Applied Mathematics and Computational Intelligence (AMCI)

Integration of Multiple Distributed Generation Sources in Radial Distribution System Using a Hybrid Evolutionary Programming-Firefly Algorithm

2024-02-14T01:43:26+00:00

This paper presents an approach for the optimal integration of multiple distributed generation (DG) sources in a radial distribution system. The integration of DG sources poses various challenges such as can lead to higher power losses caused by reverse power flow, voltage exceeding secure limits, voltage stability, power quality, and economic operation. To address these challenges, a hybrid algorithm is proposed which combines the benefits of both Evolutionary Programming and Firefly Algorithm. The proposed hybrid Evolutionary - Firefly Algorithm is employed for the determination of the optimal size of the DG sources. The objective of the proposed algorithm is to minimize the total system power losses and improve the voltage profile. The algorithm considers various constraints including the DG capacity limits and voltage limits. A comprehensive case study is conducted on a radial distribution system to demonstrate the effectiveness of the proposed approach. The simulation results show that the hybrid algorithm can find the optimal size and location of DG sources while achieving the desired system performance. The integration of multiple DG sources leads to a significant reduction in power losses and improved voltage profile. Furthermore, the proposed approach provides a flexible framework for the optimal integration of DG sources in radial distribution systems, allowing for the accommodation of different types and capacities of DG sources. The proposed technique is tested on the IEEE Reliability Test systems, specifically the IEEE 69-bus. The combination of DG at bus 61 and bus 27 yields a loss reduction index of 94%.

Particle Swarm Optimization for Directional Overcurrent Relay Coordination with Distributed Generation

2024-02-14T02:06:58+00:00

The Directional Overcurrent Relays (DOCRs) Coordination with Distributed Generation (DG) optimization problem is addressed in this study using the optimization method Particle Swarm Optimization (PSO). Changes in fault current, bus voltages, power flow, and reliability may result from DG integration. Thus, it might have an impact on the current protection coordination system. The formulation is built on a Mixed Integer Non-Linear Programming (MINLP) problem to address this DOCR issue. MATLAB was used to validate the technique on the IEEE-14 bus system, and Electrical Test Transient Analyzer Programming (ETAP) version 2021 software was used to model the test system. According to the simulation results, the suggested PSO with DG for Case 2 has reduced power loss by 6.24% and relay operating time by 46.79% when compared to PSO without the presence of DG.

Mitigating Overfitting in Extreme Learning Machine Classifier Through Dropout Regularization

2024-02-14T02:17:48+00:00

Achieving optimal machine learning model performance is often hindered by the limited availability of diverse datasets, a challenge exacerbated by small sample sizes in real-world scenarios. In this study, we address this critical issue in classification tasks by integrating the Dropout technique into the Extreme Learning Machine (ELM) classifier. Our research underscores the effectiveness of Dropout-ELM in mitigating overfitting, especially when data is scarce, leading to enhanced generalization capabilities. Through extensive experiments on synthetic and real-world datasets, our findings consistently demonstrate that Dropout-ELM outperforms traditional ELM, yielding significant accuracy improvements ranging from 0.19% to 16.20%. By strategically implementing dropout during training, we promote the development of robust models that reduce reliance on specific features or neurons, resulting in increased adaptability and resilience across diverse datasets. Ultimately, Dropout-ELM emerges as a potent tool to counter overfitting and bolster the performance of ELM-based classifiers, particularly in scenarios with limited data. Its established efficacy positions it as a valuable asset for enhancing the reliability and generalization of machine learning models, providing a robust solution to the challenges posed by constrained training data.

A Comparison of the Rank-based and Slope-based Nonparametric Tests for Trend Detection in Climate Time Series

2023-10-19T08:13:46+00:00

Trend detection in climate time series data is crucial for understanding climate change, predicting future climate patterns, assessing impacts, managing resources, and formulating policies. Several trend detection methods have been introduced in the literature, including parametric and non-parametric approaches. Nonparametric trend detection methods are often considered more preferable than parametric methods in certain situations due to their flexibility and robustness. Comparing various nonparametric methods of trend detection is vital in data analysis because different techniques can yield divergent results based on the same dataset. In this study, three nonparametric trend tests which were the MannKendall (MK), Sen’s Innovative Trend Analysis (ITA) and Modified Mann-Kendall by Sen’s Innovative Trend Analysis (MMK_ITA) were compared based on their power. The MK test is a rank-based test and the ITA is a slope-based test. Meanwhile, the combination of rank-based and slope-based methods is known as the MMK_ITA test. The power analysis was conducted through Monte Carlo simulation on normal, non-normal and autocorrelated time series. The simulation results indicated that test power relied on magnitude of linear trend slope, sample sizes, distribution type and variation in time series. These tests were then applied to monthly maximum temperature from 2002 until 2021 for Selangor, Malaysia. This study found that the slope-based test performed better compared to the rank-based test and their combined methods from the simulation studies and real data application based on the calculated power.

A New Hybrid Three-Term HS-DY Conjugate Gradient In Solving Unconstrained Optimization Problems

2024-01-23T07:50:41+00:00

Conjugate Gradient (CG) method is an interesting tool to solve optimization problems in many fields, such design, economics, physics and engineering. Until now, many CG methods have been developed to improve computational performance and have applied in the real-world problems. Combining two CG parameters with distinct denominators may result in non-optimal outcomes and congestion.In this paper, a new hybrid three-term CG method is proposed for solving unconstrained optimization problems. The hybrid threeterm search direction combines Hestenes-Stiefel (HS) and Dai-Yuan (DY) CG parameters which standardized by using a spectral to determine the suitable conjugate parameter choice and it satisfies the sufficient descent condition. Additionally, the global convergence was proved under standard Wolfe conditions and some suitable assumptions. Furthermore, the numerical experiments showed the proposed method is most robust and superior efficiency compared to some existing methods.

Charging Ahead: Statistics on Electric Vehicle Charging Station Allocation and Uptake Trends in Malaysia

2023-10-20T07:23:53+00:00

The emergence of electric vehicles is attributable to the accessibility of charging stations, which is essential in reducing EV drivers' range anxiety. EV batteries need to recharge after a certain number of miles driven. As a result, for EVs to be widely deployed, a sustainable charging station must be constructed. The National Electric Mobility Blueprint states that Malaysia's primary goal is for the nation to become the marketing hub for the EV industry by 2030. By 2030, Malaysia reportedly expects to have 125,000 electric vehicle charging stations. EVCS are available in many types, each with different charging capabilities and speeds. The most popular EVCS are slow charging stations, fast charging stations, battery swap charging stations, and wireless charging stations. The type of EVCS is discussed in this study, particularly from the perspectives of Malaysia. The mechanisms, advantages, disadvantages, and associated issues of these EVCS are thoroughly discussed. Furthermore, to reduce range anxiety among EV users and enhance EV adoptions in Malaysia, several criteria are considered in determining the suitable location for Photovoltaic Electric Vehicle Charging Stations. For future studies, all the selected criteria will be calculated using Multi-Criteria Decision-Making methods.

Medical Supply Transportation Scheduling in Pandemic

2023-09-14T07:00:10+00:00

The COVID-19 pandemic has brought the world to its knees, with healthcare systems struggling to cope with the surge in demand for medical supplies. One of the major challenges faced by healthcare providers has been the transportation of essential medical supplies from manufacturers to hospitals and clinics. The pandemic has exposed the weaknesses in our supply chain systems and has highlighted the need for a more resilient and efficient transportation network. This project aims to investigate the medical supply problem during the pandemic, with a focus on transportation. It uses the Simple Heuristic Method and C programming language. The data generated using exponential distribution. The result shows that the application of the Simple Heuristic Method can minimize and optimize transportation time, providing a solution to the medical supply problem during pandemics. This project examine the challenges faced by healthcare providers in sourcing and transporting essential medical supplies and the impact of the pandemic on transportation networks. The results of this research provide valuable insights into the medical supply problem during pandemics and help inform the development of more effective transportation systems for the healthcare industry.

Implicit Block and Runge- Kutta type Methods for Solution of Second-Order Ordinary Differential Equations.

2023-09-07T02:16:58+00:00

In this research, implicit discrete schemes which form our block integrators were developed for solving Initial Valued Problems of Ordinary Differential Equations. The equivalent second order Runge-Kutta type Methods (RKTM) were also constructed for the same purpose. Both methods were demonstrated on linear and nonlinear problems of Ordinary Differential Equations. Numerical results obtained from RKTM show that the method is competitive with the existing one.

Pricing Writer-Extendable Call Options with Monte Carlo Simulation

2024-01-22T08:28:47+00:00

Writer-extendable option is an exotic option that can either be exercised at its initial maturity time, or be extended to a future maturity time. Within the Black-Scholes environment, this study aims to price writer-extendable call options using the Monte Carlo simulation technique, and compare the obtained prices with the closed-form pricing formula. Numerical examples are provided using the closed-form solutions and the Monte Carlo simulation via Euler scheme, which shows that the prices obtained via the latter are accurate.

A new Soil Management System in Enhancing the Yield of Plantation Using IoT Technique and Machine Learning for Smart Pineapple Farming

2024-02-14T03:55:26+00:00

The machine learning technique is studied to aid farmers in decision-making and analysing soil quality based on the nitrogen, phosphorus, and potassium NPK nutrients as the current soil in Malaysia experience degradation of soil organic that affect in production of the nutrient for the crops. The research aim is to study and analyse the Artificial Neural Network model in analysing the quality of soil based on the prediction of NPK level class, which the data collected from Smart Agri-Scan. Next objective is to evaluate the prediction and accuracy of the model. The ANN model is constructed in Neural Net Fitting App in MATLAB. A feedforward neural network is applied to the ANN model and trains it with two different training functions and a different number of neurons of hidden layers. The model with the smallest Mean Square Error is chosen for data analysis as it means the model has the best performance. From the prediction graph, the output of training and validation that corresponds to the prediction model is observed. The points of the output prediction close to the reference line are considered a good prediction model, which means it can analyse soil quality accurately. In future, the model might be able to do the analysis and decision directly at the monitoring platform based on the real-life prediction data.