Performance comparison of neural networks for intelligent management of distributed generators in a distribution system |
| |
| Affiliation: | 1. Faculty of Electrical and Electronic Engineering, Universiti Tun Hussein Onn Malaysia, Malaysia;2. Department of Electrical, Electronic and Systems Engineering, Universiti Kebangsaan Malaysia, Malaysia;1. The College of Information Science and Engineering, Northeastern University, Shenyang 110819, China;2. Information and Communication Branch, State Grid Liaoning Electric Power Company Ltd, Shenyang 110819, China;1. Federal Rural University of Pernambuco, Brazil;2. Federal University of Paraíba, Brazil;3. Federal University of Campina Grande, Brazil;4. University of Brasília, Brazil;1. Departament de Sanitat i Anatomia Animals, Universitat Autònoma de Barcelona (UAB), 08193, Bellaterra, Barcelona, Spain;2. Departament de Sociologia / IGOP, Universitat Autònoma de Barcelona (UAB), 08193, Bellaterra, Barcelona, Spain;3. IRTA, Centre de Recerca en Sanitat Animal (CRESA, IRTA-UAB), Campus de la Universitat Autònoma de Barcelona, 08193, Bellaterra, Spain;4. Servicio de Sanidad Animal, Consejería de Agricultura, Pesca y Desarrollo Rural de la Junta de Andalucía, 41013, Sevilla, Spain;5. Departament d’Agricultura, Ramaderia, Pesca i Alimentació, Generalitat de Catalunya, Servei de Prevenció en Salut Animal, 08007, Barcelona, Spain |
| |
| Abstract: | The Multilayer Perceptron (MLP) neural network has been proven to be a very successful type of neural network in many applications. The MLP activation function is one of the important elements to be considered in neural network training in which proper selection of the activation function will give a huge impact on the network performance. This paper presents a comparative study of the four most commonly used activation functions in the neural network which include the sigmoid, hyperbolic tangent and linear functions used in the MLP neural network and the Gaussian function used in the Radial Basis Function (RBF) network for managing active and reactive power of distributed generation (DG) units in distribution systems. Simulation results show that the sigmoid activation functions give better performance in predicting the optimal power reference of the DG units. However, the RBF neural network gives the fastest conversion time compared to the MLP neural network. |
| |
| Keywords: | Artificial neural network Multilayer Perceptron Radial basis function Activation function |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
