Browsing by Issue Date, starting with "2018-09-25"
Now showing 1 - 4 of 4
Results Per Page
Sort Options
- Design and Implementation of MPPT System Based on PSO AlgorithmPublication . Calvinho, Gonçalo; Pombo, José Álvaro Nunes; Mariano, S.; Calado, M. Do RosárioThis paper presents a method for maximum power point tracking (MPPT) based on the particle swarm optimization (PSO) algorithm with variable step size in order to prevent steady state oscillations. This will avoid the impact of partial shading conditions in the efficiency of photovoltaic (PV) systems. To optimize power output of the solar panels a DC-DC boost converter is used. Special emphasis is put on software development and implementation in the TMS320F28027 microcontroller in Texas Instruments Code Composer Studio.
- Position Control of Linear Switched Reluctance Machine using Flower Pollination AlgorithmPublication . Nunes, H.G.G.; Pestana, Luís; Mariano, S.; Calado, M. Do RosárioThis paper presents a control mechanism for position control of linear switched reluctance machine (LSRM) using flower pollination algorithm (FPA). The control mechanism consists of the proportional-integral-derivative (PID) position controller. Therefore, the problem of determining the optimal values for the gains (proportional, integral and derivative) of the position controller is defined as an optimization problem that aims to obtain the optimal gains by minimizing the integral of time multiplied by absolute error (ITAE) of the position. In order to evaluate the performance of the FPA different operating scenarios were considered and the salp swarm algorithm (SSA) and multi-verse optimizer (MVO) were also implemented for results comparison. The results reveal that position control based on the optimal gains obtained by the FPA provides the smallest error, improving the dynamic performance of the LSRM
- Short-Term Load Forecasting using optimized LSTM Networks via Improved Bat AlgorithmPublication . Bento, P.M.R.; Pombo, José Álvaro Nunes; Mariano, S.; Calado, M. Do RosárioShort-term load forecasting plays a preponderant role in the daily basis system's operation and planning. The state- of-the-art comprises a far-reaching set of methodologies, which are traditionally based on time-series analysis and multilayer neural networks. In particular, the existence of countless neural network architectures has highlighted its ability to cope with 'hard' nonlinear approximation tasks, thus making them appropriate to perform load forecasts. Following this successful path, long short-term memory networks were employed in an optimized arrangement as forecasters, this type of recurrent neural networks has received in recent years a renewed interest for machine learning tasks. Firstly, a preprocessing stage takes place, where through the selection of similar days and correlation analysis, meaningful statistics and characteristics are extracted from the load time-series, to assemble the proper training sets. Then, Bat Algorithm is used to excel the long short-term memory network functioning, by fine-tuning its size and its learning hyperparameters. Numerical testing conducted on the Portuguese load time-series reveals promising forecasting results in an overall assessment, when compared with other state-of-the-art methods.
- Lookup Table Based Intelligent Charging and Balancing Algorithm for Li-ion Battery PacksPublication . Velho, Ricardo Lopes; Pombo, José Álvaro Nunes; Fermeiro, J.B.L.; Calado, M. Do Rosário; Mariano, S.In this article, an energy storage system (ESS) and its entire monitoring system are implemented. A new charging algorithm is developed based on the parameters of the battery pack in real time, extending the battery lifespan, improving the capacity usage and performance of the ESS. The proposed algorithm analyses, in real time, the difference between the desired voltage and the mean voltage of the cells, the temperature of the pack, and the difference of voltage between cells. Based on the obtained information, by trilinear interpolation, the algorithm calculates the charging current. The proposed charging algorithm also combines a balancing algorithm. This represents an innovation compared to the existing methods in the literature. The experimental results demonstrate that the proposed algorithm can successfully charge Li-ion battery packs with different capacities and life cycles, providing a better charging time and a much lower temperature increase.