Hourly day-ahead solar irradiance prediction using weather forecasts by LSTM

Qing, Xiangyun; Niu, Yugang

doi:10.1016/j.energy.2018.01.177

Cited by 759 publications

(317 citation statements)

References 16 publications

Supporting

Mentioning

309

Contrasting

Unclassified

Order By: Relevance

“…et al, 2015), etc. More closely related to our work, LSTMs have also been used for photovoltaic forecasting from weather data (Gensler et al, 2016), from historical photovoltaic power (Abdel-Nasser and Mahmoud, 2017) or for day-ahead solar irradiance prediction (Qing and Niu, 2018;Ogliari et al, 2018). Unlike stateless CNNs, LSTM networks contain loops which allow sequential states to be memorized.…”

Section: Lstm For Modeling Temporal Informationmentioning

confidence: 98%

“…Deep learning techniques have also been applied to the task of forecasting solar irradiance and/or power. For example, solar irradiance can be predicted on a per-hour, one-day ahead time horizon using deep learning (Qing and Niu, 2018;Ogliari et al, 2018). Future photovoltaic output can be predicted from historical photovoltaic power (Abdel-Nasser and Mahmoud, 2017), or from weather data (Gensler et al, 2016), using a time horizon of 1 hour.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Deep photovoltaic nowcasting

et al. 2018

View full text Add to dashboard Cite

Predicting the short-term power output of a photovoltaic panel is an important task for the efficient management of smart grids. Short-term forecasting at the minute scale, also known as nowcasting, can benefit from sky images captured by regular cameras and installed close to the solar panel. However, estimating the weather conditions from these images-sun intensity, cloud appearance and movement, etc.-is a very challenging task that the community has yet to solve with traditional computer vision techniques. In this work, we propose to learn the relationship between sky appearance and the future photovoltaic power output using deep learning. We train several variants of convolutional neural networks which take historical photovoltaic power values and sky images as input and estimate photovoltaic power in a very short term future. In particular, we compare three different architectures based on: a multi-layer perceptron (MLP), a convolutional neural network (CNN), and a long short term memory (LSTM) module. We evaluate our approach quantitatively on a dataset of photovoltaic power values and corresponding images gathered in Kyoto, Japan. Our experiments reveal that the MLP network, already used similarly in previous work, achieves an RMSE skill score of 7% over the commonly-used persistence baseline on the 1-minute future photovoltaic power prediction task. Our CNN-based network improves upon this with a 12% skill score. In contrast, our LSTM-based model, which can learn the temporal dependencies in the data, achieves a 21% RMSE skill score, thus outperforming all other approaches.

show abstract

Section: Lstm For Modeling Temporal Informationmentioning

confidence: 98%

Section: Related Workmentioning

confidence: 99%

Deep photovoltaic nowcasting

et al. 2018

View full text Add to dashboard Cite

show abstract

“…Sequence prediction is the problem of using information embedded in a series of times steps to predict a certain output [8]. In recent years, researchers applied LSTM to classic time-series problems such as stock, weather forecasting and machine translation [9][10][11]. They often outperform traditional machine learning models such as FNN in these tasks.…”

Section: Long Short-term Memory Networkmentioning

confidence: 99%

Partial discharge detection on aerial covered conductors using time-series decomposition and long short-term memory network

Dong¹,

Sun²

2020

Electric Power Systems Research

View full text Add to dashboard Cite

Nowadays, aerial covered conductors (CC) are increasingly used in many places of the world due to their higher operational reliability, reduced construction space and effective protection for wildlife animals. In spite of these advantages, a major challenge of using CC is that the ordinary upstream protection devices are not able to detect the phase-to-ground faults and the frequent tree/tree branch hitting conductor events on such conductors. This is because these events only lead to partial discharge (PD) activities rather than overcurrent signatures typically seen on bare conductors. To solve this problem, in recent years, ENET Centre in Czech Republic (ENET) devised a simple meter to measure the voltage signal of the electric stray field along CC, aiming to detect the above hazardous PD activities. In 2018, ENET shared a large amount of waveform data recorded by their meter on Kaggle, the world's largest data science collaboration platform, encouraging worldwide experts to develop an effective pattern recognition method for the acquired signals.For this challenge, we developed a unique method based on time-series decomposition and Long Short-Term Memory Network (LSTM) in addition to unique feature engineering process to recognize PD activities on aerial covered conductors. The proposed method is tested on the ENET public dataset and compared to various traditional classification methods. It demonstrated superior performance and great practicality.

show abstract

“…Many researchers have conducted many methods of study by using solar radiation parameters such as Global Horizontal Irradiance (GHI), Direct Normal Irradiance (DNI) and Diffuse Irradiance (DIF) to analyze the PV power generation. Xiangyun Qing et al (2018) [6] using Long Short-Term Memory (LSTM) compared to backpropagation neural networks (BPNN), linear regression (LR), and persistence algorithm for one day of the rain season on August 20, 2013, in the island of Santiago, Cape Verde. This study found that the LSTM algorithm error is smallest compared to the other three algorithms.…”

Section: Introductionmentioning

confidence: 99%

Performance comparison of solar radiation forecasting between WRF and LSTM in Gifu, Japan

Araujo

2020

Environ. Res. Commun.

View full text Add to dashboard Cite

Three months comparison of hourly solar radiation forecasting from 1st January to 31st March 2017 between Weather Research and Forecasting (WRF) mesoscale model and Long short-term memory (LSTM) algorithm is presented in this study. One-way grid nesting technique of the WRF model is applied for the simulation with a six-hourly input dataset downloaded from the National Oceanic and Atmospheric Administration -National Operational Model Archive and Distribution System (NOMADS) website. Three years'data of solar radiation from 1st January 2014 to 31st December 2016 are used as input data for Long Short Term Memory (LSTM) algorithm to simulate solar radiation. The results show the root mean square error of the LSTM algorithm is 310 W m −2 higher compared to 210 W m −2 from the WRF model. The MBE and the nMBE of the WRF model are obtained positive value 96 W m −2 and 9% compared to −101 W m −2 and −9% of LSTM for 2160 h prediction. Meanwhile, the performance error percentage of WRF is 19% lower compared to 28% of LSTM for the nRMSE error metric. Although this study found that the WRF model performed better and lower error compared to the LSTM algorithm, however, it also recommends the LSTM algorithm configuration can be used for long-term prediction.

show abstract

Hourly day-ahead solar irradiance prediction using weather forecasts by LSTM

Cited by 759 publications

References 16 publications

Deep photovoltaic nowcasting

Deep photovoltaic nowcasting

Partial discharge detection on aerial covered conductors using time-series decomposition and long short-term memory network

Performance comparison of solar radiation forecasting between WRF and LSTM in Gifu, Japan

Contact Info

Product

Resources

About