On Simulation Performance of Feedforward and NARX Networks Under Different Numerical Training Algorithms
نویسنده
چکیده
This chapter focuses on comparing the forecasting ability of the backpropagation neural network (BPNN) and the nonlinear autoregressive moving average with exogenous inputs (NARX) network trained with different algorithms; namely the quasi-Newton (Broyden-Fletcher-Goldfarb-Shanno, BFGS), conjugate gradient (Fletcher-Reeves update, Polak-Ribiére update, Powell-Beale restart), and Levenberg-Marquardt algorithm. Three synthetic signals are generated to conduct experiments. The simulation results showed that in general the NARX which is a dynamic system outperforms the popular BPNN. In addition, conjugate gradient algorithms provide better prediction accuracy than the Levenberg-Marquardt algorithm widely used in the literature in modeling exponential signal. However, the LM performed the best when used for forecasting the Moroccan and South African stock price indices under both the BPNN and NARX systems.
منابع مشابه
Modeling and Multi-Objective Optimization of Stall Control on NACA0015 Airfoil with a Synthetic Jet using GMDH Type Neural Networks and Genetic Algorithms
This study concerns numerical simulation, modeling and optimization of aerodynamic stall control using a synthetic jet actuator. Thenumerical simulation was carried out by a large-eddy simulation that employs a RNG-based model as the subgrid-scale model. The flow around a NACA0015 airfoil, including a synthetic jet located at 10 % of the chord, is studied under Reynolds number Re = 12.7 × 106 a...
متن کاملNonlinear Model Identification Using Recurrent Neural Networks: Application to Acetone Cracking
This paper presents the formulation of a nonlinear model identification method based on recurrent neural network (RNN) Nonlinear AutoRegressive with eXternal input (NARX) model derived from dynamic feedforward neural network (DFNN) by adding feedback connection between output and input layers. The proposed identification method identifies the neural network (NN) model of an input-output system....
متن کاملDay-Ahead Solar Forecasting Based on Multi-level Solar Measurements
The growing proliferation in solar deployment, especially at distribution level, has made the case for power system operators to develop more accurate solar forecasting models. This paper proposes a solar photovoltaic (PV) generation forecasting model based on multi-level solar measurements and utilizing a nonlinear autoregressive with exogenous input (NARX) model to improve the training and ac...
متن کاملA Framework for the Development of Globally Convergent Adaptive Learning Rate Algorithms
In this paper we propose a framework for developing globally convergent batch training algorithms with adaptive learning rate. The proposed framework provides conditions under which global convergence is guaranteed for adaptive learning rate training algorithms. To this end, the learning rate is appropriately tuned along the given descent direction. Providing conditions regarding the search dir...
متن کاملForecasting of heavy metals concentration in groundwater resources of Asadabad plain using artificial neural network approach
Nowadays 90% of the required water of Iran is secured with groundwater resources and forecasting of pollutants content in these resources is vital. Therefore, this research aimed to develop and employ the feedforward artificial neural network (ANN) to forecast the arsenic (As), lead (Pb), and zinc (Zn) concentration in groundwater resources of Asadabad plain. In this research, the ANN models we...
متن کامل