Garuda - Garba Rujukan Digital

Performance Comparison of Artificial Intelligence Techniques for Non-intrusive Electrical Load Monitoring Khairuddin Khalid; Azah Mohamed; Ramizi Mohamed; Hussain Shareef
Bulletin of Electrical Engineering and Informatics Vol 7, No 2: June 2018
Publisher : Institute of Advanced Engineering and Science

The increased awareness in reducing energy consumption and encouraging response from the use of smart meters have triggered the idea of non-intrusive load monitoring (NILM). The purpose of NILM is to obtain useful information about the usage of electrical appliances usually measured at the main entrance of electricity to obtain aggregate power signal by using a smart meter. The load operating states based on the on/off loads can be detected by analysing the aggregate power signals. This paper presents a comparative study for evaluating the performance of artificial intelligence techniques in classifying the type and operating states of three load types that are usually available in commercial buildings, such as fluorescent light, air-conditioner and personal computer. In this NILM study, experiments were carried out to collect information of the load usage pattern by using a commercial smart meter. From the power parameters captured by the smart meter, effective signal analysis has been done using the time time (TT)-transform to achieve accurate load disaggregation. Load feature selection is also considered by using three power parameters which are real power, reactive power and the TT-transform parameters. These three parameters are used as inputs for training the artificial intelligence techniques in classifying the type and operating states of the loads. The load classification results showed that the proposed extreme learning machine (ELM) technique has successfully achieved high accuracy and fast learning compared with artificial neural network and support vector machine. Based on validation results, ELM achieved the highest load classification with 100% accuracy for data sampled at 1 minute time interval.

Performance Comparison of Artificial Intelligence Techniques for Non-intrusive Electrical Load Monitoring Khairuddin Khalid; Azah Mohamed; Ramizi Mohamed; Hussain Shareef
Bulletin of Electrical Engineering and Informatics Vol 7, No 2: June 2018
Publisher : Institute of Advanced Engineering and Science

The increased awareness in reducing energy consumption and encouraging response from the use of smart meters have triggered the idea of non-intrusive load monitoring (NILM). The purpose of NILM is to obtain useful information about the usage of electrical appliances usually measured at the main entrance of electricity to obtain aggregate power signal by using a smart meter. The load operating states based on the on/off loads can be detected by analysing the aggregate power signals. This paper presents a comparative study for evaluating the performance of artificial intelligence techniques in classifying the type and operating states of three load types that are usually available in commercial buildings, such as fluorescent light, air-conditioner and personal computer. In this NILM study, experiments were carried out to collect information of the load usage pattern by using a commercial smart meter. From the power parameters captured by the smart meter, effective signal analysis has been done using the time time (TT)-transform to achieve accurate load disaggregation. Load feature selection is also considered by using three power parameters which are real power, reactive power and the TT-transform parameters. These three parameters are used as inputs for training the artificial intelligence techniques in classifying the type and operating states of the loads. The load classification results showed that the proposed extreme learning machine (ELM) technique has successfully achieved high accuracy and fast learning compared with artificial neural network and support vector machine. Based on validation results, ELM achieved the highest load classification with 100% accuracy for data sampled at 1 minute time interval.

Performance Comparison of Artificial Intelligence Techniques for Non-intrusive Electrical Load Monitoring Khairuddin Khalid; Azah Mohamed; Ramizi Mohamed; Hussain Shareef
Bulletin of Electrical Engineering and Informatics Vol 7, No 2: June 2018
Publisher : Institute of Advanced Engineering and Science

The increased awareness in reducing energy consumption and encouraging response from the use of smart meters have triggered the idea of non-intrusive load monitoring (NILM). The purpose of NILM is to obtain useful information about the usage of electrical appliances usually measured at the main entrance of electricity to obtain aggregate power signal by using a smart meter. The load operating states based on the on/off loads can be detected by analysing the aggregate power signals. This paper presents a comparative study for evaluating the performance of artificial intelligence techniques in classifying the type and operating states of three load types that are usually available in commercial buildings, such as fluorescent light, air-conditioner and personal computer. In this NILM study, experiments were carried out to collect information of the load usage pattern by using a commercial smart meter. From the power parameters captured by the smart meter, effective signal analysis has been done using the time time (TT)-transform to achieve accurate load disaggregation. Load feature selection is also considered by using three power parameters which are real power, reactive power and the TT-transform parameters. These three parameters are used as inputs for training the artificial intelligence techniques in classifying the type and operating states of the loads. The load classification results showed that the proposed extreme learning machine (ELM) technique has successfully achieved high accuracy and fast learning compared with artificial neural network and support vector machine. Based on validation results, ELM achieved the highest load classification with 100% accuracy for data sampled at 1 minute time interval.

Optimal placement of grid-connected photovoltaic generators in a power system for voltage stability enhancement Zetty Adibah Kamaruzzaman; Azah Mohamed; ramizi mohamed
Indonesian Journal of Electrical Engineering and Computer Science Vol 13, No 1: January 2019
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v13.i1.pp339-346

The high penetration of photovoltaic (PV) generation can cause many technical issues such as power quality and impact on the power system voltage stability. To improve voltage stability and reducing power loss in a power system with PV generators, appropriate planning of PV generators is considered by optimal placement of PV. Thus, an effective heuristic optimization technique such as the Wind Driven Optimization (WDO) technique is applied for determining optimal location of PV generators in a power system. For determining the optimal location of PV, the objective function considers maximizing the Improved Voltage Stability Index. The proposed method for optimal location of PV generators is implemented on the IEEE 118 and 30 bus transmission systems and the 69-radial distribution system. The optimization results show that integrating PV into the test systems improves voltage stability in the system. Comparing the performance of the WDO with the particle swarm optimization technique, it is shown that the WDO technique gives faster convergence.

Modelling of a Low Frequency Based Rectangular Shape Piezoelectric Cantilever Beam for Energy Harvesting Applications Ramizi Mohamed; Mahidur R. Sarker; Azah Mohamed
Indonesian Journal of Electrical Engineering and Computer Science Vol 12, No 1: October 2018
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v12.i1.pp290-295

Harvesting few amount of charge from environmental ambient sources namely, wind, thermal, heat, vibration, solar utilizing micro scale energy harvesting devices, offers vast view of powering for numerous portable low power electronic devices. However, power harvesting using piezoelectric crystal from low power ambient source nowdays has increasing popularity with the advantages of low cost, long life time, stability and clean energy. Recent trends have shown that most researchers are interested in designing a low resonance frequency vibration based energy harvesting devices despite of its challenges ahead. In this paper, a low frequency based rectangular shape piezoelectric cantilever beam has been developed for energy harvesting applications. The proposed vibration based low frequency cantilever beam using piezoelectric element has been developed by finite element analysis (FEA) employing COMSOL Multiphysics platform. The main goal of the study is to analyze the outcome of geometric model of a piezoelectric cantilever beam and to calculate the resonance frequency of the structure according to its length. The material of PZT-5H, has been considered to enhance the efficiency of the low frequency based cantilever beam. Finally, the proposed result is compared with other existing works.

Comparison of Weak Load Bus Detection using LQP_LT Index with PV and QV Analysis of PSS/E Renuga Verayiah; Azah Mohamed
Indonesian Journal of Electrical Engineering and Computer Science Vol 12, No 2: November 2018
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v12.i2.pp577-584

Identification of weak load buses which contributes to voltage instability problem is crucial in order for an appropriate mitigation action to be executed. The current power system transmission is not only stressed to deliver high load demand at the receiving end but also facing new challenges brought by the penetratrion of renewable energy sources. This new scenario requires power system operation and analysis to be robust and fast in detecting the accurate weak load bus for correction action. Due to this, many online indices to detect weak load bus during power system contingency have been developed. Nevertheless, LQP_LT is of the latest index developed which ultimately has the reactive power tracing capability for weak load bus detection and generate priority ranking list of the weak load buses. This index was tested on IEEE 14 bus test system for different contingency scenarios. The results obtained from the LQP_LT index is compared and validated with the PV and QV analyses obtained using industrial graded PSS/E software. It was concluded that the LQP_LT index is found to be robust, efficient and need less computation time as compared to the execution of voltage stability analysis using the PSS/E Tool.

Optimisation of zinc oxide surge arrester design using gravitational search algorithm and imperialist competitive algorithm Syahirah Abd Halim; Azah Mohamed; Nor Azwan Mohamed Kamari; Afida Ayob; Ab Halim Abu Bakar; Hazlee Azil Illias
Indonesian Journal of Electrical Engineering and Computer Science Vol 13, No 3: March 2019
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v13.i3.pp853-860

Reducing electric field stress near the energised end of surge arresters is very important because it may increase the lifetime of the highly stressed ZnO column in vicinity of the high voltage electrode. Most of previous works were based on manufacturers’ procedures and trial and error method to improve the surge arrester designs. In this work, optimisation of ZnO surge arrester design models using Gravitational Search Algorithm (GSA) and Imperialist Competitive Algorithm (ICA) is proposed. The surge arrester models were developed using finite element analysis (FEA) and used to determine the electric field distribution. The optimisation methods were used to determine the arrester design parameters which yield the minimum electric field stress surrounding the energized end of the surge arresters. GSA is less complex since it requires only two parameters to be adjusted i.e. mass and velocity while ICA demonstrates faster convergence and better achievement of global optimum. The performance of the proposed methods was then compared with the manufacturer’s test data and previously developed methods.

Title

Found 7 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 7 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 7 Documents
Search