Keywords: DERs, flexibility, markets, services, TSO-DSO coordination

Renewable Energy Communities (RECs) represent a promising approach to accelerate the energy transition by enabling collective self-consumption and local energy management. However, the intermittent nature of renewable generation and the increasing integration of Electric Vehicles (EVs) pose significant challenges for optimal energy scheduling. This paper proposes a day-ahead multi-objective optimization model for RECs that simultaneously considers load shifting, EV charging coordination, and Vehicle-to-Grid (V2G) technology to minimize operational costs while maintaining user comfort. The model is formulated as a Mixed Integer Linear Programming (MILP) problem and implements the epsilon-constraint method to generate Pareto-optimal solutions, revealing trade-offs between economic efficiency and user preferences. Load shifting is modeled using a Multiple Knapsack Problem (MKP) approach with penalty functions to account for deviations from preferred time slots. Results from a case study composed of three different objectives demonstrated that, in the best case, self-sufficiency can be increased from 17.06% to 99.27%, and a significant reduction from 8.54 € to −3.47 € can be achieved in a single day.

Keywords: renewable energy communities; load balancing; load shifting; multiple knapsack; mixed integer linear programming; electric vehicles; vehicle-to-grid

Peer-to-peer trading has emerged as a complement to traditional electricity supply models, with potential benefits for residential consumers and grid infrastructure. This study presents a model-based comparative analysis of three peer-to-peer market designs: auction-based pricing (ABP), supply-demand ratio pricing (SDR), and mid-market rate pricing (MMR), under both real-time pricing and fixed retail pricing. Unlike most prior work, our study incorporates long-term investment decisions and examines local grid issues. This enables a comprehensive evaluation of how different P2P pricing designs affect distributed energy resource (DER) adoption, consumer costs, system efficiency, and grid stress. We also assess whether P2P trading provides added value in settings where consumer decisions are already coordinated by dynamic prices. Our results show that peer-to-peer trading significantly reduces consumer electricity costs, but savings are less pronounced under dynamic pricing contracts. Of the mechanisms evaluated, ABP yields the lowest total consumer cost but can exacerbate local grid issues. In contrast, the MMR and SDR mechanisms alleviate congestion by spreading peak offtake and injection more evenly. Notably, we show that peer-to-peer trading could serve as a potential alternative to real-time pricing contracts, offering comparable benefits in terms of self-consumption and cost savings, while shielding consumers from price risk.

Keywords: peer-to-peer; local electricity markets; energy trading; distributed energy resources

Energy consumption profiles are a critical component of energy management strategies. With the recent widespread adoption of smart meters, there is a pressing need to develop robust methodologies for obtaining, characterizing, and visualizing these profiles. This paper presents a comparative analysis of various clustering methods for deriving consumer electricity profiles, aiming to identify the most suitable techniques for big time-series data and to evaluate how the granularity of the data influences the final profiles. Four approaches were considered for obtaining house electricity consumption profiles: K-means, Principal Component Analysis (PCA) combined with K-means, Self-Organizing Maps (SOM), and SOM combined with K-means. Additionally, an iterative study with the scores silhouette coefficient and Davies-Bouldin index validated the subjective indications from the elbow method. The results demonstrate that hybrid approaches offer superior performance compared to conventional clustering models, highlighting the effectiveness of combining PCA and SOM in improving model generalization and supporting more targeted energy management strategies. SOM combined with K-means provides the best clustering quality across all tested scenarios, making it the preferred method when computational resources are not a limiting factor. On the other hand, PCA combined with K-means highlights a good balance between meaningful profiles and the capacity to handle large datasets effectively.

Keywords: electricity, self-organizing feature maps, principal component analysis, buildings, indexes, energy management, smart meters, europe, energy consumption, forecasting

This work explores the effectiveness of explainable artificial intelligence in mapping solar photovoltaic power outputs based on weather data, focusing on short-term mappings. We analyzed the impact values provided by the Shapley additive explanation method when applied to two algorithms designed for tabular data—XGBoost and TabNet—and conducted a comprehensive evaluation of the overall model and across seasons. Our findings revealed that the impact of selected features remained relatively consistent throughout the year, underscoring their uniformity across seasons. Additionally, we propose a feature selection methodology utilizing the explanation values to produce more efficient models, by reducing data requirements while maintaining performance within a threshold of the original model. The effectiveness of the proposed methodology was demonstrated through its application to a residential dataset in Madeira, Portugal, augmented with weather data sourced from SolCast.

Keywords: explainable artificial intelligence; feature selection; machine learning; photovoltaic seasonality

The focus on the development of control strategies for Local Energy Systems is a hot topic of research for the inclusion of distributed renewable energy resources into the energy ecosystem. Although there has been significant research on the application of pure data-driven Machine Learning methods to develop these control strategies, the paradigm of combining scientific computing with the data-driven approaches through a multi-model method is still unexplored. This paper provides one of the first multi-model approaches of scientific machine learning in a real demonstrator site. The architecture proposed connects Agent-Based Modeling(Anylogic-Java) for stakeholder simulation with Pandapower(Python) for power flow analysis, facilitated by state-of-the-art transformer-based forecasting (Chronos 2) and Model Predictive Control (MPC)(Python). The results demonstrate a reduction of peak load and equivalent battery cycles and better performance in comparison to pure data-driven forecasting.

Keywords: energy communities, scientific machine learning (SciML), physics informed neural networks (PINN), multimodel methods, model predictive control

This paper proposes a unified classification framework for local energy sharing and trading by introducing six fundamental models that capture the main approaches used in practice, piloted in demonstration projects, and studied in the literature. The framework follows a decision-tree that first distinguishes collective asset sharing, where members co-invest in shared assets (e.g., PV or community batteries) and benefit through predefined capacity, energy, or revenue allocation, from individual asset-based sharing, where participants exchange energy based on their own generation, storage, or flexible demand. Individual sharing is further divided into centralized peer-to-pool/pool-to-peer designs without bilateral matching and distributed designs with explicit peer-to-peer transactions that support counterpart-specific preferences and prices. A broad set of real-world initiatives are then mapped onto the framework, while assessing each model’s operational strengths and implementation challenges.

Keywords: local energy sharing, peer-to-peer trading, energy communities, electricity markets, distributed energy resources

As energy systems evolve, protecting and empowering consumers is vital, enabling participation in decentralized electricity markets and maximizing benefits from energy resources. The integration of Distributed Energy Resources (DER) and Renewable Energy Sources (RES) fosters new energy communities, shifting from centralized systems to distributed structures. Consumers can sell excess production to neighbors, increasing income, reducing bills, and advancing energy transition goals. This paper proposes a community-based peer-to-peer (P2P) energy market model that reduces costs while respecting network constraints. Using the Alternating Direction Method of Multipliers (ADMM), ensures privacy enhancement, decentralization, and scalability. The Relaxed Branch Flow Model (RBFM) manages constraints, and Electric Vehicles (EVs) reduce imports and costs through strategic discharging. Tested on a 33-bus distribution network, the ADMM-based approach aligns closely with a centralized benchmark, showing minor discrepancies while maintaining system reliability. This model underscores the potential of decentralized markets for consumer- centric, flexible, and efficient energy trading.

Keywords: alternating direction method of multipliers, distributed energy resources, distributed optimization, energy trading, peer-to-peer markets 

Forecasting algorithms for photovoltaic (PV) power generation play an important role in energy management systems. Nevertheless, the precision of machine learning models is significantly compromised when historical data is limited. This situation is challenging for new plants for which a long history of measurements is not yet available. The unpredictable nature of the weather gives the perception that a competitive forecast requires a substantial amount of data and a very complicated algorithm. However, in this manuscript, it was found that using five historical days for the inverse quantification of uncertainty, can implicitly describe complex non-linear relationships between last five-day records and day-ahead PV power generation. The proposed approach learns the emerging patterns across various seasons throughout the year without relying on exogenous data such as air temperature, wind speed, pressure, cloud cover, and relative humidity. Results using real-world data collected at the microgrid of the University of Campinas (UNICAMP) confirm that our proposed model outperforms previous state-of-the-art deep learning models as Long short-term memory (LSTM), Gated Recurrent Unit (GRU) and traditional Autoregressive Integrated Moving Average (ARIMA) statistical model, using limited data. The proposed approach is flexible and can be easily adapted to other PV power generation systems with limited data. The source code is available at https://github.com/byronacunia/Day-Ahead-Photovoltaic-Power-Forecasting-with-Limited-Data.git

Keywords: adaptive learning, forecasting, photovoltaic, statistical approach

As energy systems evolve, protecting and empowering consumers is vital, enabling participation in decentralized electricity markets and maximizing benefits from energy resources. The integration of Distributed Energy Resources (DER) and Renewable Energy Sources (RES) fosters new energy communities, shifting from centralized systems to distributed structures. Consumers can sell excess production to neighbors, increasing income, reducing bills, and advancing energy transition goals. This poster proposes a community-based peer-to-peer (P2P) energy market model that reduces costs while respecting network constraints. Using the Alternating Direction Method of Multipliers (ADMM), ensures privacy enhancement, decentralization, and scalability. The Relaxed Branch Flow Model (RBFM) manages constraints, and Electric Vehicles (EVs) reduce imports and costs through strategic discharging. Tested on a 33-bus distribution network, the ADMM-based approach aligns closely with a centralized benchmark, showing minor discrepancies while maintaining system reliability. This model underscores the potential of decentralized markets for consumer-centric, flexible, and efficient energy trading.