ZZZuhaina Zakaria

Zuhaina Zakaria

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Zuhaina Zakaria has a total of 69 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Hybrid YOLOv8 and Fast R-CNN for Accurate Schematic Detection in Power Distribution Networks

    by Aviv Yuniar Rahman, Zuhaina Zakaria

    Accurate schematic detection in Power Distribution Networks (PDNs) is critical for effective fault detection, asset management, and predictive maintenance. Conventional edge detection methods often struggle with the complexity and scale of modern PDNs, while standalone deep learning approaches face challenges in balancing real-time performance and high precision. To address these limitations, this paper introduces a hybrid detection framework that synergizes YOLOv8 and Fast R-CNN, leveraging their complementary strengths. YOLOv8 enables rapid initial detections with real-time capabilities, while Fast R-CNN refines these outputs to enhance contextual accuracy. A key contribution of this work is the integration of ensemble techniques—Soft Voting, Hard Voting, and Weighted Average Voting—to further optimize detection performance by effectively aggregating predictions from both models. Using a curated dataset of 3,304 schematic images, the proposed method achieves state-of-the-art results, including a precision of 96.59%, recall of 97.27%, and mean Average Precision at an Intersection over Union (IoU) threshold of 0.50 (mAP@50) of 99.06% with the Hard Voting ensemble. These findings underscore the robustness, scalability, and applicability of the proposed framework in automating schematic analysis in PDNs, offering a transformative solution to enhance operational efficiency and system reliability.


  • Open Access

    An innovative fast iterative process algorithm computerization for intermittency LSSPV generation reconfiguration

    by Zuhaina Zakaria, Nofri Yenita Dahlan, Ihsan Mohd Yassin, Mohd Najib Mohd Hussain

    The recent implementation of solar photovoltaic (SPV) power generation in low-voltage distribution networks has increased due to its environmentally friendly technology, low cost, and high efficiency. However, SPV generation carried both the availability of uncertainty and intermittency on power energy exceeding voltage range, increased losses during reverse power flow action, and energy transmission problems. This paper presents a new capabilities methodology with accurate analysis to simulate the intermittent nature of SPV energy including normal generators associated with uncertain customer demand of high resolution with 1-minute temporal resolution using a fast iterative process algorithm (FIPA) simulated by Python programming. The primary goal is to address the unpredictable nature of SPV using computer operation technology connected to a real network with a fast iteration process. The result shows that in 0-10% of standard generators, grid energy (GE) is still required in daily supply, and the intermittent nature influences voltage violations and losses. Besides, the prediction typical SPV method (zero fluctuation) can serve as guidelines for engineers to design the photovoltaic (PV) module reducing its fluctuating nature and battery installation area. The research provides utilities with accurate information to plan for various difficulties at different levels of PV penetration while reducing time, effort, and resource utilization.


  • Open Access

    Blockchain Framework of UiTM Postgraduate Tracking System (UPTrackS) for Good Governance Practice

    by Aman Mohd Ihsan Mamat, Siti Farhana Zakaria, Zuhaina Zakaria

    Traditional bureaucracy in universities deters good governance. Moving to digital bureaucracy, like digital governance that uses blockchain technology, improves transparency, accountability, and efficiency. A digital architecture called UiTM Postgraduate Tracking System (UPTrackS) leverages blockchain technology to manage governance procedures. According to a poll on UPTrackS deployment, the system delivers sound governance, with a confidence rating of 7.9 out of 10. Enhancing the computer literacy skills of administrative employees and improving the user interface of the system they use are necessary steps to enhance efficiency. Additionally, implementing these changes can lead to better administrative practices that adhere to good governance principles.

  • Open Access

    Optimal reactive power pricing with transformer variable taps using genetic algorithm

    by Ahmad Kor, Hossein Zeynal, Zuhaina Zakaria, Seyed Hamid Hosseini

    Ancillary services in interconnected networks are crucial to secure real power transfers, maintaining network reliability, improving power quality as well as network stability. Reactive power has always been of special importance as one of the most substantial ancillary services required to control the voltage in power grid. This paper presents a fresh reactive power pricing approach by embedding variable transformer taps into voltage ampere reactive (var) pricing method. To carry out the resultant optimization problem with a set of complicating constraints, the genetic algorithm takes part and guarantees the global optimal solution. The simulation results show that when transformer tap works as a control variable, the total cost of reactive power can be decreased. However, the incorporation of transformer taps in the pricing model can slightly complicates voltage profiles as the sensitivity of bus voltages to the reactive power variations in the system is increased. Further, the findings reiterate that by optimal position of transformer taps, technically, the security index of the system can be enhanced while the var price for end-users (lowest purchase cost for independent system operator) being more reasonable. To simulate the proposed reactive pricing method, the standard IEEE 30-bus system is employed to analyze the proposed method.

  • Open Access

    An efficient MPPT based photovoltaic control model considering environmental parameters

    by Hossein Zeynal, Zuhaina Zakaria, Bahareh Pourveis

    This paper presents an efficient way for maximum power point tracking (MPPT) in photovoltaic (PV) system. MPPT is one of the crucial issues when working with PV system as well as the grid. To gain the highest efficiency for PV system the maximum power has to be generated continuously. The proposed MPPT method allows PV system to have real-time maximum power all the time with high accuracy and less fluctuations. As of the developed PV system control model presented in this work, an efficient MPP can be realized taking into account changes in irradiation level and temperature which are the thorny issues for other contender algorithms. To validate the model, results obtained from the proposed algorithm is compared with incremental conductance (IC) which is a universally accepted MPPT method. The simulation results exhibited that the developed model outperforms IC method in terms of accuracy of MPP and stability of the output in presence of variable irradiations and temperature. Based on the simulation results, the proposed algorithm is suitable for practical and real-time applications with promising results in terms of solution accuracy and execution. The model is implemented in MATLAB/Simulink.


  • Open Access

    Analysis of Energy Conservation Intention of Residential Consumer in Malaysia

    by N Suraya, Z Zakaria, S Halijjah

    The residential sector displays complicated energy consumption patterns owing to the household’s human and physical features. Using the theory of planned behavior (TPB) framework, this suggested study focuses on researching the intention of residential consumers in Malaysia to conserve household energy but adding expertise measured by the highest level of academic qualification. The objective of this study is to analyze the correlation between attitude, subjective norm, belief and awareness towards consumers’ intention on performing energy conservation behavior. This research shows that Multiple Linear Regression (MLR) was an appropriate technique for defining energy-related behavior drivers. The result of this study shows that there is a favorable connection between attitude, subjective norm belief and awareness and intention of consumers towards conservation of household energy. The research also discovered that only attitude and subjective norm contribute more to the intention of consumers to conduct the conservation of household energy.


  • Development of graphical user interface to monitor the power system frequency stability due to cascading failure

    by Nur Ashida Salim, Zuhaina Zakaria, Hasmaini Mohamad, Zuhaila Mat Yasin, Muhammad Ashri Ab Aziz

    In many countries around the world, the electric power systems are operating in a deregulated environment where the generation, transmission and distribution systems owned by different companies will enhance intense competition in the electricity market among them in order to provide more reliable, cost effective and efficient electricity to the consumers. For that reason, the power system dynamic security assessment and control is becoming more challenging task in the transfer capability determination due to several new constraints, obligations and challenges that need to be encountered by the utility. Dynamic response of a system plays an imperative role in the analysis of system stability and blackout events that usually caused by the impact of enormous and unforeseen occurrence of fault, unexpected generation and load outages, and abrupt disengagement of loads. This paper presents a monitoring tool by using the Graphical User Interface (GUI) in order to monitor the frequency response of a power system due to the effect of contingency event. The proposed technique has been validated by using the IEEE Reliability Test System. This technique can assist the utility in order to monitor the stability of a power system in the event of contingency.


  • Development of GUI Power System Load Flow Analysis tool based on Newton Raphson method

    by Hasmaini Mohamad, Zuhaina Zakaria, Muhamad Zulfakri Bin Mazlan

    Power flow calculation is very important for power system operation, economic scheduling and planning. This paper presents a development of Power System Load Flow Analysis tool based on the Newton Raphson method by using a User Friendly Graphical User Interface (GUI) Matlab Program. This tool introduces a simple interface for the user to perform load flow analysis. It is also designed for a user to view power flow results for each iteration and thus will facilitate especially undergraduate electrical students to verify their manual calculation of load flow solution. By just point and click, the students will easily get the required solution. The load flow tool is evaluated by solving the load flow of several test systems including IEEE bus system. For such reason, the tools is designed specifically for 2, 3 and 14 buses systems. The result shows that all the answers/solutions displayed in GUI for every required calculation steps for Newton Raphson load flow are successfully verified with the manual calculation and load flow solution in Power World Simulator and VBA Excel. Thus, this tool helps student and lecturer to learn and verify their manual calculation and at the same time reduce their calculation time.


  • Unbalanced faults analysis in grid - Connected PV system

    by Listhianne Willy Anak Badi, Zuhaina Zakaria, Atiqah Hamizah Mohd Nordin, Rijalul Fahmi Mustapa

    A search for replacement of non-renewable energy leads to a new founding that is renewable energy which is unlimited energy source. One of the renewable energy is solar energy where photovoltaic (PV) array is used to convert the energy from the sun to electrical energy. PV is widely use in the grid-connected system nowadays. Since the founding of this method, the technology of extracting solar energy from photovoltaic array into grid network system has been growing rapidly. However, with the best installation method the photovoltaic system could not guarantee the system is immune to fault and its effects. The existence of fault in the grid system may cause a drop in the outputs and will drop even lower with penetration of photovoltaic devices in the system. This paper presents the effects of faults penetration inside the grid-connected PV system with three unbalanced faults being tested for this purpose and compare the results obtained. To observe the effects of these faults, a model of grid-connected PV system is built using MATLAB® 2009/Simulink with the help of Simscape and SimPowerSystems toolboxes. First, a PV system is developed in order to make the photovoltaic sourcing the system using a solar cell lumped with 70 others cell to make a PV module. With the help of a booster, the PV system voltage output is regulated and linked to a three-phase inverter circuit. Step-up transformers then are placed at the end of the inverter to replicate real-life utility. Lastly, faults are injected to the connection of inverter and the second transformer of the end of the system is observed for any changes in the voltage magnitude and waveform.


  • Optimal least squares support vector machines parameter selection in predicting the output of distributed generation

    by Zuhaila Mat Yasin, Titik Khawa Abdul Rahman, Zuhaina Zakaria

    This paper presents a novel technique to optimise the least squares support vector machines (LS-SVM) parameters in predicting the output of Distributed Generation (DG) in a distribution system. In LS-SVM, the accuracy of the prediction is depends on the selection of kernel parameters. Unfortunately, there is no systematic methodology for selection of their optimal values. Therefore, a novel hybrid Quantum-Inspired Evolutionary Programming - Least Squares Support Vector Machine (QIEP-SVM) is developed for accurate prediction. In QIEP-SVM, Quantum-Inspired Evolutionary Programming (QIEP) is developed to optimise selected parameters for the LS-SVM which are gamma and sigma. QIEP is combining Evolutionary Programming (EP) with quantum mechanics concepts such as interference and superposition in order to enhance classical Evolutionary Programming (EP). The optimal output of DG is first generated using multiobjective Quantum-Inspired Evolutionary Programming (QIEP) at various loading condition according to 24-hours load profile. The data from the simulations are then used as the inputs to the Least-Squares Support Vector Machine (LS-SVM). There are three inputs which are active load (MW), reactive load (MVAR) and minimum voltage (p.u). Whereas, there are five outputs that represents the output of DG at five buses. The objective function for the optimisation process is to minimise the mean square error between predicted and targeted output. The performance of QIEP-SVM is then compared to classical LS-SVM using cross-validation technique and hybrid Artificial Neural Network-Quantum-Inspired Evolutionary Programming (QIEP-ANN). The results of QIEP-SVM model had shown better prediction performance as compared to classical LS-SVM and QIEP-ANN. All simulations in this study were carried out using IEEE 69-bus distribution test system.