scholarly journals Gated Recurrent Unit Network-Based Short-Term Photovoltaic Forecasting

Energies ◽  
2018 ◽  
Vol 11 (8) ◽  
pp. 2163 ◽  
Author(s):  
Yusen Wang ◽  
Wenlong Liao ◽  
Yuqing Chang
Keyword(s):  
Power Output ◽  
Short Term ◽  
Network Training ◽  
Photovoltaic Power ◽  
Novel Approach ◽  
Pearson Coefficient ◽  
The Future ◽  
The Relationship ◽  
Gated Recurrent Unit

Photovoltaic power has great volatility and intermittency due to environmental factors. Forecasting photovoltaic power is of great significance to ensure the safe and economical operation of distribution network. This paper proposes a novel approach to forecast short-term photovoltaic power based on a gated recurrent unit (GRU) network. Firstly, the Pearson coefficient is used to extract the main features that affect photovoltaic power output at the next moment, and qualitatively analyze the relationship between the historical photovoltaic power and the future photovoltaic power output. Secondly, the K-means method is utilized to divide training sets into several groups based on the similarities of each feature, and then GRU network training is applied to each group. The output of each GRU network is averaged to obtain the photovoltaic power output at the next moment. The case study shows that the proposed approach can effectively consider the influence of features and historical photovoltaic power on the future photovoltaic power output, and has higher accuracy than the traditional methods.

Gentrifiers Against Gentrification

2020 ◽  
pp. 1-23
Author(s):  
Jorge André Guerreiro ◽  
João Filipe Marques
Keyword(s):  
Mixed Methods ◽  
Mixed Methods Research ◽  
Fishing Industry ◽  
Short Term ◽  
Industrial City ◽  
The Future ◽  
Historic Centre ◽  
South Portugal ◽  
The City

This chapter presents a case-study of tourism gentrification in a fishing town in Algarve, South Portugal. Olhão is a former industrial city that saw much of its fishing industry disappear since the 1980s. Over the last few years, hundreds of foreigners have moved into its historic centre. This rapid influx of citizens to derelict neighbours mostly comprised of old retirees and few active fishermen prompted a gentrification process. Olhão now faces the threat of mass displacements of its older and most vulnerable citizens, a fact that is worrying the foreigners that criticize the touristification of the city, with rents at historical highs and landlords forcing out the Portuguese residents in order to promote short-term rentals to tourists. The chapter presents the results obtained from an extensive mixed-methods research, ending with some notes about the future of the city and the implications that can be taken from this case.

Short-term photovoltaic power generation forecasting based on random forest feature selection and CEEMD: A case study

2020 ◽  
Vol 93 ◽  
pp. 106389 ◽  
Author(s):  
Dongxiao Niu ◽  
Keke Wang ◽  
Lijie Sun ◽  
Jing Wu ◽  
Xiaomin Xu
Keyword(s):  
Power Generation ◽  
Feature Selection ◽  
Random Forest ◽  
Short Term ◽  
Photovoltaic Power

scholarly journals Learning from Differences

2018 ◽  
Vol 2 (4) ◽  
pp. 21-36 ◽  
Author(s):  
Virginija Bortkeviciene ◽  
Hermina Gunnthorsdottir ◽  
Karin Hjaelmeskog ◽  
Ilze Ivanova ◽  
Katriina Maaranen ◽  
...  
Keyword(s):  
Nordic Countries ◽  
Short Term ◽  
The Future ◽  
Social Pedagogue ◽  
Intensive Course ◽  
Future Work

This paper presents a case study of an intensive international course aimed at pre-service teachers and having a focus on inclusion. The course was funded by Nordplus. Twenty-three students from six Baltic and Nordic countries were interviewed during and after the course on their views on professionalism and their future work as teachers. The results show that the students’ understanding of professionalism was multifaceted, and they had gained several experiences of professionalism during the course. One of the main results of this study is, in our opinion, the co-operation and the opportunities the intensive course afforded the students in developing skills to work together with different people, to appreciate difference and to learn from others. In other words, to become more open-minded. This allows us to conclude that students can be trained to consider the importance and understanding of knowledge and its use for now and in the future. Thus, providing such short-term international opportunities is an important part of studying and becoming a teacher or social pedagogue for the globalized future.  

Maximum leg force and power output during short-term dynamic exercise

1981 ◽  
Vol 51 (5) ◽  
pp. 1175-1182 ◽  
Author(s):  
A. J. Sargeant ◽  
E. Hoinville ◽  
A. Young
Keyword(s):  
Power Output ◽  
Maximum Level ◽  
Bicycle Ergometer ◽  
Peak Force ◽  
Short Term ◽  
Mean Power ◽  
Mechanical Power Output ◽  
Rate Of Decline ◽  
Mean Power Output ◽  
The Relationship

Force exerted and power generated were measured during short-term exercise performed on a bicycle ergometer that had been modified by the addition of an electric motor driving the cranks at a chosen constant velocity. Five subjects made a series of 20-s maximum efforts at different crank velocities (range 23--171 rev/min). The forces exerted were continuously monitored with strain gauges bonded to the cranks. Peak force was exerted at approximately 90 degrees past top dead center in each revolution. During the 20-s effort peak force declined from the maximum level (PFmax) attained near the start of exercise, the rate of decline being velocity dependent. PFmax was found to be inversely and linearly related to crank velocity and when standardized for upper leg muscle (plus bone) volume (ULV) was given by PFmax (kgf/l ULV) = 27.51--0.125 crank velocity (rev/min). Integration of the force records with pedal velocity enabled power output to be calculated. Maximum power output was a parabolic function of crank velocity, the apex of the relationship indicating that the velocity for greatest power output was 110 rev/min. At this velocity our subjects achieved a maximum mean power output, averaged over a complete revolution, of 840 +/- 153 W (85 +/- 5 W/l ULV). This was compared with the calculated value for maximum mechanical power output from aerobic sources, which was 272 +/- 49 W (30 +/- 1 W/l ULV).

Ministers and their Mandarins

1977 ◽  
Vol 12 (2) ◽  
pp. 135-149 ◽  
Author(s):  
Douglas Allen
Keyword(s):  
Civil Service ◽  
Civil Servant ◽  
Civil Servants ◽  
Short Term ◽  
The Future ◽  
Working Together ◽  
Democratic System ◽  
The Relationship ◽  
Actual Relationship

TYPICAL STATEMENTS ABOUT THE RELATIONSHIP BETWEEN CIVIL servants and ministers include the following which I have come across myselc ‘it is the Civil Service mandarins who really run the country’, ‘a strong minister must frequently reject his department's advice to prove he is master’; ‘all decisions by government are based not on the merits of the case but whether they are likely to attract votes at the next election’. The first of these implies that a minister is powerless in the grip of his department and the last that a minister ignores all departmental advice unless it suits his short-term political objectives. The actual relationship between politician and civil servant cannot be explained in such simple and extreme terms. It is also in most cases a relationship which develops and improves as those concerned get used to working together. This is fortunate because if any of the above statements was entirely true, it would be difficult to have much confidence in the future of our particular democratic system.

scholarly journals The Benefits of Enterprise Architecture for Library Technology Management: An Exploratory Case Study

2018 ◽  
Vol 37 (4) ◽  
pp. 27-46
Author(s):  
Sam Searle
Keyword(s):  
Technology Management ◽  
Enterprise Architecture ◽  
Short Term ◽  
Exploratory Case Study ◽  
It Planning ◽  
The Future ◽  
Strategic Procurement ◽  
Technology Specialists ◽  
Library Technology

This case study describes how librarians and enterprise architects at an Australian university worked together to document key components of the Library’s “as-is” enterprise architecture (EA). The article covers the rationale for conducting this activity, how work was scoped, the processes used, and the outputs delivered. The author discusses the short-term benefits of undertaking this work, with practical examples of how outputs from this process are being used to better plan future library system replacements, upgrades, and enhancements. Longer-term benefits may also accrue in the future as the results of this architecture work inform the Library’s IT planning and strategic procurement. This article has implications for practice for library technology specialists as it validates views from other practitioners on the benefits for libraries in adopting enterprise architecture methods and for librarians in working alongside enterprise architects within their organizations.

scholarly journals Improvement of Short-Term BIPV Power Predictions Using Feature Engineering and a Recurrent Neural Network

Energies ◽  
2019 ◽  
Vol 12 (17) ◽  
pp. 3247 ◽  
Author(s):  
Dongkyu Lee ◽  
Jinhwa Jeong ◽  
Sung Hoon Yoon ◽  
Young Tae Chae
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Recurrent Neural Network ◽  
Power Output ◽  
Prediction Accuracy ◽  
Support Vector ◽  
Feature Engineering ◽  
Short Term ◽  
Interaction Detection ◽  
Photovoltaic Power

The time resolution and prediction accuracy of the power generated by building-integrated photovoltaics are important for managing electricity demand and formulating a strategy to trade power with the grid. This study presents a novel approach to improve short-term hourly photovoltaic power output predictions using feature engineering and machine learning. Feature selection measured the importance score of input features by using a model-based variable importance. It verified that the normative sky index in the weather forecasted data had the least importance as a predictor for hourly prediction of photovoltaic power output. Six different machine-learning algorithms were assessed to select an appropriate model for the hourly power output prediction with onsite weather forecast data. The recurrent neural network outperformed five other models, including artificial neural networks, support vector machines, classification and regression trees, chi-square automatic interaction detection, and random forests, in terms of its ability to predict photovoltaic power output at an hourly and daily resolution for 64 tested days. Feature engineering was then used to apply dropout observation to the normative sky index from the training and prediction process, which improved the hourly prediction performance. In particular, the prediction accuracy for overcast days improved by 20% compared to the original weather dataset used without dropout observation. The results show that feature engineering effectively improves the short-term predictions of photovoltaic power output in buildings with a simple weather forecasting service.

Sign in / Sign up

Export Citation Format

Share Document