Bulletin of Electrical Engineering and Informatics
Not a member yet
2885 research outputs found
Sort by
Parasitic isolation structure for mutual coupling reduction in a multiple input multiple output antenna
Get PDFThis paper reports a design of 2×1 multiple input multiple output (MIMO) structure of antenna with 23×45 mm2 dimension. Each element in the MIMO antenna is a quarter wave transformer fed microstrip patch antenna. To lessen the effect of coupling, a rectangular parasitic decoupler is positioned between the two elements. Results report that antenna resonates at 6 GHz, coupling is reduced by 14 dB using parasitic decoupler S12 and S21 obtained with parasitic decoupler are same which -33.06 dB. The diversity gain (DG) is 9.99 dB, which is nearly close to 10 dB, and the envelope correlation coefficient (ECC) is less than 0.00034. These values reflect the good diversity performance. Measured findings match those from the simulation. As we confront the delicate environment, the proposed antenna is suited for number of wireless applications, including 802.11, 802.16 standards of IEEE
Design and analysis of sustainable photovoltaic solar charging system with battery storage for electric vehicles
Get PDFThis paper presents a sustainable electric vehicle (EV) charging system that operates in three modes of operation to maximize the yield of photovoltaic (PV) system. The design and analysis of the EV charging system is customized based on the operational or office hours of a corporation. The proposed system incorporates a battery pack capable of providing at least one day of autonomy to overcome the weather conditions during early morning, shading times, or cloudy days. In this study, the perturb and observe (PO) algorithm is modified and used to operate the PV system at maximum power point (MPP) when charging either the EV or the storage battery. The load current, in both cases, is regulated using proportional integral (PI) controllers and pulse width modulation (PWM) switching of DC-DC converter. The proposed system operation is switched between three modes (boost operation for direct charging of EV and discharging of storage battery, and buck operation for charging of storage battery) by a simple event-driven finite state machine (FSM). Simulation results showed excellent tracking behavior of the proposed system when supplying a 5 kW load with variation in solar irradiance between 1000 and 400 W/m2, battery state of charge (SOC) between 40% and 100%, and temperature between 15 to 39 ℃
Golden jackal optimization for economic load dispatch problems with complex constraints
Get PDFThis research paper uses the golden jackal optimization (GJO), a novel meta-heuristic algorithm, to address power system economic load dispatch (ELD) problems. The GJO emulates the hunting behavior of golden jackals. GJO algorithm uses the cooperative attacking behavior of golden jackals to tackle complicated optimization problems efficaciously. The objective of ELD problem is to distribute power system load requirement to the different generators with a minimum total fuel cost of generation. ELD problems are highly complex, non-linear, and non-convex optimization problems while considering constraints namely valve point loading effect (VPL) and prohibited operating zones (POZs). The proposed GJO algorithm is applied to solve complex, non-linear, and non-convex ELD problems. Six different test systems having 6, 10, 13, 40, and 140 generators with various constraints are used to validate the usefulness of the suggested GJO method. Simulation outcomes of the test system are compared with various algorithms reported in the algorithms such as particle swarm optimization (PSO), ant colony optimization (ACO), and backtracking search algorithm (BSA). Results show that the proposed GJO algorithm produces minimal fuel cost and has good convergence in solving ELD problems of power system engineering
An ANN enabled joint power allocation and base station switching system for EE heterogeneous networks
Get PDFIn recent years, dynamic and complex development in wireless communication in network models or environments led to more tedious and complicated resource management issues (i.e., power allocation and base station switching (BSS)). Conventional solutions often suffer from delays and degraded network service quality. Due to the ability of machine learning in analyzing huge volumes of data and automatically adapt to environmental changes, it emerges as a highly sought-after technique. In this work, we propose a machine learning approach based on feed-forward neural network (FFNN) to predict the active BS sets and estimate the power allocation to each user equipment (UE) within the active BSs for energy-efficiency (EE) maximization of a coordinated multi-point (CoMP-enabled) cellular system with hybrid-powered transmitting nodes in a HetNet-based architecture. By training the neural network model efficiently using a regression-based supervised learning technique that employs various backpropagation algorithms, almost similar EE performance (less than 5% difference) can be achieved with significantly reduced computational complexity and delay compared to the traditional methods, such as the well-known dual decomposition and brute force techniques. The effects of various hyper parameters and back-propagation algorithms are also investigated. Our results demonstrate that the proposed framework is a promising solution for establishing a fully green and intelligent network
An image analysis technique for wheat head count detection using machine learning
Get PDFDeep learning (DL) techniques have significantly enhanced the potential for wheat head detection in recent times. The different development phases of canopy, genotype, wheat heads, and wheat head orientation provide considerable obstacles. The overlapping density of wheat heads and wind- induced picture blurring complicate wheat head recognition. This study describes an effective wheat head detection and counting method. Due to its high throughput in agricultural field analysis, remote sensing phenotyping has grown in popularity. Applying DL methods for image processing and other technological advancements has increased the scope for the quantitative evaluation of various crop traits. The ability to detect and characterize wheat heads in the industry is an important part of the wheat breeding process for selecting high-yielding cultivars. The proposed method uses the Mask region-based convolutional neural network (RCNN) framework to detect and classify the wheat ears. The complete detection task is done in three steps: region proposal generation, region of interest alignment, and mask generation. The global wheat head detection (GWHD) dataset is used for the experimental analysis of the dataset. The proposed method achieved an accuracy of 95.11% on the GWHD dataset, demonstrating its effectiveness in wheat head detection and classification tasks
Solar power forecasting model as a renewable generation source on virtual power plants
Get PDFThis paper describes modeling solar power generation as a renewable energy generator by simulating the analytical approach mean absolute error and root mean square error (MAE and RMSE). This research estimates the error referring to long short-term memory (LSTM) network learning. Related to this, the Indonesian government is currently actively developing solar power plants without ignoring the surrounding environment. The integration of solar power sources without accurate power prediction can hinder the work of the grid and the use of new and renewable generation sources. To overcome this, virtual power plant modeling can be a solution to minimize prediction errors. This study proposes a method for on-site virtual solar power plant efficiency with a research approach using two models, namely RMSE and MAE to account for prediction uncertainty from additional information on power plants using virtual solar power plants. A prediction strategy verified against the output power of photovoltaic (PV) modules and a set based on data from meteorological stations used to simulate the virtual power plants (VPP) model. This forecast prediction refers to the LSTM network and provides forecast errors with other learning methods, where the approach simulated with 12.36% and 11.85% accuracy for MAE and RMSE, respectively
Malaysian views on COVID-19 vaccination program: a sentiment analysis study using Twitter
Get PDFThis study aimed to analyze the opinions and emotions of Malaysians towards the COVID-19 vaccination program, as expressed on Twitter. By collecting data from the Twitter network and utilizing the machine learning life cycle technique. The results show that Malaysians have a mostly neutral viewpoint of the COVID-19 vaccination, with an accuracy score of 93%, an F1-score of 94%, a recall measurement of 94%, and a precision measure of 93%. These findings emphasize the significance of understanding public sentiment and perception towards crucial issues such as the COVID-19 vaccine and can be utilized to support healthcare professionals, policymakers, and the public in making informed decisions regarding the COVID-19 vaccination program
Simplifying the electronic wedge brake system model through model order reduction techniques
Get PDFThe electronic wedge brake (EWB) uses self-reinforcement principles to optimise stopping power, but its mathematical model has various actuation angles and system dynamics making controller design complex and computationally burdensome. Therefore, the model order reduction (MOR) is made based on three factors that may have a negligible influence on the EWB system: the motor inductance, lead screw axial damping, and wedge mass. Six reduced order model (ROM) types were proposed when one, two, or all factors were ignored. The ROM accuracy was analysed using the frequency and time domain. The percentage of root means square error (RMSE) response value between the EWB benchmark model, and the predicted response based on the ROM was found to be less than 2%, with ROM size reduced from 5 to 2 orders. It guarantees that the new ROM series will be useful for simpler EWB controller design. The proposed ROM simplifies the original model drastically while retaining accuracy at an adequate level. Even though the simplest EWB model is a 2nd  order linear system, the best ROM vary depending on EWB design parameters
Quasi resonant topology based highly efficient solar-powered induction cooker
Get PDFThe energy crisis is a major issue in developing countries, with fossil fuels being the main source of cooking. Induction cookers have received attention due to their safe operation and eco-friendliness, but traditional AC induction cookers are costly and inefficient due to an inverter and rectifier. In this regard, this paper aims to model and develop a solar-powered, low-cost, and highly efficient induction cooker that can be operated directly by solar panels through a battery. By utilizing the solar panels’ maximum output, a maximum power point tracking (MPPT)-based solar power controller has been utilized to charge the battery. A modified coil structure for the cooker is proposed to decrease the coil’s excitation time and increase the resonant frequency. A quasi-resonant converter topology has been used in the proposed induction cooker, as it operates at high frequencies above 20 kHz to avert audible noise and below 100 kHz to minimize losses in switching. The performance of the suggested induction cooktop has been validated by modifying the circuit and the coil of a traditional 220 V, 2 kW induction cooker. Based on the outcomes, it is observed that the efficiency of the proposed induction cooker reached 93%, which is better than that of existing induction cookers
Bidirectional recommendation in HR analytics through text summarization
Get PDFFor over a decade, online job portals have been providing their services to both job seekers and employers in search of hiring opportunities. Because of the high demand for recruitment, it is insufficient to use conventional hiring methods to find a suitable candidate to fill the position. Validating resumes online is challenging due to the potential for manual errors, making the process inherently risky. The bidirectional method comprises named entity recognition (NER) for extracting the required resumes for recruiters. Cosine similarity shows the match percentage of resumes for the job requirements and vice versa. In an attempt to tackle an issue of unregistered words, a solution called decoder attention with pointer network (DA-PN) has been introduced. This method incorporates the use of coverage mechanism to prevent word repetition through generated text summary. DA-PN+Cover method with mixed learning objective (MLO) (DA-PN+Cover+MLO) is utilized for protecting grow of increasing faults in generated text summary. Performance of proposed method is estimated using evaluation indicator recall oriented understudy for gisting evaluation (ROUGE) and attains an average of 27.47 which is comparatively higher than existing methods