T. K. Abdul Rahman

Novel fast voltage stability index (FVSI) for voltage stability analysis in power transmission system

Since a couple of decades ago, voltage stability assessment has received increasing attention due to the complexity of power systems. With the increase in power demand and limited power sources has caused the system to operate at its maximum capacity. Therefore, a study that is able to determine the maximum capacity limit before voltage collapse must be carried out so that necessary precaution can be taken to avoid system capacity violation. This paper presents a novel fast voltage stability index (FVSI) simplified from a pre-developed voltage stability index referred to a line initiated from the voltage quadratic equation at the sending end of a representation of a 2-bus system. The line index in the interconnected system in which the value that is closed to 1.00 indicates that the line has reached its instability limit which could cause sudden voltage drop to the corresponding bus caused by the reactive load variation. The formulated index was tested on the IEEE reliability test system in order to verify the performance of the proposed indicator. Results showed that the proposed technique is indicative in predicting the occurrence of system collapse and hence necessary action can be taken to avoid such incident.

Fast automatic contingency analysis and ranking technique for power system security assessment

One of the essential aspects of modern power system security assessment is the consideration of any contingencies arise due to planned or unplanned line outages leading to system overloads or abnormal system voltages. Several techniques have been developed in the past few years to address this problem but computation time has been identified as the constraint making the process inefficient. This paper presents a new algorithm for automatic contingency analysis and ranking caused by line outage in a power transmission system. All steps in the algorithms including the load flow analysis; removal and reinsertion of line and overall ranking process were accommodated in one complete programme making it a complete and effective solution for contingency analysis and ranking. A pre-developed line-based voltage stability index is used as a tool in determining the severity of the contingencies. Results from experiments showed that this technique is much faster than the existing technique while reducing human error constraint.

Partial Evolutionary ANN for Output Prediction of a Grid-Connected Photovoltaic System

This paper presents the Evolutionary Programming (EP) based technique to optimize the architecture and training parameters of a one-hidden layer backpropagation Artificial Neural Network (ANN) model for the prediction of total AC power output from a grid connected photovoltaic system. A partial Evolutionary Programming-ANN (EPANN) model has been developed for the prediction. It utilizes solar radiation, wind speed and ambient temperature as its inputs while the output is the total AC power produced from the grid connected PV system. EP is used to optimize the regression performance of the ANN model by determining the optimum values for the number of nodes in the hidden layer as well as the optimal momentum rate and learning rate for training. The results obtained from the EPANN have been compared with the results from a classical ANN with similar input and output settings. It is observed that the prediction of total AC power output from a grid connected PV system could be accelerated and simplified using the partial evolutionary ANN model. Index Terms—Artificial neural network (ANN), Correlation coefficient (R), Evolutionary programming-ANN (EPANN), and Photovoltaic (PV).

Optimizing three-layer neural network model for grid-connected photovoltaic system output prediction

This paper presents the Evolutionary Neural Network (ENN) model for the prediction of output from a grid-connected photovoltaic system installed at Malaysian Energy Centre (PTM), Bangi, Malaysia. The ENN model had been developed using Evolutionary Programming (EP) through the optimization of the number of nodes in the hidden layer, the learning rate and the momentum rate. The ENN model employs solar irradiance and ambient temperature as its inputs while the sole output is the kilowatt-hour energy output produced from the grid connected PV system. On the other hand, the objective function of the ENN is to maximize the correlation coefficient, R of the prediction task. In this study, the optimal pool population size in the ENN algorithm was investigated. Apart from that, the maximum average correlation coefficient obtained for the ENN training is 0.9942. Besides that, the testing process produced sufficiently high correlation coefficient value of 0.9922.

Artificial immune system based machine learning for voltage stability prediction in power system

Voltage instability has recently become a challenging problem for many power system operators. This phenomenon has been reported to be responsible for severe low voltage condition leading to major blackouts. This paper presents the application of Artificial Immune Systems (AIS) for online voltage stability evaluation that could be used as early warning system to the power system operator so that necessary action could be taken in order to avoid the occurrence of voltage collapse. Key features of the proposed method are the implementation of clonal selection principle that has the capability in performing pattern recognition task. The proposed technique was tested on the IEEE 30 bus power system and the results shows that fast performance with accurate evaluation for voltage stability condition has been obtained.

Case study of Short Term Load Forecasting for weekends

This paper presents the Short Term Load Forecasting (STLF) to predict the demand in the future. STLF is a method used to predict a day ahead, 24 hours load demand. Two factors were considered in this forecasting: time and also the temperature of the day. The main objective of this project is to analyze the profile or pattern of the forecasted load and also to predict the load demand during weekends. Artificial Neural Network (ANN) in MATLAB software was used in solving the forecasting problem. The percentage of average error was determined by using the Mean Absolute Percentage Error (MAPE).

Optimizing one-hidden layer neural network design using Evolutionary Programming

This paper presents the optimization of one-hidden layer Artificial Neural Network (ANN) design using Evolutionary Programming (EP) for predicting the energy output of a grid-connected photovoltaic system installed at Malaysian Energy Centre (PTM), Bangi, Malaysia. In this study, the architecture and training parameters of the multi-layer feedforward back-propagation ANN model had been optimized while the prediction performance of the ANN was maximized. The proposed Evolutionary Programming-ANN (EPANN) model employs solar radiation and ambient temperature as its inputs while the sole output is the kilowatt-hour energy output produced from the grid connected PV system. The prediction performance was quantified using the average correlation coefficient and it was maximized by determining the optimum values for the number of nodes in the hidden layer, momentum rate and learning rate during an evolutionary training. Besides searching for the optimal number of nodes and optimal training parameters for each model, the highest correlation coefficient for the prediction required for the EPANN was investigated. It was found that the maximum average correlation coefficient obtained for the EPANN training is 0.9962. Besides that, the testing process produced sufficiently high correlation coefficient value of 0.9976.

Design of grid-connected photovoltaic system using evolutionary programming

This paper presents an intelligent-based sizing algorithm for the design of grid-connected photovoltaic system using evolutionary programming. Evolutionary programming had been used to select the optimal PV module and inverter from pre-developed databases such that the expected technical performance of the design could be maximized. The proposed algorithm, known as evolutionary programming-based sizing algorithm (EPSA), was able to produce similar sizing results with an iterative-based benchmark sizing algorithm. In addition, EPSA was also found to produce the accurate results at a faster rate than the benchmark algorithm. Further investigation on the evolution of the fitness value had shown a consistent improvement of the fitness value after each evolution.

Artificial neural network-based forecast for electricity consumption in Malaysia

An essential element of electric utility resource planning is the long term forecast of the electricity consumption. This paper presents an approach to forecast annual electricity consumption by using artificial neural network based on historical data for Malaysia. It involves developing several ANN designs and selecting the best network that can produce the best results in terms of its accuracy. The network is developed by means of economical conditions and how the variables are going to be changed in the following years. After obtaining the most reliable model, ANN is used to forecast the electricity consumption. The developed ANN model yields very satisfactory results and as a result, the range of electricity consumption can be successfully obtained.

Short-term Hydrothermal Generation Scheduling Using Evolutionary Computing Technique

This paper presents a solution of a short term hydrothermal scheduling problem using evolutionary computing technique. The technique is used to handle the problems of short-term hydrothermal scheduling and economic load dispatch while satisfying hydraulic and thermal constraints in order to minimize the total system cost. This technique is tested on a system consisting of a hydroplant and a steam unit and the test results are compared with those obtained using lambdamiddotgamma iteration and genetic algorithm method.