Artificial Neural Network Based Approach for Anti-islanding Protection of Distributed Generators
- PDF / 1,326,789 Bytes
- 10 Pages / 595.276 x 790.866 pts Page_size
- 40 Downloads / 153 Views
Artificial Neural Network Based Approach for Anti-islanding Protection of Distributed Generators Victor Luiz Merlin · Ricardo Caneloi dos Santos · Ahda Pionkoski Grilo Pavani · Denis Vinicius Coury · Mário Oleskovicz · José Carlos de Melo Vieira Jr.
Received: 4 May 2013 / Revised: 5 November 2013 / Accepted: 12 December 2013 © Brazilian Society for Automatics–SBA 2014
Abstract The anti-islanding protection of synchronous generators is typically performed by voltage and frequency relays. However, one of the main issues related to setting these relays is to identify and differentiate the magnitude and frequency variations of an islanding event from other disturbances that may occur along the system, such as severe load switching. By using an artificial neural network (ANN) based approach, it is possible to recognize existent patterns on the distributed generator voltage waveform, which makes possible to obtain an accurate response about islanding events. However, the ANN training process is not so easy, because it involves important issues such as the definition of the ANN architecture, the size of data window, sampling rate, and selection of a representative training set for the studied problem. In this context, this paper discusses the fundamental aspects for training an ANN used for islanding detection of synchronous distributed generators. Keywords Distributed generation · Anti-islanding protection · Artificial neural network 1 Introduction The connection of generators in distribution networks allows the use of many different sources. This type of generation, V. L. Merlin · R. C. dos Santos (B) · A. P. Grillo Pavani Center for Engineering, Modeling and Applied Social Sciences, Federal University of ABC, Av. dos Estados, 5001, Santo Andre CEP 09210-580, SP, Brazil e-mail: [email protected] D. V. Coury · M. Oleskovicz · J. C. de Melo Vieira Jr. Electrical and Computer Engineering Department, Sao Carlos School of Engineering, University of Sao Paulo, Av. Trabalhador Sao-carlense, 400, Sao Carlos CEP 13566-590, SP, Brazil
known as distributed generation, represents an alternative to supply the growing demand for energy, mainly by the use of renewable sources. In addition, it also has advantages such as increasing the efficiency of industrial plants and increase the reliability of energy supply (Tolmasquim 2003; Lora and Haddad 2006). The installation of these generators, however, must follow many different technical evaluations to ensure a safe, reliable, and efficient operation of the entire electrical system, especially after the occurrence of short circuits or contingencies. These evaluations should determine if the operation of the generator meets the requirements demanded by the distribution companies. These requirements are different from those usually applied in conventional generators connected to transmission networks, since the distribution networks, specially the feeders, was not designed to receive power injection by generation systems (Trindade et al. 2013). One of the requirements that dese
Data Loading...
