Mohd Faris Abdullah

Electricity forecasting for small scale power system using fuzzy logic

Electricity supply to Universiti Teknologi PETRONAS (UTP) comes from gas district cooling (GDC) plant as a primary source of energy and utility company Tenaga Nasional Berhad (TNB) as a backup. With a maximum capacity of 8.4 MW which comes from 2 nos of gas turbine generators rated at 4.2 MW each, this work aims to forecast short term electricity demand of the plant. As a sole customer of the plant, UTP 2008 electricity demand data is being used as a basis to design a forecast model using Fuzzy Logic. With the forecast model, it will help GDC for pre-planned scheduling and maintenance of the plant and also as guidance for the daily operation of the plant. The proposed fuzzy logic model is applied to obtain one week forecast load demand data for GDC. The forecast accuracy is obtained and it is represented in mean absolute percentage error (MAPE).

Electricity forecasting for small scale power system using artificial neural network

Short term load forecasting (STLF) method is the basis of efficient operation for power system. It has an important role in planning and operation of power system. In this paper, a practical STLF using artificial neural network method (ANN) for Gas District Cooling (GDC) power plant of Universiti Teknologi PETRONAS (UTP) is presented. As a sole customer of GDC power plant, the load data from 2006 till 2009 are gathered and utilized for model developments. The developed models forecast electricity load for one week ahead. The paper proposes a method of a multilayer perceptron neural network and it is trained and simulated by using MATLAB. The models have been tested with the actual load data and perform relatively good results.

A novel method for vegetation encroachment monitoring of transmission lines using a single 2D camera

AbstractThe dangerous, overgrown vegetation/trees under high voltage transmission lines right-of-ways (ROWs) have caused severe blackouts/flashovers due to interference with power lines which leads to short circuiting among the conductors. Therefore, these dangerous encroachments are monitored periodically along the electrical distribution networks ROWs through visual inspection, or by airborne system. Each of these methods has its own attributes and limitations and have proved to be costly, time consuming and not much accurate. In these circumstances, it is necessary for the electrical utilities to review their vegetation management practices so as to avoid incidents of unintended encroachments. In tropical countries, overgrown vegetation is a common cause for power line failure. This paper proposes an innovative concept of utilizing a single camera for monitoring dangerous vegetation (trees, shrubs and plants, etc.) under transmission lines ROWs. The main focus is on using an imaging device (camera) integrated on each transmission pole to automate inspection for the vegetation encroachments endangering the transmission lines. These cameras are envisioned to be connected wirelessly to each other, forming a series of wireless camera networks that can be monitored remotely. A single camera mounted on power poles acquires images and sends them wirelessly to the base station. At base station, algorithm (software) trained by image processing and pattern recognition techniques is used to identify (height, depth, and width of encroached vegetation, etc.) excess vegetation encroachments within and outside ROWs. The performance evaluation of a real time developed test-bed scenario proves the feasibilities of integrating the method for transmission line maintenance.

Investigation on high neutral earthing resistor temperature when islanded generator connected to utility grid

Electricity supply to Universiti Teknologi PETRONAS (UTP) is provided by two generating units at gas district cooling (GDC) plant located in the campus. Under normal operation, UTP power system is operating in island mode and during emergency, it will be connected to utility grid of Tenaga Nasional Berhad (TNB). Each generating unit is grounded through neutral earthing resistor (NER). It has been observed that NER temperature become high when generator operating in parallel with the grid. Investigation reveals that triplen harmonics currents continuously flow through NER during island and parallel operation. Higher triplen harmonics currents are noticed during parallel operation as compared to island mode of operation. High NER temperature is caused by increase in triplen harmonics currents that flow through it. The above phenomena are described in this paper together with some proposed measures to overcome the problem.

Scene classification for aerial images based on CNN using sparse coding technique

ABSTRACT Aerial scene classification purposes to automatically label aerial images with specific semantic categories. However, cataloguing presents a fundamental problem for high-resolution remote-sensing imagery (HRRS). Recent developments include several approaches and numerous algorithms address the task. This article proposes a convolutional neural network (CNN) approach that utilizes sparse coding for scene classification applicable for HRRS unmanned aerial vehicle (UAV) and satellite imagery. The article has two major sections: the first describes the extraction of dense multiscale features (multiple scales) from the last convolutional layer of a pre-trained CNN models; the second describes the encoding of extracted features into global image features via sparse coding to achieve scene classification. The authors compared experimental outcomes with existing techniques such as Scale-Invariant Feature Transform and demonstrated that features from pre-trained CNNs generalized well with HRRS datasets and were more expressive than low- and mid-level features, exhibiting an overall 90.3% accuracy rate for scene classification compared to 85.4% achieved by SIFT with sparse coding. Thus, the proposed CNN-based sparse coding approach obtained a robust performance that holds promising potential for future applications in satellite and UAV imaging.

Triplen harmonics currents propagation through medium voltage distribution network

Harmonics propagation can be studied by various harmonics load flow methods. The propagation of balanced triplen harmonics currents produced by synchronous generator through medium voltage underground cable of distribution network can be modeled by triplen harmonics voltages acting as the source for zero sequence network. Third harmonics current being a major component of triplen harmonics is being studied for various underground cable parameters, generator and transformer grounding methods, load variation/connection and distributed generation configuration. Time domain analysis is used for simulation and the model is validated with the third harmonics current measurement at site. Third harmonics current propagation is influenced by third harmonics voltage source, cable length, generator grounding, number of parallel cables, cable size, load, load connection and DG configuration.

The study of triplen harmonics currents produced by salient pole synchronous generator

Triplen harmonics study for harmonics produced by salient pole synchronous generator is very important because their presence have caused communication line interference, damage to neutral earthing resistor etc. The purpose of this paper is to study the characteristics of triplen harmonics under balanced/unbalanced resistive/inductive loads, different generator neutral earthing resistor values and various transformer winding configurations. Lab scale salient pole synchronous generator is used for the experiment and third harmonic currents are recorded for analysis to represent triplen harmonics currents characteristics. Under balanced load, third harmonic current is inversely proportional to load impedance and neutral current is three times the phase current. During unbalanced load condition, the neutral current is lower than arithmetic sum of phase current due to different phase current magnitude and angle. The phase and neutral third harmonic currents magnitude is inversely proportional to generator NER resistance under balanced load. Transformer winding configurations under balanced load permit third harmonic current flowing through them in accordance to zero sequence network for the transformer apart from higher transformer reactive impedance at third harmonic. This study provides a very important input to mitigation method in reducing triplen harmonics currents propagation in the network.

The Third Harmonic Model for Salient Pole Synchronous Generator Under Balanced Load

The third harmonic current produced by salient pole synchronous generator has always been associated with high neutral current causing problem to neutral earthing resistor, telecommunication system, and earth fault protection. In this paper, the third harmonic model for salient pole synchronous generator in symmetrical component domain is proposed that comprise of generator parameter and generated voltage. The new computational technique in determining the third harmonic zero-sequence synchronous impedance is introduced. In completing the model, the method to characterize generated third harmonic zero-sequence voltage under balanced combine resistive and inductive load is described. In order to study the third harmonic current flowing in the network, the propagation model is also established. The third harmonic synchronous generator parameters are measured and comparatively validated with laboratory experiment results. In addition to that, the third harmonic generated voltage is characterized and validated experimentally.

Estimation of Power System Harmonic Using Modified Normalized Least Mean Square

A new adaptive power system harmonic estimator is presented, which is competent of tracking power system harmonic components. The proposed estimator technique is based on the normalized Least Mean Square (LMS), which is a stochastic gradient descent algorithm. The learning method of the proposed estimator is based upon the recursive estimate of the signal power, and is faster tracking of harmonic components as compared to the introduced Adaptive Linear Element (ADALINE).

Forecasting Solar Radiation Data Using Gaussian and Polynomial Fitting Methods

Solar radiation prediction is an important task prior to installation of solar photovoltaic panel or to estimate the amount solar radiation received at certain time with respective location. The main objective of the work presented in this chapter is to perform fitting for solar radiation data by using polynomials, Gaussian function and sine fitting as well as Jain’s methods. Comparison among all methods are measured by using Root Mean Square Error (RMSE) and the coefficient of determination, R². Two fitting models are proposed for the prediction of solar radiation in the campus of Universiti Teknologi PETRONAS (UTP), Malaysia..