Zuhaila Mat Yasin

Artificial-immune-based for solving economic dispatch in power system

This paper presents an artificial immune system based optimization approach for solving the economic dispatch problem in a power system. Economic dispatch determines the electrical power to be generated by the committed generating units in a power system so that the generation cost is minimised, while satisfying the load demand simultaneously. The developed artificial immune system optimization technique used the total generation cost as the objective function and represented as the affinity measure. Through genetic evolution, the antibodies with high affinity measure are produced and become the solution. The simulation results reveal that the developed technique is easy to implement, converged within an acceptable execution time and highly optimal solution for economic dispatch with minimum generation cost can be achieved. The result also confirms that AIS based optimization technique can be a useful tool for solving optimal solution in economic dispatch problem, which involves a large number of generating units and at the same time to comply with a large number of constraints.

Optimal sizing of distributed generation by using quantum-inspired evolutionary programming

The paper proposes a novel evolutionary programming inspired by quantum mechanics, called a quantum-inspired evolutionary programming (QIEP). The proposed algorithm consists of three levels, quantum individuals, quantum groups and quantum universes. The proposed algorithm is implemented to determine the optimal sizing of distributed generation (DG) for loss minimization at the optimal location. The location of the distributed generation was identified using the sensitivity indices. In order to demonstrate its performance, comparative studies are performed with conventional evolutionary programming in terms of loss minimization and computation time. The installation of single DG and multiple DG also presented and the results shows better improvement in terms of loss minimization and voltage profile. The proposed study was conducted on the IEEE 69-bus test system.

Outcome Based Education Performance Evaluation on Electrical Engineering laboratory module

Implementing Outcome Based Education (OBE) in evaluating program outcomes is a standard practice nowadays at the Faculty of Electrical Engineering (FEE), Universiti Teknologi MARA (UiTM). Previously, laboratory assessments method was merely based only on lab report submitted by each group of students and the procedure is inconsistence as each module consists of different area of electrical engineering fields and involves many lecturers from various disciplines in the FEE. Furthermore, there were no specific guidelines for grading the report and lecturers would rely on their experiences, resulting large variance of judgments in giving the marks. To overcome such problem, an OBE assessment tool known as Laboratory Sensor Performance Evaluation Course Tool (LAB-SPECT) has been designed recently for evaluating laboratory modules. This tool has taken into account additional students attributes that represents teamwork skill, practical skill and ethical in the lab. With rubrics table provided, it has successfully facilitated lecturers to evaluate students fairly in terms of their Group Related Skills (GRS) besides than the laboratory report. Each of the assessment section in this process is addressing the respective the course outcome (CO) and program outcome (PO). The output plots produced by this tool would be used as indicators for Continual Quality Improvement (CQI) recommendations.

Service Restoration in Distribution Network with Distributed Generation

This paper studies the influence of location and capacity sizing of distributed generation during service restoration. It is assumed that after the occurrence of fault at particular section of a distribution network, the loads get disconnected and are left unsupplied. Service should be restored to the affected loads through a network reconfiguration procedure. In this study, network reconfiguration was implemented using the TOPO application in the power system simulation programme for planning, design and analysis of distribution system (PSS/Adept). This application determines the optimal sectionalizing-tie switch pairs based on minimum losses configuration and at the same time, all nodes are assured for the supply. The location of the distributed generation was identified using the pre-determined sensitivity indices, while evolutionary programming was used to determine the size of the installed distributed generations. The proposed study was conducted on the IEEE 69 bus distribution system. The results show that installing distributed generation at the suitable location with appropriate sizing has able to provide lower loss level and higher voltage profile in fault condition as compared to that obtained when the network was installed with compensating capacitor.

Quantum-Inspired Evolutionary Programming-Artificial Neural Network for prediction of undervoltage load shedding

This paper presents new intelligent-based technique namely Quantum-Inspired Evolutionary Programming-Artificial Neural Network (QIEP-ANN) to predict the amount of load to be shed in a distribution systems during undervoltage load shedding. The proposed technique is applied to two hidden layers feedforward neural network with back propagation. The inputs to the ANN are the load buses and the minimum voltage while the outputs are the amount of load shedding. ANN is trained to perform a particular function by adjusting the values of the connections (weights) between elements, so that a particular input leads to a specific target output. The network is trained based on a comparison of the output and the target, until the network output matches the target. The parameters of ANN are optimally selected using Quantum-Inspired Evolutionary Programming (QIEP) optimization technique for accurate prediction. The QIEP-ANN is developed to search for the optimal training parameters such as number of neurons in hidden layers, the learning rate and the momentum rate. This method has been tested on IEEE 69-bus distribution test systems. The results show better prediction performance in terms of mean square error (MSE) and coefficients of determination (R2) as compared to classical ANN.

Multiobjective quantum-inspired evolutionary programming for optimal load shedding

This paper present new technique namely Quantum-Inspired Evolutionary Programming (QIEP) to determine the optimal location and optimal amount of load to be shed for undervoltage load shedding schemes. This approach is based on the concept of quantum mechanics in the Evolutionary Programming (EP). Quantum-Inspired is implemented according to three levels defined by quantum individuals, quantum groups and quantum universe in order to improve the speed of the algorithm. The QIEP is employed to search for the best location and amount of load to be shed based on multiobjective functions which are power loss minimisation, voltage profile improvement and power interruption cost minimisation. The effectiveness of multiobjective QIEP optimisation technique is illustrated in IEEE 33-bus distribution test system, IEEE 69-bus distribution test system and 141-bus distribution system. The results were also compared with other techniques in terms of fitness values and computation time.

Influence of Distributed Generation on Distribution Network Performance during Network Reconfiguration for Service Restoration

The effect of location and sizing of distributed generation to the power losses and voltage profile during network reconfiguration for service restoration are investigated in this paper. The location of the distributed generation was identified using the pre-determined sensitivity indices, while evolutionary programming was used to determine the size of the installed distributed generations. The simulation was conducted by applying three phase fault at an identified location. After the fault is isolated, the network is reconfigured by changing the open/closed states of the tie lines and sectionalising switches for service restoration while minimising the total power losses in the network. Network reconfiguration was implemented using the TOPO application in the power system simulation programme for planning, design and analysis of distribution system (PSS/Adept). The simulation was conducted on the 69-bus distribution system.

Multiobjective quantum-inspired evolutionary programming for optimal location and sizing of distributed generation

This paper presents Quantum-Inspired Evolutionary Programming (QIEP) technique to determine the optimal locations and sizing of multiple distributed generations (DG) in a distribution system. QIEP is an algorithm that employs the concept of quantum mechanics in the Evolutionary Programming (EP). Quantum-Inspired is implemented according to three levels defined by quantum individuals, quantum groups and quantum universe. The problem formulation is based on a multiobjective model in which the multiobjective are defined as reducing power losses, increasing maximum loadability limits and cost minimisation. Three cases are considered to test the effectiveness of the proposed technique namely single objective function, multiobjective function with fixed weighted sum and multiobjective function with randomly optimised weighted sum. The performances of the multiobjective QIEP optimisation technique were compared with those obtain from conventional evolutionary programming in terms of fitness values and computation time. The proposed study was conducted on the IEEE 69-bus distribution test system and the 141-bus distribution system.

Modelling neutral to earth voltage (NTEV) on the commercial building

Power Quality (PQ) problems on distribution system (DS) can be categorized as voltage sag, voltage swell, harmonic, transient and others. Nowadays, due to the nonlinear loads, imbalanced loads, improper wiring and poor grounding on DS, the neutral to earth voltage (NTEV) become issue of the PQ problem. Generally, magnitude of the NTEV is zero value if the system is balance, however it changes to the nonzero value due many factor as mention above. Furthermore, in order to study the effect and factor of commercial building and DS, a reliable model need to be applied. The main contribution of this paper is to determine NTEV and NC magnitude and shape in the DS. Then, this paper presented the model of the three phase four-wire underground cable on the commercial building; the comparison of measurement data and simulation result on the NTEV and NC. This model using XLPE cable as the connection from the transformer to the load, CIM as the load at commercial building, and RLC ground electrode as the grounding system. In order to validated this simulation, the model is tested on the two different data of the commercial building. The simulation results are similar identical with the measurement, even the shape of the NTEV and NC are different. As the conclusion, the objective is to determine the magnitude and shape of the NTEV and NC are successfully done and this model can be used to determine the NTEV rise on the others commercial building and also can be used to study the factor contribution due to elevated of NTEV.

Optimal least squares support vector machines parameter selection in predicting the output of distributed generation

This paper presents a novel technique to optimise the least squares support vector machines (LS-SVM) parameters in predicting the output of Distributed Generation (DG) in a distribution system. In LS-SVM, the accuracy of the prediction is depends on the selection of kernel parameters. Unfortunately, there is no systematic methodology for selection of their optimal values. Therefore, a novel hybrid Quantum-Inspired Evolutionary Programming - Least Squares Support Vector Machine (QIEP-SVM) is developed for accurate prediction. In QIEP-SVM, Quantum-Inspired Evolutionary Programming (QIEP) is developed to optimise selected parameters for the LS-SVM which are gamma and sigma. QIEP is combining Evolutionary Programming (EP) with quantum mechanics concepts such as interference and superposition in order to enhance classical Evolutionary Programming (EP). The optimal output of DG is first generated using multiobjective Quantum-Inspired Evolutionary Programming (QIEP) at various loading condition according to 24-hours load profile. The data from the simulations are then used as the inputs to the Least-Squares Support Vector Machine (LS-SVM). There are three inputs which are active load (MW), reactive load (MVAR) and minimum voltage (p.u). Whereas, there are five outputs that represents the output of DG at five buses. The objective function for the optimisation process is to minimise the mean square error between predicted and targeted output. The performance of QIEP-SVM is then compared to classical LS-SVM using cross-validation technique and hybrid Artificial Neural Network-Quantum-Inspired Evolutionary Programming (QIEP-ANN). The results of QIEP-SVM model had shown better prediction performance as compared to classical LS-SVM and QIEP-ANN. All simulations in this study were carried out using IEEE 69-bus distribution test system.