@fe.up.pt
Department of Electrical and Computer Engineering / Faculty of Engineering of Porto
University of Porto
Power systems, renewable energy, artificial intelligence, forecasting
Scopus Publications
Leonarda F. C. Castro, Paulo C. M. Carvalho, João P. T. Saraiva, and José Nuno Fidalgo
EconJournals
Motivated by initiatives such as the UN Sustainable Development Goals (SDG), particularly SDG 1 - Poverty Eradication and SDG 7 - Clean and Accessible Energy, the search for solutions aiming to mitigate poverty has been recurrent in several studies. This paper main objective is to evaluate the dynamics of global research on the use of photovoltaic projects for poverty alleviation (PVPA) from 2003 to 2022. We use a bibliometric analysis to identify publication patterns and consequently list research trends and gaps of the area. A total of 336 publications from Scopus database are identified and complemented by a state-of-the-art study, where the articles are investigated and classified according to: business model and financing and evaluation of PVPA results. The results show that PA is often associated with PV power and its application in rural areas. “Biomass” and “application in developing countries” have become a trend. Urban areas application, aiming to reduce poverty, and the need for a synergetic integration of energy and urban planning, to mitigate the risks associated with energy flow and efficiency, are the most relevant gaps identified. Most of the publications focus on macropolicies effects involving PV technology; papers on projects construction and ex-post are not identified.
Ana Rita Silva, José Nuno Fidalgo, and José Ricardo Andrade
IEEE
This paper explores the application of Deep Learning techniques to forecast electricity market prices. Three Deep Learning (DL) techniques are tested: Dense Neural Networks (DNN), Long Short-Term Memory Networks (LSTM) and Convolutional Neural Networks (CNN); and two non-DL techniques: Multiple Linear Regression and Gradient Boosting (GB). First, this work compares the forecast skill of all techniques for electricity price forecasting. The results analysis showed that CNN consistently remained among the best performers when predicting the most unusual periods such as the Covid19 pandemic one. The second study evaluates the potential application of CNN for automatic feature extraction over a dataset composed by multiple explanatory variables of different types, overcoming part of the feature selection challenges. The results showed that CNNs can be used to reduce the need for a variable selection phase.
José Nuno Fidalgo, Pedro M. Macedo, and Hugo F. R. Rocha
IEEE
A common problem in distribution planning is the scarcity of historic data (training examples) relative to the number of variables, meaning that most data-driven techniques cannot be applied in such situations, due to the risk of overfitting. Thus, the suitable regression techniques are restrained to efficient models, preferably with embedded regularization features. This article compares three of these techniques: LASSO, Bayesian and CMLR (Conditioned multi-linear regression – a new approach developed within the scope of a project with a distribution company). The results showed that each technique has its own advantages and limitations. The Bayesian regression has the main advantage of providing inherent confidence intervals. The LASSO is a very economic and efficient regression tool. The CMLR is versatile and provided the best performance.
J. Nuno Fidalgo and F. Azevedo
Elsevier BV
José Nuno Fidalgo and Pedro Macedo
MDPI AG
Nontechnical losses in electricity distribution networks are often associated with a countries’ socioeconomic situation. Although the amount of global losses is usually known, the separation between technical and commercial (nontechnical) losses will remain one of the main challenges for DSO until smart grids become fully implemented and operational. The most common origins of commercial losses are energy theft and deliberate or accidental failures of energy measuring equipment. In any case, the consequences can be regarded as consumption anomalies. The work described in this paper aims to answer a request from a DSO, for the development of tools to detect consumption anomalies at end-customer facilities (HV, MV and LV), invoking two types of assessment. The first consists of the identification of typical patterns in the set of consumption profiles of a given group or zone and the detection of atypical consumers (outliers) within it. The second assessment involves the exploration of the load diagram evolution of each specific consumer to detect changes in the consumption pattern that could represent situations of probable irregularities. After a representative period, typically 12 months, these assessments are repeated, and the results are compared to the initial ones. The eventual changes in the typical classes or consumption scales are used to build a classifier indicating the risk of anomaly.
Jose Nuno Fidalgo, Jose Pedro Paulos, and Pedro Macedo
IEEE
This article analyzes the effects of the current policy trends - high levels of distributed generation (DG) and grid load/capacity ratio - on network efficiency. It starts by illustrating the network losses performance under different DG and load/capacity conditions. The second part concerns the simulation of network investments with the purpose of loss reduction for diverse system circumstances, including the impact of DG levels, energy cost, and discount rate. The attained results showed that DG, particularly large parks, have a negative impact on network efficiency: network losses tend to intensify with DG growth, under the current regulation. Furthermore, network investments in loss reduction would have a small global impact on network efficiency if the DG parks’ connection lines are not included in the grid concession (not subjected to upgrade). Finally, the study determines that it is preferable to invest sooner, rather than to postpone the grid reinforcement for certain conditions, namely for low discount rates.
Leonarda F. C. Castro, Paulo C. M. Carvalho, J. N. Fidalgo, and J. T. Saraiva
IEEE
Energy communities (ECs) are emerging as a promising step to mitigate energy poverty and climate changes, since their main objective is to obtain environmental, economic, and social benefits for the participants, namely in terms of increasing local production using primary renewable resources. In the European Union (EU), Directives D2018 and D944 established a common regime for the promotion of ECs. Given the relevance of the topic, comparing regulations in force in Brazil, Germany, Portugal, and Spain, can contribute to mitigate risks, as well as save time and energy resources. Among the assessed aspects, this work analyzes requirements to access to the activity and measurement issues, which are already well and clearly defined. As for business models and remuneration, focus is given to energy cooperatives and feed-in payments. In turn, the main barriers include financing, end of incentives, need to develop new business models, and issues related to peer-to-peer (P2P) transactions.
Pedro Miguel Macedo, Jose Nuno Fidalgo, and Joao Tome Saraiva
IEEE
The financial planning of distribution systems usually includes the prediction of annual mandatory investments, concerning the resources that the DSO is compelled to allocate as a result of new network connections, required by new consumers or new energy producers. This paper presents a methodology to estimate the mandatory investments that the DSO should do in the distribution network. These estimations are based on historical data, load growth expectations and various socioeconomic indices. However, the available database contains very few annual investment examples (one aggregated value per year since 2002) compared to the large number of variables (potential inputs), which is a factor of regression overfitting. Thus, the applicable regression techniques are restrained to simple but efficient models. This paper describes a new methodology to identify the most suitable estimation models. The implemented application automatically builds, selects, and tests estimation models resulting from combinations of input variables. The final forecast is provided by a committee of models. Results obtained so far confirm the feasibility of the adopted methodology.
Jose Pedro Paulos, Jose Nuno Fidalgo, J. T. Saraiva, and Nuno Barbosa
IEEE
In Europe, clean distributed generation, DG, is perceived as a crucial instrument to build the path towards carbon emission neutrality. DG already reached a large share in the generation mix of several countries and the reduction of technical losses is one of its most mentioned advantages. In this scope, this paper discusses the weaknesses of this postulation using real networks. The adopted methodology involves the power flow simulation of a collection of real networks, using 15 min real measurements of loads and generations for a whole year. The clustering of similar cases allows identifying the situations that cause higher losses. A complementary objective of this research was to define an approach to mitigate this problem in terms of identifying the branches that, if reinforced, most contribute to losses reduction. The results obtained confirm the rationality of the proposed methodology.
Jose Pedro Paulos, Jose Nuno Fidalgo, and Joao Gama
IEEE
The present work aims to compare several load disaggregation methods. While the supervised alternative was found to be the most competent, the semi-supervised is proved to be close in terms of potential, while the unsupervised alternative seems insufficient. By the same token, the tests with long-lasting data prove beneficial to confirm the long-term performance since no significant loss of performance is noticed with the scalar of the time-horizon. Finally, the patchwork of new parametrization and methodology fine-tuning also proves interesting for improving global performance in several methods.
Matheus Paula, Colnago Marilaine, Fidalgo Jose Nuno, and Casaca Wallace
Institute of Electrical and Electronics Engineers (IEEE)
The rapid growth of wind generation in northeast Brazil has led to multiple benefits to many different stakeholders of energy industry, especially because the wind is a renewable resource – an abundant and ubiquitous power source present in almost every state in the northeast region of Brazil. Despite the several benefits of wind power, forecasting the wind speed becomes a challenging task in practice, as it is highly volatile over time, especially when one has to deal with long-term predictions. Therefore, this paper focuses on applying different Machine Learning strategies such as Random Forest, Neural Networks and Gradient Boosting to perform regression on wind data for long periods of time. Three wind farms in the northeast Brazil have been investigated, whose data sets were constructed from the wind farms data collections and the National Institute of Meteorology (INMET). Statistical analyses of the wind data and the optimization of the trained predictors were conducted, as well as several quantitative assessments of the obtained forecast results.
Pedro Macedo, Jose Nuno Fidalgo, and Joao Tome Saraiva
IEEE
The expansion and development of the electricity distribution grid is a complex multicriteria decision problem. The planning definition should take into consideration the investment benefits on the security of supply, quality of service, losses, as well as in other network features. Given the variety of assets and their context-dependent effects, estimating their global impact is very challenging. An additional difficulty is the combination of different types of benefits into a simple and clear portrayal of the planning alternatives. This paper proposes a methodology to estimate the benefits of distribution investments, in terms of five features: security of supply, quality of service, network losses, operational efficiency and new services. The approach is based on the adoption of objective and measurable indicators for each feature. The approach was tested with real data of Portuguese distribution grids and the results support the adopted approach and are being used as a decision-aid tool for grid planning.
P. Vilaca, J. T. Saraiva, and J. N. Fidalgo
IEEE
This paper reports the main results that were obtained in the scope of a consultancy study that was developed for EDP Distribuição, the main Portuguese distribution company, to evaluate the impact of a number of changes to be introduced in the Tariff System. These changes were proposed by ERSE, the Portuguese Regulatory Agency for the Energy Services, and included the redesign of the tariff periods and the possible introduction of a geographic differentiation on the Access Tariff to reflect different daily and yearly demand and flow patterns along the country. This work involved the development of a Cost Benefit Analysis, CBA, as well as a Pilot Project that included 82 MV and HV consumers to evaluate several Key Performance Indices, KPI, used to characterize the proposed changes on the tariff system.
J. Nuno Fidalgo, Debora de Sao Jose, and Carlos Silva
IEEE
Global climate change is currently a focus issue because of its impacts on the most diverse natural systems and, consequently, the development of humanity. The electricity sector is a major contributor to climate change because of its long-standing dependence on fossil fuels. However, the energy paradigm is changing, and renewable sources tend to play an increasingly important role in the energy mix in Portugal. Due to the strong relationship between renewable energies and climate-related natural resources, the climate change phenomenon could have considerable effects on the electricity sector. This paper analyzes the effects of climate change on the energy mix in Portugal in the medium / long term (up to 2050). The proposed methodology is based on the simulation of climate scenarios and projections of installed power by type and consumption. The combinations of these conditions are inputted to an energy accounting simulation tool, able to combine all information and provide a characterization of the system state for each case. The most favorable forecasted scenarios indicate that a fully renewable electricity system is achievable in the medium term, in line with the objectives of the European Union, as long as investments in renewable sources continue to be stimulated in the coming years.
Jose Pedro Alves and Jose Nuno Fidalgo
IEEE
The building sector is responsible for a large share of Europe's energy consumption. Modelling buildings thermal behavior is a key factor for achieving the EU energy efficiency goals. Moreover, it can be used in load forecasting applications, for the prediction of buildings total energy consumption. The first phase of this work is the application of Artificial Immune Systems (AIS) for clustering buildings with similar physical characteristics and similar thermal efficiency. In the second phase, Artificial Neural Networks (ANN) are used to estimate the buildings heating and cooling loads. A final sensitivity test is performed to identify which building features have the most impact on the heating and cooling loads. The results obtained in the first phase revealed very distinct cluster prototypes, which demonstrates the AIS discriminating ability. The good estimation performance obtained in the second phase showed that this approach can be integrated in energy efficiency audits. Finally, the sensitivity analysis provided indications for actions (or legislation directives) in order to promote the design of more efficient buildings.
J. Nuno Fidalgo, Carlos Moreira, and Rafael Cavalheiro
IEEE
The total losses volume represents a substantial amount of energy and, consequently, a large cost that is often included in the tariffs structure. Uneven connection of single-phase loads is a major cause for three-phase unbalance and a fundamental cause for active power losses, particularly in Low Voltage (LV) networks. This paper analyzes the impact of load unbalance on LV network losses. In the first phase, several load scenarios per phase are considered to characterize how losses depend on load unbalance. The second phase examines the data collected per phase on a set of real networks, aiming at illustrating real-world cases. The third phase analyzes the effect that public lighting and microgeneration may have in the load unbalance and on the subsequent energy losses. The results of this work clearly demonstrate that it is possible to reduce three-phase unbalance (and losses) through a judicious distribution of loads and microgeneration.
Jose Pedro Paulos and Jose Nuno Fidalgo
IEEE
Over time, the electricity price and energy consumption are increasingly growing their weight as prime foundations of the electrical sector, with their analysis and forecasts being targeted as key elements for the stable maintenance of electricity markets. The advent of smart grids is escalating the importance of forecasting because of the expected ubiquitous monitoring and growing complexity of a data-rich ever-changing milieu. So, the increasing data volatility will require forecasting tools able to rapidly readjust to a dynamic environment. The Generalized Regression Neural Network (GRNN) approach is a solution that has recently re-emerged, emphasizing good performance, fast run-times and ease of parameterization. The merging of this model with more conventional methods allows us to obtain more sturdy solutions with shortened training times, when compared to conventional Artificial Neural Networks (ANN). Overall, the performance of the GRNN, although slightly inferior to that of the ANN, is suitable, but linked to much lower training times. Ultimately, the GRNN would be a proper solution to blend with the latest smart grids features, which may require much reduced forecasting training times.
J. Nuno Fidalgo and Eduardo F. N. R. Da Rocha
IEEE
The price evolution in electricity market with large share of renewables often exhibits a deep volatility, triggered by external factors such as wind and water availability, load level and also by business strategies of market agents. Consequently, in many real applications, the performance of electricity price is not appropriate. The goal of this article is to analyze the available market data and characterize circumstances that affect the evolution of prices, in order to allow the identification of states that promote price instability and to confirm that class segmentation allows increasing forecast performance. A regression technique (based on Artificial Neural Networks) was applied first to the whole set and then to each class individually. Performances results showed a clear advantage (above 20%) of the second approach when compared to the first one.
Débora de São José and J. Nuno Fidalgo
Springer International Publishing
Jose Nuno Fidalgo and Paulo Adelino P. L. da Rocha
IEEE
In the beginning of the Iberian Electricity Market (MIBEL), in 2006, the Portuguese regulator created a new tariff scheme, aiming at responding to the new market competition environment. At the same time, the regulator intended to improve consumers' awareness and incentivize renewables generation. After one decade, this policy may be considered successful, as it led to a good level of transparency (all tariff costs are clear and public) and renewables production had increased considerably. However, this strategy has brought other less positive aspects. One of them is the attractiveness of the tariff system in terms of energy savings. In fact, the test cases present in this article demonstrate that the current tariff scheme does not stimulate energy efficiency. Other complementary studies are performed to illustrate the impact of the tariff structure design on the potential energy savings.
J. Nuno Fidalgo and Elsa M. F. Moura
IEEE
Last decade has witnessed the birth and dissemination of microgeneration (MG) in most EU countries. MG growth and diffusion in LV networks are expected to continue in the next decade. At the same time, the interest on energy storage systems (ESS) applications to power systems has been intensifying in the last years, following some major technological achievements that improved ESS abilities and decreased their price. This article analyzes the impacts of MG and ESS dissemination in LV networks' losses. The central goal is to estimate the global impact on the Portuguese LV distribution system. For that purpose, a set of empirical studies was carried out over a set of representative networks, in which different MG and ESS scenarios were considered. The extrapolation of the results to the global LV points out to a loss reduction potential of more than 15%.
José Nuno Fidalgo, Mário Couto, and Laurent Fournié
Elsevier BV
J. T. Saraiva, J. N. Fidalgo, R. B. Pinto, R. Soares, J. Santos Afonso, and G. Pires
IEEE
The current Portuguese Tariff Code dates from December 2014 and requires that the Distribution Network Operators (DSO), submit to the Portuguese Energy Services Regulatory Agency, ERSE, a plan for a pilot experiment and a Cost Benefit Analysis (CBA) regarding the introduction of dynamic options in the Access Tariffs in Portugal. In view of this request, EDP Distribuição, the main Portuguese DSO, established a contract with INESC TEC to conduct these studies and to prepare a report to submit to ERSE by June 2016. In this scope, this paper reports the results obtained so far namely regarding the CBA analysis. This analysis includes the identification of critical hours during which dynamic tariffs can be activated, the estimate of the impact of demand transfers to adjacent hours on the electricity market Social Welfare Function, on network losses, on the investment network avoided costs due to the possible deferral of reinforcements or expansions and on the costs of contracting reserves. These items were estimated along a period of 15 years and together with the estimate of the implementation costs of dynamic tariffs were used to conduct the mentioned CBA analysis.
J. Nuno Fidalgo and Leonardo Ribeiro Progano
IEEE
Load profiles are a crucial tool for power system planning and operation, and also in several operations of electricity markets. This article proposes a new methodology for the determination of load profiles based on a two-step approach. The first phase employs a neural network autoencoder to reduce the dimensionality of the input vectors. The second phase is a clustering process based on the Kohonen Self-Organizing Maps, to identify cohesive consumers' classes. The implemented approach produces classes based on load diagrams and, simultaneously, a class identification based on consumers' billing data.