In modern digital ecosystems, managing heterogeneous data sources is a significant challenge, particularly within Renewable Energy Communities (RECs), where multiple energy vectors, such as electricity, heating, and water, must be integrated seamlessly. The GAIA meta-platform addresses the persistent fragmentation of IoT ecosystems by enabling federated access, semantic harmonization, and cross-domain analytics across heterogeneous data silos. Designed to support both expert and non-expert users, GAIA combines modular data processing, a Python SDK, and an AI-driven conversational agent (i.e., GAIA Chat) to facilitate intuitive interaction with multi-source datasets. This paper presents the platform's architecture and functionalities, emphasizing its role in advancing data-driven services for RECs. Finally, a real-world deployment demonstrates GAIA's ability to integrate energy and water data, enabling advanced use cases such as cross-domain anomaly detection and indirect consumption estimation. The results validate GAIA as a scalable, domain-agnostic infrastructure capable of supporting intelligent services in complex smart environments.

Despite of the global environmental crisis with record-high CO 2 levels, urgent climate action is imperative. The EU's ambitious emission reduction targets and the goal of climate neutrality by 2050 underline the severity of the situation. The Italy case study encounters challenges aligning with these objectives, necessitating significant emission cuts despite advancements in renewable energy and reduced energy consumption. Renewable Energy Communities (RECs) emerge as vital players, focusing on local production, consumption, and management of electrical enerzy. Our research introduces the GAIA federated software meta-platform, addressing the lack of multi-energy vector management by integrating diverse Internet-of-Things (IoT) software infrastructures. It simplifies the development of multi-energy vector services by amalgamating data from federated simple vector IoT infrastructures. GAIA aims to bridge the information gap on resource consumption and interconnections, benefiting RECs citizens and service providers. The platform enhances transparency, facilitating informed decision-making for REC stakeholders and it provides new opportunities and perspectives.

Nonintrusive load monitoring allows to estimate the energy consumption of major household appliances by just analyzing the aggregated power consumption collected at the main meter of the house. Recent disaggregation algorithms based on deep learning techniques showed superior performance with respect to previous methods. However, they require a large amount of submeter data to be trained. In this work, we present a new solution for training nonintrusive load monitoring algorithms without any supervision from submeters. To achieve this goal, we divided the disaggregation algorithm into two stages— appliance detection and state-based disaggregation . In the first stage, we aim at identifying the start and stop times of the individual appliance operations within the whole-house power signal. In the second stage, we reconstruct the power signature of the target device by exploiting appliance-specific power states learned in the house. We tested our methodology on fridges, washing machines, and dishwashers in a public dataset, showing double-digit improvements with respect to previous methods trained with submeter data. Most importantly, the proposed solution allows to collect a large number of appliance power signatures with minor costs, thus helping to achieve the generalization capabilities required by a real-world disaggregation system.

In smart grids, consumers can be involved in demand response programs to reduce the total power consumption of their households during the peak hours of the day. Unfortunately, nowadays, utility companies are facing important challenges in the implementation of demand response programs because of their negative impact on the comfort of end-users. In this article, we cluster the different operation modes of household appliances based on the analysis of their power signatures. For this purpose, we implement an autoencoder neural network to create a better data representation of the power signatures. Then, we cluster the different operational programs by using a K-means algorithm fitted to the new data representation. To test our methodology, we study the operation modes of some washing machines and dishwashers whose power signatures were derived from both submeters and nonintrusive load monitoring techniques. Our clustering analysis reveals the existence of multiple working programs showing well-defined features in terms of both average energy consumption and duration. Our results can then be used to improve demand response programs by reducing their impact on the comfort of end-users. Furthermore, end-users can rely on our framework to favor lighter operation modes and reduce their overall energy consumption.

Electrical anomalies in residential buildings represent a serious problem that can unpredictably change the power profiles of end-users, causing a sub-optimal energy distribution. In addition, electrical faults can cause unnoticed energy wastages and higher energy bills, or even severe damages for properties and people in the most critical cases. In this paper, we introduce a novel anomaly detection method for detecting electrical faults in household appliances based on the analysis of their power signatures with unsupervised deep learning techniques. For this purpose, we trained a variational autoencoder to reconstruct the power signatures of three commonly used devices: the dishwasher, the washing machine and the dryer. For each use case, we injected several randomly generated anomalies that simulate to our best realistic electrical faults in these devices. To demonstrate the effectiveness of our method, we compared the accuracy of the variational autoencoder with the classification performance of a one-class support vector machine (OC-SVM) trained with two manual features: the energy consumption and the duration of the appliance’s operations. The variational autoencoder showed higher classification accuracy with respect to the OC-SVM, reporting an F1-score greater than 90% in all the use cases. Most importantly, the results demonstrate that deep anomaly detection methods outperform traditional algorithms based on handcrafted features, allowing to better characterize the set of normal cycles and produce more precise alerts for the monitored devices.

Nowadays, Non-Intrusive Load Monitoring techniques are sufficiently accurate to provide valuable insights to the end-users and improve their electricity behaviours. Indeed, previous works show that commonly used appliances (fridge, dishwasher, washing machine) can be easily disaggregated thanks to their abundance of electrical features. Nevertheless, there are still many ON/OFF devices (e.g. heaters, kettles, air conditioners, hair dryers) that present very poor power signatures, preventing their disaggregation with traditional algorithms. In this work, we propose a new online clustering method exploiting both operational features (peak power, duration) and external features (time of use, day of week, weekday/weekend) in order to recognize ON/OFF devices. The proposed algorithm is intended to support an existing disaggregation algorithm that is already able to classify at least 80% of the total energy consumption of the house. Thanks to our approach, we improved the performance of our existing disaggreation algorithm from 80% to 87% of the total energy consumption in the monitored houses. In particular, we found that 85% of the clusters were identified by only using operational features, while external features allowed us to identify the remaining 15% of the clusters. The algorithm needs to collect on average less than 40 operations to find a cluster, which demonstrates its applicability in the real world.

The detection of anomalous power consumption in household appliances plays a key role for the optimization of grid operations and for reducing unwanted electrical absorptions in residential buildings. Smart Plugs, Smart Appliances and other appliance-level monitoring devices allow to continuously monitor the power consumption of individual appliances present in the house. This work is aimed at detecting electrical anomalies in household appliances by analyzing the disaggregated load consumption derived from appliance-level monitoring devices. For this purpose, we implemented an anomaly detection framework which monitors the hourly energy consumption of three common sources of power absorption: the baseline, the fridge and the electrical devices. Here, we focused our analysis on two kinds of anomalies: single-point deviations and anomalous trends. The analysis of single-point deviations allowed us to identify short-term power peaks due either to unexpected electrical faults or sudden variations in end-users routines. The analysis of anomalous trends revealed several cases in which the end-users gradually increased their ordinary power consumption profile towards more energy-intensive practices. In summary, the results of our work showed that the power consumption derived from appliance-level load monitoring can be used to detect several anomalous power consumption in household appliances.

Having continuous load structure and composition information of substations has a great relevance in power system analysis such as load modeling, load forecasting and demand-side management. In this paper, a parsimonious approach for load composition estimation using non-intrusive load disaggregation techniques for low voltage substations is presented with a concept of using ZIP load model characteristics of the aggregate active and reactive powers as predictor features. The disaggregation system uses machine learning algorithms such as Function Fitting Multi-Layer Perceptron Artificial Neural Network (MLP-ANN), Particle Swarm Optimization (PSO) and Genetic Algorithm (GA). During the study, a simulation dataset was generated using Monte Carlo simulation. Moreover, a comparative analysis with a benchmarked paper has been assessed and the proposed approach significantly outperforms.

It is generally recognized that our behaviours affect the environment. However, it is difficult to correlate behaviour of an individual person to large-scale problems. This is usually due to insufficient ergonomy of available tools. The main cause is that most of user-awareness tools available are technology-centered instead of user-centered. In this paper, we present a participatory design approach we followed to design and develop an energy-aware mobile application for user-awareness on energy consumption for Smart Home monitoring. To engage end-users from the early design stages, we conduct two on-line surveys and a focus group involving about 630 people. Results allowed on identifying functional requirements and guidelines for mobile app design. The purpose of this research is to increase user-awareness on energy consumption using tools and methods required by users themselves. Furthermore in this paper, we present the technological choices that drove our implementation of an energy-aware application based on prosumers' requirements.

Non-Intrusive Appliances Load Monitoring systems are crucial for augmenting virtuous energy saving behavior and providing residential energy monitoring solutions. NILM is aimed to accurately account for energy costs and load distribution by reporting where exactly the energy is going and what kind of devices are using it. To address this issue, much of existing methods require a lot of time consuming training, complex optimization algorithms and does not focus on the actual energy estimation problem rather concentrate on classification problem. In this paper, we propose a simple active window based NILM (AWB-NILM) approach that relies on an unsupervised localized events clustering, pairing and self-learning using automatic evolutionary clustering methods. We have tested our approach on a real residential power consumption data. The F-measure attained by the event detector is 94.6%. In this paper we showed accuracies of appliance events correctly classified and energy correctly assigned.