Article Per Year (5 Year)
p-Index From 2020 - 2025
0.444
P-Index
This Author published in this journals
All Journal IAES International Journal of Artificial Intelligence (IJ-AI) Indonesian Journal of Electrical Engineering and Informatics (IJEEI) Indonesian Journal of Electrical Engineering and Computer Science
Md Pauzi Abdullah
Universiti Teknologi Malaysia
Computer Science & IT Electrical & Electronics Engineering Engineering

Published : 7 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 7 Documents
Search

 1 
Fault detection for air conditioning system using machine learning Noor Asyikin Sulaiman; Md Pauzi Abdullah; Hayati Abdullah; Muhammad Noorazlan Shah Zainudin; Azdiana Md Yusop
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 9, No 1: March 2020
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (568.712 KB) | DOI: 10.11591/ijai.v9.i1.pp109-116

Abstract

Air conditioning system is a complex system and consumes the most energy in a building. Any fault in the system operation such as cooling tower fan faulty, compressor failure, damper stuck, etc. could lead to energy wastage and reduction in the system’s coefficient of performance (COP). Due to the complexity of the air conditioning system, detecting those faults is hard as it requires exhaustive inspections. This paper consists of two parts; i) to investigate the impact of different faults related to the air conditioning system on COP and ii) to analyse the performances of machine learning algorithms to classify those faults. Three supervised learning classifier models were developed, which were deep learning, support vector machine (SVM) and multi-layer perceptron (MLP). The performances of each classifier were investigated in terms of six different classes of faults. Results showed that different faults give different negative impacts on the COP. Also, the three supervised learning classifier models able to classify all faults for more than 94%, and MLP produced the highest accuracy and precision among all.
Integration of time of use (TOU) tariff in net energy metering (NEM) scheme for electricity customers Abdul Hafiz Razali; MD Pauzi Abdullah; Mohammad Yusri Hassan; Dalila Mat Said; Faridah Hussin
Indonesian Journal of Electrical Engineering and Informatics (IJEEI) Vol 7, No 2: June 2019
Publisher : IAES Indonesian Section

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (360.639 KB) | DOI: 10.52549/ijeei.v7i2.1173

Abstract

The introduction of Net Energy Metering (NEM) scheme for electricity customers in Malaysia is seen as an improvement from the previous Feed-In Tariff (FIT). However, the new NEM scheme only benefited the large residential customers but not to medium and small residential customers. Due to electricity tariff blocks structure, the large customers can avoid paying expensive tariff and hence reducing their electricity bill. This is not the case for medium and small customers since they are already paying lower tariff blocks due to their lower electricity consumption. This issue will discourage most residential customers to install solar PV system in their home and affect the Malaysia’s renewable energy target. This paper proposed a NEM scheme that integrates Time of Use (TOU) electricity tariff to the scheme. The proposed NEM-TOU scheme will be simulated, tested and compared to the new NEM scheme by using practical small, medium and large residential customers’ data. The results show that the proposed TOU-NEM scheme able to overcome the weakness of the current scheme where all customers (large, medium and low) can benefited by installing solar PV system in their home.
Energy efficiency index by considering number of occupants: a study on the lecture rooms in a university building Noor Ameera Zakaria; Mohammad Yusri Hassan; Hayati Abdullah; Md Pauzi Abdullah; Faridah Hussin; Siti Maherah Hussin; Nur Najihah Abu Bakar
Indonesian Journal of Electrical Engineering and Computer Science Vol 15, No 3: September 2019
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v15.i3.pp1154-1160

Abstract

The building sector is attributed to approximately 40% of the nation’s energy consumption and this accounts for a significant percentage of the nation’s energy consumption. For this reason, energy efficiency in buildings has now become an important subject in the national energy scenario. Energy Efficiency Index (EEI) is one of the energy consumption indicators that is widely used in the building sector for measuring energy performance. This index is generally measured based on the energy used per unit of building floor area. However, this index is not able to directly identify other factors affecting energy usage. This paper suggests an Energy Efficiency Index (EEI) for determining the performance of lecturer rooms in a university building. Unlike the conventional EEI, the proposed EEI determines the room’s energy usage performance by considering the number of occupants. The study was conducted at the Faculty of Electrical Engineering, Universiti Teknologi Malaysia (UTM) and the results show that the number of occupants significantly influences the energy usage performance of rooms in a university building.
Enhanced Time of Use Electricity Pricing for Industrial Customers in Malaysia Nur Azrina Mohd Azman; Md Pauzi Abdullah; Mohammad Yusri hasan; Dalila Mat Said; Faridah Hussin
Indonesian Journal of Electrical Engineering and Computer Science Vol 6, No 1: April 2017
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v6.i1.pp155-159

Abstract

New Time of Use (ToU) tariff scheme known as Enhanced ToU (EToU) has been introduced on 1st January 2016 for industrial customers in Malaysia. EToU scheme is the advanced version of current ToU where the daily time frame is divided into six period blocks, as compared to only two in the existing ToU. Mid-peak tariff is introduced on top of peak-hour and off-peak tariff. The new scheme is designed to reduce Malaysia’s peak hour electricity demand. On customer side, they could be benefited from the low off-peak tariff by simply shifting their consumption. However, it depends on their consumption profile and their flexibility in shifting their consumption. Since EToU scheme is voluntary, each customer needs to perform cost-benefit analysis before deciding to switch into the scheme. This paper analyzes this problem by considering EToU tariff scheme for industry and customer’s electricity consumption profile. Case studies using different practical data from different industries are presented and discussed in this paper.
Performance of a Small-sized Savonious Blade with Wind Concentrator Dygku. Asmanissa Awg. Osman; Norzanah Rosmin; Aede Hatib Mustaamal; Siti Maherah Hussin; Md Pauzi Abdullah
Indonesian Journal of Electrical Engineering and Computer Science Vol 10, No 3: June 2018
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v10.i3.pp1227-1233

Abstract

This paper presents the performance of a fabricated small-sized Savonious wind turbine with two blades. The design of Savonius vertical axis wind turbine (VAWT) was based on Malaysia wind speed condition. Meanwhile, the design of wind concentrator was based on the dimensions and the constant airflow of an air compressor. From the experimental testing in a laboratory, it was found that the proposed Savonious turbine has best performance when tested using wind concentrator. To conclude, airflow from air compressor can be increased when the proposed wind concentrator is used and hence increasing the proposed VAWT performance in terms of its angular speed (ω), tip speed ratio (TSR) and the generated electrical power (PE).
Impact of Different Time of Use Electricity Pricing Structure on Residential Consumer Nur Azrina Mohd Azman; Md Pauzi Abdullah; Mohammad Yusri Hassan; Dalila Mat Said; Faridah Hussin; Norzanah Rosmin; Siti Maherah Hussin
Indonesian Journal of Electrical Engineering and Computer Science Vol 10, No 3: June 2018
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v10.i3.pp1053-1060

Abstract

Load profile for residential users is different from commercial users where peak load occurs outside of work hours compared to working hours. Consequently, the Time of Use-based electricity price must be different not only in terms of price, but also in terms of time block structure. This paper examines the impacts of different TOU structures on TOU prices and load profiles of residential consumer. Four TOU structures are tested on the real load profile for a selected residential consumer area in Malaysia. Two elasticity factors are used for each structure to represent two different groups of users, a group that responds highly to price changes and a group that does not. The TOU price set for each structure is determined optimally subject to the following constraints; the price difference between the TOU and a fixed price per hour should be minimized and the amount of difference between price increase and price drop should be equal. From the analysis, the TOU structure with 12-time blocks provides better price signals and peak load reduction.
Detection of occupancy status from internet connectivity for non-intrusive load monitoring Manjula Wickramathilaka; Md Pauzi Abdullah; Mohammad Yusri Hassan; Hayati Abdullah
Indonesian Journal of Electrical Engineering and Computer Science Vol 30, No 3: June 2023
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v30.i3.pp1678-1688

Abstract

Non-intrusive load monitoring (NILM) methods are widely used for appliance level energy disaggregation in residential buildings. These methods mostly depend on electrical features, and they have not been much successful in applying for commercial buildings. However, recent research has indicated that the accuracy of existing NILM methods can be improved by associating with occupancy data. Therefore, in this paper a novel occupancy detection algorithm is proposed which can detect occupancy status of individuals using the connectivity of their information technology (IT) devices to the local area network of the building. The model is validated using data collected at a university building, with mean errors of 01:23 and 04:02 minutes for the detection of arrival and departure. The occupancy profiles developed by the proposed model can be used to disaggregate energy consumption in a commercial building to appliance and occupant level.
Co-Authors Abdul Hafiz Razali Aede Hatib Mustaamal Azdiana Md Yusop Dalila Mat Said Dygku. Asmanissa Awg. Osman Faridah Hussin Hayati Abdullah Manjula Wickramathilaka Mohammad Yusri hasan Mohammad Yusri Hassan Muhammad Noorazlan Shah Zainudin Noor Ameera Zakaria Noor Asyikin Sulaiman Norzanah Rosmin Nur Azrina Mohd Azman Nur Najihah Abu Bakar Siti Maherah Hussin