The Real-Time Recurrent Learning Gradient (RTRL) algorithm is characterized by being an online learning method for training dynamic recurrent neural networks, which makes it ideal for working with non-linear control systems. For this reason, this paper presents the design of a novel Maximum Power Point Tracking (MPPT) controller with an artificial neural network type Adaptive Linear Neuron (ADALINE), with Finite Impulse Response (FIR) architecture, trained with the RTRL algorithm. With this same network architecture, the Least Mean Square (LMS) algorithm was developed to evaluate the results obtained with the RTRL controller and then make comparisons with the Perturb and Observe (P&O) algorithm. This control method receives as input signals the current and voltage of a photovoltaic module under sudden changes in operating conditions. Additionally, the efficiency of the controllers was appraised with a fuzzy controller and a Nonlinear Autoregressive Network with Exogenous Inputs (NARX) controller, which were developed in previous investigations. It was concluded that the RTRL controller with adaptive training has better results, a faster response, and fewer bifurcations due to sudden changes in the input signals, being the ideal control method for systems that require a real-time response.
In the field of engineering when a situation is not resolved analytically, efforts are made to develop methods that approximate a possible solution. These efforts have originated the numerical methods known at present, which allow formulating mathematical problems that can be solved using logical and arithmetic operations. This paper presents a comparison between the numerical optimization algorithms golden section search and simulated annealing, which are tested in four different scenarios. These scenarios are functions implemented with a feedforward neural network, which emulate a partial shading behavior in photovoltaic modules with local and global maxima. The presence of the local maxima makes it difficult to track the maximum power point, necessary to obtain the highest possible performance of the photovoltaic module. The programming of the algorithms was performed in C language. The results demonstrate the effectiveness of the algorithms to find global maxima. However, the golden section search method showed a better performance in terms of percentage of error, computation time and number of iterations, except in test scenario number three, where a better percentage of error was obtained with the simulated annealing algorithm for a computational temperature of 1000.
This paper presents a detailed description of the data obtained as a result of the computational simulations and experimental tests of an MPPT controller based on an ADALINE artificial neural network with FIR architecture, trained with the RTRL and LMS algorithms that were used as mechanisms of control in an off-grid photovoltaic system. In addition to the data obtained with the neural control method, the data for the MPPT controller based on the traditional Perturb and Observe (P&O) algorithm are presented. The simulations were performed in MATLAB/Simulink software without using the Neural Network Toolbox for controller training. The experimental tests were performed in an open space without shaded areas, exposing the neurocontroller to varying environmental conditions. Additionally, the scripts developed in MATLAB for the neural training algorithms used in the simulations are presented. These computational simulations were structured in five test cases to represent the behavior of each controller under varying environmental conditions. The codes developed in C are part of the implementation of the MPPT neurocontroller in the PIC18F2550, from which the experimental data were obtained. The data and codes presented in this research are available in the Mendeley Data repository, which allows evaluating the performance and optimizing the training algorithms with the purpose of improving the control methods applied to photovoltaic systems.
This paper presents the data of multimodal functions that emulate the performance of an array of five photovoltaic modules under partial shading conditions. These functions were obtained through mathematical modeling and represent the P–V curves of a photovoltaic module with several local maximums and a global maximum. In addition, data from a feedforward neural network are shown, which represent an approximation of the multimodal functions that were obtained with mathematical modeling. The modeling of multimodal functions, the architecture of the neural network and the use of the data were discussed in our previous work entitled “Search for Global Maxima in Multimodal Functions by Applying Numerical Optimization Algorithms: A Comparison Between Golden Section and Simulated Annealing” [1]. Data were obtained through simulations in a C code, which were exported to DAT files and subsequently organized into four Excel tables. Each table shows the voltage and power data for the five modules of the photovoltaic array, for multimodal functions and for the approximation of the multimodal functions implemented by the artificial neural network. In this way, a dataset that can be used to evaluate the performance of optimization algorithms and system identification techniques applied in multimodal functions was obtained.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.