Ali N. Hasan

Perturb and observe based on fuzzy logic controller maximum power point tracking (MPPT)

Photovoltaic (PV) systems are considered to be renewable resources of energy that utilize direct sun radiation and converts it to electric power. The most important elements in such systems are photovoltaic cells that are connected as an array to produce usable electric energy. These systems need electronic converters to convert the systems output current and voltage into a proper form when considering the conditions of the systems load and its needs. The most commonly used electronic converter is the DC to DC converter where high voltage is generated from the low solar cell voltage. This paper, explores the PV system and DC to DC converter with reference to two cases: in the first case, the system was designed as a closed loop system, since the situation of the system depends on the algorithm of the maximum power point tracking (MPPT), which captures the maximum amount of sunshine to generate the maximum electrical power. This system simulation and hardware implementation was done using the MATLAB/SIMULINK software program and real components integration. In the second case, the system was designed depending on MPPT, but the simulation was done by using a fuzzy logic controller. The implementation and simulation results for both cases are presented to illustrate the output voltages steady state returning ability when the input voltage influence varied. The presence of a minute settling time and over-shoot in output voltage return ia apparent as well. Finally, the result for the two cases is compared to ascertain which case is better.

Comparison of modified Incremental Conductance and Fuzzy Logic MPPT algorithm using modified CUK converter

Incremental Conductance (IC) algorithm is considered cheap, and easy to implement for Maximum Power Point Tracking (MPPT). However, the IC technique takes time to find the MPP if the voltage is far away from the MPP, and suffers when subjected to rapid change in irradiance. In this paper, IC technique was compared to the modified Incremental Conductance technique (MIC) under the standard test conditions (STC). Then the MIC was compared to a Fuzzy Logic Controller (FLC) MPPT technique in order to evaluate the best and the accurate controller for the MPPT. Results suggest that using FLC and MIC could improve the MPPT and increase the PV system stability.

Curve fitting polynomial technique compared to ANFIS technique for maximum power point tracking

In this paper, an approach of designing a fast tracking MPPT is introduced using a predicted sixth order polynomial curve fitting MPPT technique. The results are compared with the lower order polynomials curve fitting MPPT and also compared with the Artificial Neuro-Fuzzy Inference System (ANFIS) results. The polynomials were generated from an offline solar data. This work was done to validate the effect of using a higher order polynomials under various weather conditions using modified CUK DC-DC converter. Findings suggest that using the 6th order polynomial curve fitting and the ANFIS techniques could track the highest maximum power point than the lower order curve techniques.

Improving single classifiers prediction accuracy for underground water pump station in a gold mine using ensemble techniques

In this paper six single classifiers (support vector machine, artificial neural network, naïve Bayesian classifier, decision trees, radial basis function and k nearest neighbors) were utilized to predict water dam levels in a deep gold mine underground pump station. Also, Bagging and Boosting ensemble techniques were used to increase the prediction accuracy of the single classifiers. In order to enhance the prediction accuracy even more a mutual information ensemble approach is introduced to improve the single classifiers and the Bagging and Boosting prediction results. This ensemble is used to classify, thus monitoring and predicting the underground water dam levels on a single-pump station deep gold mine in South Africa, Mutual information theory is used in order to determine the classifiers optimum number to build the most accurate ensemble. In terms of prediction accuracy, the results show that the mutual information ensemble over performed the other used ensembles and single classifiers and is more efficient for classification of underground water dam levels. However the ensemble construction is more complicated than the Bagging and Boosting techniques.

Moving towards accurate monitoring and prediction of gold mine underground dam levels

In this paper a comparison between an ensembles (multi-classifier) constructed of several machine learning methods (support vector machine, artificial neural network, naive Bayesian classifier, decision trees, radial basis function and k nearest neighbors) versus each single classifiers of these methods in term of gold mine underground dam levels prediction is presented. The ensembles as well as the single classifiers are used to classify, thus monitoring and predicting the underground water dam levels on a single-pump station deep gold in South Africa. In order to improve the classification accuracy an ensemble was constructed based on each single classifier performance, therefore, five ensembles were built and tested. In terms of misclassification error, the results show the ensemble to be more efficient for classification of underground water dam levels compared to each of the single classifiers.

Implementation of modified incremental conductance and fuzzy logic MPPT techniques using MCUK converter under various environmental conditions

Incremental Conductance (IC) technique is a cheap, and easy algorithm to implement for Maximum Power Point Tracking (MPPT). However, the IC technique usually takes time and suffers some delay to approach the MPP if the voltage is not near to the MPP or when subjected to rapid change in irradiance. In this paper, IC technique was implemented and compared to the modified Incremental Conductance technique (MIC) under various environmental conditions such as standard test conditions (STC) and partial shading conditions. Also the MIC method was compared to a Fuzzy Logic Controller (FLC) MPPT technique in order to evaluate the best and the accurate controller for the MPPT for different weather conditions. Results show that using FLC and MIC techniques are efficient for MPPT and may increase the PV system stability.

Impulse Noise Detection in OFDM Communication System Using Machine Learning Ensemble Algorithms

An impulse noise detection scheme employing machine learning (ML) algorithm in Orthogonal Frequency Division Multiplexing (OFDM) is investigated. Four powerful ML’s multi-classifiers (ensemble) algorithms (Boosting (Bos), Bagging (Bag), Stacking (Stack) and Random Forest (RF)) were used at the receiver side of the OFDM system to detect if the received noisy signal contained impulse noise or not. The ML’s ensembles were trained with the Middleton Class A noise model which was the noise model used in the OFDM system. In terms of prediction accuracy, the results obtained from the four ML’s Ensembles techniques show that ML can be used to predict impulse noise in communication systems, in particular OFDM.

The Use of Multilayer Perceptron to Classify and Locate Power Transmission Line Faults

This paper investigates the use of multilayer perceptron (MLP) technique for locating and detecting faults in a power transmission line. MLP was used twice in this paper to locate and to detect faults. The experiments were conducted on a 600-km-length, three-phase power transmission line data which include the required faults to detect and locate the fault. Matlab was used to perform the experiments. Results show that MLP achieved high prediction accuracy for fault type detection of 98% and a prediction accuracy of 78% for fault location.

Distributive MPPT Approach Using ANFIS and Perturb&Observe Techniques Under Uniform and Partial Shading Conditions

PV systems work under different weather conditions such as uniform and partial shading weather conditions. This causes inconsistent power in PV systems. This paper presents a reconfigurable interconnections approach that uses and compares between two powerful maximum power point tracking (MPPT) techniques of artificial neuro-fuzzy inference system [ANFIS front-end distributive MPPT (DMPPT)] technique and Perturb&Observe distributive MPPT technique. This approach is introduced in order to decrease the partial shading and mismatch effect caused by varying light falling on the PV arrays, which will lead to extract more power from the PV modules. The PV systems were configured as series-connected PV string that uses Perturb&Observe MPPT technique and as a PV series-connected system that uses ANFIS-MPPT technique. The proposed PV systems were tested under uniform and partial shading weather conditions. The results show that MPPT could be tracked accurately with the ANFIS-DMPPT for both cases of uniform irradiance and partial shaded irradiance conditions.

The use of machine learning techniques to classify power transmission line fault types and locations

Transmission lines are very important component of the electric power system. Therefore it is necessary to predict and detect transmission lines fault types and locations to enhance the power system protection scheme and increase its reliability. This paper investigates the use of four powerful machine learning classifiers to detect and predict fault types and locations over a 750KV, 600km long power transmission line. Bagging, Boosting, radial basis functions and naïve Bayesian classifiers were utilized for locating and detecting faults in a power transmission line. Findings exhibits that using machine learning technique could be feasible for such task and may represent a great opportunity to increase the power system protection and efficiency.