genetic algorithm

Load forecasting is a key component of electric utility operations and planning. Because of today's highly developed electricity markets and rapidly growing power systems, load forecasting is becoming an essential part of power system operation scheduling. This paper proposes a new short-term load forecasting model based on the large margin nearest neighbor (LMNN) classification algorithm to improve prediction accuracy. The accuracy of many classification methods, such as k-nearest neighbor (k-NN), is significantly influenced by the technique used to calculate sample distances. The Mahalanobis distance is one of the most widely used methods for calculating distance. Numerous techniques have been used to enhance k-NN performance in recent years, including LMNN. Our proposed approach aims to solve the local optimum problem of LMNN, compute data similarities, and optimize the cost function that establishes the distances between instances. Before using gradient descent to determine the ideal parameter values for the cost function, we employ a genetic algorithm to shrink the size of the solution space. Additionally, our method's forecasting errors are contrasted with those of the BPNN and ARMA models. The comparative findings show how well the recommended forecasting model performs in short-term load forecasting.

In electrical distribution networks, inefficiencies and instabilities often arise from inductive loads like motors and transformers, which exhibit a lagging power factor. This reduces system capacity, increases losses, and can lead to lower voltage levels. To address these issues, integrating parallel capacitors proves effective, enhancing the power factor, improving voltage profiles, and reducing overall system losses and costs. This research explores the optimal placement of parallel capacitors within a distribution network to manage reactive power effectively, thereby minimizing losses and improving voltage stability and system efficiency. Utilizing DigSILENT Power Factory and MATLAB, a genetic algorithm optimizes the location and sizing of capacitors in a 33-bus distribution network, considering scenarios with and without distributed generation (DG) and the impact of harmonic currents. The study finds that incorrect sizing or placement of capacitors can worsen voltage deviations when higher harmonic levels are present. However, the optimization method accurately determines the best parameters for capacitor installation, ensuring compliance with voltage and harmonic constraints. Deploying more than three to four capacitors does not significantly affect outcomes, while a single busbar capacitor often fails to meet operational standards. In conclusion, strategic capacitor placement and sizing can significantly reduce losses, enhance voltage stability, and mitigate inefficiencies caused by inductive loads. Attention to harmonics is crucial to avoid negative impacts on the network. This approach offers a replicable framework for similar optimizations in other distribution systems, advancing smart grid technology implementation.

In recent decades, because of some main and principle world problems such as increasing the population, global warming, climate changes, and fossil fuel sources reduction, the using of renewable energies has impressively increased that can solve and reduce the caused problems by traditional power plants, and also can control power system the important indexes such as losses, voltage drop, transferring capacity. Reactive power has an important role in controlling and minimizing of losses, the optimal distribution of reactive power in presence of Distributed generation (DG) units in distribution networks is an important and key problem. In this paper, for uncertainties modelling of DG units and optimizing the reactive power, the statistical-quality based Taguchi method and Genetic algorithm are used, respectively.  The simulation of this paper is checked and done in MATLAB and MINITAB using IEEE 57-bus standard network, and simulation results show 5.5 MW reduction of the distribution network losses.

This study presents a four-element compact Multi-Input Multi-Output antenna with enhanced isolation for applications with three bands. The four-port antenna elements have hook-shape multiband monopole elements with 50 ⦠microstrip feed lines and are placed such that they are perpendicular to one another to enhance the act of the MIMO system. Simulation and measurement consequences demonstrate that the antenna operates at a consistent gain and radiation patterns at the major frequency bands of 2.11-2.47 GHz, 3.14-3.54 GHz, and 5.15-5.85 GHz with S11<-10 dB. To verify the claimed MIMO antenna performance, data in the format of radiation patterns, peak gain (4.9,5.2,5.8 dB), diversity gain (DG) (9.95,9.92,9.92 dB), envelope correlation coefficient (ECC) (0.005,0.003,0.002), TRAC, channel capacity and MEG ratio are retrieved. These specifications of the suggested antenna make it a suitable candidate for WiMAX, Bluetooth, and WLAN uses. Additionally, the suggested antenna outperformed current work by providing a superior balance of size, bandwidth, and several performance characteristics.

Distribution systems pose a significant challenge within the power grid, primarily due to their high current, low voltage, and comparatively high ohmic resistance compared to transmission and sub-transmission systems.This results in substantial power losses, necessitating the need for effective mitigation strategies.To address this issue, a wide range of methods and algorithms have been proposed and continuously developed. Over the past half-century, reconfiguring the distribution network has emerged as a cost-effective and straightforward approach to reducing distribution losses. Distribution system reconfiguration has been extensively studied, with each study aiming to achieve distinct objectives. Additionally, numerous studies have explored the dynamics of distribution system reconfiguration, evaluating and comparing various approaches. This study comprehensively assesses both static and dynamic methods of reconfiguring distribution systems and introduces a novel dynamic reconfiguration technique. Unlike traditional methods that rely on real-time or hourly load models, this approach utilizes a load model to address the dynamic reconfiguration problem. Simulations were conducted on the well-established IEEE 33-bus test system, employing MATLAB software in conjunction with a genetic algorithm to minimize losses and optimize voltage profiles. Based on the simulation results, this novel dynamic reconfiguration method demonstrated superior performance compared to previously employed methods. It effectively reduced power losses and enhanced the voltage profile, demonstrating its potential for improving the overall efficiency of distribution systems.

‎ The development of digital technologies has improved the transfer of data over the Internet in recent years. Image encryption is a technique to ensure security in information transfers. The current paper presents an evolutionary model on the basis of a hybridization of DNA biomolecule operators and the LS2 Map ‎chaos function for encryption of image. The model proposed here includes three stages. In the initial stage, the MSC (Magic Square Chaotic) algorithm and a secret key are utilized with the SHA-256 algorithm t‎o determine the initiating the LS2 Map function value, which is then employed to manipulate the pixels of the image. Then, DNA biomolecule operators and the chaos function are used for propagation. Additionally, the previous stages process is iterated with the starting population of the genetic algorithm in the third stage. Afterward, the optimization is carried out through genetic algorithm operators. The results indicate ‎that the introduced model is superior to other rivals. Furthermore, as for the high level of entropy obtained, the model exhibits strong resistance to common attacks.‎

Increasing the accuracy of time-series clustering while reducing execution time is a primary challenge in the field of time-series clustering. Researchers have recently applied approaches, such as the development of distance metrics and dimensionality reduction, to address this challenge. However, using segmentation and ensemble clustering to solve this issue is a key aspect that has received less attention in previous research. In this study, an algorithm based on the selection and combination of the best segments created from a time-series dataset was developed. In the first step, the dataset was divided into segments of equal lengths. In the second step, each segment is clustered using a hierarchical clustering algorithm. In the third step, a genetic algorithm selects different segments and combines them using combinatorial clustering. The resulting clustering of the selected segments was selected as the final dataset clustering. At this stage, an internal clustering criterion evaluates and sorts the produced solutions. The proposed algorithm was executed on 82 different datasets in 10 repetitions. The results of the algorithm indicated an increase in the clustering efficiency of 3.07%, reaching a value of 67.40. The obtained results were evaluated based on the length of the time series and the type of dataset. In addition, the results were assessed using statistical tests with the six algorithms existing in the literature.