In this paper, we propose a scalable Big Data framework that collects the data from smart meters and weather sensors, pre-processes and loads it into a NoSQL database that is capable to store and further process large volumes of heterogeneous data. Then, a set of Machine Learning (ML) algorithms are designed and implemented to determine the load profiles and forecast the electricity consumption for residential buildings for the next 24 hours. For the Short-Term Load Forecast (STLF), a Feed-Forward Artificial Neural Network (FF-ANN) algorithm with backtracking adjustment of the learning rate that extends and optimizes the Nesterov learning method is proposed. Its performance is compared with six algorithms, i.e. FF-ANN with well-known learning methods, namely Momentum and Nesterov, Non-linear AutoRegressive with eXogenous (NARX), Deep Neural Network (DNN), Gradient Tree Boosting (GTB) and Random Forests (RF) that are competitive and powerful ML algorithms which have been successfully used for load forecast. Hence, for STLF, the seven algorithms are executed simultaneously and the best one is automatically selected considering its accuracy in terms of Root Mean Square Errors (RMSE). The proposed methodology contains the steps required to implement the Big Data framework, i.e. data pre-processing, transformation and loading, the configuration of the ML algorithms for dimensionality reduction, clustering, STLF with different algorithms from which the Best Performant Algorithm (BPA) is automatically selected to provide STLF for the next 24 hours. The methodology is ultimately tested considering a real case of a residential smart building.

When analyzing smart metering data, both reading errors and frauds can be identified. The purpose of this analysis is to alert the utility companies to suspicious consumption behavior that could be further investigated with on-site inspections or other methods. The use of Machine Learning (ML) algorithms to analyze consumption readings can lead to the identification of malfunctions, cyberattacks interrupting measurements, or physical tampering with smart meters. Fraud detection is one of the classical anomaly detection examples, as it is not easy to label consumption or transactional data. Furthermore, frauds differ in nature, and learning is not always possible. In this paper, we analyze large datasets of readings provided by smart meters installed in a trial study in Ireland by applying a hybrid approach. More precisely, we propose an unsupervised ML technique to detect anomalous values in the time series, establish a threshold for the percentage of anomalous readings from the total readings, and then label that time series as suspicious or not. Initially, we propose two types of algorithms for anomaly detection for unlabeled data: Spectral Residual-Convolutional Neural Network (SR-CNN) and an anomaly trained model based on martingales for determining variations in time-series data streams. Then, the Two-Class Boosted Decision Tree and Fisher Linear Discriminant analysis are applied on the previously processed dataset. By training the model, we obtain the required capabilities of detecting suspicious consumers proved by an accuracy of 90%, precision score of 0.875, and F1 score of 0.894.

Renewable energy systems (RES) are reliable by nature; the sun and wind are theoretically endless resources. From the beginnings of the power systems, the concern was to know “how much” energy will be generated. Initially, there were voltmeters and power meters; nowadays, there are much more advanced solar controllers, with small displays and built-in modules that handle big data. Usually, large photovoltaic (PV)-battery systems have sophisticated energy management strategies in order to operate unattended. By adding the information collected by sensors managed with powerful technologies such as big data and analytics, the system is able to efficiently react to environmental factors and respond to consumers’ requirements in real time. According to the weather parameters, the output of PV could be symmetric, supplying an asymmetric electricity demand. Thus, a smart adaptive switching module that includes a forecasting component is proposed to improve the symmetry between the PV output and daily load curve. A scaling approach for smaller off-grid systems that provides an accurate forecast of the PV output based on data collected from sensors is developed. The proposed methodology is based on sensor implementation in RES operation and big data technologies are considered for data processing and analytics. In this respect, we analyze data captured from loggers and forecast the PV output with Support Vector Machine (SVM) and linear regression, finding that Root Mean Square Error (RMSE) for prediction is considerably improved when using more parameters in the machine learning process.

The progress of ICT technologies, day-ahead forecast, home energy management systems, implementation of smart meters, and Distributed Energy Sources (DER) enables new business opportunities for prosumers to locally trade the surplus via blockchain platforms leading to considerable advantages at the community level. The current research handles settlement similar to a centralized market that it is not necessarily the best solution for blockchain. Nonetheless, the settlement is essential as sellers and buyers perceive the attractiveness of the local trading through the market results. In this paper, we propose two novel and efficient settlement mechanisms (Global Balancing Settlement GBS and Splitting Settlement SS) for Peer-to-Peer (P2P) electricity exchange enhancing the performance of the classic Pairwise Settlement PS. These will be written as stored procedures embedded into the smart contracts along with auctioning procedures. The simulations are performed using a small residential community with 30% of the electricity that can be locally traded to lower the bills and unstress the public grid. The performance of the two proposed settlement methods is proved by the 14 scenarios that thoroughly indicate that GBS and SS provide better results for both sellers and buyers than PS. In the reference scenario, with GBS, sellers have the highest encashments with almost 4% more, whereas buyers encounter the lowest payments with almost 5% less than in case of the classic settlement. Starting from reference scenario, alternative scenarios are envisioned to extend the analyses and assess the performance of the settlement mechanisms. The highest gain is recorded with GBS mechanism: almost 8.8% for sellers and 6.5% for buyers. Another interesting outcome is that GBS is providing better results than SS. When deviations are small, SS provides almost 6% gain for both sellers and buyers, but when they increase, the gain is exceedingly small or none.

In this paper, we investigated the role of generative AI in education in academic publications extracted from Web of Science (3506 records; 2019–2024). The proposed methodology included three main streams: (1) Monthly analysis trends; top-ranking research areas, keywords and universities; frequency of keywords over time; a keyword co-occurrence map; collaboration networks; and a Sankey diagram illustrating the relationship between AI-related terms, publication years and research areas; (2) Sentiment analysis using a custom list of words, VADER and TextBlob; (3) Topic modeling using Latent Dirichlet Allocation (LDA). Terms such as “artificial intelligence” and “generative artificial intelligence” were predominant, but they diverged and evolved over time. By 2024, AI applications had branched into specialized fields, including education and educational research, computer science, engineering, psychology, medical informatics, healthcare sciences, general medicine and surgery. The sentiment analysis reveals a growing optimism in academic publications regarding generative AI in education, with a steady increase in positive sentiment from 2023 to 2024, while maintaining a predominantly neutral tone. Five main topics were derived from AI applications in education, based on an analysis of the most relevant terms extracted by LDA: (1) Gen-AI’s impact in education and research; (2) ChatGPT as a tool for university students and teachers; (3) Large language models (LLMs) and prompting in computing education; (4) Applications of ChatGPT in patient education; (5) ChatGPT’s performance in medical examinations. The research identified several emerging topics: discipline-specific application of LLMs, multimodal gen-AI, personalized learning, AI as a peer or tutor and cross-cultural and multilingual tools aimed at developing culturally relevant educational content and supporting the teaching of lesser-known languages. Further, gamification with generative AI involves designing interactive storytelling and adaptive educational games to enhance engagement and hybrid human–AI classrooms explore co-teaching dynamics, teacher–student relationships and the impact on classroom authority.

Research background: Over the last ten years, a substantial amount of scholarly research has delved into energy communities (ECs) from diverse viewpoints. These ECs are extremely important in setting the pathway to a clean energy transition. Purpose of the article: Our objective is to glean valuable insights from publications indexed in the Web of Science (WoS) database to deepen our comprehension of ECs and their academic discourse. Methods: Data analytics, factorial analysis, and more complex natural language processing (NLP) techniques such as latent Dirichlet allocation (LDA) are implemented to extract valuable insights from over 1000 WoS publications relevant in the EC field. The primary contribution of this study lies in furnishing details regarding the key contributors to the EC scholarly landscape, including authors, their affiliations, universities, and countries of origin. Additionally, we aim to elucidate the prevalent keywords and thematic approaches employed in their research endeavors. Findings & value added: Considering the extracted dataset, an annual growth rate of 21.15% has been recorded, highlighting the research community’s interest in the field of ECs. Furthermore, three topics are optimally obtained. Overall, a coherence score of 0.44 suggests that the LDA model performs adequately in terms of topic interpretation. Topic 1 relates to community-based energy initiatives. Topic 2, featuring terms like “grid,” “study” and “EU” alongside “energy” and “community,” suggests a focus on energy systems. Topic 3 includes terms such as “generation,” “analysis” and “consumption,” indicating a topic that is centered around the technical or analytical aspects of energy production and usage. This study underscores how the alignment between state laws and EU directives in supporting ECs can serve as a model for other regions. The findings suggest that similar policy frameworks could be effectively adapted to different national contexts, providing valuable insights for countries looking to enhance their renewable energy strategies.