Development of the smart photovoltaic system blind and its impact on net-zero energy solar buildings using technical-economic-political analyses

Koo, Choongwan; Hong, Taehoon; Jeong, Kwangbok; Ban, Cheolwoo; Oh, Jeongyoon

doi:10.1016/j.energy.2017.02.088

Cited by 61 publications

(13 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Solar energy is a new energy with zero emissions, pollutionfree and inexhaustible [1]. But, photovoltaic power generation is influenced by many variables, such as the local solar irradiance, wind speed, the density of the atmosphere, the temperature and the state of photovoltaic power generation systems, which would cause a high volatility and randomness eventually [2]- [4].…”

Section: Introductionmentioning

confidence: 99%

Ultra-Short-Term Photovoltaic Power Prediction Based on Self-Attention Mechanism and Multi-Task Learning

Sun

2020

IEEE Access

View full text Add to dashboard Cite

Due to the volatility and randomness of the photovoltaic power generation, it is difficult for traditional models to predict it accurately. To solve the problem, we established a model based on the selfattention mechanism and multi-task learning to predict the ultra-short-term photovoltaic power generation. First, we selected the data with the optimal timing length and input the data into the Encoder-Decoder network based on the self-attention. The validity of features extracted by the encoder was checked by the decoder. Then, we added a restriction to the middle layer of the Encoder-Decoder network to prevent the autoencoder from copying the input to the output mechanically. This condition is used to predict the photovoltaic power generation, so a multi-task learning model was established. Finally, to take full advantage of the features that are efficiently expressed and allow our main task, the prediction task, to learn some unique features autonomously, we proposed a step-by-step training method and have validated the effectiveness of this view in experiments. Through experimental contrast, it is found that compared with the Encoder-Decoder network based on CNN and LSTM, the performance of the proposed method has been increased by 14.82% and 8.09% respectively. The RMSE and MAE of the Encoder-Decoder model based on the self-attention mechanism using step-by-step training are 0.071 and 0.040 respectively. INDEX TERMS Energy, PV power prediction, self-attention mechanism, multi-task learning, autoencoder.

show abstract

Section: Introductionmentioning

confidence: 99%

Ultra-Short-Term Photovoltaic Power Prediction Based on Self-Attention Mechanism and Multi-Task Learning

Sun

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The development and utilization of renewable energy technologies is still of great significance [1], and photovoltaic power generation is currently one of the most promising renewable power generation technologies [2]. Because photovoltaic energy is easily available, pollution-free and inexhaustible, it has become the best substitute for industrial and residential power generation [3]. According to the 2020 report of the International Renewable Energy Agency, in the past 8 years, the global PV power generation cost has fallen by more than 70%, and the global installed capacity has reached 578.553 GW [4].…”

Section: Introductionmentioning

confidence: 99%

A Short-Term PV Power Forecasting Method Using a Hybrid Kmeans-GRA-SVR Model under Ideal Weather Condition

Lin¹,

Li²

2020

JCC

View full text Add to dashboard Cite

With the continuous increase of solar penetration rate, it has brought challenges to the smooth operation of the power grid. Therefore, to make photovoltaic power generation not affect the smooth operation of the grid, accurate photovoltaic power prediction is required. And short-term forecasting is essential for the deployment of daily power generation plans. In this paper, A short-term photovoltaic power generation forecast method based on K-means++, grey relational analysis (GRA) and support vector regression (SVR) (Hybrid Kmeans-GRA-SVR, HKGSVR) was proposed. The historical power data was clustered through the multi-index K-means++ algorithm. And the similar days and the nearest neighbor similar day of the prediction day were selected by the GRA algorithm. Then, similar days and nearest neighbor similar days were used to train SVR to obtain an accurate photovoltaic power prediction model. Under ideal weather, the average values of MAE, RMSE, and R 2 were 0.8101 kW, 0.9608 kW, and 99.66%, respectively. The average computation time was 1.7487 s, which was significantly better than the SVR model. Thus, the demonstrated numerical results verify the effectiveness of the proposed model for short-term PV power prediction.

show abstract

“…Traditional assessments of the values of buildings and real estate were carried out through economic or environmental assessments (Kim, Hong, and Koo 2012;Hong et al 2015;Koo, Hong, and Park 2016;Jeong et al 2018;Kim et al 2015aKim et al , 2015bKoo et al 2017;Jeong et al 2017;Ji et al 2016;Hong et al 2016;Park et al 2016;Kim et al 2016bKim et al , 2016aHong et al 2013). Due to the environmental issues, however, reducing a building's energy consumption and providing an improved IEQ are the two major issues that building professionals the world over are dealing with (Aglan, 2003;Hamilton M, Rackes A, Gurian PL, Waring MS 2016;Park and Yoon 2011;Varjo et al 2015;Cheong et al 2003;Ravindu et al 2015;Lan et al 2011;Xue, Mak, and Ai 2016;Jaggs and Palmer 2000;Zhang, Wargocki, and Lian 2016;Kajtár and Herczeg 2012;Chen and Hsiao 2015;Cheng et al 1995;Budd and Warhaft 1966;Sun and Zhu 2013;Mehler et al 2009;Haapalainen et al 2010;Carayon 1993;Fisk and Rosenfeld 1997;Worrell et al 2003).…”

Section: Introductionmentioning

confidence: 99%

Intelligent planning unit for the artificial intelligent based built environment focusing on human-building interaction

Kim

Hong

Hastak

et al. 2020

Journal of Asian Architecture and Building Engineering

Self Cite

View full text Add to dashboard Cite

The buildings' indoor condition called "indoor environmental quality (IEQ)" has become a major goal, all IEQ elements must be maintained within a certain range for the comfort and health of the occupants. To achieve this goal, the previous studies focused on building occupants' responses based on their activities and the changes in IEQ. Few studies, however, have comprehensively analyzed the above and reflected it in building design and operation. The study of this concept can be expressed as "human-building interaction management." This approach is a paradigm for the healthy, sustainable, and simultaneous management of people, IEQ, and buildings. This study conducted an in-depth literature review on the abovementioned studies. In addition, it ultimately proposed an intelligent planning unit (IPU), a new approach that can be used as a tool to apply the above human-building interaction concept to the practical design concept focusing on the planning phase. The IPU theory is designed to meet the customer expectations for the various objectives of a complex built environment. Eventually, it is expected that the proposed IPU concept will promote the spread of good health and environment-friendly buildings.

show abstract

Development of the smart photovoltaic system blind and its impact on net-zero energy solar buildings using technical-economic-political analyses

Cited by 61 publications

References 34 publications

Ultra-Short-Term Photovoltaic Power Prediction Based on Self-Attention Mechanism and Multi-Task Learning

Ultra-Short-Term Photovoltaic Power Prediction Based on Self-Attention Mechanism and Multi-Task Learning

A Short-Term PV Power Forecasting Method Using a Hybrid Kmeans-GRA-SVR Model under Ideal Weather Condition

Intelligent planning unit for the artificial intelligent based built environment focusing on human-building interaction

Contact Info

Product

Resources

About