Hybrid Chaotic Zebra Optimization Algorithm and Long Short-Term Memory for Cyber Threats Detection DOI Creative Commons

Reham Amin,

Ghada Eltaweel,

Ahmed F. Ali

et al.

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 93235 - 93260

Published: Jan. 1, 2024

Cyber Threat Detection (CTD) is subject to complicated and rapidly accelerating developments. Poor accuracy, high learning complexity, limited scalability, a false positive rate are problems that CTD encounters. Deep Learning defense mechanisms aim build effective models for threat detection protection allowing them adapt the complex ever-accelerating changes in field of CTD. Furthermore, swarm intelligence algorithms have been developed tackle optimization challenges. In this paper, Chaotic Zebra Optimization Long-Short Term Memory (CZOLSTM) algorithm proposed. The proposed hybrid between Algorithm (CZOA) feature selection LSTM cyber classification CSE-CIC-IDS2018 dataset. Invoking chaotic map CZOLSTM can improve diversity search avoid trapping local minimum. evaluating effectiveness newly CZOLSTM, binary multi-class classifications considered. acquired outcomes demonstrate efficiency implemented improvements across many other algorithms. When comparing performance detection, it outperforms six innovative deep five classification. Other evaluation criteria such as recall, F1 score, precision also used comparison. results showed best accuracy was achieved using 99.83%, with F1-score 99.82%, recall 99.82%. among compared

Language: Английский

Towards smart energy management for community microgrids: Leveraging deep learning in probabilistic forecasting of renewable energy sources DOI Creative Commons
Jhon J. Quiñones, Luis R. Pineda, Jason K. Ostanek

et al.

Energy Conversion and Management, Journal Year: 2023, Volume and Issue: 293, P. 117440 - 117440

Published: Aug. 2, 2023

Language: Английский

Citations

27
Two-step deep learning framework with error compensation technique for short-term, half-hourly electricity price forecasting DOI Creative Commons
Sujan Ghimire, Ravinesh C. Deo, David Casillas-Pérez

et al.

Applied Energy, Journal Year: 2023, Volume and Issue: 353, P. 122059 - 122059

Published: Oct. 18, 2023

Prediction of electricity price is crucial for national markets supporting sale prices, bidding strategies, dispatch, control and market volatility management. High volatility, non-stationarity multi-seasonality prices make it significantly challenging to estimate its future trend, especially over near real-time forecast horizons. An error compensation strategy that integrates Long Short-Term Memory (LSTM) network, Convolution Neural Network (CNN) the Variational Mode Decomposition (VMD) algorithm proposed predict half-hourly step prices. A prediction model incorporating VMD CLSTM first used obtain an initial prediction. To improve predictive accuracy, a novel framework, which built using Random Forest Regression (RF) algorithm, also used. The VMD-CLSTM-VMD-ERCRF evaluated from Queensland, Australia. results reveal highly accurate performance all datasets considered, including winter, autumn, spring, summer, yearly predictions. As compared with without (i.e., VMD-CLSTM model), outperforms benchmark models. For predictions, average Legates McCabe Index seen increase by 15.97%, 16.31%, 20.23%, 10.24%, 14.03%, respectively, relative According tests performed on independent datasets, can be practical stratagem useful short-term, forecasting. Therefore research outcomes demonstrate framework effective decision-support tool improving accuracy price. It could value energy companies, policymakers operators develop their insight analysis, distribution optimization strategies.

Language: Английский

Citations

27
Future Food Production Prediction Using AROA Based Hybrid Deep Learning Model in Agri-Sector DOI Creative Commons

Swathi Baswaraju,

V. Uma Maheswari,

Krishna Keerthi Chennam

et al.

Human-Centric Intelligent Systems, Journal Year: 2023, Volume and Issue: 3(4), P. 521 - 536

Published: Oct. 6, 2023

Abstract Policymaking and administration of national tactics action for food security rely heavily on advances in models accurate estimation output. In several fields, including science engineering, machine learning (ML) has been established to be an effective tool data investigation modelling. There a rise recent years the application ML tracking forecasting safety. our analysis, we focused two sources production: livestock production agricultural production. Livestock was measured terms yield, number animals, sum animals slaughtered; crop output yields losses. An innovative hybrid deep model is proposed this paper by fusing Dense Convolutional Network (DenseNet) with Long Short-Term Memory (LSTM) do analysis. The hybridised algorithm, or A-ROA short, combines Arithmetic Optimisation Algorithm (AOA) Rider (ROA) determine ideal weight LSTM. current focuses Iran as case study. Therefore, have collected FAOSTAT time series farming outputs from 1961 2017. Findings study can help policymakers plan future generations' safety supply providing anticipate upcoming construction.

Language: Английский

Citations

24
Probabilistic-based electricity demand forecasting with hybrid convolutional neural network-extreme learning machine model DOI
Sujan Ghimire, Ravinesh C. Deo, David Casillas-Pérez

et al.

Engineering Applications of Artificial Intelligence, Journal Year: 2024, Volume and Issue: 132, P. 107918 - 107918

Published: Feb. 3, 2024

Language: Английский

Citations

16
Electricity demand error corrections with attention bi-directional neural networks DOI
Sujan Ghimire, Ravinesh C. Deo, David Casillas-Pérez

et al.

Energy, Journal Year: 2024, Volume and Issue: 291, P. 129938 - 129938

Published: Jan. 3, 2024

Language: Английский

Citations

13
A complementary fused method using GRU and XGBoost models for long-term solar energy hourly forecasting DOI

Yaojian Xu,

Shaifeng Zheng,

Qingling Zhu

et al.

Expert Systems with Applications, Journal Year: 2024, Volume and Issue: 254, P. 124286 - 124286

Published: June 5, 2024

Language: Английский

Citations

13
Short-Medium-Term Solar Irradiance Forecasting with a CEEMDAN-CNN-ATT-LSTM Hybrid Model Using Meteorological Data DOI Creative Commons

M Mora Camacho,

Jorge Maldonado-Correa, Joel Torres-Cabrera

et al.

Applied Sciences, Journal Year: 2025, Volume and Issue: 15(3), P. 1275 - 1275

Published: Jan. 26, 2025

In recent years, the adverse effects of climate change have increased rapidly worldwide, driving countries to transition clean energy sources such as solar and wind. However, these energies face challenges cloud cover, precipitation, wind speed, temperature, which introduce variability intermittency in power generation, making integration into interconnected grid difficult. To achieve this, we present a novel hybrid deep learning model, CEEMDAN-CNN-ATT-LSTM, for short- medium-term irradiance prediction. The model utilizes complete empirical ensemble modal decomposition with adaptive noise (CEEMDAN) extract intrinsic seasonal patterns irradiance. addition, it employs encoder-decoder framework that combines convolutional neural networks (CNN) capture spatial relationships between variables, an attention mechanism (ATT) identify long-term patterns, long short-term memory (LSTM) network dependencies time series data. This has been validated using meteorological data more than 2400 masl region characterized by complex climatic conditions south Ecuador. It was able predict at 1, 6, 12 h horizons, mean absolute error (MAE) 99.89 W/m2 winter 110.13 summer, outperforming reference methods this study. These results demonstrate our represents progress contributing scientific community field environments high its applicability real scenarios.

Language: Английский

Citations

1
Advanced artificial intelligence model for solar irradiance forecasting for solar electric vehicles DOI

Mohamed Abdellatif Khalfa,

Lazhar Manai,

Walid Mchara

et al.

International Journal of Dynamics and Control, Journal Year: 2025, Volume and Issue: 13(3)

Published: Feb. 11, 2025

Language: Английский

Citations

1
Hybrid deep learning model for wave height prediction in Australia's wave energy region DOI Creative Commons
A. A. Masrur Ahmed, S. Janifer Jabin Jui, Mohanad S. AL‐Musaylh

et al.

Applied Soft Computing, Journal Year: 2023, Volume and Issue: 150, P. 111003 - 111003

Published: Nov. 2, 2023

Waves are emerging as a renewable energy resource, but the harnessing of such remains among least developed in terms technologies on regional or global basis. To generate usable energy, wave heights must be predicted near-real-time, which is driving force for converters. This study develops hybrid Convolutional Neural Network-Long Short-Term Memory-Bidirectional Gated Recurrent Unit forecast system (CLSTM-BiGRU) trained to accurately predict significant height (Hsig) at multiple forecasting horizons (30 minutes, 0.5H; 2 hours, 02H; 3 03H and 6 06H. In this model, convolutional neural networks (CNNs), long-short-term memories (LSTMs), bidirectional gated recurrent units (BiGRUs) employed Hsig. construct proposed CLSTM-BiGRU historical properties, including maximum height, zero-up crossing period, peak sea surface temperature, analysed. Several generation sites Queensland, Australia were tested using deep learning model. Based statistical score metrics, scatterplots, error evaluations, model generates more accurate forecasts than benchmark models. established practical utility modelling Hsig therefore shows could have implications ocean systems, tidal monitoring well sustainable resource evaluation where prediction required.

Language: Английский

Citations

22
Efficient daily electricity demand prediction with hybrid deep-learning multi-algorithm approach DOI Creative Commons
Sujan Ghimire, Ravinesh C. Deo, David Casillas-Pérez

et al.

Energy Conversion and Management, Journal Year: 2023, Volume and Issue: 297, P. 117707 - 117707

Published: Oct. 5, 2023

Predicting electricity demand (G) is crucial for grid operation and management. In order to make reliable predictions, model inputs must be analyzed predictive features before they can incorporated into a forecast model. this study, hybrid multi-algorithm framework developed by incorporating Artificial Neural Networks (ANN), Encoder-Decoder Based Long Short-Term Memory (EDLSTM) Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (ICMD). Following the partitioning of data, G time-series are decomposed multiple using ICEEMDAN algorithm, partial autocorrelation applied training sets determine lagged features. We combine where components highest frequency predicted an ANN model, while remaining EDLSTM To generate results, all IMF components' predictions merged ICMD-ANN-EDLSTM models. A comparison made between objective standalone models (ANN, RFR, LSTM), (CLSTM), three decomposition-based on Relative Mean Absolute Error at Duffield Road substation was ≈2.82%, ≈4.15%, ≈3.17%, ≈6.41%, ≈6.60%, ≈6.49%, ≈6.602%, compared ICMD-RFR-LSTM, ICMD-RFR-CLSTM, LSTM, CLSTM, ANN. According statistical score metrics, performed better than other benchmark Further, results show that not only detect seasonality in but also predict analyze market add valuable insight analysis.

Language: Английский

Citations

20