Siti Amely Jumaat

Transmission loss minimization using SVC based on Particle Swarm Optimization

This paper describes optimal sizing of static var compensator (SVC) based on Particle Swarm Optimization for minimization of transmission losses considering cost function. Particle Swarm Optimization (PSO) is one of the artificial intelligent search approaches which has the potential to solve such a problem. For this study, static var compensator (SVC) is chosen as the compensation device. Validation through the implementation on the IEEE 26-bus system shows that the PSO is found feasible to achieve the task. The simulations results are compared with those obtained from the Bee Algorithm (BA) technique in the attempt to highlight its merit.

Optimal Location and Sizing of SVC Using Particle Swarm Optimization Technique

This paper describes optimal location and sizing of static var compensator (SVC) based on Particle Swarm Optimization for minimization of transmission losses considering cost function. Particle Swarm Optimization (PSO) is population-based stochastic search algorithms approaches as the potential techniques to solving such a problem. For this study, static var compensator (SVC) is chosen as the compensation device. Validation through the implementation on the IEEE 30-bus system indicated that PSO is feasible to achieve the task. The simulation results are compared with those obtained from Evolutionary Programming (EP) technique in the attempt to highlight its merit.

PSO based technique for loss minimization considering voltage profile and cost function

This paper describes optimal sizing of FACTS devices based on Particle Swarm Optimization for minimization of transmission loss considering voltage profile and cost function. Particle Swarm Optimization (PSO) is one of the artificial intelligent search approaches which have the potential in solving such a problem. In this study one of FACTS devices is used as a scheme for transmission loss. For this study, static var compensator (SVC) is chosen as the compensation device. The effect of population size during the optimization process towards achieving the solution is also investigated. Validation through the implementation on the IEEE 30-bus RTS indicated that PSO is feasible to achieve the task.

Particle swarm optimization techniques for optimal location and sizing of thyristor controlled series capacitor

One of the disturbances experienced by the power system is increase in loading condition, which often led the system to no longer remains in secure operating region. When the power system is exposed to any kind of time delay and inaccessibility of control scheme, system may become inconsistent leading to uncontrolled condition. Under this condition, the main purpose of the operator is to execute control actions to get the system back into the secure operating regions. Flexible AC transmission system (FACTS) device is one of the devices, which can be inserting to control power system stability improvement. This paper describes the optimal placement and sizing of TCSC using on Particle Swarm Optimization (PSO) method. The objective function for this study is to minimize the transmission loss, increase the voltage profile, while considering the cost of installation. Effect of weight coefficient and effect of population size during the optimization process towards obtaining the solution is also explored. To validate the proposed techniques, simulations are performed on an IEEE 30-bus system.

Placement and sizing of thyristor controlled series compensator using PSO based technique for loss minimization

Minimizing the transmission loss in power system is one of the important issues in power system research these days. Transmission loss can be reduced by installing reactive power compensation components. Installing the thyristor controlled series compensator (TCSC) in power system has been known to increase the voltage level in the system and hence reduce the system losses. This paper describes placement and sizing of FACTS devices based on Particle Swarm Optimization for minimization of transmission loss considering voltage profile and cost function. Particle Swarm Optimization (PSO) is one of the artificial intelligent search approaches which have the potential in solving such a problem. In this study one of FACTS device is used as a scheme for transmission loss. For this study, TCSC is chosen as the compensation device. Validation through the implementation on the IEEE 30-bus system indicated that PSO is feasible to achieve the task. The simulation results are compared with those obtained from the Evolutionary Programming (EP) technique in the attempt to highlight its merit.

MOPSO approach for FACTS device installation in power system

This paper presents an approach to sigma multiobjective optimization particle swarm (σ-MOPSO) technique for optimal allocation of Flexible AC Transmission System (FACTS) devices. For this study, Static Var Compensator (SVC) is selected as a compensation device. Proposal σ-MOPSO technique has been implemented to minimize the transmission losses and the cost of investment in the system. Simulations performed on standard IEEE RTS 30-bus and IEEE 118-bus RTS. Results are compared with those obtained from the programming of multiobjective evolutionary technique (MOEP) in order to highlight its advantages.

Cluster Identification for Optimal Placement of Static Var Compensator

This paper introduces a new concept of artificial intelligence based algorithm for clustering the placement of SVCs in power system. The algorithm is based on particle swarm optimization (PSO) technique with objective function to minimize the transmission loss in the system. Experiments were performed on the IEEE 30- and IEEE 118-bus RTS to realize the effectiveness of the proposed technique, while verification was conducted through comparative studies with evolutionary programming (EP).

Developed cluster of SVC installation in power system network via hybrid meta-heuristic method

This paper introduces a new approach of meta-heuristic based method for clustering the optimal location of SVC installation in power system. The algorithm is based on evolutionary particle swarm optimization (EPSO) technique with the objective to minimize the transmission loss in power system. With the formation of cluster decision can be made by power system operators to perform power compensation scheme considering selected loading conditions and loaded buses. Experiments were performed on the IEEE 30-bus RTS to realize the effectiveness of the proposed method. Comparison with respect to conventional PSO was conducted which eventually resulted superiority in terms of loss minimization.

Cluster identification through FACTS device installation in bulk power system

Weak once in power system is normally referred to the area which is prone to system collapse. This is due lower to maximum loadability within the area. On the other hand, compensation process may also lead to cluster which represents the optimal location for FACTS device installation. This paper presents cluster development using Evolutionary Particle Swarm Optimization (EPSO) for flexible alternating currents transmission system (FACTS) device installation. The technique has been implemented in a bulk power system. In the meantime voltage profile improvement is monitored while cost of installation of installation is conducted. Comparison with respect to traditional PSO was conducted which eventually resulted superiority in terms of voltage profile improvement loss minimization and cost of installation. Validation was conducted on the IEEE 118-Bus system.

Prediction of Photovoltaic (PV) Output Using Artificial Neutral Network (ANN) Based on Ambient Factors

This paper is proposed an artificial neural network (ANN) to apply in the system of prediction of power output from photovoltaic (PV) panel system. In order to test the efficiency and reliability of a proposed ANN model experimental output will be comparing with mathematical equation. The objectives of this project are to develop the ANN model that capable of predicting power output. The activation functions using for the hidden layer is hyperbolic tangent. The training algorithm is used Levenberg-Marquardt backpropagation. The meteorology data as input data was obtained from RET screen database in the period from 1st January 2015 until 31st August 2016. There were two locations in Malaysia to be the subject test; Melaka and Kuala Lumpur. From the result, for Melaka, Malaysia the outputs Vm (MAPE = 0.0003% and RMSE = 8.5%) and Im (MAPE = 4.3% and RMSE = 26.8%). Then, for Kuala Lumpur, Malaysia have a less error and good correlation with Vm (RMSE = 0.2%) and Im (MAPE = 0.008% and RMSE = 0.3%). Hence, average power output was high level in January to March for both locations. The conclusion shows that the performance of power output is depending on the level of solar radiation on the day.