Loading...
8 results
Search Results
Now showing 1 - 8 of 8
- Anomaly detection of consumption in Hotel Units: A case study comparing isolation forest and variational autoencoder algorithmsPublication . Mendes, Tomás; Cardoso, Pedro; Monteiro, Jânio; Raposo, JoãoBuildings are responsible for a high percentage of global energy consumption, and thus, the improvement of their efficiency can positively impact not only the costs to the companies they house, but also at a global level. One way to reduce that impact is to constantly monitor the consumption levels of these buildings and to quickly act when unjustified levels are detected. Currently, a variety of sensor networks can be deployed to constantly monitor many variables associated with these buildings, including distinct types of meters, air temperature, solar radiation, etc. However, as consumption is highly dependent on occupancy and environmental variables, the identification of anomalous consumption levels is a challenging task. This study focuses on the implementation of an intelligent system, capable of performing the early detection of anomalous sequences of values in consumption time series applied to distinct hotel unit meters. The development of the system was performed in several steps, which resulted in the implementation of several modules. An initial (i) Exploratory Data Analysis (EDA) phase was made to analyze the data, including the consumption datasets of electricity, water, and gas, obtained over several years. The results of the EDA were used to implement a (ii) data correction module, capable of dealing with the transmission losses and erroneous values identified during the EDA’s phase. Then, a (iii) comparative study was performed between a machine learning (ML) algorithm and a deep learning (DL) one, respectively, the isolation forest (IF) and a variational autoencoder (VAE). The study was made, taking into consideration a (iv) proposed performance metric for anomaly detection algorithms in unsupervised time series, also considering computational requirements and adaptability to different types of data. (v) The results show that the IF algorithm is a better solution for the presented problem, since it is easily adaptable to different sources of data, to different combinations of features, and has lower computational complexity. This allows its deployment without major computational requirements, high knowledge, and data history, whilst also being less prone to problems with missing data. As a global outcome, an architecture of a platform is proposed that encompasses the mentioned modules. The platform represents a running system, performing continuous detection and quickly alerting hotel managers about possible anomalous consumption levels, allowing them to take more timely measures to investigate and solve the associated causes.
- A digital twin of charging stations for fleets of electric vehiclesPublication . Francisco, André; Monteiro, Jânio; Cardoso, PedroThe increasing concern over the environmental impact of fossil fuels and associated CO2 emissions created a growing interest on the use of electric vehicles (EVs) and green energy utilization. In this context, the widespread adoption of EVs should be accompanied by the introduction of generation from renewable energy sources (RES). That insertion, at the distribution level, presents challenges that result from their intermittent nature, requiring demand-response measures that can be addressed by adjusting the charging processes to match the available power. In the framework of EVs renting companies, it is essential to have an efficient charging management that allows achieving high levels of self-consumption and self-sufficiency, lower operational costs and lower payback periods for the investments made. The utilization of digital twins (DTs) can be key to achieve those goals, providing accurate simulations and predictions. Their use in the context of EV charging can offer valuable insights into optimizing charging scheduling and predicting energy demands, taking into consideration distinct scenarios. This paper presents the work done to implement DTs of a set of charging stations (CSs) and EVs, which allow the modeling and improved management of the charging processes of EV fleets, for a set of CSs, integrating RES. In this charging context, experimental results using the DT were applied considering a predicted mobility. The applied scenarios supported an effective and optimized managing performance, reaching low paybacks and high self-sufficiency values. The obtained results show that this method is a viable and cost-effective solution for companies renting EVs.
- Energy transition process and community engagement on geographic islands: the case of Culatra Island (Ria Formosa, Portugal)Publication . Pacheco, André; Monteiro, Jânio; Santos, Joni; Sequeira, Claudia; Nunes, J.Islands have the potential to be precursors in the transition to clean energy, by adopting new technologies and applying innovative solutions that can serve as showcases at an international level. This paper is a contribution towards understating the importance of community engagement on energy transition processes. It covers multiple aspects of a green transition process, including technical, environmental, social, and economic issues. Starting by a participatory diagnosis process, the community of a small island located in Portugal (Culatra Island, Algarve), was challenged to lead the transition process and define different pillars of energy transition. The process brought together local authorities, academia, citizens and companies. Using practical examples, it is shown how the community is succeeding in tailoring new technological solutions for a green transition, according with the specific needs of the island, as expressed by the islanders themselves, including batteries, electric vehicles, retrofitting of homes, or heat pumps, which, when combined, could lay the foundations for the creation of a Renewable Energy Community and leverage socioeconomic benefits.
- A Gray Code model for the encoding of grid cells in the Entorhinal CortexPublication . Monteiro, Jânio; Pedro, André; Silva, AntónioIn the brains of humans and mammals, the formation of episodic memories results from the association between objects, space and time. Both the hippocampus and the entorhinal cortex have shown to play an essential role in the formation of these memories. The hippocampus may be considered as an indexer of the pattern of neocortical activity produced by an episode, while the entorhinal cortex is characterized as performing time and space integration, conveying that information to the hippocampus, in the form of grid cells. Although these grid cells are biological based, non-biological grid cells are used in discrete global grid systems that currently support the indexing of assets across the globe, allowing a more adequate partitioning of the Earth into logical structures that take into account the heterogeneity of the scales of the associated geospatial data. The reasons that led to the definition of these grid systems at macro-levels may have led to the formation of similar structures inside our brains. In this paper, we investigate a representation that unifies these views, creating new types of Gray encodings for both one- and two-dimensional spaces. We start by defining a multilayer ternary encoder based on an equilateral triangular coordinate system. After defining a space filling method for this two-dimensional architecture, two Gray codes for one-dimensional signals are defined, for both circular/periodic and non-circular representations of signals. An algorithm is defined to build the two-dimensional Gray encoding of grid cells, which is then successfully applied in a navigation system of a robot, generating patterns of grid cells similar with the ones observed in neuroscience.
- On a new method to design solar photovoltaic systems in renewable energy communities: The case of Culatra Island (Ria Formosa, Portugal)Publication . Ewart, M.; Santos, J.; Pacheco, A.; Monteiro, Jânio; Sequeira, ClaudiaIslands must reach sustainable lifestyles by improving resources management and by getting accustomed to renewable energy sources. Culatra, a small Portuguese island, is actively increasing renewable energy penetration into local processes in order to be the first 100% sustainable Portuguese territory by 2030. Based on the electric consumption of Culatra, the objective of the present study is to project a photovoltaic unit composed of several sub-fields, each with a distinct orientation, in order to increase the self-consumption ratio while at the same time reducing the surplus of energy production, assessed by the self-sufficiency ratio criteria, resulting in a lower levelised cost of energy of the power system. To achieve this, MATLAB's implementation of a genetic algorithm was used to find the optimised set of orientations for a given load profile. The results indicate that it is possible to optimise the photovoltaic plant to reach a more continuous electricity generation through daytime, reducing the storage needs and increasing the value of photovoltaic systems. The method can be extended to other locations or demand curves, assisting on comparing different energy management strategies, and their respective advantages and disadvantages.
- Development and implementation of a smart charging system for electric vehicles based on the ISO 15118 standardPublication . Santos, Joni; Francisco, André; Cabrita, Cristiano Lourenço; Monteiro, Jânio; Pacheco, André; Cardoso, PedroThere is currently exponential growth in the electric vehicle market, which will require an increase in the electrical grid capacity to meet the associated charging demand. If, on the one hand, the introduction of energy generation from renewable energy sources can be used to meet that requirement, the intermittent nature of some of these sources will challenge the mandatory real-time equilibrium between generation and consumption. In order to use most of the energy generated via these sources, mechanisms are required to manage the charging of batteries in electric vehicles, according to the levels of generation. An effective smart charging process requires communication and/or control mechanisms between the supply equipment and the electric vehicle, enabling the adjustment of the energy transfer according to the generation levels. At this level, the ISO 15118 standard supports high-level communication mechanisms, far beyond the basic control solutions offered through the IEC 61851-1 specification. It is, thus, relevant to evaluate it in smart charging scenarios. In this context, this paper presents the development of a charge emulation system using the ISO 15118 communication protocol, and it discusses its application for demand response purposes. The system comprises several modules developed at both ends, supply equipment and electric vehicles, and allows the exchange of data during an emulated charging process. The system also includes human interfaces to facilitate interactions with users at both ends. Tests performed using the implemented system have shown that it supports a demand response when integrated with a photovoltaic renewable energy source. The dynamic adjustment to charging parameters, based on real-time energy availability, ensures efficient and sustainable charging processes, reducing the reliance on the grid and promoting the use of renewable energy.
- Livro de Atas, 9.º Congresso Nacional de Práticas Pedagógicas no Ensino Superior, 6 e 7 de julho de 2023Publication . Esteves, Eduardo; Estêvão, Maria Dulce da Mota Antunes de Oliveira ; Monteiro, Jânio; Correia, MarisolJá com a próxima edição do CNaPPES no horizonte, temos uma enorme satisfação de vos apresentar o Livro de Atas do 9.º Congresso Nacional de Práticas Pedagógicas no Ensino Superior, CNaPPES.23, onde poderão encontrar todos os artigos completos que os autores entenderam partilhar connosco, também sujeitos a revisão antes desta sua publicação. O CNaPPES nasceu para permitir e promover a partilha pedagógica no Ensino Superior e esta é a melhor forma de refletirmos juntos sobre o que funcionou (e não funcionou) em contexto real de prática pedagógica, nas diversas áreas do Ensino Universitário e o Ensino Politécnico. Neste livro poderão reencontrar os contactos dos diversos autores, o que poderá permitir uma maior proximidade entre elementos da comunidade académica que têm interesses comuns.
- Fair shares or smart savings? exploring business models, justice and efficiency trade-offs in Portuguese energy communitiesPublication . Scharnigg, Renée; Monteiro, Jânio; Pacheco, André; Santos, JoniEnergy communities are increasingly playing an important role in citizen engagement during energy transitions. However, the functional benefits for participants are heavily reliant on how energy and profits are shared, which are dictated by regulations. While optimizing trade-offs can prove significant in making energy community projects viable, related techno-regulatory innovations on energy-sharing mechanisms still require in-depth analysis. A key unresolved issue is how to balance justice considerations with model attractiveness by aligning members' perceptions of fair redistribution with optimal energy utilization. This study investigates the interplay between sharing and metering mechanisms and their respective advantages and disadvantages, using the Portuguese case study as an example. Four hypothetical scenarios related to the implementation of European directives into Portuguese national law are analysed to quantify trade-offs between self-consumption, self-sufficiency, and participant equity. The findings demonstrate how different energy-sharing and metering mechanisms can influence resource allocation, benefit distribution, and financial sustainability. Each of these scenarios reveals that there is no one-size-fits-all solution. The consumption-proportional sharing maximizes selfconsumption and self-sufficiency indexes at the community level but fails to uphold principles of energy justice, as it disproportionately benefits high-consuming members. In contrast, the fixed coefficients sharing ensures a distribution proportional to each member's monetary investment but leads to lower efficiency. These findings underscore the socio-economic implications of techno-regulatory innovations and the need to reconcile equity and efficiency. The study offers guidance to policymakers in designing fair and effective frameworks, reducing the risk of unintentionally obstructing energy community development due to impaired economic viability.