Improved satellite-based intra-day solar forecasting with a chain of deep learning models

Energy Conversion and Management, Год журнала: 2024, Номер 313, С. 118598 - 118598

Опубликована: Май 30, 2024

Язык: Английский

---

AI-Driven precision in solar forecasting: Breakthroughs in machine learning and deep learning

AIMS Geosciences, Год журнала: 2024, Номер 10(4), С. 684 - 734

Опубликована: Янв. 1, 2024

<p>The need for accurate solar energy forecasting is paramount as the global push towards renewable intensifies. We aimed to provide a comprehensive analysis of latest advancements in forecasting, focusing on Machine Learning (ML) and Deep (DL) techniques. The novelty this review lies its detailed examination ML DL models, highlighting their ability handle complex nonlinear patterns Solar Irradiance (SI) data. systematically explored evolution from traditional empirical, including machine learning (ML), physical approaches these advanced delved into real-world applications, discussing economic policy implications. Additionally, we covered variety image-based, statistical, ML, DL, foundation, hybrid models. Our revealed that models significantly enhance accuracy, operational efficiency, grid reliability, contributing benefits supporting sustainable policies. By addressing challenges related data quality model interpretability, underscores importance continuous innovation techniques fully realize potential. findings suggest integrating with offers most promising path forward improving forecasting.</p>

Язык: Английский

---

Improving cross-site generalisability of vision-based solar forecasting models with physics-informed transfer learning

Energy Conversion and Management, Год журнала: 2024, Номер 309, С. 118398 - 118398

Опубликована: Апрель 17, 2024

Forecasting solar energy from cloud cover observations is crucial to truly anticipate future changes in power supply. On an intra-hour timescale, ground-level sky cameras located near a site offer the most valuable source of information on incoming clouds. In literature, analysis these hyperlocal for modelling increasingly performed by deep learning algorithms trained and tested years' worth local data. However, this approach not suitable industrial applications since producers cannot wait years data collection start generating reliable forecasts. they might own relevant multi-location collected other sites over time. This study thus explores capability such generalise beyond their training location two scarce conditions: zero-shot (i.e. direct application model new without fine-tuning) few-shot calibration pre-trained based very limited as day observations). Zero-shot results show that using clear-sky models normalise output variables (e.g. irradiance or production values) facilitates cross-dataset transfer learning. Compared previous methods, resulting forecast skill increases close 25% cloudy conditions more than 700% conditions. An additional gain observed when overcast weather are used via The corresponding neural networks achieve comparable performance expert These promising shed light potential large-scale image datasets improve generalisation skills forecasting algorithms.

Язык: Английский

---

A Review of Recent Hardware and Software Advances in GPU-Accelerated Edge-Computing Single-Board Computers (SBCs) for Computer Vision

Sensors, Год журнала: 2024, Номер 24(15), С. 4830 - 4830

Опубликована: Июль 25, 2024

Computer Vision (CV) has become increasingly important for Single-Board Computers (SBCs) due to their widespread deployment in addressing real-world problems. Specifically, the context of smart cities, there is an emerging trend developing end-to-end video analytics solutions designed address urban challenges such as traffic management, disaster response, and waste management. However, deploying CV on SBCs presents several pressing (e.g., limited computation power, inefficient energy real-time processing needs) hindering use at scale. Graphical Processing Units (GPUs) software-level developments have emerged recently these enable elevated performance SBCs; however, it still active area research. There a gap literature comprehensive review recent rapidly evolving advancements both software hardware fronts. The presented provides detailed overview existing GPU-accelerated edge-computing including algorithm optimization techniques, packages, development frameworks, specific packages. This subjective comparative analysis based critical factors help applied Artificial Intelligence (AI) researchers demonstrating state art selecting best suited combinations use-case. At end, paper also discusses potential limitations highlights future research directions this domain.

Язык: Английский

---

Extending intraday solar forecast horizons with deep generative models

Applied Energy, Год журнала: 2024, Номер 377, С. 124186 - 124186

Опубликована: Сен. 5, 2024

Язык: Английский

---

A graph attention network framework for generalized-horizon multi-plant solar power generation forecasting using heterogeneous data

Renewable Energy, Год журнала: 2025, Номер unknown, С. 122520 - 122520

Опубликована: Фев. 1, 2025

Язык: Английский

---

Synthesizing Images with Aligned Masks Using Text-to-Image Based Generative Ai for Robust Pv Segmentation

Опубликована: Янв. 1, 2025

Язык: Английский

---

Monthly and Quarter-Hourly Hydro Scheduling for Assessing Retrofit of Conventional to Reversible Turbines with Wind and PV Integration

Energy, Год журнала: 2025, Номер unknown, С. 135223 - 135223

Опубликована: Фев. 1, 2025

Язык: Английский

---

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

Опубликована: Март 3, 2025

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.

Язык: Английский

---

Application of Artificial Intelligence and Machine Learning in Assessing Solar Energy Potential

Опубликована: Март 21, 2025

Язык: Английский

---