Sulaiman Shaari

Sizing grid-connected photovoltaic system using genetic algorithm

This paper presents an intelligent-based algorithm for sizing grid-connected photovoltaic (GCPV) system using Genetic Algorithm (GA). GA had been used to determine the optimal PV module and inverter from pre-developed PV module and inverter databases such that the expected technical performance of the design could be optimized. In addition, the technical sizing outputs such as the number of photovoltaic (PV) modules, PV array configuration and inverter-to-PV array sizing factor were computed. The GA had outperformed the Evolutionary Strategies (ES) during the sizing process in terms of producing better optimum results. Low error had also been produced by GA when compared to a benchmark sizing algorithm using iterative sizing approach.

A hybrid artificial neural network for grid-connected photovoltaic system output prediction

This paper presents a hybrid Particle Swarm Optimization-Artificial Neural Network (PSO-ANN) for predicting the kWh output from a grid-connected photovoltaic (GCPV) system. In this study, the ANN-based prediction utilized solar irradiance (SI), ambient temperature (AT) and module temperature (MT) as the inputs and kWh energy from the GCPV system as the sole output. Besides that, Particle Swarm Optimization (PSO) was used to optimize the number of neurons in the hidden layer during the ANN training process such that the Root Mean Square Error (RMSE) of the prediction was minimized. After the training process, testing was performed to validate the ANN training. The results showed that the proposed hybrid PSO-ANN had outperformed the hybrid Fast Evolutionary Programming-Artificial Neural Network (FEP-ANN) in producing lower RMSE. In addition, the optimal learning algorithm and population size in PSO were also investigated in this study.

Power prediction for grid-connected photovoltaic system in Malaysia

This paper presents the prediction performance and analysis of the power output from grid-connected photovoltaic (GCPV) system using power model. The power model used is presently applied in the testing, commissioning and acceptance test of grid-connected systems procedure in Malaysia. This study involved outdoor testing and validation of model through mathematical formula, root mean square error (RMSE), Pearson correlation coefficient (R2) and standard deviation (STD) determination. Results showed that most of the time, the actual power output was lower than the modelled power output. This implies that more derating factors should be considered in the existing power model such as aging and installation criteria.

Stand-Alone Photovoltaic Power System applications in Malaysia

This paper presents an overview and status Stand-Alone Photovoltaic Power System (SAPVPS) in Malaysia. Malaysia is located at equatorial line is suitable to generate a power supply from solar. Electrification of remote area in Malaysia shows progress in terms of capacity of SAPVPS installation. Malaysia seriously intends to invest in renewable energy has initiate many incentive and programs to ensures the future of solar in Malaysia is bright.

Artificial neural network versus linear regression for predicting Grid-Connected Photovoltaic system output

This paper presents a classically trained Multi-Layer Feedforward Neural Network (MLFNN) technique for predicting the output from a Grid-Connected Photovoltaic (GCPV) system. In the proposed MLFNN, the selection of the training parameters was conducted using a series of prescribed steps. The MLFNN utilized solar irradiance (SI) and module temperature (MT) as its inputs and AC kWh energy as its output. When compared with the linear regression method, the MLFNN offered superior performance by producing lower prediction error.

Performance analysis of 45.36 kWp grid-connected photovoltaic systems at Malaysia Green Technology Corporation

This paper presents the performance of a 45.36 kWp grid-connected photovoltaic (PV) system at Malaysia Green Technology Corporation (MGTC), Bangi, Malaysia. The site is located at latitude of approximately 2.96°N and longitude of 101.75°E. The system was commissioned on 14th June 2007 and the system performance has been monitored since 1st Feb 2008. The system comprises 45.36 kWp of PV array size, a 40 kW inverter and other balance of system (BOS) components. An irradiance sensor and two temperature sensors are connected externally to the system via the inverter to obtain the irradiance, ambient temperature and module temperature profiles at the site. In contrast, other performance data such as AC current AC voltage, DC current and DC voltage are recorded from the inverter. During the monitoring period, all data were recorded based on 15 minute interval. The system had produced 787.25 MWh of solar electricity since its being monitored with an average daily output of 144 kWh. On the other hand, the inverter efficiency has been fluctuating from 86% to 97%. The average monthly final yield was found to be 96 kWhkWp−1 while the performance ratio (PR) varies from 71.37% to 91.99%.

An Automated Solar Photovoltaic Biaxial Tracking System: SolT2A

This paper describes a prototype product code-named SolT2A. It is a system that automatically tracks the sun as it traverses the hemispherical sky vault. The system has been comprehensively used in photovoltaic (PV) satellite systems and is an option for terrestrial applications. For earthbound systems, locations near the Equator experience the crossing of solar altitude across the zenith daily and a reversal of the azimuth over a year. Consequently, static PV systems do not produce maximum generation. Thus SolT2A has been designed and built to address this problem. The system has a four-point solar irradiance sensors and compares their intensity levels. The differentials are analysed and processed by a controller before and then sent to a set of DC motors. Thus SolT2A is a self-correcting system that ensures maximum irradiance captured by the PV arrays at all times, thus ensuring maximum PV generation. Based on field data, the open circuit voltage produced by the SolT2A tracking system is up to 82% better than from static systems The over all increase in open circuit voltage production is between 15 to 20% daily. Further developmental work includes optimising power consumption of the tracking and cost benefit analysis.

Fast Evolutionary Programming-based Hybrid Multi-Layer Feedforward Neural Network for predicting Grid-Connected Photovoltaic system output

This paper presents a Hybrid Multi-Layer Feedforward Neural Network (HMLFNN) technique for predicting the output from a Grid-Connected Photovoltaic (GCPV) system. In the proposed HMLFNN, Fast Evolutionary Programming (FEP) was employed to optimize the training process of the Multi-Layer Feedforward Neural Network (MLFNN). FEP was used to select the optimal values for the number of neurons in the hidden layer, the learning rate, the momentum rate, the type of activation function and the learning algorithm. In addition, the MLFNN utilized solar irradiance (SI) and module temperature (MT) as its inputs and AC kWh energy as its output. When compared with the Classical Evolutionary Programming (CEP) trained MLFNN, the proposed FEP-based HMLFNN offered superior performance by producing lower computation time and lower prediction error.

A development and challenges of grid-connected photovoltaic system in Malaysia

This paper presents the update status of a grid-connected photovoltaic (GCPV) system installed in Malaysia. There are 125 sites with total PV capacity power is approximately 1137.21 kWp of GC BIPV systems until the end of June, 2011 was monitored by Photovoltaic System Monitoring Centre (PVSMC). After 5 years of operation under MBIPV project, two main problems have been identified due to technical and environmental, which contributes to 60% and 40% respectively. This factor may contribute the decrement on the PV system performances in terms of field yield. By identifying the potential problem occurred, the knowledge and experiences in a GCPV system will used as the input and the potential problem will be avoided, in order to achieve the maximize the energy production. All issues are identified, which affects the system performances based on 5 years experience through MBIPV project by conducting short-term investigation.

Sizing ratio of inverter and PV array for a-Si FS GCPV system in Malaysia's perspectives

System designs sizing and natural environmental analysis are two common issues and considered to be among the most crucial part of the study with the objective of enhancing the Grid-connected Photovoltaic (GCPV) performance in Malaysias perspective. This a-Si GCPV system located near to the Green Energy Research Centre (GERC) Building at Universiti Teknologi MARA (UiTM), Shah Alam, Malaysia. This a-Si GCPV system installation was referred to Malaysian Standard MS1837:2010 and designed based on initial data values of PV module characteristics. To date, most of GCPV system applications using thin-film (TF) PV module technologies in Malaysia were designed at stabilized data values. So, this system is conducted to study the derating factor for matching inverter and PV array sizing and behavior of a-Si FS GCPV system under Malaysias real condition. The P-V analysis fully utilizes the infield data as a guideline for sizing inverter and PV array, with the aim of guiding the system designer during initial design stage for Malaysias climate.