Workload Prediction in Cloud Data Centers Using Complex‐Valued Spatio‐Temporal Graph Convolutional Neural Network Optimized With Gazelle Optimization Algorithm DOI Open Access

R. Karthikeyan,

A. Saleem Raja,

V. Balamurugan

и другие.

Transactions on Emerging Telecommunications Technologies, Год журнала: 2025, Номер 36(3)

Опубликована: Март 1, 2025

ABSTRACT Workload prediction is the necessary factor in cloud data center for maintaining elasticity and scalability of resources. However, accuracy workload very low, because redundancy, noise, low center. In this manuscript, Prediction Cloud Data Centers using Complex‐Valued Spatio‐Temporal Graph Convolutional Neural Network Optimized with Gazelle Optimization Algorithm (CVSTGCN‐WLP‐CDC) proposed. Initially, input collected from two standard datasets such as NASA Saskatchewan HTTP traces dataset. Then, preprocessing Multi‐Window Savitzky–Golay Filter (MWSGF) used to remove noise redundant data. The preprocessed fed CVSTGCN a dynamic environment. work, proposed Approach (GOA) enhance weight bias parameters. CVSTGCN‐WLP‐CDC technique executed efficacy based on structure evaluated several performances metrics accuracy, recall, precision, energy consumption correlation coefficient, sum index (SEI), root mean square error (RMSE), squared (MPE), percentage (PER). provides 23.32%, 28.53% 24.65% higher accuracy; 22.34%, 25.62%, 22.84% lower when comparing existing methods Artificial Intelligence augmented evolutionary approach espoused centres architecture (TCNN‐CDC‐WLP), Performance analysis machine learning centered techniques (PA‐BPNN‐CWPC), Machine effectual utilization centers (ARNN‐EU‐CDC) respectively.

Язык: Английский

Investigation of Recent Metaheuristics Based Selective Harmonic Elimination Problem for Different Levels of Multilevel Inverters DOI Open Access
Satılmış Ürgün, Halil Yiğit, Seyedali Mirjalili

и другие.

Electronics, Год журнала: 2023, Номер 12(4), С. 1058 - 1058

Опубликована: Фев. 20, 2023

Multilevel inverters (MLI) are popular in high-power applications. MLIs generally configured to have switches reduced by switching techniques that eliminate low-order harmonics. The selective harmonic elimination (SHE) method, which significantly reduces the number of switching, determines optimal moments obtain desired output voltage and eliminates components. To solve SHE problem, classical methods primarily employed. disadvantages such high probability trapping locally solutions their dependence on initial controlling parameters. One solution overcome this problem is use metaheuristic algorithms. In study, firstly, 22 algorithms with different sources inspiration were used at levels MLIs, performances extensively analyzed. reveal method offers best solution, these first applied an 11-level MLI circuit, six determined as a result performance analysis. As evaluation, outstanding SPBO, BMO, GA, GWO, MFO, SPSA. application superior 7-, 11-, 15-, 19-level according IEEE 519—2014 standard, it has been shown BMO outperforms 7-level MLI, GA SPBO 15- terms THD, while quality, SPSA 15-level come forward.

Язык: Английский

Процитировано

15
Optimal Planning of PV Sources and D-STATCOM Devices with Network Reconfiguration Employing Modified Ant Lion Optimizer DOI Creative Commons

B. C. Sujatha,

A. Usha,

R. Geetha

и другие.

Energies, Год журнала: 2024, Номер 17(10), С. 2238 - 2238

Опубликована: Май 7, 2024

This research emphasizes a meta-heuristic modified ant lion optimizer (MALO) optimization approach for the simultaneous utilization of DSTATCOM devices and distributed photovoltaic (PV) sources with network reconfiguration in radial power distribution scheme. In reconfiguration, majority is based on constant model analysis. However, it noticed that load models have substantial impact PV device’s optimal size position. The effect (CP) polynomial (ZIP) growth insertion examined this work system planning. penetration levels considered investigation are 25%, 50%, 75%, 100%. principal objective to reduce total losses, enhance voltage magnitude profile at all buses, overall operating cost while adhering equality inequality constraints. proposed algorithm verified 118-node test systems. carried out planning upgrading high-voltage (HVDS) 317 nodes rural Bangalore Electricity Supply Company Limited (BESCOM) simulated results obtained method validated BAT techniques available literature. It observed IEEE 118-bus system, via placement sizing considering 25% level during loss reduction 41.47% 42.98% ZIP model. For 317-bus 11 kV 49.77% 59.34% growth. Similarly, 22 51.69% 55.75%

Язык: Английский

Процитировано

6
Sustainable inventory prediction with random defect and rework using Bat algorithm DOI Creative Commons
Madhu Jain, Nidhi Sharma, Praveendra Singh

и другие.

RAIRO - Operations Research, Год журнала: 2023, Номер 57(2), С. 481 - 501

Опубликована: Фев. 1, 2023

The sustainable EPQ models that have been proposed in the inventory literature are insufficient to address practical scenario of defects manufacturing and subsequent rework for remedial actions. In this article, model with faulty products has studied. Promotional activities key factors significantly affect market demand an item. impacts random combining economic environmental elements on order quantity price promotional effort dependent addressed. Numerical illustrations along sensitivity analysis presented reveal relevancy as well computational tractability investigation. For profit optimization, a mixed integer problem formulated analyzed by using Bat meta-heuristic optimization algorithm.

Язык: Английский

Процитировано

12
Hybrid Modified Chimp Optimization Algorithm and Reinforcement Learning for Global Numeric Optimization DOI
Mohammad Sh. Daoud, Mohammad Shehab, Laith Abualigah

и другие.

Journal of Bionic Engineering, Год журнала: 2023, Номер 20(6), С. 2896 - 2915

Опубликована: Июнь 13, 2023

Язык: Английский

Процитировано

12
A hybrid chaotic bat algorithm for optimal placement and sizing of dg units in radial distribution networks DOI Creative Commons
Imene Khenissi, Tawfik Guesmi, Badr M. Alshammari

и другие.

Energy Reports, Год журнала: 2024, Номер 12, С. 1723 - 1741

Опубликована: Авг. 3, 2024

Язык: Английский

Процитировано

5
FC-PV-battery-Z source-BBO integrated unified power quality conditioner for sensitive load & EV charging station DOI
Krishna Sarker

Journal of Energy Storage, Год журнала: 2023, Номер 75, С. 109671 - 109671

Опубликована: Ноя. 16, 2023

Язык: Английский

Процитировано

10
Artificial Intelligence in Visible Light Positioning for Indoor IoT: A Methodological Review DOI Creative Commons
Vasileios P. Rekkas, Lazaros Alexios Iliadis, Sotirios P. Sotiroudis

и другие.

IEEE Open Journal of the Communications Society, Год журнала: 2023, Номер 4, С. 2838 - 2869

Опубликована: Янв. 1, 2023

Indoor communication and positioning are significant fields of applications for indoor Internet Things (IoT) given the rapid growth IoT in smart cities, grids, industries. Visible light (VLP) has become more attractive researchers to provide location-aware services. Additionally, artificial intelligence (AI) attracted considerable research effort address challenges visible-light (VLC) systems. This is an emerging technology next-generation wireless networks. However, despite progress, use AI localization, navigation, position estimation still underexplored VLC systems, various open. methodological review summarizes efforts regarding field VLP, improve accuracy both two-dimensional (2D) three-dimensional (3D) applications. treatise also presents open issues potential future directions motivating further field. Various databases were utilized this paper: Scopus, Google Scholar, IEEE Xplore; obtained 88 papers from 2017 early 2023. Most (68%) articles VLP systems machine learning (ML) methods applied localization while other 32% focussed on evolutionary algorithms. ML models may present limitations terms complexity time-consuming nature but offer highly accurate, robust, reliable, cost-effective results over conventional approaches.

Язык: Английский

Процитировано

9
Demand side management using optimization strategies for efficient electric vehicle load management in modern power grids DOI Creative Commons

Manoj kumar M.V,

C. Bharatiraja,

S. Devakirubakaran

и другие.

PLoS ONE, Год журнала: 2024, Номер 19(3), С. e0300803 - e0300803

Опубликована: Март 21, 2024

The Electric Vehicle (EV) landscape has witnessed unprecedented growth in recent years. integration of EVs into the grid increased demand for power while maintaining grid’s balance and efficiency. Demand Side Management (DSM) plays a pivotal role this system, ensuring that can accommodate additional load without compromising stability or necessitating costly infrastructure upgrades. In work, DSM algorithm been developed with appropriate objective functions necessary constraints, including EV load, distributed generation from Solar Photo Voltaic (PV), Battery Energy Storage Systems. are constructed using various optimization strategies, such as Bat Optimization Algorithm (BOA), African Vulture (AVOA), Cuckoo Search Algorithm, Chaotic Harris Hawk (CHHO), Chaotic-based Interactive Autodidact School (CIAS) algorithm, Slime Mould (SMA). This algorithm-based method is simulated MATLAB/Simulink different cases loads, residential Information Technology (IT) sector loads. results show peak reduced 4.5 MW to 2.6 MW, minimum raised 0.5 1.2 successfully reducing gap between low points. Additionally, performance each was compared terms difference valley points, computation time, convergence rate achieve best fitness value.

Язык: Английский

Процитировано

3
Transformer-based decoder of melanoma classification using hand-crafted texture feature fusion and Gray Wolf Optimization algorithm DOI Creative Commons
Hemant Kumar, Abhishek Dwivedi, Abhishek Kumar Mishra

и другие.

MethodsX, Год журнала: 2024, Номер 13, С. 102839 - 102839

Опубликована: Июль 3, 2024

Melanoma is a type of skin cancer that poses significant health risks and requires early detection for effective treatment. This study proposing novel approach integrates transformer-based model with hand-crafted texture features Gray Wolf Optimization, aiming to enhance efficiency melanoma classification. Preprocessing involves standardizing image dimensions enhancing quality through median filtering techniques. Texture features, including GLCM LBP, are extracted capture spatial patterns indicative melanoma. The GWO algorithm applied select the most discriminative features. A decoder then employed classification, leveraging attention mechanisms contextual dependencies. experimental validation on HAM10000 dataset ISIC2019 showcases effectiveness proposed methodology. model, integrated guided by achieves outstanding results. results showed method performed well in tasks, achieving an accuracy F1-score 99.54% 99.11% dataset, 99.47%, 99.25% dataset. • We use concepts LBP extract from lesion images. Optimization (GWO) feature selection. based Transformers utilized

Язык: Английский

Процитировано

3
Evolutionary and Nature-Inspired Algorithms for Disaster-Resilient Networks DOI Creative Commons
Bidyarani Langpoklakpam, Lithungo K. Murry

IntechOpen eBooks, Год журнала: 2025, Номер unknown

Опубликована: Янв. 19, 2025

Disaster management system necessitates efficient and resilient communication networks to ensure effective emergency response recovery efforts. Disasters pose significant challenges infrastructures, often leading breakdowns in disrupting rescue relief In recent years, metaheuristic algorithms have emerged as a promising solution for optimizing various aspects of disaster scenarios. this paper, we investigate the use application addressing optimization problems that arise during operations. The key design, including victim localization, routing, coverage, resource allocation, are discussed. This study also discusses strengths limitations different Finally, it highlights recently developed models future research directions area network optimization.

Язык: Английский

Процитировано

0