Ensemble of machine learning and spatiotemporal parameters to forecast very short-term solar irradiation to compute photovoltaic generators’ output power
TL;DR: The results indicate that the developed forecaster can be integrated into photovoltaic generators’ to predict their output power, thus promoting their inclusion in the main power network.
About: This article is published in Energy.The article was published on 2021-08-15. It has received 26 citations till now. The article focuses on the topics: Photovoltaic system.
Citations
More filters
TL;DR: A new model for predicting photovoltaic generators' output power confidence interval 10 min ahead is developed, based on deep learning, mathematical probability density functions and meteorological parameters, which has been validated with a real data series collected from Spanish meteorological stations.
21 citations
TL;DR: In this article , a wavelet based time-frequency analysis of the used data with deep learning neural networks to forecast solar irradiation, in next 10 min, to compute solar photovoltaic generation.
17 citations
TL;DR: In this paper , the authors developed a new model for predicting photovoltaic generators' output power confidence interval 10 min ahead, based on deep learning, mathematical probability density functions and meteorological parameters.
16 citations
TL;DR: A heterogeneous ensemble dynamic selection model, named HetDS, to forecast solar irradiance with an overall accuracy that is superior to the single models in terms of five well-known error metrics is proposed.
Abstract: Solar irradiance forecasting has been an essential topic in renewable energy generation. Forecasting is an important task because it can improve the planning and operation of photovoltaic systems, resulting in economic advantages. Traditionally, single models are employed in this task. However, issues regarding the selection of an inappropriate model, misspecification, or the presence of random fluctuations in the solar irradiance series can result in this approach underperforming. This paper proposes a heterogeneous ensemble dynamic selection model, named HetDS, to forecast solar irradiance. For each unseen test pattern, HetDS chooses the most suitable forecasting model based on a pool of seven well-known literature methods: ARIMA, support vector regression (SVR), multilayer perceptron neural network (MLP), extreme learning machine (ELM), deep belief network (DBN), random forest (RF), and gradient boosting (GB). The experimental evaluation was performed with four data sets of hourly solar irradiance measurements in Brazil. The proposed model attained an overall accuracy that is superior to the single models in terms of five well-known error metrics.
14 citations
References
More filters
Book•
[...]
TL;DR: Deep learning as mentioned in this paper is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts, and it is used in many applications such as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames.
Abstract: Deep learning is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts. Because the computer gathers knowledge from experience, there is no need for a human computer operator to formally specify all the knowledge that the computer needs. The hierarchy of concepts allows the computer to learn complicated concepts by building them out of simpler ones; a graph of these hierarchies would be many layers deep. This book introduces a broad range of topics in deep learning. The text offers mathematical and conceptual background, covering relevant concepts in linear algebra, probability theory and information theory, numerical computation, and machine learning. It describes deep learning techniques used by practitioners in industry, including deep feedforward networks, regularization, optimization algorithms, convolutional networks, sequence modeling, and practical methodology; and it surveys such applications as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames. Finally, the book offers research perspectives, covering such theoretical topics as linear factor models, autoencoders, representation learning, structured probabilistic models, Monte Carlo methods, the partition function, approximate inference, and deep generative models. Deep Learning can be used by undergraduate or graduate students planning careers in either industry or research, and by software engineers who want to begin using deep learning in their products or platforms. A website offers supplementary material for both readers and instructors.
38,208 citations
TL;DR: In this paper, a multilayer perceptron (MLP) model was proposed to forecast the solar irradiance on a base of 24h using the present values of the mean daily solar irradiances and air temperature.
749 citations
TL;DR: A novel solar prediction scheme for hourly day-ahead solar irradiance prediction by using the weather forecasting data is proposed and it is demonstrated that the proposed algorithm outperforms these competitive algorithms for single output prediction.
568 citations
TL;DR: In this paper, the authors used regressions in logs, Autoregressive Integrated Moving Average (ARIMA), and Unobserved Components models to forecast radiation over short time horizons.
559 citations
TL;DR: In this article, a comprehensive research about the combined models is called on for how these models are constructed and affect the forecasting performance, and an up-to-date annotated bibliography of the wind forecasting literature is presented.
Abstract: With the continuous increase of wind power penetration in power systems, the problems caused by the volatile nature of wind speed and its occurrence in the system operations such as scheduling and dispatching have drawn attention of system operators, utilities and researchers towards the state-of-the-art wind speed and power forecasting methods These methods have the required capability of reducing the influence of the intermittent wind power on system operations as well as of harvesting the wind energy effectively In this context, combining different methodologies in order to circumvent the challenging model selection and take advantage of the unique strength of plausible models have recently emerged as a promising research area Therefore, a comprehensive research about the combined models is called on for how these models are constructed and affect the forecasting performance Aiming to fill the mentioned research gap, this paper outlines the combined forecasting approaches and presents an up-to date annotated bibliography of the wind forecasting literature Furthermore, the paper also points out the possible further research directions of combined techniques so as to help the researchers in the field develop more effective wind speed and power forecasting methods
514 citations