Renewable energy sources integration via machine learning modelling: A systematic literature review

Heliyon, Год журнала: 2024, Номер 10(4), С. e26088 - e26088

Опубликована: Фев. 1, 2024

The use of renewable energy sources (RESs) at the distribution level has become increasingly appealing in terms costs and technology, expecting a massive diffusion near future placing several challenges to power grid. Since RESs depend on stochastic —solar radiation, temperature wind speed, among others— they introduce high uncertainty grid, leading imbalance deteriorating network stability. In this scenario, managing forecasting RES is vital successfully integrate them into grids. Traditionally, physical- statistical-based models have been used predict outputs. Nevertheless, former are computationally expensive since rely solving complex mathematical atmospheric dynamics, whereas latter usually consider linear models, preventing from addressing challenging scenarios. recent years, advances machine learning techniques, which can learn historical data, allowing analysis large-scale datasets either under non-uniform characteristics or noisy provided researchers with powerful data-driven tools that outperform traditional methods. paper, systematic literature review conducted identify most widely learning-based approaches forecast results show deep artificial neural networks, especially long-short term memory accurately model autoregressive nature output, ensemble strategies, allow handling large amounts highly fluctuating best suited ones. addition, promising integrating forecasted output decision-making problems, such as unit commitment, address economic, operational managerial grid discussed, solid directions for research provided.

Язык: Английский

---

Hybrid prediction method for solar photovoltaic power generation using normal cloud parrot optimization algorithm integrated with extreme learning machine

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Фев. 22, 2025

As the energy crisis environmental concerns rise, harnessing renewable sources like photovoltaics (PV) is critical for sustainable development. However, seasonal variability and random intermittency of solar power pose significant forecasting challenges, threatening grid stability. Therefore, this paper proposes a novel hybrid method, NCPO-ELM, to adequately capture spatial temporal dependencies within meteorological data crucial accurate predictions. To effectively optimize performance Extreme Learning Machine (ELM), Normal Cloud Parrot Optimization (NCPO) algorithm developed, inspired by Pyrrhura Molinae parrots' flock behavior cloud model theory. NCPO integrates five unique search strategies utilizes structure explore exploit. By introducing normal generate samples with specific distributions, enhances solution space coverage. subsequently employed Single-Layer Feedforward Network (SLFN) hidden layer hyperparameters, yielding optimal weights biases output layer, thereby reducing benchmark ELM's sensitivity noise instability from initialization. The actual results PV stations across different regions demonstrate that proposed NCPO-ELM shows superior prediction accuracy compared existing approaches, particularly time series diverse characteristics variations.

Язык: Английский

---

The role of ESG reporting, artificial intelligence, stakeholders and innovation performance in fostering sustainability culture and climate resilience

Journal of financial reporting & accounting, Год журнала: 2024, Номер unknown

Опубликована: Сен. 10, 2024

Purpose This study aims to investigate the causal relationships among environmental, social and governance reporting (ESGR), stakeholder sustainability awareness, use of artificial intelligence (AI), culture, innovation performance climate resilience organizations across diverse sectors in Sri Lanka. Design/methodology/approach A survey was conducted 327 respondents, including senior accounting professionals, operations managers functional heads gather company-level data various industries disjoint two-stage approach validated measurement model, partial least squares structural equation model (SEM) used test proposed hypotheses. Findings The analysis evidences mediating role stakeholders' awareness on relationship between ESGR culture. Furthermore, it emphasizes culture driving resilience. Innovation acts as a moderator, strengthening AI Practical implications suggests that should strategically ESGR, integrate prioritize engagement strengthen their commitment sustainability. These provide insight for decision-making seeking align with sustainable business practices. Originality/value It explores enhance providing broader understanding how manage stakeholders issues.

Язык: Английский

---

Energy in Smart Cities: Technological Trends and Prospects

Energies, Год журнала: 2024, Номер 17(24), С. 6439 - 6439

Опубликована: Дек. 20, 2024

Energy management in smart cities has gained particular significance the context of climate change and evolving geopolitical landscape. It become a key element sustainable urban development. In this context, energy plays central role facilitating growth cities. The aim article is to analyse existing scientific research related cities, identify technological trends, highlight prospective directions for future studies field. involves literature review based on analysis articles from Scopus Web Science databases evaluate concerning findings suggest that should focus development grids, storage, integration renewable sources, as well innovative technologies (e.g., Internet Things, 5G/6G, artificial intelligence, blockchain, digital twins). This emphasises can enhance efficiency contributing their recommended practical policy grids cornerstone adaptive underpinned by regulations encouraging collaboration between operators consumers. Municipal policies prioritise adoption advanced technologies, such IoT, AI, twins, storage systems, improve forecasting resource efficiency. Investments zero-emission buildings, renewable-powered public transport, green infrastructure are essential enhancing reducing emissions. Furthermore, community engagement awareness campaigns form an integral part promoting practices aligned with broader objectives.

Язык: Английский

---

Solar Irradiance Forecasting Using Temporal Fusion Transformers

International Journal of Energy Research, Год журнала: 2025, Номер 2025(1)

Опубликована: Янв. 1, 2025

Global climate change has intensified the search for renewable energy sources. Solar power is a cost‐effective option electricity generation. Accurate forecasting crucial efficient planning. While various techniques have been introduced forecasting, transformer‐based models are effective capturing long‐range dependencies in data. This study proposes N hours‐ahead solar irradiance framework based on variational mode decomposition (VMD) handling meteorological data and modified temporal fusion transformer (TFT) irradiance. The proposed model decomposes raw sequences into intrinsic functions (IMFs) using VMD optimizes TFT variable screening network gated recurrent unit (GRU)‐based encoder–decoder. Our specifically targets 1‐h as well different horizons resulting deep learning offers insights, including prioritization of subsequences an analysis window sizes. An empirical shows that our method achieved high performance compared to other time series models, such artificial neural (ANN), long short‐term memory (LSTM), CNN–LSTM, CNN–LSTM with attention (CNN–LSTM‐t), transformer, original model.

Язык: Английский

---

Advanced computing to support urban climate neutrality

Energy Sustainability and Society, Год журнала: 2025, Номер 15(1)

Опубликована: Март 11, 2025

Язык: Английский

---

Optimizing energy systems of livestock farms with computational intelligence for achieving energy autonomy

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Март 28, 2025

The relevance of the study is due to need increase energy autonomy livestock farms by introducing innovative solutions based on computational intelligence. Given significant consumption farms, as well reduced dependence traditional sources, there a optimise systems using renewable sources. aim research develop model for integrating intelligence achieve their autonomy. use models will allow farmers manage more efficiently, minimise carbon emissions, and overall stability supply. object including subject methods optimisation used resource management. paper develops optimising genetic algorithm that involves systematic implementation 5 steps. In contrast static models, proposed takes into account possibility dynamic adaptation structure supply system real production conditions. This done taking demand external factors such power grid failures weather multi-criteria approach simultaneously reduces CO₂ costs increases sustainability farms. in provides flexible parameter settings search an optimal solution context variable complex system. Based model, Python 3.10 program was created perform labour-intensive calculations According results testing at farm Volyn Nova LLC (Volyn region, Ukraine), it found optimised allows reducing emissions from 1263 kg/day 92.3 increasing Prospects further include other types development integration combined several

Язык: Английский

---

A Survey on Machine Learning Applications in Renewable Energies Forecasting

Power systems, Год журнала: 2024, Номер unknown, С. 305 - 326

Опубликована: Янв. 1, 2024

Язык: Английский

---

Harnessing Multidimensional Insights and Advanced Machine Learning for Optimized Energy Efficiency: Revolutionizing Sustainable Systems through Predictive Optimization, Ensemble Learning and IoT Integration for Enhanced Heating and Cooling Load Management

Опубликована: Май 4, 2024

Integrating Multidimensional Insights for Enhanced Feature Selection in Energy Transition Models presents a comprehensive approach to enhancing the energy efficiency of sustainable systems. The purpose this research is find categorical features that can be boosted with ensemble learning finding most relevant aspect generation. study leverages sophisticated machine techniques, including deep and methods, improve prediction optimization heating cooling loads systems using application Advanced Machine Learning Algorithms. In article, we are trying focus on critical consumption areas like cooling. These crucial aspects building consumption, study's emphasis these demonstrates an understanding key factors efficiency. This represents significant step forward applying design savings. It underscores potential transforming way designed operated better Understanding algorithms cross-domain optimization, such as integrating electric vehicles smart grid technologies, create synergies enhance overall holistic lead more savings by optimizing across multiple domains simultaneously. We also improving scalability generalization capabilities models ensure they effectively applied different types buildings geographic locations. involves developing adapt diverse conditions without retraining. enhances collaboration IoT Devices strengthening between (Internet Things) devices granularity precision management. provide detailed, real-time data, which, when analyzed advanced algorithms, nuanced effective energy-saving. model performing reasonably well, ability predict values correlate actual data. Y1 far predictive model's output, which could mean focusing feature improvements performance. accuracy our near 97% further scope XG boosting.

Язык: Английский

---

Data-driven economic predictive control for sustainable management of renewable energy systems

E3S Web of Conferences, Год журнала: 2024, Номер 501, С. 01005 - 01005

Опубликована: Янв. 1, 2024

The transition to renewable energy sources is driven by the need reduce greenhouse gas emissions, mitigate climate change, and enhance security. Renewable sources, such as solar, wind, hydropower, are inherently intermittent, making their integration into power grid complex. This paper emphasizes significance of predictive modelling for optimization it establishes connection between machine learning economic model control techniques realization sustainable management sources. Machine Learning based frameworks can assist providers in preparing fluctuating supplies predicting demand forecasting production capabilities plants. Moreover, combining smart designs with proposed technique ensure consumer satisfaction while adhering sustainability requirements.

Язык: Английский

---