Energetics Systems and artificial intelligence: Applications of industry 4.0

Energy Reports, Год журнала: 2021, Номер 8, С. 334 - 361

Опубликована: Дек. 16, 2021

Industrial development with the growth, strengthening, stability, technical advancement, reliability, selection, and dynamic response of power system is essential. Governments companies invest billions dollars in technologies to convert, harvest, rising demand, changing demand supply patterns, efficiency, lack analytics required for optimal energy planning, store energy. In this scenario, artificial intelligence (AI) starting play a major role market. Recognizing importance AI, study was conducted on seven different energetics systems their variety applications, including: i) electricity production; ii) delivery; iii) electric distribution networks; iv) storage; v) saving, new materials, devices; vi) efficiency nanotechnology; vii) policy, economics. The main drivers are four key techniques used current AI technologies, fuzzy logic systems; neural genetic algorithms; expert systems. developed countries, industry has started using connect smart meters, grids, Internet Things devices. These will lead improvement management, transparency, usage renewable energies. recent decades/years, technology brought significant improvements how devices monitor data, communicate system, analyze input–output, display data unprecedented ways. New applications become feasible when these developments incorporated into industry. But contrary, much more investment needed global research data-driven models. terms supply, can help utilities provide customers affordable from complex sources secure manner, while at same time providing opportunity use own efficiently. Moreover, policy recommendations, opportunities, 4.0 improve sustainability have been briefly described.

Язык: Английский

---

Improved solar photovoltaic energy generation forecast using deep learning-based ensemble stacking approach

Energy, Год журнала: 2021, Номер 240, С. 122812 - 122812

Опубликована: Дек. 4, 2021

An accurate solar energy forecast is of utmost importance to allow a higher level integration renewable into the controls existing electricity grid. With availability data in unprecedented granularities, there an opportunity use data-driven algorithms for improved prediction generation. In this paper, generally applicable stacked ensemble algorithm (DSE-XGB) proposed utilizing two deep learning namely artificial neural network (ANN) and long short-term memory (LSTM) as base models forecast. The predictions from are integrated using extreme gradient boosting enhance accuracy PV generation model was evaluated on four different datasets provide comprehensive assessment. Additionally, shapely additive explanation framework utilized study deeper insight mechanism algorithm. performance by comparing results with individual ANN, LSTM, Bagging. DSE-XGB method exhibits best combination consistency stability case studies irrespective weather variations demonstrates improvement R2 value 10%–12% other models.

Язык: Английский

---

A review and taxonomy of wind and solar energy forecasting methods based on deep learning

Energy and AI, Год журнала: 2021, Номер 4, С. 100060 - 100060

Опубликована: Март 7, 2021

Renewable energy is essential for planet sustainability. output forecasting has a significant impact on making decisions related to operating and managing power systems. Accurate prediction of renewable vital ensure grid reliability permanency reduce the risk cost market Deep learning's recent success in many applications attracted researchers this field its promising potential manifested richness proposed methods increasing number publications. To facilitate further research development area, paper provides review deep learning-based solar wind published during last five years discussing extensively data datasets used reviewed works, pre-processing methods, deterministic probabilistic evaluation comparison methods. The core characteristics all works are summarised tabular forms enable methodological comparisons. current challenges future directions given. trends show that hybrid models most followed by Recurrent Neural Network including Long Short-Term Memory Gated Unit, third place Convolutional Networks. We also find multistep ahead gaining more attention. Moreover, we devise broad taxonomy using key insights gained from extensive review, believe will be understanding cutting-edge accelerating innovation field.

Язык: Английский

---

Photovoltaic Power Forecasting With a Hybrid Deep Learning Approach

IEEE Access, Год журнала: 2020, Номер 8, С. 175871 - 175880

Опубликована: Янв. 1, 2020

Solar energy is the key to clean energy, which can generate large amounts of electricity for future smart grid. Unfortunately, randomness and intermittency solar resources bring difficulties stable operation management power systems. To reduce negative impact photovoltaic (PV) plants accessing on systems, it great significant predict PV accurately. In light this, we propose a hybrid deep learning approach based convolutional neural network (CNN) long-short term memory recurrent (LSTM) output forecasting. The CNN model leveraged discover nonlinear features invariant structures exhibited in previous data, thereby facilitating prediction power. LSTM used temporal changes latest next time step. Then, results two models are comprehensively considered obtain expected proposed extensively evaluated real data Limberg, Belgium, numerical demonstrate that provide good performance

Язык: Английский

---

Machine learning for site-adaptation and solar radiation forecasting

Renewable Energy, Год журнала: 2020, Номер 167, С. 333 - 342

Опубликована: Ноя. 20, 2020

Язык: Английский

---

Artificial intelligence-based solutions for climate change: a review

Environmental Chemistry Letters, Год журнала: 2023, Номер 21(5), С. 2525 - 2557

Опубликована: Июнь 13, 2023

Abstract Climate change is a major threat already causing system damage to urban and natural systems, inducing global economic losses of over $500 billion. These issues may be partly solved by artificial intelligence because integrates internet resources make prompt suggestions based on accurate climate predictions. Here we review recent research applications in mitigating the adverse effects change, with focus energy efficiency, carbon sequestration storage, weather renewable forecasting, grid management, building design, transportation, precision agriculture, industrial processes, reducing deforestation, resilient cities. We found that enhancing efficiency can significantly contribute impact change. Smart manufacturing reduce consumption, waste, emissions 30–50% and, particular, consumption buildings 30–50%. About 70% gas industry utilizes technologies enhance accuracy reliability forecasts. Combining smart grids optimize power thereby electricity bills 10–20%. Intelligent transportation systems dioxide approximately 60%. Moreover, management design cities through application further promote sustainability.

Язык: Английский

---

Time series forecasting for hourly photovoltaic power using conditional generative adversarial network and Bi-LSTM

Energy, Год журнала: 2022, Номер 246, С. 123403 - 123403

Опубликована: Фев. 8, 2022

Язык: Английский

---

DMPPT Control of Photovoltaic Microgrid Based on Improved Sparrow Search Algorithm

IEEE Access, Год журнала: 2021, Номер 9, С. 16623 - 16629

Опубликована: Янв. 1, 2021

There are some problems in the photovoltaic microgrid system due to solar irradiance-change environment, such as power fluctuation, which leads larger imbalance and affects stable operation of microgrid. Aiming at mismatch loss under partial shading systems, this paper proposed a distributed maximum point tracking (DMPPT) approach based on an improved sparrow search algorithm (ISSA). First, used center gravity reverse learning mechanism initialize population, so that population has better spatial solution distribution; Secondly, coefficient was introduced location update part discoverer improve global ability algorithm; Simultaneously mutation operator position joiner avoid falling into local extreme value. The results model Matlab showed ISSA can track point(MPP) more accurately quickly than perturbation observation method (P&O) particle swarm optimization (PSO) algorithm, had good steady-state performance.

Язык: Английский

---

Forecasting and uncertainty analysis of day-ahead photovoltaic power using a novel forecasting method

Applied Energy, Год журнала: 2021, Номер 299, С. 117291 - 117291

Опубликована: Июнь 24, 2021

Язык: Английский

---

Emerging artificial intelligence in piezoelectric and triboelectric nanogenerators

Nano Energy, Год журнала: 2021, Номер 88, С. 106227 - 106227

Опубликована: Июнь 9, 2021

Piezoelectric nanogenerators (PENG) and triboelectric (TENG) have opened an exciting venue to sustainably harvest electrical energy from the environments, which led multifunctional applications in different fields. More recently, a paradigm shift has directed emerging artificial intelligence (AI) PENG TENG, aiming address challenges of analysis, design, fabrication, application. AI-PENG AI-TENG are envisioned enhance optimize mechanical-to-electrical performance favorable behavior. However, overview on topic not yet been exploited literature. In this review article, we showcase recent progress TENG discuss future trends AI-enhanced with desirable performance, i.e., using AI-enabled design models as viable tool predict, structures materials TENG. This topical explains why extensively considered one promising solutions especially suitable for certain engineering life science, how surpass limitations by AI-based structural material discovery, what technological avenues that may provide green innovations.

Язык: Английский

---