Regional Pv Power Prediction Based on Transfer Learning and Satellite Cloud Imagery DOI
Yang Xie, Jianyong Zheng, Fei Mei

et al.

Published: Jan. 1, 2023

As renewable energy, particularly regional photovoltaic (PV), becomes more prevalent in the power grid, accurate forecasting of its output is paramount for efficient operation. However, challenges persist, including lack reliable data, inappropriate data usage, and computational burdens stemming from vast number dispersed nature PV installations. To address these problems, a prediction based on transfer learning satellite cloud imagery proposed. Firstly, an algorithmic architecture composed gray-level co-occurrence matrix (GLCM) random forest (RF) established extracting texture features (TFs) images selecting TFs with highest correlation to irradiance. Furthermore, attention mechanism (AM) long short-term memory (LSTM) employed at reconstruct significant TFs. These reconstructed are then integrated into training model, aiming enhance between outcome. Finally, structure combine convolutional neural network (CNN) LSTM taken as maximum mean discrepancy (MMD) algorithm utilized measure correlations source target stations. Both single located UK station China analysis verify effectiveness, several benchmark methods have been compared, approach this research demonstrated superior performance.

Language: Английский

Lyrebird Optimization Algorithm: A New Bio-Inspired Metaheuristic Algorithm for Solving Optimization Problems DOI Creative Commons
Mohammad Dehghani,

Gulnara Bektemyssova,

Zeinab Montazeri

et al.

Biomimetics, Journal Year: 2023, Volume and Issue: 8(6), P. 507 - 507

Published: Oct. 23, 2023

In this paper, a new bio-inspired metaheuristic algorithm called the Lyrebird Optimization Algorithm (LOA) that imitates natural behavior of lyrebirds in wild is introduced. The fundamental inspiration LOA strategy when faced with danger. situation, scan their surroundings carefully, then either run away or hide somewhere, immobile. theory described and mathematically modeled two phases: (i) exploration based on simulation lyrebird escape (ii) exploitation hiding strategy. performance was evaluated optimization CEC 2017 test suite for problem dimensions equal to 10, 30, 50, 100. results show proposed approach has high ability terms exploration, exploitation, balancing them during search process problem-solving space. order evaluate capability dealing tasks, obtained from were compared twelve well-known algorithms. superior competitor algorithms by providing better most benchmark functions, achieving rank first best optimizer. A statistical analysis shows significant superiority comparison addition, efficiency handling real-world applications investigated through twenty-two constrained problems 2011 four engineering design problems. effective tasks while

Language: Английский

Citations

42
Metaheuristic Algorithms for Solar Radiation Prediction: A Systematic Analysis DOI Creative Commons
Sergio A. Pérez-Rodríguez, José M. Álvarez-Alvarado, Julio-Alejandro Romero-González

et al.

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 100134 - 100151

Published: Jan. 1, 2024

In the contemporary world, where escalating demand for energy and imperative sustainable sources, notably solar energy, have taken precedence, investigation into radiation (SR) has become indispensable. Characterized by its intermittency volatility, SR may experience considerable fluctuations, exerting a significant influence on supply security. Consequently, precise prediction of imperative, particularly in context potential proliferation photovoltaic panels need optimized management. Several works existing literature review state art prediction, focusing trends identified using machine learning (ML) or deep (DL) techniques. However, there is gap regarding integration optimization algorithms with ML DL techniques prediction. This systematic addresses this studying models that leverage metaheuristic alongside artificial intelligence (AI) techniques, aiming primarily maximum accuracy. Metaheuristic such as Particle Swarm Optimization (PSO) Genetic Algorithm (GA) featured 29% 12.1% analyzed articles, respectively, while intelligent approaches like Convolutional Neural Networks (CNN), Extreme Learning Machine (ELM), Multilayer Perceptron (MLP) emerged predominant choices, collectively accounting 43.9% studies. Analysis encompassed studies examining across hourly, daily, monthly intervals, daily intervals representing 48.7% focus. Noteworthy variables including temperature, humidity, wind speed, atmospheric pressure surfaced, capturing proportions 90%, 68.2%, 56%, 41.4%, within reviewed literature.

Language: Английский

Citations

5
AI-driven optimization of indoor environmental quality and energy consumption in smart buildings: a bio-inspired algorithmic approach DOI Creative Commons
Rehab Salaheldin Ghoneim,

Mazin Arabasy,

A. Abdul-Hadi

et al.

Journal of Asian Architecture and Building Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 25

Published: Feb. 28, 2025

Language: Английский

Citations

0
Financial Time Series Forecasting: A Comprehensive Review of Signal Processing and Optimization-Driven Intelligent Models DOI

Matoori Praveen,

Satish Dekka,

Sai Dai

et al.

Computational Economics, Journal Year: 2025, Volume and Issue: unknown

Published: March 5, 2025

Language: Английский

Citations

0
Review on Distribution System State Estimation Considering Renewable Energy Sources DOI Creative Commons
Hanshan Qing, Abhinav Kumar Singh, Efstratios I. Batzelis

et al.

Energies, Journal Year: 2025, Volume and Issue: 18(10), P. 2524 - 2524

Published: May 13, 2025

Power system state estimation (PSSE) is critical for accurately monitoring and managing electrical networks, especially with the increasing integration of renewable energy sources (RESs). This review aims to explicitly evaluate compare techniques specifically adapted handle RES-related uncertainties, providing both theoretical insights clear practical guidance. It categorizes analytically compares physical-model-based, forecasting-aided, neural network-based approaches, summarizing their strengths, limitations, ideal application scenarios. The paper concludes recommendations method selection under different conditions, highlighting opportunities future research.

Language: Английский

Citations

0
Short-term wind power forecasting using integrated boosting approach DOI Creative Commons
Ubaid Ahmed,

Rasheed Muhammad,

Syed Sami Abbas

et al.

Frontiers in Energy Research, Journal Year: 2024, Volume and Issue: 12

Published: May 30, 2024

Rapidly increasing global energy demand and environmental concerns have shifted the attention of policymakers toward large-scale integration renewable resources (RERs). Wind is a type RERs with vast potential no pollution associated it. The sustainable development goals: affordable clean energy, climate action, industry, innovation infrastructure, can be achieved by integrating wind into existing power systems. However, will bring instability challenges due to its intermittent nature. Mitigating these necessitates implementation effective forecasting models. Therefore, we proposed novel integrated approach, Boost-LR, for hour-ahead forecasting. Boost-LR multilevel technique consisting non-parametric models, extreme gradient boosting (XgBoost), categorical (CatBoost), random forest (RF), parametric linear regression (LR). first layer uses algorithms that process data according their tree architectures pass intermediary forecast LR which deployed in two processes forecasts one models provide final predicted power. To demonstrate generalizability robustness study, performance compared individual CatBoost, XgBoost, RF, deep learning networks: long short-term memory (LSTM) gated recurrent unit (GRU), Transformer Informer using root mean square error (RMSE), (MSE), absolute (MAE) normalized (NRMSE). Findings effectiveness as superior improvement MAE recorded 31.42%, 32.14%, 27.55% datasets Bruska, Jelinak, Inland farm, respectively CatBoost revealed second-best performing model. Moreover, study also reports literature comparison further validates

Language: Английский

Citations

3
Short-Term Marine Wind Speed Forecasting Based on Dynamic Graph Embedding and Spatiotemporal Information DOI Creative Commons

Dibo Dong,

Shangwei Wang,

Qiaoying Guo

et al.

Journal of Marine Science and Engineering, Journal Year: 2024, Volume and Issue: 12(3), P. 502 - 502

Published: March 18, 2024

Predicting wind speed over the ocean is difficult due to unequal distribution of buoy stations and occasional fluctuations in field. This study proposes a dynamic graph embedding-based neural network—long short-term memory joint framework (DGE-GAT-LSTM) estimate at numerous by considering their spatio-temporal information properties. To begin, buoys that are pertinent target station chosen based on geographic position. Then, local structures connecting represented using cosine similarity each time interval. Subsequently, network captures intricate spatial characteristics, while LSTM module acquires knowledge temporal interdependence. The sequentially interconnected collectively capture correlations. Ultimately, multi-step prediction outcomes produced sequential way, where step relies previous predictions. empirical data derived from direct measurements made NDBC buoys. results indicate suggested method achieves mean absolute error reduction ranging 1% 36% when compared other benchmark methods. improvement accuracy statistically significant. approach effectively addresses challenges inadequate integration complexity modeling correlations forecast speed. It offers valuable insights for optimizing selection offshore farm locations enhancing operational management capabilities.

Language: Английский

Citations

2
Advancing Smart Zero-Carbon Cities: High-Resolution Wind Energy Forecasting to 36 Hours Ahead DOI Creative Commons
Haytham H. Elmousalami,

Aljawharah A. Alnaser,

Felix Kin Peng Hui

et al.

Applied Sciences, Journal Year: 2024, Volume and Issue: 14(24), P. 11918 - 11918

Published: Dec. 19, 2024

Accurate wind speed and power forecasting are key to optimizing renewable station management, which is essential for smart zero-energy cities. This paper presents a novel integrated speed–power system (WSPFS) that operates across various time horizons, demonstrated through case study in high-wind area within the Middle East. The WSPFS leverages 12 AI algorithms both individual ensemble models forecast (WSF) (WPF) at intervals of 10 min 36 h. A multi-horizon prediction approach proposed, using WSF model outputs as inputs WPF modeling. Predictive accuracy was evaluated mean absolute percentage error (MAPE) square (MSE). Additionally, advances energy deep decarbonization (SWEDD) framework by calculating carbon city index (CCI) define carbon-city transformation curve (CCTC). Findings from this have broad implications, enabling urban projects mega-developments like NEOM Suez Canal advancing global trading supply management.

Language: Английский

Citations

2
Type-3 Fuzzy Dynamic Adaptation of Bee Colony Optimization Applied to Mathematical Functions DOI
Leticia Amador-Angulo, Oscar Castillo, Patricia Melín

et al.

Fuzzy Sets and Systems, Journal Year: 2024, Volume and Issue: 489, P. 109014 - 109014

Published: May 21, 2024

Language: Английский

Citations

1
An Investigation into the Effectiveness of Different Methodologies in Enhancing Genetic Algorithm Performance DOI

Krishn Murari,

N. V. Balaji,

S. Hemalatha

et al.

Published: Dec. 29, 2023

this examines investigates the impact of different algorithmic methodologies on improving overall performance genetic algorithms. A complete evaluate literature became carried out including both theoretical and empirical investigations. fourteen studies has been covered, with ten being four in nature. The studied synthesis covered use operators inclusive mutation, crossover, choice, as well strategies consisting elitism, micro-mutation, mimetic Throughout all studies, outcomes confirmed that those can have a fine enhancing given set rules. However, value development turned into found to vary considerably between one kind rules structures. Therefore, it seems particular methodology ought be cautiously chosen primarily based at characteristics problem domain. Additionally, similarly research should cognizance exploring approaches optimize combination various for stepped forward performance.

Language: Английский

Citations

1