Maryam Khademi

Power Prediction and Technoeconomic Analysis of a Solar PV Power Plant by MLP-ABC and COMFAR III, considering Cloudy Weather Conditions

The prediction of power generated by photovoltaic (PV) panels in different climates is of great importance. The aim of this paper is to predict the output power of a 3.2 kW PV power plant using the MLP-ABC (multilayer perceptron-artificial bee colony) algorithm. Experimental data (ambient temperature, solar radiation, and relative humidity) was gathered at five-minute intervals from Tehran University’s PV Power Plant from September 22nd, 2012, to January 14th, 2013. Following data validation, 10665 data sets, equivalent to 35 days, were used in the analysis. The output power was predicted using the MLP-ABC algorithm with the mean absolute percentage error (MAPE), the mean bias error (MBE), and correlation coefficient (), of 3.7, 3.1, and 94.7%, respectively. The optimized configuration of the network consisted of two hidden layers. The first layer had four neurons and the second had two neurons. A detailed economic analysis is also presented for sunny and cloudy weather conditions using COMFAR III software. A detailed cost analysis indicated that the total investment’s payback period would be 3.83 years in sunny periods and 4.08 years in cloudy periods. The results showed that the solar PV power plant is feasible from an economic point of view in both cloudy and sunny weather conditions.

Optimizing Exergy Efficiency of Flat Plate Solar Collectors Using SQP and Genetic Algorithm

An increase in exergy efficiency of flat plate solar collector leads to a considerable improvement in collector’s performance. Different parameters influence the performance of collector. In this paper, Sequential Quadratic Programming (SQP) and Genetic Algorithm (GA) have been employed for optimizing exergy efficiency of the flat plate solar collector. Absorber plate area and mass flow rate of inlet water have been considered as optimization’s variables. The results show the possibility to reach higher exergy efficiency with lower absorber area and consequently lower price. Also it is obvious that SQP method performs optimization process with higher convergence speed but lower accuracy than GA.

The application of Local Linear Neuro Fuzzy model in recognition of online Persian isolated characters

In this paper, we propose an approach for recognizing online Persian isolated characters using LLNF model. Local Linear Neuro Fuzzy (LLNF) Model is a powerful approach for classification tasks. It uses divide-and-conquer strategy to partition the problem space into sub-problems and construct Local Linear Models (LLMs). In order to classify the characters, at first, we extract some generic features of Persian character and build a features vector. Then we construct a LLNF model by the features vector as input data. The constructed LLNF model will be later used to recognize the written letters. Our experimental results for 100 different people show recognition rate of 99.15%.

A proposed architecture for collaborative data visualization systems

Managing knowledge through analyzing big data is a complex and difficult task owing to extensive amount of hidden information and patterns within them. Visualization is a technique that helps analysts to overcome such difficulties by representing data in a graphical view. Collaborative visualization refers to a group effort of analyzers who work on a same problem where they share their collective knowledge over the issue. Providing a flexible, robust and powerful system helps the analysts to collaborate better while investigating a problem. In this paper we present a 5-tier architecture for developing a collaborative visualization system which addresses several aspects of such system from importing of data to visualizing them on different devices.

A fuzzy logic-based approach to verify the optimized parameters a gas turbine power plant by PSO algorithm

Exergoeconomic and thermoeconomic analysis are among powerful and effective tools to find the best solutions between the two objective functions that can be used by energy engineers, minimizing economic cost and maximizing exergetic efficiency. In this research, operating parameters of a gas turbine power plant that produces 140 MW of electricity is optimized by using exergoeconomic principles and PSO algorithm. The comparison of results between the PSO algorithm and the base model shows very good improvements, i.e. the fuel mass flow rate by optimized parameters is 11.24% lower than the base case. Also the exergetic efficiency is 6.55% more than the base case. The verification by fuzzy logic shows that total matching PSO results and base case is 99.5%.

Optimizing the Tilt Angle of Solar Panels by SQP Algorithm

In present research we propose a nonlinear solving method to obtain the optimum tilt angle for solar panels. For this purpose, solar radiation on tilted panels are estimated by applying anisotropic model in Maple and the maximum is obtained by solving parametric nonlinear equations with Sequential Quadratic Programming (SQP) algorithm. Comparing its results with prevalent calculation proved this method faster and more efficient. The used model is validated by comparing results with measured data on a 45o-tilted surface in Tehran, Iran. Results showed solar radiation on a tilted surface increases 32% by monthly adjustments, in comparison with a fixed horizontal surface.