An Integrated Missing-Data Tolerant Model for Probabilistic PV Power Generation Forecasting DOI
Qiaoqiao Li, Yan Xu, Benjamin Si Hao Chew

и другие.

IEEE Transactions on Power Systems, Год журнала: 2022, Номер 37(6), С. 4447 - 4459

Опубликована: Янв. 31, 2022

Accurate solar photovoltaic (PV) generation forecast is critical to the reliable and economic operation of a modern power system. In practice, due various faulty issues in sensor, communication, or database system, historical online measurement data may not be always complete, missing could dramatically degrade forecasting model's accuracy. To solve this problem, paper proposes an integrated missing-data tolerant model for probabilistic PV forecasting. Taking generations as input, based on recursive long short-term memory network (Rec-LSTM), which can provide multi-step ahead probability distribution generation. The unobserved input will imputed recursively output at previous time step. During training process, imputations values are iteratively updated by negative log-likelihood loss function. As salient advantage, method deal with scenarios both offline stages. Numerical experiments conducted two one-year datasets from Australia Singapore, respectively. Probabilistic large-scale small-scale building-level tested resolution 15 mins. Testing results show proposed achieve superior prediction accuracy well strong robustness under scenarios, compared other state-of-the-art methods.

Язык: Английский

Forecasting: theory and practice DOI Creative Commons
Fotios Petropoulos, Daniele Apiletti,

Vassilios Assimakopoulos

и другие.

International Journal of Forecasting, Год журнала: 2022, Номер 38(3), С. 705 - 871

Опубликована: Янв. 20, 2022

Forecasting has always been at the forefront of decision making and planning. The uncertainty that surrounds future is both exciting challenging, with individuals organisations seeking to minimise risks maximise utilities. large number forecasting applications calls for a diverse set methods tackle real-life challenges. This article provides non-systematic review theory practice forecasting. We provide an overview wide range theoretical, state-of-the-art models, methods, principles, approaches prepare, produce, organise, evaluate forecasts. then demonstrate how such theoretical concepts are applied in variety contexts. do not claim this exhaustive list applications. However, we wish our encyclopedic presentation will offer point reference rich work undertaken over last decades, some key insights practice. Given its nature, intended mode reading non-linear. cross-references allow readers navigate through various topics. complement covered by lists free or open-source software implementations publicly-available databases.

Язык: Английский

Процитировано

560
Deep learning neural networks for short-term photovoltaic power forecasting DOI
A. Mellit, Alessandro Pavan, Vanni Lughi

и другие.

Renewable Energy, Год журнала: 2021, Номер 172, С. 276 - 288

Опубликована: Март 6, 2021

Язык: Английский

Процитировано

241
A review and taxonomy of wind and solar energy forecasting methods based on deep learning DOI Creative Commons
Ghadah Alkhayat, Rashid Mehmood

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

Процитировано

205
A Survey of Machine Learning Models in Renewable Energy Predictions DOI Creative Commons
Jung-Pin Lai, Yu-Ming Chang,

Chieh-Huang Chen

и другие.

Applied Sciences, Год журнала: 2020, Номер 10(17), С. 5975 - 5975

Опубликована: Авг. 28, 2020

The use of renewable energy to reduce the effects climate change and global warming has become an increasing trend. In order improve prediction ability energy, various techniques have been developed. aims this review are illustrated as follows. First, survey attempts provide a analysis machine-learning models in renewable-energy predictions. Secondly, study depicts procedures, including data pre-processing techniques, parameter selection algorithms, performance measurements, used for Thirdly, sources values mean absolute percentage error, coefficient determination were conducted. Finally, some possible potential opportunities future work provided at end survey.

Язык: Английский

Процитировано

155
Deep Learning in Smart Grid Technology: A Review of Recent Advancements and Future Prospects DOI Creative Commons
Mohamed Massaoudi, Haitham Abu‐Rub, Shady S. Refaat

и другие.

IEEE Access, Год журнала: 2021, Номер 9, С. 54558 - 54578

Опубликована: Янв. 1, 2021

The current electric power system witnesses a significant transition into Smart Grids (SG) as promising landscape for high grid reliability and efficient energy management. This ongoing undergoes rapid changes, requiring plethora of advanced methodologies to process the big data generated by various units. In this context, SG stands tied very closely Deep Learning (DL) an emerging technology creating more decentralized intelligent paradigm while integrating intelligence in supervisory operational decision-making. Motivated outstanding success DL-based prediction methods, article attempts provide thorough review from broad perspective on state-of-the-art advances DL systems. Firstly, bibliometric analysis has been conducted categorize review's methodology. Further, we taxonomically delve mechanism behind some trending algorithms. We then showcase enabling technologies SG, such federated learning, edge intelligence, distributed computing. Finally, challenges research frontiers are provided serve guidelines future work futuristic domain. study's core objective is foster synergy between these two fields decision-makers researchers accelerate DL's practical deployment

Язык: Английский

Процитировано

133
Solar Photovoltaic Power Forecasting: A Review DOI Open Access

Kelachukwu J. Iheanetu

Sustainability, Год журнала: 2022, Номер 14(24), С. 17005 - 17005

Опубликована: Дек. 19, 2022

The recent global warming effect has brought into focus different solutions for combating climate change. generation of climate-friendly renewable energy alternatives been vastly improved and commercialized power generation. As a result this industrial revolution, solar photovoltaic (PV) systems have drawn much attention as source varying applications, including the main utility-grid supply. There tremendous growth in both on- off-grid PV installations last few years. This trend is expected to continue over next years government legislation awareness campaigns increase encourage shift toward using alternatives. Despite numerous advantages generation, highly variable nature sun’s irradiance seasons various geopolitical areas/regions can significantly affect yield. variation directly impacts profitability or economic viability system, cannot be neglected. To overcome challenge, procedures applied forecast generated energy. study provides comprehensive systematic review advances forecasting techniques with on data-driven procedures. It critically analyzes studies highlight strengths weaknesses models implemented. clarity provided will form basis higher accuracy future applications.

Язык: Английский

Процитировано

93
Accurate solar PV power prediction interval method based on frequency-domain decomposition and LSTM model DOI
Lining Wang, Mingxuan Mao,

Jili Xie

и другие.

Energy, Год журнала: 2022, Номер 262, С. 125592 - 125592

Опубликована: Сен. 30, 2022

Язык: Английский

Процитировано

86
Trends and gaps in photovoltaic power forecasting with machine learning DOI Creative Commons
Alba Alcañiz, Daniel Grzebyk, Hesan Ziar

и другие.

Energy Reports, Год журнала: 2022, Номер 9, С. 447 - 471

Опубликована: Дек. 10, 2022

The share of solar energy in the electricity mix increases year after year. Knowing production photovoltaic (PV) power at each instant time is crucial for its integration into grid. However, due to meteorological phenomena, PV output can be uncertain and continuously varying, which complicates yield prediction. In recent years, machine learning (ML) techniques have entered world forecasting help increase accuracy predictions. Researchers seen great potential this approach, creating a vast literature on topic. This paper intends identify most popular approaches gaps discipline. To do so, representative part consisting 100 publications classified based different aspects such as ML family, location systems, number systems considered, features, etc. Via classification, main trends highlighted while offering advice researchers interested

Язык: Английский

Процитировано

76
A comprehensive review on sustainable energy management systems for optimal operation of future-generation of solar microgrids DOI
Salwan Tajjour, Shyam Singh Chandel

Sustainable Energy Technologies and Assessments, Год журнала: 2023, Номер 58, С. 103377 - 103377

Опубликована: Июль 22, 2023

Язык: Английский

Процитировано

69
ARIMA Models in Solar Radiation Forecasting in Different Geographic Locations DOI Creative Commons
Ewa Chodakowska, Joanicjusz Nazarko, Łukasz Nazarko

и другие.

Energies, Год журнала: 2023, Номер 16(13), С. 5029 - 5029

Опубликована: Июнь 28, 2023

The increasing demand for clean energy and the global shift towards renewable sources necessitate reliable solar radiation forecasting effective integration of into system. Reliable has become crucial design, planning, operational management systems, especially in context ambitious greenhouse gas emission goals. This paper presents a study on application auto-regressive integrated moving average (ARIMA) models seasonal different climatic conditions. performance prediction capacity ARIMA are evaluated using data from Jordan Poland. essence modeling analysis use both as reference model evaluating other approaches basic generation presented. current state source utilization selected countries adopted transition strategies to more sustainable system investigated. two time series (for monthly hourly data) built locations forecast is developed. research findings demonstrate that suitable can contribute stable long-term countries’ systems. However, it develop location-specific due variability characteristics. provides insights highlights their potential supporting planning operation

Язык: Английский

Процитировано

51