Luis Gomes

Electrical Energy Consumption Forecast Using External Facility Data

Recent changes in the power systems gives place to the active consumers participation. The participation in demand response programs requires consumers to undertake strategic management of their consumption. Small and medium players should have the capability of performing day-ahead and hour-ahead load management which requires forecasting techniques applied to the consumption and generation. A good forecasting accuracy is very important for the quality of the management results but also very difficult to achieve. This paper proposes an artificial neural network based methodology to forecast the consumption in an office building. The considered building is equipped with a Supervisory Control and Data Acquisition (SCADA) system that stores data every 10 seconds. The stored data are used together with additional data, such as, the temperature and the solar radiation.

Contextual and environmental awareness laboratory for energy consumption management

The recent changes on power systems paradigm requires the active participation of small and medium players in energy management. With an electricity price fluctuation these players must manage the consumption. Lowering costs and ensuring adequate user comfort levels. Demand response can improve the power system management and bring benefits for the small and medium players. The work presented in this paper, which is developed aiming the smart grid context, can also be used in the current power system paradigm. The proposed system is the combination of several fields of research, namely multi-agent systems and artificial neural networks. This system is physically implemented in our laboratories and it is used daily by researchers. The physical implementation gives the system an improvement in the proof of concept, distancing itself from the conventional systems. This paper presents a case study illustrating the simulation of real-time pricing in a laboratory.

Simulation and control of consumption and generation of hardware resources in microgrid real-time digital simulator

The appearance of new concepts in power systems, such as, smart grids and microgrids brings several advantages. This includes the use of distributed generation and the execution of demand response programs. However, their implementation can also bring management and stability problems. The system presented in this paper allows the real-time simulation of microgrids using real generation and consumption resources. The proposed system can follow real profiles and reply them into the simulation by using real loads and wind generation. The focus is given to the control of the resources in each desired consumption and generation requirement. The case studies use a real consumption profile of a residential house, small commerce facility and a real profile of a home-scale wind turbine. The use of real loads gives a more reliable simulation.

Smart Grid and Electricity Market joint simulation using complementary Multi-Agent platforms

This paper presents an enhanced simulation platform composed by the integration of two distinct multi-agent based simulators. The two simulators are: (i) the Multi-Agent Simulator of Competitive Electricity Markets (MASCEM), which provides a simulation platform for electricity markets participation, considering scenarios based on real data from several distinct market operators; and (ii) the Multi-Agent Smart Grid Platform (MASGriP), which facilitates the simulation of smart grids and microgrids, by modeling the power network at the distribution level, and representing the main entities that act in this scope. With the cooperation between the two simulation platforms, huge studying opportunities under different perspectives are provided, resulting in an important contribution in the fields of transactive energy, electricity markets, and smart grids. A case study is presented, showing the potentialities for interaction between players of the two ecosystems, namely by demonstrating a case in which a smart grid operator, which manages the internal resources of a smart grid, is able to participate in electricity market negotiations to sell the surplus of generation in some periods of the day, and buy the necessary power to satisfy the demand of smart grid consumers in other periods of the day.

Publishing real-time microgrid consumption data on the web of Linked Data

Decentralising the power systems management brings clear advantages for the grid and for the stakeholders (consumers, generators, operational and management actors). The grid decentralisation can be achieved using microgrids. Some microgrids emerge worldwide, working as small energy islands. It is admitted that ontologies and open (Semantic) Web standards can form a basis for advanced communication architectures in smart grids. True, ontologies enable semantic interoperability and logical reasoning; the Linked Data principles enable the discovery of new information on the web. This paper reports on the use of these formalisms and principles to develop a new information system for a microgrid site already in place. More specifically, we developed a new ontology to represent time series of multiple observations, and made real-time consumption data available on the web as Linked Data. This enables consumption reporting, and enables other researchers to test their algorithms against real-time consumption data.

Multi-Agent based Smart Grid management and simulation: Situation awareness and learning in a test bed with simulated and real installations and players

The rising usage of distributed energy resources has been creating several problems in power systems operation. Virtual Power Players arise as a solution for the management of such resources. Additionally, approaching the main network as a series of subsystems gives birth to the concepts of smart grid and micro grid. Simulation, particularly based on multi-agent technology is suitable to model all these new and evolving concepts. MASGriP (Multi-Agent Smart Grid simulation Platform) is a system that was developed to allow deep studies of the mentioned concepts. This paper focuses on a laboratorial test bed which represents a house managed by a MASGriP player. This player is able to control a real installation, responding to requests sent by the system operators and reacting to observed events depending on the context.

Application of a Home Energy Management System for Incentive-Based Demand Response Program Implementation

This paper presents an experimental real-time implementation of an incentive-based demand response program with hardware demonstration of a home energy management system. This system controls the electricity consumption of a residential electricity customer. For this purpose, the real consumption and generation profiles of a typical Portuguese household equipped with a home-scale photovoltaic system are employed. These profiles are simulated by the real-time digital simulator using real hardware resources. In the case studies, three different scenarios are simulated for a period of 24 hours with the consideration of the demand response programs and a 2 kW photovoltaic system. Different pricing scenarios are considered and the performance of the home energy management system is evaluated under each scenario. The focus is given to demonstrate how a home-scale photovoltaic system, and demand response programs, especially load-shifting scenario, can be cost-effective in the daily electricity costs of the residential customers.

Microgrid demonstration gateway for players communication and load monitoring and management

The integration of decentralized generation units and the application of demand response programs brings changes to the power systems. Microgrids are emerging with relevant advantages for the power system operation. For this reason, several research projects are currently studding and finding methods to improve microgrids management. The development of adequate management systems, taking into account relevant retrofitting levels is of upmost importance. This paper presents and describes a gateway to be used in existing buildings in order to enable their integration in systems that are capable of managing microgrids. The gateway can monitor and control loads, generators and other equipment. For the case study the gateways will be installed in three buildings and integrated in SOICAM system able to manage microgrids. The results show the data retrieved by the gateways and sent to the central operation room.

Real-time simulation of renewable energy transactions in microgrid context using real hardware resources

The recent changes on the electrical power systems make the role of distributed generation more important. Employing distributed generation in demand side allows the consumers to have active participation in the electricity markets. This paper implements the real-time simulation of a local microgrid that consists of two subsystems: home area network and neighborhood area network. In this system, the home area network is the electrical grid of a house and the neighborhood area network is the low voltage electrical distribution grid of the neighborhood. The main contribution of this paper is to assess scenarios for energy transactions between these two areas using real resources. In the case studies, several real profiles have been employed for simulating the consumption and generation of this local microgrid.

English-Portuguese Biomedical Translation Task Using a Genuine Phrase-Based Statistical Machine Translation Approach.

Our approach to produce translations for the ACL-2016 Biomedical Translation Task on the English-Portuguese language pair, in both directions, is described. Own preliminary tests results and final results, measured by the shared task organizers, are also presented.