Giacomo Capizzi

A radial basis function neural network based approach for the electrical characteristics estimation of a photovoltaic module

The design process of photovoltaic (PV) modules can be greatly enhanced by using advanced and accurate models in order to predict accurately their electrical output behavior. The main aim of this paper is to investigate the application of an advanced neural network based model of a module to improve the accuracy of the predicted output I–V and P–V curves and to keep in account the change of all the parameters at different operating conditions. Radial basis function neural networks (RBFNN) are here utilized to predict the output characteristic of a commercial PV module, by reading only the data of solar irradiation and temperature. A lot of available experimental data were used for the training of the RBFNN, and a backpropagation algorithm was employed. Simulation and experimental validation is reported.

Innovative Second-Generation Wavelets Construction With Recurrent Neural Networks for Solar Radiation Forecasting

Solar radiation prediction is an important challenge for the electrical engineer because it is used to estimate the power developed by commercial photovoltaic modules. This paper deals with the problem of solar radiation prediction based on observed meteorological data. A 2-day forecast is obtained by using novel wavelet recurrent neural networks (WRNNs). In fact, these WRNNS are used to exploit the correlation between solar radiation and timescale-related variations of wind speed, humidity, and temperature. The input to the selected WRNN is provided by timescale-related bands of wavelet coefficients obtained from meteorological time series. The experimental setup available at the University of Catania, Italy, provided this information. The novelty of this approach is that the proposed WRNN performs the prediction in the wavelet domain and, in addition, also performs the inverse wavelet transform, giving the predicted signal as output. The obtained simulation results show a very low root-mean-square error compared to the results of the solar radiation prediction approaches obtained by hybrid neural networks reported in the recent literature.

Recurrent Neural Network-Based Modeling and Simulation of Lead-Acid Batteries Charge–Discharge

This paper presents the main experiences and results obtained about the problem of the lead-acid battery modeling and simulation. A nonlinear mathematical model is presented as well as results of neuroprocessing of the charge-discharge experimental and simulated data. Recurrent neural networks were used to provide a state-of-charge observer and model parameter estimation and tuning. The simulation results are compared with those obtained by extensive lab tests performed on different batteries used for electric vehicle and photovoltaic application.

A Cascade Neural Network Architecture Investigating Surface Plasmon Polaritons Propagation for Thin Metals in OpenMP

Surface plasmon polaritons (SPPs) confined along metal-dielectric interface have attracted a relevant interest in the area of ultracompact photonic circuits, photovoltaic devices and other applications due to their strong field confinement and enhancement. This paper investigates a novel cascade neural network (NN) architecture to find the dependance of metal thickness on the SPP propagation. Additionally, a novel training procedure for the proposed cascade NN has been developed using an OpenMP-based framework, thus greatly reducing training time. The performed experiments confirm the effectiveness of the proposed NN architecture for the problem at hand.

Some remarks on the application of RNN and PRNN for the charge-discharge simulation of advanced Lithium-ions battery energy storage

In this paper is reported a critical review, experiences and results about state of charge (SOC) and voltage prediction of Lithium-ions batteries obtained by recurrent neural network (RNN) and pipelined recurrent neural network (PRNN) based simulation. These soft computing technologies will be here presented, utilized and implemented to obtain the typical charge characteristics and the charge/discharge simulation procedure of a commercial solid-polymer technology based cell. Simulations are compared with experimental data manufacturers.

Recurrent neural network-based control strategy for battery energy storage in generation systems with intermittent renewable energy sources

The intermittent nature of renewable sources as wind and solar puts a challenge for their use in supply energy to small islands, isolated communities or in developing countries. The integration of battery energy storage system (BESS) or diesel groups is then mandatory. The aim of the paper is to propose a complete recurrent neural networks (RNN) based control strategy of the BESS accounting state of charge (SOC) and terminal voltage and that can be used for their size and to test the use of different type of BESS.

Optimal management of various renewable energy sources by a new forecasting method

Hybrid power systems are increasingly considered in order to produce more electrical energy by renewable sources. Energy management of these plants is a challenge and in this paper we propose a new forecasting method for renewable sources an load demand to obtain an improved management. The novelty of this approach is that the proposed wavelet recurrent neural network, WRNN performs the prediction in the wavelet domain and in addiction it also performs the inverse wavelet transform giving as output the predicted renewables and loads. The case study is an hybrid plant assembled at the University of Catania.

Hybrid neural networks architectures for SOC and voltage prediction of new generation batteries storage

This paper presents some experiences and results obtained about the problem of the SOC and voltage prediction and simulation of new generation batteries. A complex pipelined recurrent neural network (PRNN) was designed for modeling of new generation batteries storage in order to predict the SOC and the terminal voltage. The simulation results are compared with experimental data obtained on commercial batteries.

A novel cloud-distributed toolbox for optimal energy dispatch management from renewables in IGSs by using WRNN predictors and GPU parallel solutions

Integrated generation systems (IGSs) are today increasingly considered to exploit renewable energy in order to supply load for remote areas, less developed countries and small isolated communities. The IGS investigated in this paper enclose a PV park with battery energy storage system and this configuration is considered as case study for the campus called Cittadella at the University of Catania. A novel cloud distributed toolbox for the purpose of an optimal energy dispatch management by using Wavelet Recurrent Neural Networks (WRNN) predictors and Graphic Processing Units (GPU) parallel solutions in the IGS considered as case study is proposed. Results coming from the implementation of the proposed cloud architecture are here presented.

Exploiting solar wind time series correlation with magnetospheric response by using an hybrid neuro-wavelet approach

The studies about the Sun rise a strong interest regarding modifications caused by the solar activity on the Earth. For almost a century in literature was discussed the problem of forecasting and analysis of the space weather, which in his definition covers both the nearearth space and the biospheric affection due to the environmental interaction with the Sun. In particular in the last years increased the attention for magnetospheric response in conjunction with the technological infrastructure and the biosphere itself. This to prevent i.e. spacecraft failures or possible treats to human health. Since the main effect of the activity of the Sun is the solar wind, rises the aim to found a correlation between itself and the localized variations induced on the magnetosphere being the purpose to predict long-term variation of the magnetic field from solar wind time series. As recently proposed for solar wind forecasting, an hybrid approach will be here used than joining the wavelet analysis with the prediction capabilities of recurrent neural networks with an adaptive amplitude activation function algorithm in order to avoid the need to standardize or rescaling the input signal and to match the exact range of the activation function. BibTeX of the published version: @INPROCEEDINGS{Napoli2010a, author={Napoli, C. and Capizzi, G. and Bonanno, F.}, title={Exploiting solar wind time series correlation with magnetospheric response by using an hybrid neuro-wavelet approach}, booktitle={Proceedings IAU Symposium No. 274, 2010}, editor={A. Bonanno, E. de Gouveia Dal Pino & A.G. Kosovichev}, year={2011}, pages={153-155}, doi={10.1017/S1743921311006806},} Copyright