Solar photovoltaic generation forecasting methods: A review

Sobri, Sobrina; Koohi-Kamali, Sam; Rahim, Nasrudin Abd

doi:10.1016/j.enconman.2017.11.019

Cited by 693 publications

(318 citation statements)

References 106 publications

Supporting

Mentioning

268

Contrasting

Unclassified

Order By: Relevance

“…The two main approaches for solar energy forecasting are dubbed the physical (or parametric) and data-driven methods. Physical models highly depend on numerical weather predictions (NWP), such as temperature and wind predictions, which are not typically suitable for very short term forecasting (Antonanzas et al, 2016;Sobri et al, 2018). On the contrary, data-driven methods have been widely used as "black/gray-box" models for short term solar energy forecasting by learning the relationship between historical data and solar energy production.…”

Section: Related Workmentioning

confidence: 99%

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: Related Workmentioning

confidence: 99%

Deep photovoltaic nowcasting

et al. 2018

View full text Add to dashboard Cite

show abstract

“…The four popular kernel functions are linear, polynomial, radial basis function (RBF), and sigmoid functions. Among them, the RBF function shows a better performance in many nonlinear cases because of its computational effectiveness, convenience, reliability, ease of adaptation to optimize other adaptive techniques, and adaptability in handing complex parameters . The definition of the RBF kernel function is as follows:

K (x_{i}, x_{j}) = e^{- γ {false| |x_{i} - x_{j}| false|}^{2}}

where γ > 0 is called a kernel parameter.…”

Section: Methodsmentioning

confidence: 99%

“…Among them, the RBF function shows a better performance in many nonlinear cases because of its computational effectiveness, convenience, reliability, ease of adaptation to optimize other adaptive techniques, and adaptability in handing complex parameters. 32 The definition of the RBF kernel function is as follows:…”

Section: Mathematical Methodologymentioning

confidence: 99%

Predictive control based on occupant behavior prediction for domestic hot water system using data mining algorithm

Cao

Hou

et al. 2019

Energy Science & Engineering

View full text Add to dashboard Cite

Domestic hot water systems are a primary source of energy consumption in buildings, and present a promising future in terms of energy saving. Predictive control methods have been used to reduce energy consumption during an operation period. However, current methods lack consideration of occupant behavior, which significantly influences the prediction results. In this study, a data‐based predictive method is proposed to predict the shower behavior of occupants. A dataset was collected from seven occupants and was trained using support vector machine (SVM) to learn their showering habits. These results were used to predict the hot water demand. A comparative analysis shows that, in this way, the prediction results are more reliable under predictive control than predicting the hot water demand directly using SVM. A simulation of a domestic hot water system was then conducted. The results indicate that the proposed approach can reduce the heat loss from a hot water storage tank (ST) by up to 33% compared to a traditional control method, while maintaining a high assurance of the hot water supply (an insufficient hot water supply of less than 1%) with little change to the original system.

show abstract

“…Results also showed the effect of spatial and temporal profiles of input variable on model performance. Sobri et al compared different solar forecasting methods in terms of different performance parameters. The author categorized the forecasting techniques in three main classes including time series–based statistical methods, physical methods, and ANN‐based ensemble techniques.…”

Section: Solar Forecastingmentioning

confidence: 99%

A review on solar forecasting and power management approaches for energy‐harvesting wireless sensor networks

Kakkar

2020

Int J Communication

View full text Add to dashboard Cite

Summary For rechargeable wireless sensor nodes, effective power management is of prime importance because of the stochastic behaviour of the environmental resources. A key issue in integrating solar resources with wireless sensor networks (WSNs) is the need of precise irradiance measurements and power to resource modelling. WSNs are employed in an adhoc manner comprises of numerous sensing nodes and organised as a network for the sake of checking and balancing the environmental factors. Each node has sensing, computation, communication, and locomotion capabilities but operates with limited battery life. Energy harvesting is a way of powering these WSNs by harvesting energy from the environment. By considering harvested energy as an energy source, certain considerations are different from that of battery‐operated networks. Nondeterministic energy availability with respect to time is the reason behind these differences, which put a limit on the maximum rate at which energy can be used. Thus, reliable knowledge of solar radiation is essential for informed design, deployment planning, and optimal management of energy in rechargeable WSNs. Further, power management is essential in self‐powerssed networks to efficiently utilize the available energy. In this paper, a detailed survey on different solar forecasting techniques has been presented for precise energy estimates. A detailed study on energy efficient power management techniques is also proposed to address the feasibility of energy‐harvesting approach in WSNs.

show abstract

Solar photovoltaic generation forecasting methods: A review

Cited by 693 publications

References 106 publications

Deep photovoltaic nowcasting

Deep photovoltaic nowcasting

Predictive control based on occupant behavior prediction for domestic hot water system using data mining algorithm

A review on solar forecasting and power management approaches for energy‐harvesting wireless sensor networks

Contact Info

Product

Resources

About