Antonio Carlos Zambroni de Souza

A hierarchical neural model with time windows in long-term electrical load forecasting

A novel hierarchical hybrid neural model to the problem of long-term electrical load forecasting is proposed in this paper. The neural model is made up of two self-organizing map nets: one on top of the other, and a single-layer perceptron. It has application into domains which require time series analysis. The model is compared to a multilayer perceptron. Both the hierarchical and the multilayer perceptron models are endowed with time windows in their input layers. They are trained and assessed on load data extracted from a North-American electric utility. The models are required to predict once every week the electric peak-load and mean-load for the next 2xa0years. The results are presented and evaluated in the paper.

A neural model in anti-spam systems

The paper proposes the use of the multilayer perceptron model to the problem of detecting ham and spam e-mail patterns. It also proposes an intensive use of data pre-processing and feature selection methods to simplify the task of the multilayer perceptron in classifying ham and spam e-mails. The multilayer perceptron is trained and assessed on patterns extracted from the SpamAssassin Public Corpus. It is required to classify novel types of ham and spam patterns. The results are presented and evaluated in the paper.

Control Strategies for Improving Energy Efficiency and Reliability in Autonomous Microgrids with Communication Constraints

Microgrids are a feasible path to deploy smart grids, an intelligent and highly automated power system. Their operation demands a dedicated communication infrastructure to manage, control and monitor the intermittent sources of energy and loads. Therefore, smart devices will be connected to support the growth of grid smartness increasing the dependency on communication networks, which consumes a high amount of power. In an energy-limited scenario, one of the main issues is to enhance the power supply time. Therefore, this paper proposes a hybrid methodology for microgrid energy management, integrated with a communication infrastructure to improve and to optimize islanded microgrid operation at maximum energy efficiency. The hybrid methodology applies some control management rules, such as intentional load shedding, priority load management, and communication energy saving. These energy saving rules establish a trade-off between increasing microgrid energy availability and communication system reliability. To achieve a compromised solution, a continuous time Markov chain model describes the impact of energy saving policies into system reliability. The proposed methodology is simulated and tested with the help of the modified IEEE 34 node test-system.

The growing state of distributed generation and microgrids in the Ibero-American region: A view from the RIGMEI network

The Ibero-American Network of Distributed Generation and Intelligent Electrical Microgrids is a thematic network of the CYTED programme that performs cooperation activities between leading companies and research groups of the Ibero-American countries in the renewable energy area. This paper presents the results and conclusions of a study carried out recently by the network, which focused on the state of penetration of the distributed generation and the electrical microgrids in the Ibero-American countries that collaborate with the network. A list of these countries, together with the contact details of the main researchers, can be found in Apendix I.

A neural model in intrusion detection systems

The paper proposes the use of the multilayer perceptron model to the problem of detecting attack patterns in computer networks. The multilayer perceptron is trained and assessed on patterns extracted from the files of the Third International Knowledge Discovery and Data Mining Tools Competition. It is required to classify novel normal patterns and novel categories of attack patterns. The results are presented and evaluated in the paper.

A hybrid neural model in long-term electrical load forecasting

A novel hierarchical hybrid neural model to the problem of long-term electrical load forecasting is proposed in this paper. The neural model is made up of two self-organizing map nets — one on top of the other —, and a single-layer perceptron. It has application into domains which require time series analysis. The model is compared to a multilayer perceptron. Both the hierarchical and the multilayer perceptron models are endowed with time windows in their input layers. They are trained and assessed on load data extracted from a North-American electric utility. The models are required to predict once every week the electric peak-load and mean-load during the next two years. The results are presented and evaluated in the paper.

Contingency analysis with the help of voltage stability tools. Proposals for corrective actions using distributed generation

The energy consumption is a sensitive indicator in the test of the wellness and prosperity of a population, but fossil sources are limited and contaminate. The energy consumption is one of the greatest gauges of a societys progress. The concept of energy crisis appears when the sources of energy that the society provides exhaust. The rapid growth of the power demand and the depletion of the generation reserves of the current generation power stations require the study of other generation options, such as the alternative generation. The objectives of betting on renewable energies are to curb dependence on energy imports, limit the greenhouse effect, provide the necessary energy to ensure the correct electrical supply and maintain the system with a high degree of stability. To address the problem described above, a methodology was developed where, by applying voltage stability tools such as the data obtained by the Reactive Power Margin (RPM) and the Tangent Vector (TV) ranking, the most critical bus was identified, and then they were injected in the same alternative generations. This would lead the system to improve performance in terms of voltage stability and operate at load margins farther to the point of voltage collapse.

Overview on Microgrids: Technologies, Control and Communications

The modern society is highly dependent on electricity. At the same time, there is a huge concern about the greenhouse gas emissions and the current way of power generation, mainly with fossil fuels and high costs. The deployment of microgrids may be a solution for both questions. They are a solution to the supply reliability problem through the existent distributed energy resources (DERs) connected to the grid near customers, and the environmental concern is met by applying renewable sources to generate power. Beyond these goals, there is a supply cost reduction and revenue maximization through power trades with the main grid, which is also considered as desired matches. Using proper control strategies and robust communications techniques, microgrids generate, distribute and regulate the flow of power to consumers through a centralized or decentralized control. Smart microgrids are an ideal way to integrate renewable resources on the community level and allow for customer participation in all levels of the power market. Hence, a distribution system may evolve to a microgrid that may become a smart grid. Because the level of intelligence, communication, and control may vary, this chapter assumes the term microgrids in a general sense, which may stand for an ordinary microgrid or a smart grid. The goal of this chapter is to provide a brief overview on microgrids, including the state of art about the main motivation for the emergence of these networks. A survey on some existing microgrids around the world focusing on the different architecture and applications, e.g., hospitals, military bases and small isolated communities is carried out. Next, a typical microgrid’s architecture is presented. Some other topics regarding generation resources, energy storage options, suitable communication technologies, and infrastructure are discussed. From the economic and social point of view, microgrid’s effects are addressed by highlighting the main benefits. In addition, technical issues and future challenges are discussed in this chapter.

Impact of Dynamic Thermal Limits of Transmission Lines on Power System Operation

This paper discusses a methodology to determine the ampacity of transmission lines based on their dynamic thermal limits. In this sense, temperature, wind speed, season conditions, and system loading are taken into account, rendering a methodology that determines, for each operating point and weather condition, the actual thermal limit of a transmission line. The proposed technique is tested in a real scenario and compared with the technique currently employed for this purpose.

Use of the state estimator for voltage stability assessment of ITAIPU Binacional Hydroelectric power plant

This work proposes a voltage stability assessment method for the interconnection ITAIPU Hydroelectric power plant (IHPP) and ANDE. For this sake, a valid solution of a state estimator used to assess the operation safety of each equilibrium point is employed as an input. A static power flow model is used and the QV and PV curves are obtained to determine the critical bus, the load margin and the reactive power margin. This work may help the real time operation to determine the control actions that must be taken to maintain the operation within the safety limits.