Application of high performance one-dimensional chaotic map in key expansion algorithm DOI
Yuxuan Li

Published: Nov. 17, 2023

In this paper, we present a key expansion algorithm based on high-performance one-dimensional chaotic map. Traditional maps exhibit several limitations, prompting us to construct new map that overcomes these shortcomings. By analyzing the structural characteristics of classic ID maps, propose outperforms multidimensional introduced by numerous researchers in recent years. block cryptosystems, security round keys is utmost importance. To ensure generation secure keys, sufficiently robust required. The assessed statistical independence and sensitivity initial key. Leveraging properties our constructed map, introduce algorithm. Our experimental results validate proposed algorithm, demonstrating its resilience against various attacks. exhibits strong key, further strengthening generated keys.

Language: Английский

Machine learning-based Monte Carlo hyperparameter optimization for THMs prediction in urban water distribution networks DOI
Mansour Baziar, Ali Behnami, Negar Jafari

et al.

Journal of Water Process Engineering, Journal Year: 2025, Volume and Issue: 73, P. 107683 - 107683

Published: April 14, 2025

Language: Английский

Citations

1
-30°C cold start optimization of PEMFC based on a data-driven surrogate model and multi-objective optimization algorithm DOI Creative Commons
Fan Zhang, Xiyuan Zhang, Bowen Wang

et al.

Digital Chemical Engineering, Journal Year: 2024, Volume and Issue: 10, P. 100144 - 100144

Published: Feb. 2, 2024

Cold start is a critical operating scenario for the proton exchange membrane fuel cell (PEMFC), particularly in field of transportation. Under sub-freezing temperatures, water inside will freeze and obstruct gas flow paths as well cover catalyst reaction sites, resulting failed startup. This study proposes an optimization method -30°C cold PEMFC based on data-driven surrogate model to improve performance reduce irreversible damage cell. A validated mechanism utilized basis developing extreme learning machine (ELM) model, which trained using data collected from has higher computational efficiency compared with original model. In addition, NSGA-II multi-objective algorithm employed optimize current loading strategies parameters fitness function. The objectives are enhance minimum voltage startup duration time. Moreover, experimental validation confirms effectiveness proposed method. test results demonstrate that achieved within 97 s, reaching 0.44 V. Notably, there reduction time by 26 s increase 0.06 V base case. establishes foundation researchers adjust settings during diverse applications requirements.

Language: Английский

Citations

7
Forecasting solar power generation using evolutionary mating algorithm-deep neural networks DOI Creative Commons
Mohd Herwan Sulaiman, Zuriani Mustaffa

Energy and AI, Journal Year: 2024, Volume and Issue: 16, P. 100371 - 100371

Published: April 17, 2024

This paper proposes an integration of recent metaheuristic algorithm namely Evolutionary Mating Algorithm (EMA) in optimizing the weights and biases deep neural networks (DNN) for forecasting solar power generation. The study employs a Feed Forward Neural Network (FFNN) to forecast AC output using real plant measurements spanning 34-day period, recorded at 15-minute intervals. intricate nonlinear relationship between irradiation, ambient temperature, module temperature is captured accurate prediction. Additionally, conducts comprehensive comparison with established algorithms, including Differential Evolution (DE-DNN), Barnacles Optimizer (BMO-DNN), Particle Swarm Optimization (PSO-DNN), Harmony Search (HSA-DNN), DNN Adaptive Moment Estimation optimizer (ADAM) Nonlinear AutoRegressive eXogenous inputs (NARX). experimental results distinctly highlight exceptional performance EMA-DNN by attaining lowest Root Mean Squared Error (RMSE) during testing. contribution not only advances methodologies but also underscores potential merging algorithms contemporary improved accuracy reliability.

Language: Английский

Citations

6
APPLICATION OF MACHINE LEARNING ALGORITHMS TO PREDICT HOTEL OCCUPANCY DOI Creative Commons
Konstantins Kozlovskis, Liu Yuanyuan, Nataļja Lāce

et al.

Journal of Business Economics and Management, Journal Year: 2023, Volume and Issue: 24(3), P. 594 - 613

Published: Sept. 28, 2023

The development and availability of information technology the possibility deep integration internal IT systems with external ones gives a powerful opportunity to analyze data online based on providers. Recently, machine learning algorithms play significant role in predicting different processes. This research aims apply several predict high frequent daily hotel occupancy at Chinese hotel. Five models (bagged CART, bagged MARS, XGBoost, random forest, SVM) were optimized applied for occupancy. All are compared using model accuracy measures an ARDL chosen as benchmark comparison. It was found that CART showed most relevant results (R2 > 0.50) all periods, but could not beat traditional model. Thus, despite original use solving regression tasks, used this have been more effective than In addition, variables’ importance check hypothesis Baidu search index its components can be

Language: Английский

Citations

13
Smart Tunnel Fire Temperature Prediction Method with Fusion of Golden Eagle Optimization, Logistic Map, and Lévy Flight Mechanism DOI
Yan Li, Bin Sun

Journal of Pipeline Systems Engineering and Practice, Journal Year: 2025, Volume and Issue: 16(2)

Published: Feb. 25, 2025

Language: Английский

Citations

0
AI Powered Renewable Energy Balancing, Forecasting and Global Trend Analysis using ANN-LSTM Integration DOI

Sanjana Murgod,

Kartik Garg,

Triveni Magadum

et al.

Published: March 3, 2025

Abstract The instability of renewable energy sources like solar and wind places significant hurdles on distribution grid stability, thus hampering the race towards sustainable solutions. These instabilities, mainly due to fluctuating weather conditions, may lead surpluses or shortages energy-with inevitable effects grid's reliability. It is proposed that an AI-enabled system based ANN LSTM solutions be developed analyse global trends, predict generation accurately, enhance resilience. new model resides historical real-time data adequately captures long-range transition short-range fluctuations in energy, allowing better management. Along with that, intelligent forecasting will also optimize storage minimize overreliance normal fossil fuel energy. insights drawn out by this provide considerable assistance decision-makers, suppliers, operators their drive for a more stable, efficient, dependable, infrastructure. This research highlights role AI-driven predictive analytics should play facilitating transitions toward while addressing some critical operational challenges reliability distribution.

Language: Английский

Citations

0
Life cycle assessment and forecasting for 30kW solar power plant using machine learning algorithms DOI Creative Commons

Sushree Samikshya Pattanaik,

Ashwin Kumar Sahoo, R. Panda

et al.

e-Prime - Advances in Electrical Engineering Electronics and Energy, Journal Year: 2024, Volume and Issue: 7, P. 100476 - 100476

Published: Feb. 20, 2024

Highly competitiveness of solar power plants in the energy market requires addressing active research problem forecasting. To make precise forecasts, however, historical meteorological, production, or irradiance data is insufficient. As conservation these Renewable Energy Sources (RES) that much essential, use Photovoltaic (PV) panels have subsequently increased. The output PV completely depends on climate. convert to electrical energy, therefore, it produces most when there enough sunlight throughout summer and least rain. Accurate forecasting generation from crucial terms economics due this uncertainty different seasons change meteorological conditions. objective paper investigate machine learning algorithms can accurately anticipate for upcoming hour hourly days advance. Naïve Bayes Algorithm, Multilayer Perceptron Theorem (MLP), Long Short-Term Memory networks (LSTM) are investigated. Both weather used study. This study also includes payback period (PB) life cycle assessment calculation roof top plant located Bhubaneswar India.

Language: Английский

Citations

3
An interval neural network-based Caputo fractional-order extreme learning machine applied to classification DOI

Yuanquan Liu,

Qiang Shao, Yan Liu

et al.

Applied Soft Computing, Journal Year: 2024, Volume and Issue: unknown, P. 112310 - 112310

Published: Oct. 1, 2024

Language: Английский

Citations

3
A Short Term Multistep Forecasting Model for Photovoltaic Generation using Deep Learning Model DOI Creative Commons

Lakshmi Palaparambil Dinesh,

Nameer Al Khafaf, B. P. McGrath

et al.

Sustainable Operations and Computers, Journal Year: 2024, Volume and Issue: 6, P. 34 - 46

Published: Nov. 14, 2024

Language: Английский

Citations

2
Day-Ahead Forecast of Photovoltaic Power Based on a Novel Stacking Ensemble Method DOI Creative Commons
Luyao Liu, Qie Sun,

Ronald Wennersten

et al.

IEEE Access, Journal Year: 2023, Volume and Issue: 11, P. 113593 - 113604

Published: Jan. 1, 2023

Accurate prediction of photovoltaic (PV) power is the prerequisite for safe and stable operation grid with high penetration PV. Despite various machine learning models forecasting PV have been developed, their accuracies are generally unstable. Toward this end, study proposes a novel Stacking ensemble forecast model to improve precision day-ahead forecasts. Different from traditional that uses original training dataset train base learners, proposed creates multiple sub-training sets so as enhance diversity further accuracy. Specifically, in model, four i.e., generalized regression neural network (GRNN), extreme (ELM), Elman (ElmanNN), Long shot-term memory (LSTM) incorporated, which trained diverse datasets, variety candidate generated. For those models, ones best performance selected integrated through meta-model, namely back-propagation work (BPNN), produce final prediction. The evaluated using measured data 15kW station Ashland, Oregon, USA. Results indicate across three weather scenarios, consistently outperforms single terms errors out-of-sample forecasting, proves effectiveness developed procedure improving

Language: Английский

Citations

4