireland, incorporating country-specific tariffs, export remuneration, incentives, PV generation profiles, and technology costs. Performance is evaluated through energy (SCR, SSR), economic (NPV, IRR, payback period, annualised total cost), environmental (avoided CO$_2$), and equity (Gini coefficient) indicators, with robustness assessed through multi-seed reproducibility, one-at-a-time analyses, price-escalation scenarios, and correlated Monte Carlo simulations. The results show that optimal PV--battery configurations are strongly influenced by tariff structures, incentives, and charging strategies. Rather than optimising fairness directly, the transparent, revenue-neutral Hybrid Capped rule protects low-consumption and energy-efficient members, reducing the Gini coefficient from approximately 0.19--0.25 under load-proportional sharing to 0.04--0.12 while preserving strong thermo-economic performance. The framework provides a reproducible decision-support methodology for designing residential RECs that jointly address technical efficiency, economic profitability, environmental sustainability, and social equity.