Energy and Exergy Analysis of a Newly Designed Photovoltaic Thermal System Featuring Ribs, Petal array, and coiled twisted tapes: Experimental Analysis

Case Studies in Thermal Engineering, Journal Year: 2024, Volume and Issue: 63, P. 105388 - 105388

Published: Oct. 31, 2024

Language: Английский

---

Advanced series decomposition with a gated recurrent unit and graph convolutional neural network for non-stationary data patterns

Journal of Cloud Computing Advances Systems and Applications, Journal Year: 2024, Volume and Issue: 13(1)

Published: Jan. 18, 2024

Abstract In this study, we present the EEG-GCN, a novel hybrid model for prediction of time series data, adept at addressing inherent challenges posed by data's complex, non-linear, and periodic nature, as well noise that frequently accompanies it. This synergizes signal decomposition techniques with graph convolutional neural network (GCN) enhanced analytical precision. The EEG-GCN approaches data one-dimensional temporal signal, applying dual-layered using both Ensemble Empirical Mode Decomposition (EEMD) GRU. two-pronged process effectively eliminates interference distills complex into more tractable sub-signals. These sub-signals facilitate straightforward feature analysis learning process. To capitalize on decomposed is employed to discern intricate interplay within map interdependencies among points. predictive then synthesizes weighted outputs GCN yield final forecast. A key component our approach integration Gated Recurrent Unit (GRU) EEMD framework, referred EEMD-GRU-GCN. combination leverages strengths GRU in capturing dependencies EEMD's capability handling non-stationary thereby enriching set available enhancing overall accuracy stability model. evaluations demonstrate achieves superior performance metrics. Compared baseline model, shows an average R2 improvement 60% 90%, outperforming other methods. results substantiate advanced proposed underscoring its potential robust accurate forecasting.

Language: Английский

---

Harnessing a Better Future: Exploring AI and ML Applications in Renewable Energy

JOIV International Journal on Informatics Visualization, Journal Year: 2024, Volume and Issue: 8(1), P. 55 - 55

Published: March 16, 2024

Integrating machine learning (ML) and artificial intelligence (AI) with renewable energy sources, including biomass, biofuels, engines, solar power, can revolutionize the industry. Biomass biofuels have benefited significantly from implementing AI ML algorithms that optimize feedstock, enhance resource management, facilitate biofuel production. By applying insight derived data analysis, stakeholders improve entire supply chain - biomass conversion, fuel synthesis, agricultural growth, harvesting to mitigate environmental impacts accelerate transition a low-carbon economy. Furthermore, in combustion systems engines has yielded substantial improvements efficiency, emissions reduction, overall performance. Enhancing engine design control techniques produces cleaner, more efficient minimal impact. This contributes sustainability of power generation transportation. are employed analyze vast quantities photovoltaic systems' design, operation, maintenance. The ultimate goal is increase output system efficiency. Collaboration among academia, industry, policymakers imperative expedite sustainable future harness potential energy. these technologies, it possible establish ecosystem, which would benefit generations.

Language: Английский

---

Socio-environmental and technical factors assessment of photovoltaic hydrogen production in Antofagasta, Chile

Energy Strategy Reviews, Journal Year: 2024, Volume and Issue: 53, P. 101373 - 101373

Published: April 6, 2024

This study introduces a method for identifying territories ideal establishing photovoltaic (PV) plants green hydrogen (GH2) production in the Antofagasta region of northern Chile, location celebrated its outstanding solar energy potential. Assessing viability PV plant installation necessitates balanced consideration technical aspects and socio-environmental constraints, such as proximity to areas ecological importance indigenous communities, identify potential zones non-conventional renewable (NCRE)-based production. To tackle this challenge, we propose methodology that utilizes geospatial analysis, integrating Geographic Information System (GIS) tools with sensitivity determine most suitable sites region. Our analysis employs QGIS software these optimal locations, while uses Sørensen–Dice coefficient assess similarity among chosen variables. Applying reveals significant area within 15 km radius existing road networks electrical substations is favorable projects. further highlights limiting effects factors their interactions. Moreover, our research finds enlarging could increase total by about 10% per commune, indicating impact on

Language: Английский

---

Artificial Intelligence-Based Improvement of Empirical Methods for Accurate Global Solar Radiation Forecast: Development and Comparative Analysis

Energies, Journal Year: 2024, Volume and Issue: 17(17), P. 4302 - 4302

Published: Aug. 28, 2024

Artificial intelligence (AI) technology has expanded its potential in environmental and renewable energy applications, particularly the use of artificial neural networks (ANNs) as most widely used technique. To address shortage solar measurement various places worldwide, several radiation methods have been developed to forecast global (GSR). With this consideration, study aims develop temperature-based GSR models using a commonly utilized approach machine learning techniques, ANNs, predict just temperature data. It also compares performance these empirical Additionally, it develops precise for five new sites entire region, which currently lacks AI-based despite presence proposed plants area. The examines impact varying lengths validation datasets on models’ prediction accuracy, received little attention. Furthermore, investigates different ANN architectures estimation introduces comprehensive comparative study. findings indicate that advanced both accurately GSR, with coefficient determination, R2, values ranging from 96% 98%. Moreover, local general formulas model exhibit comparable at non-coastal sites. Conversely, ANN-based perform almost identically, high ability any location, even during winter months. fewer neurons their single hidden layer generally outperform those more. efficacy precision models, ones, are minimally impacted by size data sets. This reveals was significantly influenced weather conditions such clouds rain, especially coastal In contrast, were less variations, approximately 7% better than ones best-developed thus highly recommended. They enable rapid is useful design evaluation continuously easily recorded purposes.

Language: Английский

---

Sizing optimisation under irradiance uncertainty of irrigation systems powered by off-grid solar panels

Published: Jan. 1, 2025

Sizing a photovoltaic installation is crucial for decision-makers, researchers and practitioners managing pressurised irrigation networks powered by solar panels. Photovoltaic off-grid installations offer energy efficiency, lower operation costs, environmental benefits economic prof

Language: Английский

---

Sizing optimisation under irradiance uncertainty of irrigation systems powered by off-grid solar panels

Computers and Electronics in Agriculture, Journal Year: 2025, Volume and Issue: 232, P. 110034 - 110034

Published: Feb. 7, 2025

Language: Английский

---

Operative estimation of global horizontal irradiance using transfer functions through network types of artificial neural network in some selected sites in North-East Ethiopia: assessment and comparison

Heliyon, Journal Year: 2025, Volume and Issue: unknown, P. e43101 - e43101

Published: March 1, 2025

Language: Английский

---

A Prediction of the Monthly Average Daily Solar Radiation on a Horizontal Surface in Saudi Arabia Using Artificial Neural Network Approach

Processes, Journal Year: 2025, Volume and Issue: 13(4), P. 1149 - 1149

Published: April 10, 2025

When planning a solar energy conversion system, having sufficiently reliable values of the monthly average daily radiation (MADSR) on horizontal surface is essential. Traditionally, estimates based other climatological variables for which more information available have been relied upon to compensate lack direct measurements. Solar varies widely, requires creation site-specific forecast models. By using artificial neural network (ANN) models or similar methods historical datasets, can be easily assessed. To verify validity established ANN model, series analyses was performed mean squared error, coefficient determination (R2), and absolute error. The study used dataset collected from nine weather stations in Saudi Arabia 1985 2000. input parameters model were maximum air relative humidity, latitude, ambient temperature, longitude, minimum sunshine duration, location altitude, corresponding month. R2 whole test 0.8449. Furthermore, sensitivity analysis showed that site elevation (location altitude) had most significant effect MADSR surface, with contribution value 14.66%. results show accurately surfaces regardless seasonal variations conditions. this work important not only its shape forecasting but also establishing practical application ANNs renewable management. will help improve utilization support sustainable efforts. proposed believed useful predicting locations climatic conditions sites. approach may functional basic strategy arrangement suitable meteorological data.

Language: Английский

---

Hybrid deep learning CNN-LSTM model for forecasting direct normal irradiance: a study on solar potential in Ghardaia, Algeria

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: May 2, 2025

Language: Английский

---