Osório, Gerardo J.
Loading...
Email Address
Birth Date
Job Title
Last Name
Osório
First Name
Gerardo J.
Name
Gerardo J. Osório
Biography
Gerardo J. Osório is an Assistant Professor and Coordinator at the 1st Cycle of Industrial Engineering and Management at the Science and Technology Department of Portucalense University Infante D. Henrique, Porto, Portugal. He finished the Ph.D. degree in Industrial Engineering and Management (Specialization in Energy and Optimization Systems), on 11/07/2015/ at the University of Beira Interior, Covilhã, Portugal. From the same university, he finished the MSc. in Computer Sciences and Electrical Engineering (Specialization in Automation and Controlling), on 07/07/2011. He authored or co-authored 125 publications, including more than 35 journal papers, 86 conference proceedings papers, and 5 book chapters, with an h-index of 22 and over 1940 citations. He was awarded directly and indirectly for his research work and scientific supervision 14 times. He has participated as Research Fellow in 5 project(s), and as Post-Doctoral Fellow in 2 projects, interacting with more than 150 collaborators in co-authoring scientific works. His domains are in the areas of Engineering Sciences and Technologies, Other Engineering Sciences, considering operational research, with an emphasis on renewable energy.
BD19-D0AD-65DB
t13DoaMAAAAJ
54783251300
C-3616-2014Research Projects
Organizational Units
REMIT – Research on Economics, Management and Information Technologies
Centro de investigação que que tem como objetivo principal produzir e disseminar conhecimento teórico e aplicado que possibilite uma maior compreensão das dinâmicas e tendências económicas, empresariais, territoriais e tecnológicas do mundo contemporâneo e dos seus efeitos socioeconómicos. O REMIT adota uma perspetiva multidisciplinar que integra vários domínios científicos: Economia e Gestão; Ciências e Tecnologia; Turismo, Património e Cultura.
Founded in 2017, REMIT – Research on Economics, Management and Information Technologies is a research unit of Portucalense University. Based on a multidisciplinary and interdisciplinary perspective it aims at responding to social challenges through a holistic approach involving a wide range of scientific fields such as Economics, Management, Science, Technology, Tourism, Heritage and Culture.
Grounded on the production of advanced scientific knowledge, REMIT has a special focus on its application to the resolution of real issues and challenges, having as strategic orientations:
- the understanding of local, national and international environment;
- the development of activities oriented to professional practice, namely in the business world.
37 results
Search Results
Now showing 1 - 10 of 37
Publication Restricted Access An advanced deep neuroevolution model for probabilistic load forecasting2022-07-13 - Jalali, Seyed M.J.; Arora, Paul; Panigrahi, B.K.; Khosravi, Abbas; Najavandi, Saeid; Catalão, João P.S.; Osório, Gerardo J.Probabilistic load forecasting (PLF) is necessary for power system operations and control as it assists in proper scheduling and dispatch. Moreover, PLF adequately captures the uncertainty whether that uncertainty is related to load data or the forecasting model. And there are not many PLF models, and those which exist are very complex or difficult to interpret. This paper proposes a novel neuroevolution algorithm for handling the uncertainty associated with load forecasting. In this paper, a new modified evolutionary algorithm is proposed which is used to find the optimal hyperparameters of 1D-Convolutional neural network (CNN). The probabilistic forecasts are produced by minimizing the mean scaled interval score loss function at 50%, 90% and 95% prediction intervals. The proposed neuroevolution algorithm is tested on a global energy forecasting competition (GEFCom-2014) load dataset, and two different experiments are conducted considering load only and one with load and temperature. Strong conclusions are drawn from these experiments. Also, the proposed model is compared with other benchmark models, and it has been shown that it outperforms the other models.Publication Restricted Access Optimal participation of virtual power plants in the electricity market considering multi-energy systems2023-09-27 - Javadi, Mohammad S.; Parente, Andre S.; Catalão, João P. S.; Osório, Gerardo J.The growth and modernization of the power system are the keys to enabling economic progress. The deregulation, added to the new emerging production technologies, conversion, and storage, triggered a change in the way of managing the power system worldwide. This work analyses the optimal dispatch of a virtual power plant (VPP) with active participation in the electricity market, considering multi-energy systems. The objective is to minimize the total operating cost of the power plant. The power plant is fed by two external networks: electrical and natural gas. The VPP is composed of energy production, conversion, and storage technologies, also considering the integration of a wind turbine and a set of electric vehicles (EVs). In addition to the Grid-to-Vehicle (G2V) charging, the advantage of Vehicle-to-Grid (V2G) technology is also verified, which allows the injection of power into the grid through the vehicles and Vehicle-to-Load (V2L) technology, enabling EVs to contribute to the satisfaction of the electrical load, reducing the costs, showing the advantages as well of EVs' integration in the VPP under analysis.Publication Restricted Access An ultra-short-term wind speed forecasting model based on time scale recognition and dynamic adaptive modeling2022-02 - Zhen, Zhao; Qiu, Gang; Shengwei, Mei; Wang, Fei; Zhang, Xuemin; Yin, Rui; Li, Yu; Shafie-khah, Miadreza; Catalão, João P. S.; Osório, Gerardo J.The forecast of wind speed is a prerequisite for wind power prediction, which is one of the most effective means of promoting wind power absorption. However, when modeling for wind speed sequences with different fluctuations, most existing researchers ignore the influence of the time scale of wind speed fluctuation period, let alone the low compatibility between training and testing samples that severely limit the training performance of the forecasting model. To improve the accuracy of wind speed and wind power forecasting, an ultra-short-term wind speed forecasting model based on time scale recognition and dynamic adaptive modeling is proposed in this paper. First, a series of wind processes are divided from the historical wind speed sequence according to the natural variation characteristics of wind speed. Second, we divide all the wind processes into two patterns based on their time scale, and an SVC model with input features extracted from meteorological data is built to identify the time scale of the current wind process. Third, for a specifically identified wind process, the complex network algorithm is applied in data screening to select high compatible training samples to train the forecast model dynamically for current input. The simulation indicates that the proposed approach presents higher accuracy than benchmark models using the same forecasting algorithms but without considering the time scale and data screening.Publication Restricted Access Optimal scheduling of microgrid-based virtual power plants considering demand response and capacity withholding opportunities2021 - Tabatabaei, Mostafa; Nazar, Mehrdad S.; Shafie-khah, Miadreza; Catalão, João P. S.; Osório, Gerardo J.This work addresses a stochastic framework for optimal coordination of a microgrid-based virtual power plant (VPP) that participates in day-ahead energy and ancillary service markets. The microgrids are equipped with different types of distributed energy resources. A two-stage optimization formulation is proposed to maximize the benefit of the virtual power plant and minimize the energy procurement costs of the Distribution System Operator (DSO). The proposed model determines the optimal commitment scheduling of energy resources, considering the capacity withholding opportunities of the VPP that should be detected by the DSO. To evaluate the effectiveness of the proposed model, the algorithm is assessed for the 123-bus IEEE test system. The results show that the proposed method successfully maximizes the virtual power plant profit considering capacity withholding penalties.Publication Restricted Access A centralized home energy management system to minimize consumer’s electricity bill2022-08-19 - Nezhad, Ali Esmaeel; Nardelli, Pedro H. J.; Sahoo, Subham; Ghanavati, Farideh; Osório, Gerardo J.This work investigates a centralized, high-resolution, and fast model for home energy management. The model is provided within the mixed-integer linear programming (MILP) framework while it benefits from an open-access optimization model in Python for running the model free of charge. To minimize the electricity bill, the time-of-use (TOU) electricity tariff has been selected by the consumer to manage the daily electricity consumption. This consumer-centric home energy management system (HEMS) enhances the flexibility that can be provided by dedicated consumers during peak periods while reducing the electricity bill of the end-users benefiting from the TOU tariff. The time resolution of home appliance scheduling is 15 minutes in this study and it is compatible with the smart metering data recording for energy consumed by the end-users. The simulation results show that the electricity bill would be considerably decreased by using the proposed self-scheduling model.Publication Restricted Access Photovoltaic array fault detection and classification based on t-distributed stochastic neighbor embedding and robust soft learning vector quantization2021-09 - Afrasiabi, S.; Afrasiabi, M.; Behdani, B.; Mohammadi, M.; Javadi, Mohammad; Catalão, João P. S.; Osório, Gerardo J.Photovoltaic (PV) as one of the most promising energy alternatives brings a set of serious challenges in the operation of the power systems including PV system protection. Accordingly, it has become even more vital to provide reliable protection for the PV generations. To this end, this paper proposes two-stage data-driven methods. In the first stage, a feature selection method, namely t-distributed stochastic neighbor embedding (t-SNE) is implemented to select the optimal features. Then, the output of t-SNE is directly fed into the strong data-driven classification algorithm, namely robust soft learning vector quantization (RSLVQ) to detect PV array fault and identify the fault types in the second stage. The proposed method is able to detect the two different line-to-line faults (in strings and out of strings) and open circuit fault and fault type considering partial shedding effects. The results have been discussed based on simulation results and have been demonstrated the high accuracy and reliability of the proposed two-stage method in detection and fault type identification based on confusion matrix values.Publication Restricted Access An advanced generative deep learning framework for probabilistic spatio-temporal wind power forecasting2021-09 - Jalali, S. M.; Khodayar, M.; Khosravi, A.; Nahavandi, S.; Catalão, João P. S.; Osório, Gerardo J.This paper presents a deep generative model for capturing the conditional probability distribution of future wind power given its history by modeling and pattern recognition in a dynamic graph. The dynamic nodes show the wind sites while the dynamic edges reflect the correlation between the nodes. We propose a scalable optimization model, which is theoretically proved to catch distributions at nodes of the graph, contrary to all learning formulations in the sector of discriminatory pattern recognition. The density of probabilities for each node can be used as samples in our framework. This probabilistic deep convolutional Auto-encoder (PDCA), is based on the deep learning of localized first-order approximation of spectral graph convolutions, a novel evolutionary algorithm, and the Bayesian variational inference concepts. The presented generative model is used for the spatio-temporal probabilistic wind power problem in a wide 25 wind sites located in California, the USA for up to 24h ahead prediction. The experimental findings reveal that our proposed model outperforms other competitive temporal and spatio-temporal algorithms in terms of reliability, sharpness, and continuously ranked probability score.Publication Restricted Access Impact of the growing penetration of renewable energy production on the Iberian long-term electricity market2021-09 - Santos, Sérgio F.; Gough, Matthew; Pinto, João P. G. V.; Javadi, Mohammad; Osório, Gerardo J.; Santos, Sérgio F.The increasing penetration of renewable energy sources in areas with wholesale energy markets may have significant impacts on the prices of electricity within these markets. These renewable energy sources typically have low or zero marginal prices and thus can bid into energy markets at prices that might be below plants using other generating technologies. This work seeks to understand the impact of these zero marginal cost plants in the Iberian Energy Market. This work makes use of an Artificial Neural Network (ANN) to evaluate the impact of growing renewable energy generation on the market-clearing price. Real data from the Iberian Energy Market is chosen and used to train the ANN. The scenarios used for renewable energy generation are taken from the newly published national energy and climate plans for both Spain and Portugal. Results show that increasing penetration of renewable energy leads to significant reductions in the forecasted energy price, showing a price decrease of about 23 €/MWh in 2030 compared to the baseline. Increasing solar PV generation has the largest effect on market prices.Publication Restricted Access Optimal Operation of Renewable Energy Resources and Electric Vehicles in Microgrids [comunicação oral]2024-06-17 - Shahbazbegian, Vahid; Barroso-Pereira, João; Shafie-khah, Miadreza; Catalão, João P. S.; Osório, Gerardo J.The adoption of electric vehicles (EVs) powered by renewable energy systems has the potential to address environmental concerns, particularly air pollution, on a global scale. Additionally, leveraging the timing and enhanced storage capacity of a significant number of EVs can significantly improve the flexibility of the electrical systems. In this study, an optimization model is developed for the operation of microgrids in the presence of EVs and solar power. To examine the role of EVs and solar power, different scenarios are considered for the arrival and departure state of charge of EVs, as well as winter and summer available solar power. The model is in the form of mixed-integer nonlinear programming and coded in General Algebraic Modelling System (GAMS) software. The output of the study indicates that scheduled integration of EVs in parking lots provides higher flexibility in the operation of the microgrid under study and even 3% cost savings, which is noteworthy.Publication Restricted Access Impact of P2P market transactions on distribution network congestion considering physical constraints2023-09-27 - Santos, Sérgio F.; Branco, José T. R. A.; Catalão, João P. S.; Osório, Gerardo J.; Santos, Sérgio F.The novel trend of peer-to-peer (P2P) transactions has allowed traditional consumers to become prosumers, capable of maximizing the usage of their energy production by sharing it with their neighbors. Thus, the P2P market has emerged to allow both prosumers and consumers to trade energy independently from the conventional market. However, while local energy transactions will allow for a more open and decentralized grid, they will nevertheless have a significant impact on the planning, control and operation of distribution grids. Hence, in this paper, an improved model is presented to evaluate the impact of P2P transactions on distribution grid congestion, considering its restrictions and the uncertainty associated with renewable energy sources generation and load. The objective function has been modeled to minimize the transaction costs of each prosumer/consumer. The model was tested on a branch adapted from a 119-bus IEEE test grid, in which different operational scenarios have been considered through case studies, considering the various RES technologies and energy storage systems (ESS) installed by each prosumer/consumer. Comprehensive simulation results indicate that the introduction of smart grid enabling technologies and P2P transactions has led to both technical (voltage profile and grid congestion) and economic benefits for the distribution grid and its users.