Osório, Gerardo J.
A carregar...
Endereço de Email
Data de nascimento
Cargo
Último Nome
Osório
Primeiro Nome
Gerardo J.
Nome
Gerardo J. Osório
Biografia
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-3616-2014Projetos de investigação
Unidades organizacionais
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 resultados
Resultados da pesquisa
A mostrar 1 - 10 de 37
Publicação Acesso Restrito A new hybrid deep neural architectural search based ensemble reinforcement learning strategy for wind power forecasting2022-01 - Jalali, S. M. J.; Ahmadian, S.; Campos, Vasco M. A.; Shafie-khah, Miadreza; Khosravi, A.; Catalão, João P. S.; Osório, Gerardo J.Wind power instability and inconsistency involve the reliability of renewable power energy, the safety of the transmission system, the electrical grid stability and the rapid developments of energy market. The study on wind power forecasting is quite important at this stage in order to facilitate maximum wind energy growth as well as better efficiency of electrical power systems. In this work, we propose a novel hybrid data-driven model based on the concepts of deep learning based convolutional-long short-term memory (CLSTM), mutual information, evolutionary algorithm, neural architectural search procedure, and ensemble-based deep reinforcement learning strategies. We name this hybrid model as DOCREL. In the first step, the mutual information extracts the most effective characteristics from raw wind power time-series datasets. Secondly, we develop an improved version of the evolutionary whale optimization algorithm in order to effectively optimize the architecture of the deep CLSTM models by performing the neural architectural search procedure. At the end, our proposed deep reinforcement learning based ensemble algorithm integrates the optimized deep learning models to achieve the lowest possible wind power forecasting errors for two wind power datasets. In comparison with fourteen state of the art deep learning models, our proposed DOCREL algorithm represents an excellent performance seasonally for two different case studies.Publicação Acesso Restrito Two-stage optimal operation of smart homes participating in competitive electricity markets2021-11-03 - Silva, Pedro; Gough, Matthew; Santos, Sérgio F.; Home-Ortiz, Juan M; Shafie-khah, Miadreza; Catalão, João P.S.; Osório, Gerardo J.; Santos, Sérgio F.End users have become active participants in local electricity market transactions because of the growth of the smart grid concept and energy storage systems (ESS). This participation is optimized in this article using a stochastic two-stage model considering the day-ahead and real-time electricity market data. This model optimally schedules the operation of a Smart Home (SH) to meet its energy demand. In addition, the uncertainty of wind and photovoltaic (PV) generation is considered along with different appliances. In this paper, the participation of an EV (electric vehicle), together with the battery energy storage systems, which allow for the increase in bidirectional energy transactions are considered. Demand Response (DR) programs are also incorporated which consider market prices in real-time and impact the scheduling process. A comparative analysis of the performance of a smart home participating in the electricity market is carried out to determine an optimal DR schedule for the smart homeowner. The results show that the SH’s participation in the real-time pricing, scheme not only reduces the operating costs but also leads to better than expected profits. Moreover, total, day-ahead, and real-time expected profits are better in comparison with existing literature. The objective of this paper is to analyze the SH performance within the electrical market context so as to increase the system’s flexibility whilst optimizing DR schedules that can mitigate the variability of end-users generation and load demand.Publicação Acesso Restrito 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.Publicação Acesso Restrito 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.Publicação Acesso Restrito 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.Publicação Acesso Restrito 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.Publicação Acesso Restrito Towards reducing electricity costs in an energy community equipped with home energy management systems and a local energy controller2023-09-22 - Javadi, Mohammad S.; Cardoso, Ricardo J.A.; Catalão, João P. S.; Osório, Gerardo J.An energy community equipped with Home Energy Management Systems (HEMSs) is considered in this paper. A local energy controller in the energy community makes it possible to transact energy between houses to support the different consumption patterns of each end-user. Price-based voluntary Demand Response (DR) programs are applied to each house to motivate end-users to alter their consumption patterns, allowing the necessary flexibility of the electrical grid. Also, the existence of Renewable Energy Sources (RES) micro-generation and an Energy Storage System (ESS) are taken into account. The results demonstrate that the proposed model based on Mixed-Integer Linear Programming (MILP) is fully capable of reducing daily electricity costs while considering end-users' comfort and respecting the different technical constraints.Publicação Acesso Restrito Day-Ahead optimal management of plug-in hybrid electric vehicles in smart homes considering uncertainties2021-01-30 - Hasankhani, Arezoo; Hakimi, Seyed M.; Bodaghi, Maryam; Shafie-khah, Miadreza; Catalão, João P. S.; Osório, Gerardo J.The plug-in hybrid electric vehicles (PHEVs) integration into the electrical network introduces new challenges and opportunities for operators and PHEV owners. On the one hand, PHEVs can decrease the environmental pollution. On the other hand, the high penetration of PHEVs in the network without charging management causes harmonics, voltage instability, and increased network problems. In this study, a charging management algorithm is presented to minimize the total cost and flatten the demand curve. The behavior of the PHEV owner in terms of arrival time and leaving time is modeled with a stochastic distribution function. The battery model and hourly power consumption of PHEV are modeled, and the obtained models are applied to determine the battery's state of charge. The proposed method is tested on a sample demand curve with and without a charging management algorithm to verify the efficiency. The results verify the efficiency of the proposed method in decreasing the total cost using the management algorithm for PHEVs, especially when the PHEVs sell the electricity to the network.Publicação Acesso Restrito Bi-Level approach for flexibility provision by prosumers in distribution networks2023-11-08 - Ramírez-López, Sergio; Gutiérrez-Alcaraz, Gillermo; Gough, Matthew; Javadi, Mohammad S.; Catalão, João P. S.; Osório, Gerardo J.The increasing number of Distributed Energy Resources (DERs) provides new opportunities for increased interactions between prosumers and local distribution companies. Aggregating large numbers of prosumers through Home Energy Management Systems (HEMS) allows for easier control and coordination of these interactions. With the contribution of the dedicated end-users in fulfilling the required flexibility during the day, the network operator can easily handle the power mismatches to avoid fluctuations in the load-generation side. The bi-level optimization allows for a more comprehensive and systematic assessment of flexibility procurement strategies. By considering both the network operator’s objectives and the preferences and capabilities of end-users, this approach enables a more nuanced and informed decision-making process. Hence, this paper presents a bi-level optimization model to examine the potential for several groups of prosumers to offer flexibility services to distribution companies. The model is applied to the IEEE 33 bus test system and solved through distributed optimization techniques. The model considers various DERs, including Battery Energy Storage Systems (BESS). Results show that the groups of aggregated consumers can provide between ±7 to ±29 kW flexibility in each interval, which is significant. Furthermore, the aggregators’ flexibility capacity is closely linked to the demand at each node.Publicação Acesso Restrito Blockchain-based transactive energy framework for connected virtual power plants2022-01 - Gough, Matthew; Santos, Sérgio F.; Almeida, A.; Lotfi, Mohamed; Javadi, Mohammad; Fitiwi, Desta Z.; Castro, Rui; Catalão, João P. S.; Osório, Gerardo J.; Santos, Sérgio F.Emerging technologies are helping to accelerate the ongoing energy transition. At the forefront of these new technologies is blockchain, which has the potential to disrupt energy trading markets. This paper explores this potential by presenting an innovative multi-level Transactive Energy (TE) optimization model for the scheduling of Distributed Energy Resources (DERs) within connected Virtual Power Plants (VPPs). The model allows for energy transactions within a given VPP as well as between connected VPPs. A blockchain based smart contract layer is applied on top of the TE optimization model to automate and record energy transactions. The model is formulated to adhere to the new regulations for the self-generation and self-consumption of energy in Portugal. This new set of regulations can ease barriers to entry for consumers and increase their active participation in energy markets. Results show a decrease in energy costs for consumers and increased generation of locally produced electricity. This model shows that blockchain based smart contracts can be successfully integrated into a hierarchical energy trading model, which respects the novel energy regulation. This combination of technologies can be used to increase consumer participation, lower energy bills, and increase the penetration of locally generated electricity from renewable energy sources