Towards zero CO2 emissions society, large shares of renewable energy sources and storage systems are integrated into microgrids as part of the electrical grids for energy exchange aiming to effectively reduce the stress from the transmission grid. However, energy management within and across microgrids is complicated due to many uncertainties such as imprecise knowledge on energy production and demand, which makes energy optimization challenging. In this paper, we present an open architecture that uses machine learning algorithms at the edge to predict energy consumption and production for energy management in smart microgrids. Such predictions are aggregated across different prosumers at a centralized marketplace in the Cloud using Kafka Streams and OpenSource IoT platforms. Using pluggable optimization algorithms, different microgrids can implement different strategies for real-time optimal energy schedules. The proposed architecture is evaluated in terms of scalability and accuracy of predictions. Our heuristics can effectively optimize medium-sized microgrids.

In this paper, we address the optimal operation of energy communities, under energy production and consumption uncertainties. In the nominal case, the operational problem is formulated as the maximization of the profit of the community over a given time horizon. Inspired by the regulation adopted in Italy since 2020, the profit includes an incentive for the self-consumption realized at the community level in each time period. In the presence of uncertainties, we use a robust formulation aiming at maximizing the worst profit achievable when energy production and consumption deviate from their nominal values. The model results in a robust scheduling policy of battery charging/discharging, guaranteeing feasible operation of the community in all scenarios of the uncertainty set. On the other hand, numerical results show that the nominal scheduling policy may suffer from a high constraint violation probability.

Energy management within microgrids under the presence of large number of renewables such as photovoltaics is complicated due to uncertainties involved. Randomness in energy production and consumption make both the prediction and optimality of exchanges challenging. In this paper, we evaluate the impact of uncertainties on optimality of different robust energy exchange strategies. To address the problem, we present AIROBE, a data-driven system that uses machine-learning-based predictions of energy supply and demand as input to calculate robust energy exchange schedules using a multiband robust optimization approach to protect from deviations. AIROBE allows the decision maker to tradeoff robustness with stability of the system and energy costs. Our evaluation shows, how AIROBE can deal effectively with asymmetric deviations and how better prediction methods can reduce both the operational cost while at the same time may lead to increased operational stability of the system.

Renewable Energy Communities (RECs), characterized by localized energy generation and consumption, are a key enabler for enhancing renewable energy utilization, cost-efficient planning and clean energy transition. However, optimizing RECs operations is challenging due to the complex interplay of different stakeholders with conflicting requirements. The complexity of managing such systems often leads to a lack of transparent and reliable decision-making, creating barriers for actors within the community. This paper explores the integration of Generative AI into Renewable Energy Communities (RECs) to enhance the transparency, explainability and accessibility of energy management systems (EMSs) that depend on solving optimization problems. We propose a novel framework, Chat-SGP, which uses generative AI to synthesize optimization modeling code to provide actionable, explainable insights for managing the REC operations. Our approach allows us to interact with the EMS through natural language queries, enhancing the system’s accessibility and user-friendliness. Our evaluation shows that using GPT-4 with in-context learning performs 96.72% accuracy on average in generating correct answers.

Accurate short-term load forecasting is essential for energy-efficient building operations, however, many buildings lack sufficient historical data to train reliable predictive models. This paper investigates the use of instance-based transfer learning to improve forecasting performance in data-scarce buildings by reusing models trained on similar, data-rich buildings. We cluster buildings of various types based on their energy consumption profiles using dynamic time warping and hierarchical clustering. Within each cluster, we fine-tune XGBoost and LSTM models pretrained on source buildings (with sufficient data) to forecast the consumption in target buildings (with limited data) with access to increasing percentage of their original limited data of 7, 14, 21, 28, ... , 245 days. Our evaluation compares the performance against models trained from scratch using the same limited data. Our results show that transfer learning significantly improves forecasting accuracy in highly data-constrained settings, reducing RMSE by up to 40%. However, as more training data becomes available, its benefits diminish, and baseline models eventually outperform transferred ones beyond an average threshold of 140–168 days.